High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

fmvsm_l_conf0.5_n_a		99.09 1	99.08 1	99.11 61	99.43 63	97.48 89	98.88 127	99.30 14	98.47 18	99.85 11	99.43 43	96.71 19	99.96 4	99.86 1	99.80 25	99.89 6

SED-MVS		99.09 1	98.91 4	99.63 5	99.71 24	99.24 6	99.02 84	98.87 85	97.65 39	99.73 22	99.48 33	97.53 9	99.94 14	98.43 67	99.81 16	99.70 67

DVP-MVS++		99.08 3	98.89 5	99.64 4	99.17 111	99.23 8	99.69 1	98.88 78	97.32 63	99.53 37	99.47 35	97.81 3	99.94 14	98.47 63	99.72 68	99.74 50

fmvsm_l_conf0.5_n		99.07 4	99.05 2	99.14 57	99.41 66	97.54 87	98.89 120	99.31 13	98.49 17	99.86 8	99.42 44	96.45 27	99.96 4	99.86 1	99.74 59	99.90 5

DVP-MVS		99.03 5	98.83 10	99.63 5	99.72 17	99.25 3	98.97 95	98.58 177	97.62 41	99.45 39	99.46 40	97.42 11	99.94 14	98.47 63	99.81 16	99.69 70
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
MED-MVS		99.02 6	98.85 8	99.52 13	99.77 2	98.86 22	99.32 22	99.24 20	97.00 89	99.30 50	99.35 60	97.61 6	99.92 43	98.30 75	99.80 25	99.79 28

TestfortrainingZip a		99.02 6	98.79 12	99.70 2	99.77 2	99.30 2	99.32 22	99.24 20	96.41 121	99.30 50	99.35 60	97.61 6	99.92 43	98.35 72	99.80 25	99.88 10

APDe-MVS		99.02 6	98.84 9	99.55 10	99.57 39	98.96 17	99.39 11	98.93 65	97.38 60	99.41 42	99.54 20	96.66 20	99.84 88	98.86 39	99.85 6	99.87 11
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
lecture		98.95 9	98.78 14	99.45 19	99.75 6	98.63 30	99.43 10	99.38 8	97.60 44	99.58 33	99.47 35	95.36 64	99.93 34	98.87 38	99.57 100	99.78 33

reproduce_model		98.94 10	98.81 11	99.34 31	99.52 45	98.26 54	98.94 105	98.84 96	98.06 25	99.35 46	99.61 5	96.39 30	99.94 14	98.77 42	99.82 14	99.83 18

reproduce-ours		98.93 11	98.78 14	99.38 23	99.49 52	98.38 40	98.86 136	98.83 98	98.06 25	99.29 53	99.58 16	96.40 28	99.94 14	98.68 45	99.81 16	99.81 24

our_new_method		98.93 11	98.78 14	99.38 23	99.49 52	98.38 40	98.86 136	98.83 98	98.06 25	99.29 53	99.58 16	96.40 28	99.94 14	98.68 45	99.81 16	99.81 24

test_fmvsmconf_n		98.92 13	98.87 6	99.04 67	98.88 147	97.25 111	98.82 149	99.34 11	98.75 11	99.80 14	99.61 5	95.16 77	99.95 9	99.70 17	99.80 25	99.93 1

DPE-MVS		98.92 13	98.67 20	99.65 3	99.58 37	99.20 10	98.42 262	98.91 72	97.58 45	99.54 36	99.46 40	97.10 14	99.94 14	97.64 119	99.84 11	99.83 18
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
fmvsm_l_conf0.5_n_9		98.90 15	98.79 12	99.24 45	99.34 71	97.83 78	98.70 190	99.26 16	98.85 6	99.92 1	99.51 26	93.91 106	99.95 9	99.86 1	99.79 35	99.92 2

fmvsm_l_conf0.5_n_3		98.90 15	98.74 18	99.37 27	99.36 68	98.25 55	98.89 120	99.24 20	98.77 10	99.89 3	99.59 13	93.39 112	99.96 4	99.78 10	99.76 48	99.89 6

SteuartSystems-ACMMP		98.90 15	98.75 17	99.36 29	99.22 106	98.43 38	99.10 68	98.87 85	97.38 60	99.35 46	99.40 47	97.78 5	99.87 79	97.77 107	99.85 6	99.78 33
Skip Steuart: Steuart Systems R&D Blog.
test_fmvsm_n_1920		98.87 18	99.01 3	98.45 123	99.42 64	96.43 155	98.96 101	99.36 10	98.63 13	99.86 8	99.51 26	95.91 46	99.97 1	99.72 14	99.75 55	98.94 228

ME-MVS		98.83 19	98.60 24	99.52 13	99.58 37	98.86 22	98.69 193	98.93 65	97.00 89	99.17 62	99.35 60	96.62 23	99.90 64	98.30 75	99.80 25	99.79 28

TSAR-MVS + MP.		98.78 20	98.62 22	99.24 45	99.69 29	98.28 53	99.14 59	98.66 154	96.84 96	99.56 34	99.31 71	96.34 31	99.70 142	98.32 74	99.73 63	99.73 55
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CNVR-MVS		98.78 20	98.56 28	99.45 19	99.32 77	98.87 20	98.47 249	98.81 107	97.72 34	98.76 95	99.16 105	97.05 15	99.78 124	98.06 89	99.66 79	99.69 70

MSP-MVS		98.74 22	98.55 29	99.29 38	99.75 6	98.23 56	99.26 32	98.88 78	97.52 48	99.41 42	98.78 184	96.00 42	99.79 121	97.79 106	99.59 96	99.85 15
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
fmvsm_s_conf0.5_n_8		98.73 23	98.62 22	99.05 66	99.35 70	97.27 105	98.80 158	99.23 28	98.93 3	99.79 15	99.59 13	92.34 129	99.95 9	99.82 6	99.71 70	99.92 2

XVS		98.70 24	98.49 36	99.34 31	99.70 27	98.35 49	99.29 27	98.88 78	97.40 57	98.46 118	99.20 92	95.90 48	99.89 68	97.85 102	99.74 59	99.78 33

fmvsm_s_conf0.5_n_10		98.66 25	98.54 31	99.02 68	99.36 68	97.21 114	98.86 136	99.23 28	98.90 5	99.83 12	99.59 13	91.57 160	99.94 14	99.79 9	99.74 59	99.89 6

fmvsm_s_conf0.5_n_6		98.65 26	98.55 29	98.95 77	98.50 187	97.30 101	98.79 166	99.16 40	98.14 23	99.86 8	99.41 46	93.71 109	99.91 56	99.71 15	99.64 87	99.65 83

MCST-MVS		98.65 26	98.37 45	99.48 17	99.60 36	98.87 20	98.41 263	98.68 146	97.04 86	98.52 116	98.80 178	96.78 18	99.83 90	97.93 96	99.61 92	99.74 50

SD-MVS		98.64 28	98.68 19	98.53 112	99.33 74	98.36 48	98.90 116	98.85 95	97.28 67	99.72 25	99.39 48	96.63 22	97.60 424	98.17 84	99.85 6	99.64 86
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
fmvsm_s_conf0.5_n_9		98.63 29	98.66 21	98.54 109	99.40 67	95.83 199	98.79 166	99.17 38	98.94 2	99.92 1	99.61 5	92.49 124	99.93 34	99.86 1	99.76 48	99.86 12

HFP-MVS		98.63 29	98.40 42	99.32 37	99.72 17	98.29 52	99.23 37	98.96 60	96.10 138	98.94 77	99.17 102	96.06 39	99.92 43	97.62 120	99.78 40	99.75 48

ACMMP_NAP		98.61 31	98.30 60	99.55 10	99.62 35	98.95 18	98.82 149	98.81 107	95.80 152	99.16 66	99.47 35	95.37 63	99.92 43	97.89 100	99.75 55	99.79 28

region2R		98.61 31	98.38 44	99.29 38	99.74 12	98.16 62	99.23 37	98.93 65	96.15 134	98.94 77	99.17 102	95.91 46	99.94 14	97.55 130	99.79 35	99.78 33

NCCC		98.61 31	98.35 48	99.38 23	99.28 92	98.61 31	98.45 251	98.76 125	97.82 33	98.45 121	98.93 156	96.65 21	99.83 90	97.38 151	99.41 129	99.71 63

SF-MVS		98.59 34	98.32 59	99.41 22	99.54 41	98.71 26	99.04 78	98.81 107	95.12 203	99.32 49	99.39 48	96.22 33	99.84 88	97.72 110	99.73 63	99.67 79

ACMMPR		98.59 34	98.36 46	99.29 38	99.74 12	98.15 63	99.23 37	98.95 61	96.10 138	98.93 81	99.19 98	95.70 52	99.94 14	97.62 120	99.79 35	99.78 33

fmvsm_s_conf0.5_n_11		98.58 36	98.57 26	98.62 99	99.42 64	97.16 117	98.97 95	98.86 91	98.91 4	99.87 4	99.66 3	91.82 152	99.95 9	99.82 6	99.82 14	98.75 249

test_fmvsmconf0.1_n		98.58 36	98.44 40	98.99 70	97.73 298	97.15 118	98.84 145	98.97 57	98.75 11	99.43 41	99.54 20	93.29 114	99.93 34	99.64 20	99.79 35	99.89 6

SMA-MVS		98.58 36	98.25 63	99.56 9	99.51 46	99.04 16	98.95 102	98.80 114	93.67 297	99.37 45	99.52 23	96.52 25	99.89 68	98.06 89	99.81 16	99.76 47
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
MTAPA		98.58 36	98.29 61	99.46 18	99.76 5	98.64 29	98.90 116	98.74 129	97.27 71	98.02 147	99.39 48	94.81 87	99.96 4	97.91 98	99.79 35	99.77 40

HPM-MVS++		98.58 36	98.25 63	99.55 10	99.50 48	99.08 12	98.72 185	98.66 154	97.51 49	98.15 132	98.83 175	95.70 52	99.92 43	97.53 132	99.67 76	99.66 82

SR-MVS		98.57 41	98.35 48	99.24 45	99.53 42	98.18 60	99.09 69	98.82 101	96.58 112	99.10 68	99.32 69	95.39 61	99.82 97	97.70 115	99.63 89	99.72 59

CP-MVS		98.57 41	98.36 46	99.19 50	99.66 31	97.86 74	99.34 17	98.87 85	95.96 144	98.60 112	99.13 112	96.05 40	99.94 14	97.77 107	99.86 2	99.77 40

MSLP-MVS++		98.56 43	98.57 26	98.55 107	99.26 95	96.80 133	98.71 186	99.05 50	97.28 67	98.84 87	99.28 76	96.47 26	99.40 206	98.52 61	99.70 72	99.47 115

DeepC-MVS_fast	96.70 1	98.55 44	98.34 54	99.18 52	99.25 96	98.04 68	98.50 244	98.78 121	97.72 34	98.92 83	99.28 76	95.27 70	99.82 97	97.55 130	99.77 42	99.69 70
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SR-MVS-dyc-post		98.54 45	98.35 48	99.13 58	99.49 52	97.86 74	99.11 65	98.80 114	96.49 116	99.17 62	99.35 60	95.34 66	99.82 97	97.72 110	99.65 82	99.71 63

fmvsm_s_conf0.5_n_5		98.53 46	98.35 48	99.08 63	99.07 126	97.46 93	98.68 196	99.20 34	97.50 50	99.87 4	99.50 29	91.96 149	99.96 4	99.76 11	99.65 82	99.82 22

fmvsm_s_conf0.5_n_3		98.53 46	98.45 39	98.79 85	99.23 104	97.32 98	98.80 158	99.26 16	98.82 7	99.87 4	99.60 10	90.95 193	99.93 34	99.76 11	99.73 63	99.12 198

APD-MVS_3200maxsize		98.53 46	98.33 58	99.15 56	99.50 48	97.92 73	99.15 56	98.81 107	96.24 130	99.20 59	99.37 54	95.30 68	99.80 109	97.73 109	99.67 76	99.72 59

MM		98.51 49	98.24 65	99.33 35	99.12 120	98.14 65	98.93 111	97.02 411	98.96 1	99.17 62	99.47 35	91.97 148	99.94 14	99.85 5	99.69 73	99.91 4

mPP-MVS		98.51 49	98.26 62	99.25 44	99.75 6	98.04 68	99.28 29	98.81 107	96.24 130	98.35 128	99.23 86	95.46 58	99.94 14	97.42 146	99.81 16	99.77 40

ZNCC-MVS		98.49 51	98.20 71	99.35 30	99.73 16	98.39 39	99.19 49	98.86 91	95.77 154	98.31 131	99.10 120	95.46 58	99.93 34	97.57 129	99.81 16	99.74 50

SPE-MVS-test		98.49 51	98.50 34	98.46 122	99.20 109	97.05 123	99.64 4	98.50 199	97.45 56	98.88 84	99.14 109	95.25 72	99.15 253	98.83 40	99.56 108	99.20 182

PGM-MVS		98.49 51	98.23 67	99.27 43	99.72 17	98.08 67	98.99 91	99.49 5	95.43 179	99.03 69	99.32 69	95.56 55	99.94 14	96.80 184	99.77 42	99.78 33

EI-MVSNet-Vis-set		98.47 54	98.39 43	98.69 93	99.46 58	96.49 152	98.30 276	98.69 143	97.21 74	98.84 87	99.36 58	95.41 60	99.78 124	98.62 49	99.65 82	99.80 27

MVS_111021_HR		98.47 54	98.34 54	98.88 82	99.22 106	97.32 98	97.91 334	99.58 3	97.20 75	98.33 129	99.00 144	95.99 43	99.64 156	98.05 91	99.76 48	99.69 70

balanced_conf03		98.45 56	98.35 48	98.74 89	98.65 176	97.55 85	99.19 49	98.60 165	96.72 106	99.35 46	98.77 187	95.06 82	99.55 179	98.95 35	99.87 1	99.12 198

test_fmvsmvis_n_1920		98.44 57	98.51 32	98.23 144	98.33 218	96.15 169	98.97 95	99.15 42	98.55 16	98.45 121	99.55 18	94.26 100	99.97 1	99.65 18	99.66 79	98.57 274

CS-MVS		98.44 57	98.49 36	98.31 136	99.08 125	96.73 137	99.67 3	98.47 206	97.17 78	98.94 77	99.10 120	95.73 51	99.13 258	98.71 44	99.49 119	99.09 206

GST-MVS		98.43 59	98.12 75	99.34 31	99.72 17	98.38 40	99.09 69	98.82 101	95.71 158	98.73 98	99.06 135	95.27 70	99.93 34	97.07 161	99.63 89	99.72 59

fmvsm_s_conf0.5_n		98.42 60	98.51 32	98.13 160	99.30 83	95.25 234	98.85 141	99.39 7	97.94 29	99.74 21	99.62 4	92.59 123	99.91 56	99.65 18	99.52 114	99.25 175

EI-MVSNet-UG-set		98.41 61	98.34 54	98.61 101	99.45 61	96.32 162	98.28 279	98.68 146	97.17 78	98.74 96	99.37 54	95.25 72	99.79 121	98.57 52	99.54 111	99.73 55

DELS-MVS		98.40 62	98.20 71	98.99 70	99.00 134	97.66 80	97.75 355	98.89 75	97.71 36	98.33 129	98.97 146	94.97 84	99.88 77	98.42 69	99.76 48	99.42 130
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
fmvsm_s_conf0.5_n_a		98.38 63	98.42 41	98.27 138	99.09 124	95.41 222	98.86 136	99.37 9	97.69 38	99.78 17	99.61 5	92.38 127	99.91 56	99.58 23	99.43 127	99.49 111

TSAR-MVS + GP.		98.38 63	98.24 65	98.81 84	99.22 106	97.25 111	98.11 309	98.29 268	97.19 76	98.99 75	99.02 138	96.22 33	99.67 149	98.52 61	98.56 183	99.51 104

HPM-MVS_fast		98.38 63	98.13 74	99.12 60	99.75 6	97.86 74	99.44 9	98.82 101	94.46 251	98.94 77	99.20 92	95.16 77	99.74 134	97.58 125	99.85 6	99.77 40

patch_mono-2		98.36 66	98.87 6	96.82 272	99.53 42	90.68 388	98.64 207	99.29 15	97.88 30	99.19 61	99.52 23	96.80 17	99.97 1	99.11 31	99.86 2	99.82 22

HPM-MVS		98.36 66	98.10 78	99.13 58	99.74 12	97.82 79	99.53 6	98.80 114	94.63 238	98.61 111	98.97 146	95.13 79	99.77 129	97.65 118	99.83 13	99.79 28
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
fmvsm_s_conf0.5_n_4		98.35 68	98.50 34	97.90 186	99.16 115	95.08 243	98.75 171	99.24 20	98.39 19	99.81 13	99.52 23	92.35 128	99.90 64	99.74 13	99.51 116	98.71 255

APD-MVS		98.35 68	98.00 84	99.42 21	99.51 46	98.72 25	98.80 158	98.82 101	94.52 246	99.23 58	99.25 85	95.54 57	99.80 109	96.52 193	99.77 42	99.74 50
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_LR		98.34 70	98.23 67	98.67 95	99.27 93	96.90 129	97.95 327	99.58 3	97.14 81	98.44 123	99.01 142	95.03 83	99.62 163	97.91 98	99.75 55	99.50 106

PHI-MVS		98.34 70	98.06 79	99.18 52	99.15 118	98.12 66	99.04 78	99.09 45	93.32 314	98.83 90	99.10 120	96.54 24	99.83 90	97.70 115	99.76 48	99.59 94

MP-MVS		98.33 72	98.01 83	99.28 41	99.75 6	98.18 60	99.22 41	98.79 119	96.13 135	97.92 161	99.23 86	94.54 90	99.94 14	96.74 187	99.78 40	99.73 55
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MVSMamba_PlusPlus		98.31 73	98.19 73	98.67 95	98.96 141	97.36 96	99.24 35	98.57 179	94.81 226	98.99 75	98.90 162	95.22 75	99.59 166	99.15 30	99.84 11	99.07 214

MP-MVS-pluss		98.31 73	97.92 86	99.49 16	99.72 17	98.88 19	98.43 259	98.78 121	94.10 262	97.69 183	99.42 44	95.25 72	99.92 43	98.09 88	99.80 25	99.67 79
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.5_n_2		98.30 75	98.21 69	98.57 104	99.25 96	97.11 120	98.66 203	99.20 34	98.82 7	99.79 15	99.60 10	89.38 236	99.92 43	99.80 8	99.38 134	98.69 257

fmvsm_s_conf0.5_n_7		98.23 76	98.35 48	97.89 188	98.86 151	94.99 249	98.58 220	99.00 53	98.29 20	99.73 22	99.60 10	91.70 155	99.92 43	99.63 21	99.73 63	98.76 248

MGCNet		98.23 76	97.91 87	99.21 49	98.06 261	97.96 72	98.58 220	95.51 450	98.58 14	98.87 85	99.26 80	92.99 118	99.95 9	99.62 22	99.67 76	99.73 55

ACMMP		98.23 76	97.95 85	99.09 62	99.74 12	97.62 83	99.03 81	99.41 6	95.98 143	97.60 195	99.36 58	94.45 95	99.93 34	97.14 158	98.85 167	99.70 67
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
EC-MVSNet		98.21 79	98.11 76	98.49 119	98.34 215	97.26 110	99.61 5	98.43 224	96.78 99	98.87 85	98.84 171	93.72 108	99.01 282	98.91 37	99.50 117	99.19 186

fmvsm_s_conf0.1_n		98.18 80	98.21 69	98.11 165	98.54 185	95.24 235	98.87 130	99.24 20	97.50 50	99.70 26	99.67 1	91.33 172	99.89 68	99.47 25	99.54 111	99.21 181

fmvsm_s_conf0.1_n_2		98.14 81	98.02 82	98.53 112	98.88 147	97.07 122	98.69 193	98.82 101	98.78 9	99.77 18	99.61 5	88.83 256	99.91 56	99.71 15	99.07 150	98.61 267

fmvsm_s_conf0.1_n_a		98.08 82	98.04 81	98.21 145	97.66 304	95.39 225	98.89 120	99.17 38	97.24 72	99.76 20	99.67 1	91.13 184	99.88 77	99.39 26	99.41 129	99.35 144

dcpmvs_2		98.08 82	98.59 25	96.56 301	99.57 39	90.34 400	99.15 56	98.38 242	96.82 98	99.29 53	99.49 32	95.78 50	99.57 169	98.94 36	99.86 2	99.77 40

NormalMVS		98.07 84	97.90 88	98.59 103	99.75 6	96.60 143	98.94 105	98.60 165	97.86 31	98.71 101	99.08 130	91.22 179	99.80 109	97.40 148	99.57 100	99.37 139

CANet		98.05 85	97.76 91	98.90 81	98.73 161	97.27 105	98.35 266	98.78 121	97.37 62	97.72 180	98.96 151	91.53 165	99.92 43	98.79 41	99.65 82	99.51 104

train_agg		97.97 86	97.52 104	99.33 35	99.31 79	98.50 34	97.92 332	98.73 132	92.98 330	97.74 177	98.68 200	96.20 35	99.80 109	96.59 188	99.57 100	99.68 75

ETV-MVS		97.96 87	97.81 89	98.40 131	98.42 198	97.27 105	98.73 181	98.55 184	96.84 96	98.38 125	97.44 322	95.39 61	99.35 211	97.62 120	98.89 161	98.58 273

UA-Net		97.96 87	97.62 95	98.98 72	98.86 151	97.47 91	98.89 120	99.08 46	96.67 109	98.72 100	99.54 20	93.15 116	99.81 102	94.87 251	98.83 168	99.65 83

CDPH-MVS		97.94 89	97.49 106	99.28 41	99.47 56	98.44 36	97.91 334	98.67 151	92.57 346	98.77 94	98.85 170	95.93 45	99.72 136	95.56 229	99.69 73	99.68 75

DeepPCF-MVS	96.37 2	97.93 90	98.48 38	96.30 327	99.00 134	89.54 416	97.43 378	98.87 85	98.16 22	99.26 57	99.38 53	96.12 38	99.64 156	98.30 75	99.77 42	99.72 59

DeepC-MVS	95.98 3	97.88 91	97.58 97	98.77 87	99.25 96	96.93 127	98.83 147	98.75 127	96.96 92	96.89 227	99.50 29	90.46 204	99.87 79	97.84 104	99.76 48	99.52 101
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test_fmvsmconf0.01_n		97.86 92	97.54 103	98.83 83	95.48 428	96.83 132	98.95 102	98.60 165	98.58 14	98.93 81	99.55 18	88.57 261	99.91 56	99.54 24	99.61 92	99.77 40

DP-MVS Recon		97.86 92	97.46 109	99.06 65	99.53 42	98.35 49	98.33 268	98.89 75	92.62 343	98.05 142	98.94 154	95.34 66	99.65 153	96.04 209	99.42 128	99.19 186

CSCG		97.85 94	97.74 92	98.20 147	99.67 30	95.16 238	99.22 41	99.32 12	93.04 328	97.02 220	98.92 160	95.36 64	99.91 56	97.43 144	99.64 87	99.52 101

SymmetryMVS		97.84 95	97.58 97	98.62 99	99.01 132	96.60 143	98.94 105	98.44 213	97.86 31	98.71 101	99.08 130	91.22 179	99.80 109	97.40 148	97.53 248	99.47 115

BP-MVS1		97.82 96	97.51 105	98.76 88	98.25 231	97.39 95	99.15 56	97.68 342	96.69 107	98.47 117	99.10 120	90.29 210	99.51 186	98.60 50	99.35 137	99.37 139

MG-MVS		97.81 97	97.60 96	98.44 125	99.12 120	95.97 180	97.75 355	98.78 121	96.89 95	98.46 118	99.22 88	93.90 107	99.68 148	94.81 255	99.52 114	99.67 79

VNet		97.79 98	97.40 114	98.96 75	98.88 147	97.55 85	98.63 210	98.93 65	96.74 103	99.02 70	98.84 171	90.33 209	99.83 90	98.53 55	96.66 271	99.50 106

EIA-MVS		97.75 99	97.58 97	98.27 138	98.38 205	96.44 154	99.01 86	98.60 165	95.88 148	97.26 206	97.53 316	94.97 84	99.33 214	97.38 151	99.20 146	99.05 215

PS-MVSNAJ		97.73 100	97.77 90	97.62 218	98.68 171	95.58 212	97.34 387	98.51 194	97.29 65	98.66 108	97.88 280	94.51 91	99.90 64	97.87 101	99.17 148	97.39 317

casdiffmvs_mvg		97.72 101	97.48 108	98.44 125	98.42 198	96.59 147	98.92 113	98.44 213	96.20 132	97.76 174	99.20 92	91.66 158	99.23 240	98.27 82	98.41 203	99.49 111
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CPTT-MVS		97.72 101	97.32 120	98.92 78	99.64 33	97.10 121	99.12 63	98.81 107	92.34 354	98.09 137	99.08 130	93.01 117	99.92 43	96.06 208	99.77 42	99.75 48

PVSNet_Blended_VisFu		97.70 103	97.46 109	98.44 125	99.27 93	95.91 188	98.63 210	99.16 40	94.48 250	97.67 184	98.88 166	92.80 120	99.91 56	97.11 159	99.12 149	99.50 106

mvsany_test1		97.69 104	97.70 93	97.66 214	98.24 232	94.18 292	97.53 371	97.53 363	95.52 174	99.66 28	99.51 26	94.30 98	99.56 172	98.38 70	98.62 178	99.23 177

sasdasda		97.67 105	97.23 129	98.98 72	98.70 166	98.38 40	99.34 17	98.39 237	96.76 101	97.67 184	97.40 326	92.26 133	99.49 190	98.28 79	96.28 289	99.08 210

canonicalmvs		97.67 105	97.23 129	98.98 72	98.70 166	98.38 40	99.34 17	98.39 237	96.76 101	97.67 184	97.40 326	92.26 133	99.49 190	98.28 79	96.28 289	99.08 210

xiu_mvs_v2_base		97.66 107	97.70 93	97.56 222	98.61 180	95.46 220	97.44 375	98.46 207	97.15 80	98.65 109	98.15 255	94.33 97	99.80 109	97.84 104	98.66 177	97.41 315

GDP-MVS		97.64 108	97.28 122	98.71 92	98.30 223	97.33 97	99.05 74	98.52 191	96.34 127	98.80 91	99.05 136	89.74 223	99.51 186	96.86 180	98.86 165	99.28 165

baseline		97.64 108	97.44 111	98.25 142	98.35 210	96.20 166	99.00 88	98.32 255	96.33 129	98.03 145	99.17 102	91.35 171	99.16 249	98.10 87	98.29 212	99.39 135

casdiffmvs		97.63 110	97.41 113	98.28 137	98.33 218	96.14 170	98.82 149	98.32 255	96.38 125	97.95 156	99.21 90	91.23 178	99.23 240	98.12 86	98.37 205	99.48 113
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MGCFI-Net		97.62 111	97.19 132	98.92 78	98.66 173	98.20 58	99.32 22	98.38 242	96.69 107	97.58 197	97.42 325	92.10 142	99.50 189	98.28 79	96.25 292	99.08 210

xiu_mvs_v1_base_debu		97.60 112	97.56 100	97.72 203	98.35 210	95.98 175	97.86 344	98.51 194	97.13 82	99.01 72	98.40 227	91.56 161	99.80 109	98.53 55	98.68 173	97.37 319

xiu_mvs_v1_base		97.60 112	97.56 100	97.72 203	98.35 210	95.98 175	97.86 344	98.51 194	97.13 82	99.01 72	98.40 227	91.56 161	99.80 109	98.53 55	98.68 173	97.37 319

xiu_mvs_v1_base_debi		97.60 112	97.56 100	97.72 203	98.35 210	95.98 175	97.86 344	98.51 194	97.13 82	99.01 72	98.40 227	91.56 161	99.80 109	98.53 55	98.68 173	97.37 319

diffmvs_AUTHOR		97.59 115	97.44 111	98.01 177	98.26 230	95.47 219	98.12 305	98.36 248	96.38 125	98.84 87	99.10 120	91.13 184	99.26 227	98.24 83	98.56 183	99.30 158

diffmvs		97.58 116	97.40 114	98.13 160	98.32 221	95.81 202	98.06 315	98.37 244	96.20 132	98.74 96	98.89 165	91.31 174	99.25 231	98.16 85	98.52 187	99.34 146
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
guyue		97.57 117	97.37 116	98.20 147	98.50 187	95.86 196	98.89 120	97.03 408	97.29 65	98.73 98	98.90 162	89.41 235	99.32 215	98.68 45	98.86 165	99.42 130

MVSFormer		97.57 117	97.49 106	97.84 190	98.07 258	95.76 206	99.47 7	98.40 232	94.98 215	98.79 92	98.83 175	92.34 129	98.41 356	96.91 168	99.59 96	99.34 146

alignmvs		97.56 119	97.07 142	99.01 69	98.66 173	98.37 47	98.83 147	98.06 320	96.74 103	98.00 151	97.65 303	90.80 195	99.48 195	98.37 71	96.56 275	99.19 186

E3new		97.55 120	97.35 118	98.16 151	98.48 192	95.85 197	98.55 233	98.41 229	95.42 181	98.06 140	99.12 115	92.23 136	99.24 236	97.43 144	98.45 193	99.39 135

DPM-MVS		97.55 120	96.99 149	99.23 48	99.04 128	98.55 32	97.17 404	98.35 249	94.85 225	97.93 160	98.58 210	95.07 81	99.71 141	92.60 332	99.34 138	99.43 127

OMC-MVS		97.55 120	97.34 119	98.20 147	99.33 74	95.92 187	98.28 279	98.59 172	95.52 174	97.97 154	99.10 120	93.28 115	99.49 190	95.09 246	98.88 162	99.19 186

viewcassd2359sk11		97.53 123	97.32 120	98.16 151	98.45 195	95.83 199	98.57 229	98.42 228	95.52 174	98.07 138	99.12 115	91.81 153	99.25 231	97.46 142	98.48 192	99.41 133

LuminaMVS		97.49 124	97.18 133	98.42 129	97.50 319	97.15 118	98.45 251	97.68 342	96.56 115	98.68 103	98.78 184	89.84 220	99.32 215	98.60 50	98.57 182	98.79 240

E2		97.48 125	97.25 124	98.16 151	98.40 202	95.79 203	98.58 220	98.44 213	95.58 165	98.00 151	99.14 109	91.21 183	99.24 236	97.50 137	98.43 197	99.45 122

E3		97.48 125	97.25 124	98.16 151	98.38 205	95.79 203	98.58 220	98.44 213	95.58 165	98.00 151	99.14 109	91.25 177	99.24 236	97.50 137	98.44 194	99.45 122

KinetiMVS		97.48 125	97.05 144	98.78 86	98.37 208	97.30 101	98.99 91	98.70 141	97.18 77	99.02 70	99.01 142	87.50 291	99.67 149	95.33 236	99.33 140	99.37 139

viewmanbaseed2359cas		97.47 128	97.25 124	98.14 155	98.41 200	95.84 198	98.57 229	98.43 224	95.55 171	97.97 154	99.12 115	91.26 176	99.15 253	97.42 146	98.53 186	99.43 127

PAPM_NR		97.46 129	97.11 139	98.50 117	99.50 48	96.41 157	98.63 210	98.60 165	95.18 196	97.06 218	98.06 261	94.26 100	99.57 169	93.80 297	98.87 164	99.52 101

EPP-MVSNet		97.46 129	97.28 122	97.99 179	98.64 177	95.38 226	99.33 21	98.31 259	93.61 302	97.19 210	99.07 134	94.05 103	99.23 240	96.89 172	98.43 197	99.37 139

3Dnovator	94.51 5	97.46 129	96.93 153	99.07 64	97.78 292	97.64 81	99.35 16	99.06 48	97.02 87	93.75 345	99.16 105	89.25 240	99.92 43	97.22 157	99.75 55	99.64 86

CNLPA		97.45 132	97.03 146	98.73 90	99.05 127	97.44 94	98.07 314	98.53 188	95.32 189	96.80 232	98.53 215	93.32 113	99.72 136	94.31 278	99.31 141	99.02 219

lupinMVS		97.44 133	97.22 131	98.12 163	98.07 258	95.76 206	97.68 360	97.76 339	94.50 249	98.79 92	98.61 205	92.34 129	99.30 220	97.58 125	99.59 96	99.31 154

3Dnovator+	94.38 6	97.43 134	96.78 164	99.38 23	97.83 289	98.52 33	99.37 13	98.71 137	97.09 85	92.99 375	99.13 112	89.36 237	99.89 68	96.97 164	99.57 100	99.71 63

Vis-MVSNet		97.42 135	97.11 139	98.34 134	98.66 173	96.23 165	99.22 41	99.00 53	96.63 111	98.04 144	99.21 90	88.05 278	99.35 211	96.01 211	99.21 145	99.45 122
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
API-MVS		97.41 136	97.25 124	97.91 185	98.70 166	96.80 133	98.82 149	98.69 143	94.53 244	98.11 135	98.28 242	94.50 94	99.57 169	94.12 286	99.49 119	97.37 319

sss		97.39 137	96.98 151	98.61 101	98.60 181	96.61 142	98.22 285	98.93 65	93.97 272	98.01 150	98.48 220	91.98 146	99.85 84	96.45 195	98.15 219	99.39 135

test_cas_vis1_n_1920		97.38 138	97.36 117	97.45 226	98.95 142	93.25 332	99.00 88	98.53 188	97.70 37	99.77 18	99.35 60	84.71 347	99.85 84	98.57 52	99.66 79	99.26 173

PVSNet_Blended		97.38 138	97.12 138	98.14 155	99.25 96	95.35 229	97.28 392	99.26 16	93.13 324	97.94 158	98.21 250	92.74 121	99.81 102	96.88 174	99.40 132	99.27 166

E6		97.37 140	97.16 135	97.98 180	98.28 228	95.40 224	98.87 130	98.45 211	95.55 171	97.84 167	99.20 92	90.44 205	99.25 231	97.61 123	98.22 216	99.29 161

E5		97.37 140	97.16 135	97.98 180	98.30 223	95.41 222	98.87 130	98.45 211	95.56 167	97.84 167	99.19 98	90.39 206	99.25 231	97.61 123	98.22 216	99.29 161

E4		97.37 140	97.13 137	98.12 163	98.27 229	95.70 208	98.59 216	98.44 213	95.56 167	97.80 171	99.18 100	90.57 202	99.26 227	97.45 143	98.28 214	99.40 134

WTY-MVS		97.37 140	96.92 154	98.72 91	98.86 151	96.89 131	98.31 273	98.71 137	95.26 192	97.67 184	98.56 214	92.21 138	99.78 124	95.89 213	96.85 265	99.48 113

AstraMVS		97.34 144	97.24 128	97.65 215	98.13 252	94.15 293	98.94 105	96.25 440	97.47 54	98.60 112	99.28 76	89.67 225	99.41 205	98.73 43	98.07 223	99.38 138

viewmacassd2359aftdt		97.32 145	97.07 142	98.08 168	98.30 223	95.69 209	98.62 213	98.44 213	95.56 167	97.86 166	99.22 88	89.91 218	99.14 256	97.29 154	98.43 197	99.42 130

jason		97.32 145	97.08 141	98.06 172	97.45 325	95.59 211	97.87 342	97.91 331	94.79 228	98.55 115	98.83 175	91.12 186	99.23 240	97.58 125	99.60 94	99.34 146
jason: jason.
MVS_Test		97.28 147	97.00 147	98.13 160	98.33 218	95.97 180	98.74 175	98.07 315	94.27 257	98.44 123	98.07 260	92.48 125	99.26 227	96.43 196	98.19 218	99.16 192

EPNet		97.28 147	96.87 156	98.51 114	94.98 437	96.14 170	98.90 116	97.02 411	98.28 21	95.99 267	99.11 118	91.36 170	99.89 68	96.98 163	99.19 147	99.50 106
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SSM_0404		97.26 149	97.00 147	98.03 174	98.46 193	95.99 174	98.62 213	98.44 213	94.77 229	97.24 207	98.93 156	91.22 179	99.28 224	96.54 190	98.74 172	98.84 236

mvsmamba		97.25 150	96.99 149	98.02 176	98.34 215	95.54 216	99.18 53	97.47 369	95.04 209	98.15 132	98.57 213	89.46 232	99.31 219	97.68 117	99.01 155	99.22 179

viewdifsd2359ckpt13		97.24 151	96.97 152	98.06 172	98.43 196	95.77 205	98.59 216	98.34 252	94.81 226	97.60 195	98.94 154	90.78 199	99.09 268	96.93 167	98.33 208	99.32 153

test_yl		97.22 152	96.78 164	98.54 109	98.73 161	96.60 143	98.45 251	98.31 259	94.70 232	98.02 147	98.42 225	90.80 195	99.70 142	96.81 181	96.79 267	99.34 146

DCV-MVSNet		97.22 152	96.78 164	98.54 109	98.73 161	96.60 143	98.45 251	98.31 259	94.70 232	98.02 147	98.42 225	90.80 195	99.70 142	96.81 181	96.79 267	99.34 146

IS-MVSNet		97.22 152	96.88 155	98.25 142	98.85 154	96.36 160	99.19 49	97.97 325	95.39 183	97.23 208	98.99 145	91.11 187	98.93 294	94.60 266	98.59 180	99.47 115

viewdifsd2359ckpt07		97.20 155	97.05 144	97.65 215	98.40 202	94.33 285	98.39 264	98.43 224	95.67 160	97.66 188	99.08 130	90.04 215	99.32 215	97.47 141	98.29 212	99.31 154

PLC	95.07 4	97.20 155	96.78 164	98.44 125	99.29 88	96.31 164	98.14 302	98.76 125	92.41 352	96.39 255	98.31 240	94.92 86	99.78 124	94.06 289	98.77 171	99.23 177
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CHOSEN 280x420		97.18 157	97.18 133	97.20 239	98.81 157	93.27 329	95.78 450	99.15 42	95.25 193	96.79 233	98.11 258	92.29 132	99.07 271	98.56 54	99.85 6	99.25 175

SSM_0407		97.17 158	96.87 156	98.08 168	98.19 240	95.90 189	98.52 236	98.44 213	94.77 229	96.75 234	98.93 156	91.22 179	99.22 244	96.54 190	98.43 197	99.10 203

LS3D		97.16 159	96.66 173	98.68 94	98.53 186	97.19 115	98.93 111	98.90 73	92.83 337	95.99 267	99.37 54	92.12 141	99.87 79	93.67 301	99.57 100	98.97 224

AdaColmap		97.15 160	96.70 169	98.48 120	99.16 115	96.69 139	98.01 321	98.89 75	94.44 252	96.83 228	98.68 200	90.69 200	99.76 130	94.36 274	99.29 142	98.98 223

viewdifsd2359ckpt09		97.13 161	96.79 162	98.14 155	98.43 196	95.90 189	98.52 236	98.37 244	94.32 255	97.33 202	98.86 169	90.23 213	99.16 249	96.81 181	98.25 215	99.36 143

mamv4		97.13 161	98.11 76	94.17 414	98.97 140	83.70 459	98.66 203	98.71 137	94.63 238	97.83 169	98.90 162	96.25 32	99.55 179	99.27 28	99.76 48	99.27 166

Effi-MVS+		97.12 163	96.69 170	98.39 132	98.19 240	96.72 138	97.37 383	98.43 224	93.71 290	97.65 189	98.02 264	92.20 139	99.25 231	96.87 177	97.79 232	99.19 186

CHOSEN 1792x2688		97.12 163	96.80 160	98.08 168	99.30 83	94.56 274	98.05 316	99.71 1	93.57 304	97.09 214	98.91 161	88.17 272	99.89 68	96.87 177	99.56 108	99.81 24

F-COLMAP		97.09 165	96.80 160	97.97 182	99.45 61	94.95 253	98.55 233	98.62 164	93.02 329	96.17 262	98.58 210	94.01 104	99.81 102	93.95 291	98.90 160	99.14 196

RRT-MVS		97.03 166	96.78 164	97.77 199	97.90 285	94.34 283	99.12 63	98.35 249	95.87 149	98.06 140	98.70 198	86.45 310	99.63 159	98.04 92	98.54 185	99.35 144

TAMVS		97.02 167	96.79 162	97.70 206	98.06 261	95.31 232	98.52 236	98.31 259	93.95 273	97.05 219	98.61 205	93.49 111	98.52 338	95.33 236	97.81 231	99.29 161

viewmambaseed2359dif		97.01 168	96.84 158	97.51 224	98.19 240	94.21 291	98.16 298	98.23 280	93.61 302	97.78 172	99.13 112	90.79 198	99.18 248	97.24 155	98.40 204	99.15 193

CDS-MVSNet		96.99 169	96.69 170	97.90 186	98.05 263	95.98 175	98.20 288	98.33 254	93.67 297	96.95 221	98.49 219	93.54 110	98.42 349	95.24 243	97.74 235	99.31 154
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CANet_DTU		96.96 170	96.55 178	98.21 145	98.17 249	96.07 173	97.98 325	98.21 282	97.24 72	97.13 212	98.93 156	86.88 302	99.91 56	95.00 249	99.37 136	98.66 263

114514_t		96.93 171	96.27 191	98.92 78	99.50 48	97.63 82	98.85 141	98.90 73	84.80 454	97.77 173	99.11 118	92.84 119	99.66 152	94.85 252	99.77 42	99.47 115

MAR-MVS		96.91 172	96.40 185	98.45 123	98.69 169	96.90 129	98.66 203	98.68 146	92.40 353	97.07 217	97.96 271	91.54 164	99.75 132	93.68 299	98.92 159	98.69 257
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
HyFIR lowres test		96.90 173	96.49 182	98.14 155	99.33 74	95.56 213	97.38 381	99.65 2	92.34 354	97.61 192	98.20 251	89.29 239	99.10 267	96.97 164	97.60 240	99.77 40

Vis-MVSNet (Re-imp)		96.87 174	96.55 178	97.83 191	98.73 161	95.46 220	99.20 47	98.30 266	94.96 217	96.60 243	98.87 167	90.05 214	98.59 333	93.67 301	98.60 179	99.46 120

SDMVSNet		96.85 175	96.42 183	98.14 155	99.30 83	96.38 158	99.21 44	99.23 28	95.92 145	95.96 269	98.76 192	85.88 322	99.44 202	97.93 96	95.59 304	98.60 268

PAPR		96.84 176	96.24 193	98.65 97	98.72 165	96.92 128	97.36 385	98.57 179	93.33 313	96.67 238	97.57 312	94.30 98	99.56 172	91.05 375	98.59 180	99.47 115

HY-MVS	93.96 8	96.82 177	96.23 194	98.57 104	98.46 193	97.00 124	98.14 302	98.21 282	93.95 273	96.72 237	97.99 268	91.58 159	99.76 130	94.51 270	96.54 276	98.95 227

mamba_0408		96.81 178	96.38 186	98.09 167	98.19 240	95.90 189	95.69 451	98.32 255	94.51 247	96.75 234	98.73 194	90.99 191	99.27 226	95.83 216	98.43 197	99.10 203

UGNet		96.78 179	96.30 190	98.19 150	98.24 232	95.89 194	98.88 127	98.93 65	97.39 59	96.81 231	97.84 284	82.60 376	99.90 64	96.53 192	99.49 119	98.79 240
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
IMVS_0407		96.74 180	96.64 174	97.05 254	97.99 272	92.82 344	98.45 251	98.27 269	95.16 197	97.30 203	98.79 180	91.53 165	99.06 272	94.74 257	97.54 244	99.27 166

IMVS_0403		96.74 180	96.61 175	97.12 248	97.99 272	92.82 344	98.47 249	98.27 269	95.16 197	97.13 212	98.79 180	91.44 168	99.26 227	94.74 257	97.54 244	99.27 166

PVSNet_BlendedMVS		96.73 182	96.60 176	97.12 248	99.25 96	95.35 229	98.26 282	99.26 16	94.28 256	97.94 158	97.46 319	92.74 121	99.81 102	96.88 174	93.32 342	96.20 415

SSM_04072		96.71 183	96.38 186	97.68 209	98.19 240	95.90 189	95.69 451	98.32 255	94.51 247	96.75 234	98.73 194	90.99 191	98.02 398	95.83 216	98.43 197	99.10 203

test_vis1_n_1920		96.71 183	96.84 158	96.31 326	99.11 122	89.74 409	99.05 74	98.58 177	98.08 24	99.87 4	99.37 54	78.48 409	99.93 34	99.29 27	99.69 73	99.27 166

mvs_anonymous		96.70 185	96.53 180	97.18 242	98.19 240	93.78 303	98.31 273	98.19 286	94.01 269	94.47 301	98.27 245	92.08 144	98.46 344	97.39 150	97.91 227	99.31 154

Elysia		96.64 186	96.02 203	98.51 114	98.04 265	97.30 101	98.74 175	98.60 165	95.04 209	97.91 162	98.84 171	83.59 371	99.48 195	94.20 282	99.25 143	98.75 249

StellarMVS		96.64 186	96.02 203	98.51 114	98.04 265	97.30 101	98.74 175	98.60 165	95.04 209	97.91 162	98.84 171	83.59 371	99.48 195	94.20 282	99.25 143	98.75 249

1112_ss		96.63 188	96.00 205	98.50 117	98.56 182	96.37 159	98.18 296	98.10 308	92.92 333	94.84 289	98.43 223	92.14 140	99.58 168	94.35 275	96.51 277	99.56 100

PMMVS		96.60 189	96.33 189	97.41 230	97.90 285	93.93 299	97.35 386	98.41 229	92.84 336	97.76 174	97.45 321	91.10 188	99.20 245	96.26 201	97.91 227	99.11 201

DP-MVS		96.59 190	95.93 208	98.57 104	99.34 71	96.19 168	98.70 190	98.39 237	89.45 424	94.52 299	99.35 60	91.85 150	99.85 84	92.89 325	98.88 162	99.68 75

PatchMatch-RL		96.59 190	96.03 202	98.27 138	99.31 79	96.51 151	97.91 334	99.06 48	93.72 289	96.92 225	98.06 261	88.50 266	99.65 153	91.77 357	99.00 157	98.66 263

GeoE		96.58 192	96.07 199	98.10 166	98.35 210	95.89 194	99.34 17	98.12 302	93.12 325	96.09 263	98.87 167	89.71 224	98.97 284	92.95 321	98.08 222	99.43 127

icg_test_0407_2		96.56 193	96.50 181	96.73 278	97.99 272	92.82 344	97.18 401	98.27 269	95.16 197	97.30 203	98.79 180	91.53 165	98.10 387	94.74 257	97.54 244	99.27 166

XVG-OURS		96.55 194	96.41 184	96.99 257	98.75 160	93.76 304	97.50 374	98.52 191	95.67 160	96.83 228	99.30 74	88.95 254	99.53 182	95.88 214	96.26 291	97.69 308

FIs		96.51 195	96.12 198	97.67 211	97.13 349	97.54 87	99.36 14	99.22 33	95.89 147	94.03 330	98.35 233	91.98 146	98.44 347	96.40 197	92.76 350	97.01 327

XVG-OURS-SEG-HR		96.51 195	96.34 188	97.02 256	98.77 159	93.76 304	97.79 353	98.50 199	95.45 178	96.94 222	99.09 128	87.87 283	99.55 179	96.76 186	95.83 303	97.74 305

PS-MVSNAJss		96.43 197	96.26 192	96.92 267	95.84 417	95.08 243	99.16 55	98.50 199	95.87 149	93.84 340	98.34 237	94.51 91	98.61 329	96.88 174	93.45 337	97.06 325

test_fmvs1		96.42 198	96.67 172	95.66 358	98.82 156	88.53 436	98.80 158	98.20 284	96.39 124	99.64 30	99.20 92	80.35 397	99.67 149	99.04 33	99.57 100	98.78 244

FC-MVSNet-test		96.42 198	96.05 200	97.53 223	96.95 358	97.27 105	99.36 14	99.23 28	95.83 151	93.93 333	98.37 231	92.00 145	98.32 368	96.02 210	92.72 351	97.00 328

ab-mvs		96.42 198	95.71 219	98.55 107	98.63 178	96.75 136	97.88 341	98.74 129	93.84 279	96.54 248	98.18 253	85.34 333	99.75 132	95.93 212	96.35 281	99.15 193

FA-MVS(test-final)		96.41 201	95.94 207	97.82 193	98.21 236	95.20 237	97.80 351	97.58 353	93.21 319	97.36 201	97.70 296	89.47 230	99.56 172	94.12 286	97.99 224	98.71 255

PVSNet	91.96 18	96.35 202	96.15 195	96.96 262	99.17 111	92.05 361	96.08 443	98.68 146	93.69 293	97.75 176	97.80 290	88.86 255	99.69 147	94.26 280	99.01 155	99.15 193

Test_1112_low_res		96.34 203	95.66 224	98.36 133	98.56 182	95.94 183	97.71 358	98.07 315	92.10 363	94.79 293	97.29 334	91.75 154	99.56 172	94.17 284	96.50 278	99.58 98

viewdifsd2359ckpt11		96.30 204	96.13 196	96.81 273	98.10 255	92.10 357	98.49 247	98.40 232	96.02 140	97.61 192	99.31 71	86.37 312	99.29 222	97.52 133	93.36 341	99.04 216

viewmsd2359difaftdt		96.30 204	96.13 196	96.81 273	98.10 255	92.10 357	98.49 247	98.40 232	96.02 140	97.61 192	99.31 71	86.37 312	99.30 220	97.52 133	93.37 340	99.04 216

Effi-MVS+-dtu		96.29 206	96.56 177	95.51 363	97.89 287	90.22 401	98.80 158	98.10 308	96.57 114	96.45 253	96.66 391	90.81 194	98.91 297	95.72 223	97.99 224	97.40 316

QAPM		96.29 206	95.40 230	98.96 75	97.85 288	97.60 84	99.23 37	98.93 65	89.76 418	93.11 372	99.02 138	89.11 245	99.93 34	91.99 351	99.62 91	99.34 146

Fast-Effi-MVS+		96.28 208	95.70 221	98.03 174	98.29 226	95.97 180	98.58 220	98.25 278	91.74 371	95.29 282	97.23 339	91.03 190	99.15 253	92.90 323	97.96 226	98.97 224

nrg030		96.28 208	95.72 216	97.96 184	96.90 363	98.15 63	99.39 11	98.31 259	95.47 177	94.42 307	98.35 233	92.09 143	98.69 321	97.50 137	89.05 402	97.04 326

1314		96.25 210	95.73 215	97.79 195	97.13 349	95.55 215	98.19 291	98.59 172	93.47 308	92.03 403	97.82 288	91.33 172	99.49 190	94.62 265	98.44 194	98.32 288

sd_testset		96.17 211	95.76 214	97.42 229	99.30 83	94.34 283	98.82 149	99.08 46	95.92 145	95.96 269	98.76 192	82.83 375	99.32 215	95.56 229	95.59 304	98.60 268

h-mvs33		96.17 211	95.62 225	97.81 194	99.03 129	94.45 276	98.64 207	98.75 127	97.48 52	98.67 104	98.72 197	89.76 221	99.86 83	97.95 94	81.59 452	99.11 201

HQP_MVS		96.14 213	95.90 209	96.85 270	97.42 327	94.60 272	98.80 158	98.56 182	97.28 67	95.34 278	98.28 242	87.09 297	99.03 277	96.07 205	94.27 312	96.92 335

tttt0517		96.07 214	95.51 228	97.78 196	98.41 200	94.84 257	99.28 29	94.33 463	94.26 258	97.64 190	98.64 204	84.05 362	99.47 199	95.34 235	97.60 240	99.03 218

MVSTER		96.06 215	95.72 216	97.08 252	98.23 234	95.93 186	98.73 181	98.27 269	94.86 223	95.07 284	98.09 259	88.21 271	98.54 336	96.59 188	93.46 335	96.79 354

thisisatest0530		96.01 216	95.36 235	97.97 182	98.38 205	95.52 217	98.88 127	94.19 465	94.04 264	97.64 190	98.31 240	83.82 369	99.46 200	95.29 240	97.70 237	98.93 229

test_djsdf		96.00 217	95.69 222	96.93 264	95.72 419	95.49 218	99.47 7	98.40 232	94.98 215	94.58 297	97.86 281	89.16 243	98.41 356	96.91 168	94.12 320	96.88 344

EI-MVSNet		95.96 218	95.83 211	96.36 322	97.93 283	93.70 310	98.12 305	98.27 269	93.70 292	95.07 284	99.02 138	92.23 136	98.54 336	94.68 261	93.46 335	96.84 350

VortexMVS		95.95 219	95.79 212	96.42 318	98.29 226	93.96 298	98.68 196	98.31 259	96.02 140	94.29 315	97.57 312	89.47 230	98.37 363	97.51 136	91.93 359	96.94 333

ECVR-MVS		95.95 219	95.71 219	96.65 286	99.02 130	90.86 383	99.03 81	91.80 476	96.96 92	98.10 136	99.26 80	81.31 383	99.51 186	96.90 171	99.04 152	99.59 94

BH-untuned		95.95 219	95.72 216	96.65 286	98.55 184	92.26 353	98.23 284	97.79 338	93.73 287	94.62 296	98.01 266	88.97 253	99.00 283	93.04 318	98.51 188	98.68 259

test1111		95.94 222	95.78 213	96.41 319	98.99 137	90.12 402	99.04 78	92.45 475	96.99 91	98.03 145	99.27 79	81.40 382	99.48 195	96.87 177	99.04 152	99.63 88

MSDG		95.93 223	95.30 242	97.83 191	98.90 145	95.36 227	96.83 430	98.37 244	91.32 387	94.43 306	98.73 194	90.27 211	99.60 165	90.05 389	98.82 169	98.52 276

BH-RMVSNet		95.92 224	95.32 240	97.69 207	98.32 221	94.64 266	98.19 291	97.45 374	94.56 242	96.03 265	98.61 205	85.02 338	99.12 261	90.68 380	99.06 151	99.30 158

test_fmvs1_n		95.90 225	95.99 206	95.63 359	98.67 172	88.32 440	99.26 32	98.22 281	96.40 123	99.67 27	99.26 80	73.91 449	99.70 142	99.02 34	99.50 117	98.87 233

Fast-Effi-MVS+-dtu		95.87 226	95.85 210	95.91 345	97.74 297	91.74 367	98.69 193	98.15 298	95.56 167	94.92 287	97.68 301	88.98 252	98.79 315	93.19 313	97.78 233	97.20 323

LFMVS		95.86 227	94.98 257	98.47 121	98.87 150	96.32 162	98.84 145	96.02 441	93.40 311	98.62 110	99.20 92	74.99 441	99.63 159	97.72 110	97.20 253	99.46 120

baseline1		95.84 228	95.12 250	98.01 177	98.49 191	95.98 175	98.73 181	97.03 408	95.37 186	96.22 258	98.19 252	89.96 217	99.16 249	94.60 266	87.48 418	98.90 232

OpenMVS	93.04 13	95.83 229	95.00 255	98.32 135	97.18 346	97.32 98	99.21 44	98.97 57	89.96 414	91.14 412	99.05 136	86.64 305	99.92 43	93.38 307	99.47 122	97.73 306

IMVS_0404		95.82 230	95.52 226	96.73 278	97.99 272	92.82 344	97.23 394	98.27 269	95.16 197	94.31 313	98.79 180	85.63 326	98.10 387	94.74 257	97.54 244	99.27 166

VDD-MVS		95.82 230	95.23 244	97.61 219	98.84 155	93.98 297	98.68 196	97.40 378	95.02 213	97.95 156	99.34 68	74.37 447	99.78 124	98.64 48	96.80 266	99.08 210

UniMVSNet (Re)		95.78 232	95.19 246	97.58 220	96.99 356	97.47 91	98.79 166	99.18 37	95.60 163	93.92 334	97.04 361	91.68 156	98.48 340	95.80 220	87.66 417	96.79 354

VPA-MVSNet		95.75 233	95.11 251	97.69 207	97.24 338	97.27 105	98.94 105	99.23 28	95.13 202	95.51 276	97.32 332	85.73 324	98.91 297	97.33 153	89.55 393	96.89 343

HQP-MVS		95.72 234	95.40 230	96.69 284	97.20 342	94.25 289	98.05 316	98.46 207	96.43 118	94.45 302	97.73 293	86.75 303	98.96 288	95.30 238	94.18 316	96.86 349

hse-mvs2		95.71 235	95.30 242	96.93 264	98.50 187	93.53 315	98.36 265	98.10 308	97.48 52	98.67 104	97.99 268	89.76 221	99.02 280	97.95 94	80.91 458	98.22 291

UniMVSNet_NR-MVSNet		95.71 235	95.15 247	97.40 232	96.84 366	96.97 125	98.74 175	99.24 20	95.16 197	93.88 336	97.72 295	91.68 156	98.31 370	95.81 218	87.25 423	96.92 335

PatchmatchNet		95.71 235	95.52 226	96.29 328	97.58 310	90.72 387	96.84 429	97.52 364	94.06 263	97.08 215	96.96 371	89.24 241	98.90 300	92.03 350	98.37 205	99.26 173
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
OPM-MVS		95.69 238	95.33 239	96.76 277	96.16 402	94.63 267	98.43 259	98.39 237	96.64 110	95.02 286	98.78 184	85.15 337	99.05 273	95.21 245	94.20 315	96.60 378
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMM	93.85 9	95.69 238	95.38 234	96.61 294	97.61 307	93.84 302	98.91 115	98.44 213	95.25 193	94.28 316	98.47 221	86.04 321	99.12 261	95.50 232	93.95 325	96.87 347
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tpmrst		95.63 240	95.69 222	95.44 367	97.54 315	88.54 435	96.97 415	97.56 356	93.50 306	97.52 199	96.93 375	89.49 228	99.16 249	95.25 242	96.42 280	98.64 265

FE-MVS		95.62 241	94.90 261	97.78 196	98.37 208	94.92 254	97.17 404	97.38 380	90.95 398	97.73 179	97.70 296	85.32 335	99.63 159	91.18 367	98.33 208	98.79 240

LPG-MVS_test		95.62 241	95.34 236	96.47 312	97.46 322	93.54 313	98.99 91	98.54 186	94.67 236	94.36 310	98.77 187	85.39 330	99.11 263	95.71 224	94.15 318	96.76 357

CLD-MVS		95.62 241	95.34 236	96.46 315	97.52 318	93.75 306	97.27 393	98.46 207	95.53 173	94.42 307	98.00 267	86.21 316	98.97 284	96.25 203	94.37 310	96.66 372
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		95.61 244	94.89 262	97.76 200	98.15 251	95.15 240	96.77 431	94.41 461	92.95 332	97.18 211	97.43 323	84.78 344	99.45 201	94.63 263	97.73 236	98.68 259

MonoMVSNet		95.51 245	95.45 229	95.68 356	95.54 424	90.87 382	98.92 113	97.37 381	95.79 153	95.53 275	97.38 328	89.58 227	97.68 420	96.40 197	92.59 352	98.49 278

thres600view7		95.49 246	94.77 265	97.67 211	98.98 138	95.02 245	98.85 141	96.90 418	95.38 184	96.63 240	96.90 377	84.29 354	99.59 166	88.65 413	96.33 282	98.40 282

test_vis1_n		95.47 247	95.13 248	96.49 309	97.77 293	90.41 397	99.27 31	98.11 305	96.58 112	99.66 28	99.18 100	67.00 463	99.62 163	99.21 29	99.40 132	99.44 125

SCA		95.46 248	95.13 248	96.46 315	97.67 302	91.29 375	97.33 388	97.60 352	94.68 235	96.92 225	97.10 346	83.97 364	98.89 301	92.59 334	98.32 211	99.20 182

IterMVS-LS		95.46 248	95.21 245	96.22 330	98.12 253	93.72 309	98.32 272	98.13 301	93.71 290	94.26 317	97.31 333	92.24 135	98.10 387	94.63 263	90.12 384	96.84 350
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testing3-2		95.45 250	95.34 236	95.77 354	98.69 169	88.75 431	98.87 130	97.21 395	96.13 135	97.22 209	97.68 301	77.95 417	99.65 153	97.58 125	96.77 269	98.91 231

jajsoiax		95.45 250	95.03 254	96.73 278	95.42 432	94.63 267	99.14 59	98.52 191	95.74 155	93.22 365	98.36 232	83.87 367	98.65 326	96.95 166	94.04 321	96.91 340

CVMVSNet		95.43 252	96.04 201	93.57 421	97.93 283	83.62 460	98.12 305	98.59 172	95.68 159	96.56 244	99.02 138	87.51 289	97.51 429	93.56 305	97.44 249	99.60 92

anonymousdsp		95.42 253	94.91 260	96.94 263	95.10 436	95.90 189	99.14 59	98.41 229	93.75 284	93.16 368	97.46 319	87.50 291	98.41 356	95.63 228	94.03 322	96.50 399

DU-MVS		95.42 253	94.76 266	97.40 232	96.53 383	96.97 125	98.66 203	98.99 56	95.43 179	93.88 336	97.69 298	88.57 261	98.31 370	95.81 218	87.25 423	96.92 335

mvs_tets		95.41 255	95.00 255	96.65 286	95.58 423	94.42 278	99.00 88	98.55 184	95.73 157	93.21 366	98.38 230	83.45 373	98.63 327	97.09 160	94.00 323	96.91 340

thres100view900		95.38 256	94.70 270	97.41 230	98.98 138	94.92 254	98.87 130	96.90 418	95.38 184	96.61 242	96.88 378	84.29 354	99.56 172	88.11 416	96.29 286	97.76 303

thres400		95.38 256	94.62 274	97.65 215	98.94 143	94.98 250	98.68 196	96.93 416	95.33 187	96.55 246	96.53 397	84.23 358	99.56 172	88.11 416	96.29 286	98.40 282

BH-w/o		95.38 256	95.08 252	96.26 329	98.34 215	91.79 364	97.70 359	97.43 376	92.87 335	94.24 319	97.22 340	88.66 259	98.84 307	91.55 363	97.70 237	98.16 294

VDDNet		95.36 259	94.53 279	97.86 189	98.10 255	95.13 241	98.85 141	97.75 340	90.46 405	98.36 126	99.39 48	73.27 451	99.64 156	97.98 93	96.58 274	98.81 239

TAPA-MVS	93.98 7	95.35 260	94.56 278	97.74 202	99.13 119	94.83 259	98.33 268	98.64 159	86.62 442	96.29 257	98.61 205	94.00 105	99.29 222	80.00 460	99.41 129	99.09 206
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ACMP	93.49 10	95.34 261	94.98 257	96.43 317	97.67 302	93.48 317	98.73 181	98.44 213	94.94 221	92.53 388	98.53 215	84.50 353	99.14 256	95.48 233	94.00 323	96.66 372
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
COLMAP_ROB	93.27 12	95.33 262	94.87 263	96.71 281	99.29 88	93.24 333	98.58 220	98.11 305	89.92 415	93.57 350	99.10 120	86.37 312	99.79 121	90.78 378	98.10 221	97.09 324
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
UBG		95.32 263	94.72 269	97.13 246	98.05 263	93.26 330	97.87 342	97.20 396	94.96 217	96.18 261	95.66 431	80.97 389	99.35 211	94.47 272	97.08 256	98.78 244

tfpn200view9		95.32 263	94.62 274	97.43 228	98.94 143	94.98 250	98.68 196	96.93 416	95.33 187	96.55 246	96.53 397	84.23 358	99.56 172	88.11 416	96.29 286	97.76 303

Anonymous202405211		95.28 265	94.49 281	97.67 211	99.00 134	93.75 306	98.70 190	97.04 407	90.66 401	96.49 250	98.80 178	78.13 413	99.83 90	96.21 204	95.36 308	99.44 125

thres200		95.25 266	94.57 277	97.28 236	98.81 157	94.92 254	98.20 288	97.11 400	95.24 195	96.54 248	96.22 409	84.58 351	99.53 182	87.93 421	96.50 278	97.39 317

AllTest		95.24 267	94.65 273	96.99 257	99.25 96	93.21 334	98.59 216	98.18 289	91.36 383	93.52 352	98.77 187	84.67 348	99.72 136	89.70 396	97.87 229	98.02 298

LCM-MVSNet-Re		95.22 268	95.32 240	94.91 384	98.18 246	87.85 446	98.75 171	95.66 448	95.11 204	88.96 432	96.85 381	90.26 212	97.65 421	95.65 227	98.44 194	99.22 179

EPNet_dtu		95.21 269	94.95 259	95.99 339	96.17 400	90.45 395	98.16 298	97.27 390	96.77 100	93.14 371	98.33 238	90.34 208	98.42 349	85.57 435	98.81 170	99.09 206
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
XXY-MVS		95.20 270	94.45 287	97.46 225	96.75 373	96.56 149	98.86 136	98.65 158	93.30 316	93.27 364	98.27 245	84.85 342	98.87 304	94.82 254	91.26 370	96.96 330

D2MVS		95.18 271	95.08 252	95.48 364	97.10 351	92.07 360	98.30 276	99.13 44	94.02 266	92.90 376	96.73 387	89.48 229	98.73 319	94.48 271	93.60 334	95.65 429

WR-MVS		95.15 272	94.46 284	97.22 238	96.67 378	96.45 153	98.21 286	98.81 107	94.15 260	93.16 368	97.69 298	87.51 289	98.30 372	95.29 240	88.62 408	96.90 342

TranMVSNet+NR-MVSNet		95.14 273	94.48 282	97.11 250	96.45 389	96.36 160	99.03 81	99.03 51	95.04 209	93.58 349	97.93 274	88.27 270	98.03 397	94.13 285	86.90 428	96.95 332

myMVS_eth3d28		95.12 274	94.62 274	96.64 290	98.17 249	92.17 354	98.02 320	97.32 384	95.41 182	96.22 258	96.05 415	78.01 415	99.13 258	95.22 244	97.16 254	98.60 268

baseline2		95.11 275	94.52 280	96.87 269	96.65 379	93.56 312	98.27 281	94.10 467	93.45 309	92.02 404	97.43 323	87.45 294	99.19 246	93.88 294	97.41 251	97.87 301

miper_enhance_ethall		95.10 276	94.75 267	96.12 334	97.53 317	93.73 308	96.61 437	98.08 313	92.20 362	93.89 335	96.65 393	92.44 126	98.30 372	94.21 281	91.16 371	96.34 408

Anonymous20240529		95.10 276	94.22 298	97.75 201	99.01 132	94.26 288	98.87 130	98.83 98	85.79 450	96.64 239	98.97 146	78.73 406	99.85 84	96.27 200	94.89 309	99.12 198

test-LLR		95.10 276	94.87 263	95.80 351	96.77 370	89.70 411	96.91 420	95.21 453	95.11 204	94.83 291	95.72 428	87.71 285	98.97 284	93.06 316	98.50 189	98.72 252

WR-MVS_H		95.05 279	94.46 284	96.81 273	96.86 365	95.82 201	99.24 35	99.24 20	93.87 278	92.53 388	96.84 382	90.37 207	98.24 378	93.24 311	87.93 414	96.38 407

miper_ehance_all_eth		95.01 280	94.69 271	95.97 342	97.70 300	93.31 328	97.02 413	98.07 315	92.23 359	93.51 354	96.96 371	91.85 150	98.15 383	93.68 299	91.16 371	96.44 405

testing11		95.00 281	94.28 294	97.16 244	97.96 280	93.36 325	98.09 312	97.06 406	94.94 221	95.33 281	96.15 411	76.89 430	99.40 206	95.77 222	96.30 285	98.72 252

ADS-MVSNet		95.00 281	94.45 287	96.63 291	98.00 270	91.91 363	96.04 444	97.74 341	90.15 411	96.47 251	96.64 394	87.89 281	98.96 288	90.08 387	97.06 257	99.02 219

VPNet		94.99 283	94.19 300	97.40 232	97.16 347	96.57 148	98.71 186	98.97 57	95.67 160	94.84 289	98.24 249	80.36 396	98.67 325	96.46 194	87.32 422	96.96 330

EPMVS		94.99 283	94.48 282	96.52 307	97.22 340	91.75 366	97.23 394	91.66 477	94.11 261	97.28 205	96.81 384	85.70 325	98.84 307	93.04 318	97.28 252	98.97 224

testing91		94.98 285	94.25 297	97.20 239	97.94 281	93.41 320	98.00 323	97.58 353	94.99 214	95.45 277	96.04 416	77.20 425	99.42 204	94.97 250	96.02 299	98.78 244

NR-MVSNet		94.98 285	94.16 303	97.44 227	96.53 383	97.22 113	98.74 175	98.95 61	94.96 217	89.25 431	97.69 298	89.32 238	98.18 381	94.59 268	87.40 420	96.92 335

FMVSNet3		94.97 287	94.26 296	97.11 250	98.18 246	96.62 140	98.56 232	98.26 277	93.67 297	94.09 326	97.10 346	84.25 356	98.01 399	92.08 346	92.14 356	96.70 366

FE-MVSNET3		94.96 288	94.28 294	96.98 260	95.93 413	96.11 172	97.08 410	98.39 237	93.62 301	93.86 338	96.40 402	88.28 269	98.21 379	92.61 330	92.36 355	96.63 374

CostFormer		94.95 289	94.73 268	95.60 361	97.28 336	89.06 424	97.53 371	96.89 420	89.66 420	96.82 230	96.72 388	86.05 319	98.95 293	95.53 231	96.13 297	98.79 240

PAPM		94.95 289	94.00 316	97.78 196	97.04 353	95.65 210	96.03 446	98.25 278	91.23 392	94.19 322	97.80 290	91.27 175	98.86 306	82.61 452	97.61 239	98.84 236

CP-MVSNet		94.94 291	94.30 293	96.83 271	96.72 375	95.56 213	99.11 65	98.95 61	93.89 276	92.42 393	97.90 277	87.19 296	98.12 386	94.32 277	88.21 411	96.82 353

TR-MVS		94.94 291	94.20 299	97.17 243	97.75 294	94.14 294	97.59 368	97.02 411	92.28 358	95.75 273	97.64 306	83.88 366	98.96 288	89.77 393	96.15 296	98.40 282

RPSCF		94.87 293	95.40 230	93.26 427	98.89 146	82.06 466	98.33 268	98.06 320	90.30 410	96.56 244	99.26 80	87.09 297	99.49 190	93.82 296	96.32 283	98.24 289

testing99		94.83 294	94.08 308	97.07 253	97.94 281	93.13 336	98.10 311	97.17 398	94.86 223	95.34 278	96.00 420	76.31 433	99.40 206	95.08 247	95.90 300	98.68 259

GA-MVS		94.81 295	94.03 312	97.14 245	97.15 348	93.86 301	96.76 432	97.58 353	94.00 270	94.76 295	97.04 361	80.91 390	98.48 340	91.79 356	96.25 292	99.09 206

c3_l		94.79 296	94.43 289	95.89 347	97.75 294	93.12 338	97.16 406	98.03 322	92.23 359	93.46 358	97.05 360	91.39 169	98.01 399	93.58 304	89.21 400	96.53 390

V42		94.78 297	94.14 305	96.70 283	96.33 394	95.22 236	98.97 95	98.09 312	92.32 356	94.31 313	97.06 357	88.39 267	98.55 335	92.90 323	88.87 406	96.34 408

reproduce_monomvs		94.77 298	94.67 272	95.08 379	98.40 202	89.48 417	98.80 158	98.64 159	97.57 46	93.21 366	97.65 303	80.57 395	98.83 310	97.72 110	89.47 396	96.93 334

CR-MVSNet		94.76 299	94.15 304	96.59 297	97.00 354	93.43 318	94.96 459	97.56 356	92.46 347	96.93 223	96.24 405	88.15 273	97.88 412	87.38 424	96.65 272	98.46 280

v2v482		94.69 300	94.03 312	96.65 286	96.17 400	94.79 262	98.67 201	98.08 313	92.72 339	94.00 331	97.16 343	87.69 288	98.45 345	92.91 322	88.87 406	96.72 362

pmmvs4		94.69 300	93.99 318	96.81 273	95.74 418	95.94 183	97.40 379	97.67 345	90.42 407	93.37 361	97.59 310	89.08 246	98.20 380	92.97 320	91.67 364	96.30 411

cl22		94.68 302	94.19 300	96.13 333	98.11 254	93.60 311	96.94 417	98.31 259	92.43 351	93.32 363	96.87 380	86.51 306	98.28 376	94.10 288	91.16 371	96.51 397

eth_miper_zixun_eth		94.68 302	94.41 290	95.47 365	97.64 305	91.71 368	96.73 434	98.07 315	92.71 340	93.64 346	97.21 341	90.54 203	98.17 382	93.38 307	89.76 388	96.54 388

PCF-MVS	93.45 11	94.68 302	93.43 354	98.42 129	98.62 179	96.77 135	95.48 456	98.20 284	84.63 455	93.34 362	98.32 239	88.55 264	99.81 102	84.80 444	98.96 158	98.68 259
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MVS		94.67 305	93.54 349	98.08 168	96.88 364	96.56 149	98.19 291	98.50 199	78.05 468	92.69 383	98.02 264	91.07 189	99.63 159	90.09 386	98.36 207	98.04 297

PS-CasMVS		94.67 305	93.99 318	96.71 281	96.68 377	95.26 233	99.13 62	99.03 51	93.68 295	92.33 395	97.95 272	85.35 332	98.10 387	93.59 303	88.16 413	96.79 354

cascas		94.63 307	93.86 328	96.93 264	96.91 362	94.27 287	96.00 447	98.51 194	85.55 451	94.54 298	96.23 407	84.20 360	98.87 304	95.80 220	96.98 262	97.66 309

tpmvs		94.60 308	94.36 292	95.33 371	97.46 322	88.60 434	96.88 426	97.68 342	91.29 389	93.80 342	96.42 401	88.58 260	99.24 236	91.06 373	96.04 298	98.17 293

LTVRE_ROB	92.95 15	94.60 308	93.90 324	96.68 285	97.41 330	94.42 278	98.52 236	98.59 172	91.69 374	91.21 411	98.35 233	84.87 341	99.04 276	91.06 373	93.44 338	96.60 378
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
v1144		94.59 310	93.92 321	96.60 296	96.21 396	94.78 263	98.59 216	98.14 300	91.86 370	94.21 321	97.02 364	87.97 279	98.41 356	91.72 358	89.57 391	96.61 377

ADS-MVSNet2		94.58 311	94.40 291	95.11 377	98.00 270	88.74 432	96.04 444	97.30 386	90.15 411	96.47 251	96.64 394	87.89 281	97.56 427	90.08 387	97.06 257	99.02 219

WBMVS		94.56 312	94.04 310	96.10 335	98.03 267	93.08 340	97.82 350	98.18 289	94.02 266	93.77 344	96.82 383	81.28 384	98.34 365	95.47 234	91.00 374	96.88 344

ACMH	92.88 16	94.55 313	93.95 320	96.34 324	97.63 306	93.26 330	98.81 157	98.49 204	93.43 310	89.74 425	98.53 215	81.91 378	99.08 270	93.69 298	93.30 343	96.70 366
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		94.54 314	93.85 329	96.63 291	97.98 278	93.06 341	98.77 170	97.84 334	93.67 297	93.80 342	98.04 263	76.88 431	98.96 288	94.79 256	92.86 348	97.86 302

XVG-ACMP-BASELINE		94.54 314	94.14 305	95.75 355	96.55 382	91.65 369	98.11 309	98.44 213	94.96 217	94.22 320	97.90 277	79.18 405	99.11 263	94.05 290	93.85 327	96.48 402

AUN-MVS		94.53 316	93.73 339	96.92 267	98.50 187	93.52 316	98.34 267	98.10 308	93.83 281	95.94 271	97.98 270	85.59 328	99.03 277	94.35 275	80.94 457	98.22 291

DIV-MVS_self_test		94.52 317	94.03 312	95.99 339	97.57 314	93.38 323	97.05 411	97.94 328	91.74 371	92.81 378	97.10 346	89.12 244	98.07 395	92.60 332	90.30 381	96.53 390

cl____		94.51 318	94.01 315	96.02 337	97.58 310	93.40 322	97.05 411	97.96 327	91.73 373	92.76 380	97.08 352	89.06 247	98.13 385	92.61 330	90.29 382	96.52 393

ETVMVS		94.50 319	93.44 353	97.68 209	98.18 246	95.35 229	98.19 291	97.11 400	93.73 287	96.40 254	95.39 434	74.53 444	98.84 307	91.10 369	96.31 284	98.84 236

GBi-Net		94.49 320	93.80 332	96.56 301	98.21 236	95.00 246	98.82 149	98.18 289	92.46 347	94.09 326	97.07 353	81.16 385	97.95 404	92.08 346	92.14 356	96.72 362

test1		94.49 320	93.80 332	96.56 301	98.21 236	95.00 246	98.82 149	98.18 289	92.46 347	94.09 326	97.07 353	81.16 385	97.95 404	92.08 346	92.14 356	96.72 362

dmvs_re		94.48 322	94.18 302	95.37 369	97.68 301	90.11 403	98.54 235	97.08 402	94.56 242	94.42 307	97.24 338	84.25 356	97.76 418	91.02 376	92.83 349	98.24 289

v8		94.47 323	93.77 335	96.57 300	96.36 392	94.83 259	99.05 74	98.19 286	91.92 367	93.16 368	96.97 369	88.82 258	98.48 340	91.69 359	87.79 415	96.39 406

FMVSNet2		94.47 323	93.61 345	97.04 255	98.21 236	96.43 155	98.79 166	98.27 269	92.46 347	93.50 355	97.09 350	81.16 385	98.00 401	91.09 370	91.93 359	96.70 366

test2506		94.44 325	93.91 323	96.04 336	99.02 130	88.99 427	99.06 72	79.47 489	96.96 92	98.36 126	99.26 80	77.21 424	99.52 185	96.78 185	99.04 152	99.59 94

Patchmatch-test		94.42 326	93.68 343	96.63 291	97.60 308	91.76 365	94.83 463	97.49 368	89.45 424	94.14 324	97.10 346	88.99 249	98.83 310	85.37 438	98.13 220	99.29 161

PEN-MVS		94.42 326	93.73 339	96.49 309	96.28 395	94.84 257	99.17 54	99.00 53	93.51 305	92.23 397	97.83 287	86.10 318	97.90 408	92.55 337	86.92 427	96.74 359

v144192		94.39 328	93.70 341	96.48 311	96.06 406	94.35 282	98.58 220	98.16 297	91.45 380	94.33 312	97.02 364	87.50 291	98.45 345	91.08 372	89.11 401	96.63 374

Baseline_NR-MVSNet		94.35 329	93.81 331	95.96 343	96.20 397	94.05 296	98.61 215	96.67 430	91.44 381	93.85 339	97.60 309	88.57 261	98.14 384	94.39 273	86.93 426	95.68 428

miper_lstm_enhance		94.33 330	94.07 309	95.11 377	97.75 294	90.97 379	97.22 396	98.03 322	91.67 375	92.76 380	96.97 369	90.03 216	97.78 417	92.51 339	89.64 390	96.56 385

v1192		94.32 331	93.58 346	96.53 306	96.10 404	94.45 276	98.50 244	98.17 295	91.54 378	94.19 322	97.06 357	86.95 301	98.43 348	90.14 385	89.57 391	96.70 366

UWE-MVS		94.30 332	93.89 326	95.53 362	97.83 289	88.95 428	97.52 373	93.25 469	94.44 252	96.63 240	97.07 353	78.70 407	99.28 224	91.99 351	97.56 243	98.36 285

ACMH+	92.99 14	94.30 332	93.77 335	95.88 348	97.81 291	92.04 362	98.71 186	98.37 244	93.99 271	90.60 418	98.47 221	80.86 392	99.05 273	92.75 329	92.40 354	96.55 387

v148		94.29 334	93.76 337	95.91 345	96.10 404	92.93 342	98.58 220	97.97 325	92.59 345	93.47 357	96.95 373	88.53 265	98.32 368	92.56 336	87.06 425	96.49 400

v10		94.29 334	93.55 348	96.51 308	96.39 391	94.80 261	98.99 91	98.19 286	91.35 385	93.02 374	96.99 367	88.09 275	98.41 356	90.50 382	88.41 410	96.33 410

SD_0403		94.28 336	94.46 284	93.73 418	98.02 268	85.32 455	98.31 273	98.40 232	94.75 231	93.59 347	98.16 254	89.01 248	96.54 448	82.32 453	97.58 242	99.34 146

MVP-Stereo		94.28 336	93.92 321	95.35 370	94.95 438	92.60 349	97.97 326	97.65 346	91.61 376	90.68 417	97.09 350	86.32 315	98.42 349	89.70 396	99.34 138	95.02 442
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UniMVSNet_ETH3D		94.24 338	93.33 356	96.97 261	97.19 345	93.38 323	98.74 175	98.57 179	91.21 394	93.81 341	98.58 210	72.85 452	98.77 317	95.05 248	93.93 326	98.77 247

OurMVSNet-221017-0		94.21 339	94.00 316	94.85 389	95.60 422	89.22 422	98.89 120	97.43 376	95.29 190	92.18 400	98.52 218	82.86 374	98.59 333	93.46 306	91.76 362	96.74 359

v1921920		94.20 340	93.47 352	96.40 321	95.98 410	94.08 295	98.52 236	98.15 298	91.33 386	94.25 318	97.20 342	86.41 311	98.42 349	90.04 390	89.39 398	96.69 371

WB-MVSnew		94.19 341	94.04 310	94.66 397	96.82 368	92.14 355	97.86 344	95.96 444	93.50 306	95.64 274	96.77 386	88.06 277	97.99 402	84.87 441	96.86 263	93.85 461

v7n		94.19 341	93.43 354	96.47 312	95.90 414	94.38 281	99.26 32	98.34 252	91.99 365	92.76 380	97.13 345	88.31 268	98.52 338	89.48 401	87.70 416	96.52 393

tpm2		94.19 341	93.76 337	95.46 366	97.23 339	89.04 425	97.31 390	96.85 424	87.08 440	96.21 260	96.79 385	83.75 370	98.74 318	92.43 342	96.23 294	98.59 271

TESTMET0.1,1		94.18 344	93.69 342	95.63 359	96.92 360	89.12 423	96.91 420	94.78 458	93.17 321	94.88 288	96.45 400	78.52 408	98.92 295	93.09 315	98.50 189	98.85 234

dp		94.15 345	93.90 324	94.90 385	97.31 335	86.82 451	96.97 415	97.19 397	91.22 393	96.02 266	96.61 396	85.51 329	99.02 280	90.00 391	94.30 311	98.85 234

ET-MVSNet_ETH3D		94.13 346	92.98 364	97.58 220	98.22 235	96.20 166	97.31 390	95.37 452	94.53 244	79.56 470	97.63 308	86.51 306	97.53 428	96.91 168	90.74 376	99.02 219

tpm		94.13 346	93.80 332	95.12 376	96.50 385	87.91 445	97.44 375	95.89 447	92.62 343	96.37 256	96.30 404	84.13 361	98.30 372	93.24 311	91.66 365	99.14 196

testing222		94.12 348	93.03 363	97.37 235	98.02 268	94.66 264	97.94 330	96.65 432	94.63 238	95.78 272	95.76 423	71.49 453	98.92 295	91.17 368	95.88 301	98.52 276

IterMVS-SCA-FT		94.11 349	93.87 327	94.85 389	97.98 278	90.56 394	97.18 401	98.11 305	93.75 284	92.58 386	97.48 318	83.97 364	97.41 431	92.48 341	91.30 368	96.58 381

Anonymous20231211		94.10 350	93.26 359	96.61 294	99.11 122	94.28 286	99.01 86	98.88 78	86.43 444	92.81 378	97.57 312	81.66 381	98.68 324	94.83 253	89.02 404	96.88 344

IterMVS		94.09 351	93.85 329	94.80 393	97.99 272	90.35 399	97.18 401	98.12 302	93.68 295	92.46 392	97.34 329	84.05 362	97.41 431	92.51 339	91.33 367	96.62 376
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test-mter		94.08 352	93.51 350	95.80 351	96.77 370	89.70 411	96.91 420	95.21 453	92.89 334	94.83 291	95.72 428	77.69 419	98.97 284	93.06 316	98.50 189	98.72 252

test0.0.03 1		94.08 352	93.51 350	95.80 351	95.53 426	92.89 343	97.38 381	95.97 443	95.11 204	92.51 390	96.66 391	87.71 285	96.94 438	87.03 426	93.67 330	97.57 313

v1240		94.06 354	93.29 358	96.34 324	96.03 408	93.90 300	98.44 257	98.17 295	91.18 395	94.13 325	97.01 366	86.05 319	98.42 349	89.13 407	89.50 395	96.70 366

X-MVStestdata		94.06 354	92.30 380	99.34 31	99.70 27	98.35 49	99.29 27	98.88 78	97.40 57	98.46 118	43.50 484	95.90 48	99.89 68	97.85 102	99.74 59	99.78 33

DTE-MVSNet		93.98 356	93.26 359	96.14 332	96.06 406	94.39 280	99.20 47	98.86 91	93.06 327	91.78 405	97.81 289	85.87 323	97.58 426	90.53 381	86.17 432	96.46 404

pm-mvs1		93.94 357	93.06 362	96.59 297	96.49 386	95.16 238	98.95 102	98.03 322	92.32 356	91.08 413	97.84 284	84.54 352	98.41 356	92.16 344	86.13 435	96.19 416

MS-PatchMatch		93.84 358	93.63 344	94.46 407	96.18 399	89.45 418	97.76 354	98.27 269	92.23 359	92.13 401	97.49 317	79.50 402	98.69 321	89.75 394	99.38 134	95.25 434

tfpnnormal		93.66 359	92.70 370	96.55 305	96.94 359	95.94 183	98.97 95	99.19 36	91.04 396	91.38 410	97.34 329	84.94 340	98.61 329	85.45 437	89.02 404	95.11 438

EU-MVSNet		93.66 359	94.14 305	92.25 438	95.96 412	83.38 462	98.52 236	98.12 302	94.69 234	92.61 385	98.13 257	87.36 295	96.39 453	91.82 355	90.00 386	96.98 329

our_test_3		93.65 361	93.30 357	94.69 395	95.45 430	89.68 413	96.91 420	97.65 346	91.97 366	91.66 408	96.88 378	89.67 225	97.93 407	88.02 419	91.49 366	96.48 402

pmmvs5		93.65 361	92.97 365	95.68 356	95.49 427	92.37 350	98.20 288	97.28 389	89.66 420	92.58 386	97.26 335	82.14 377	98.09 391	93.18 314	90.95 375	96.58 381

SSC-MVS3.2		93.59 363	93.13 361	94.97 382	96.81 369	89.71 410	97.95 327	98.49 204	94.59 241	93.50 355	96.91 376	77.74 418	98.37 363	91.69 359	90.47 379	96.83 352

test_fmvs2		93.43 364	93.58 346	92.95 432	96.97 357	83.91 458	99.19 49	97.24 392	95.74 155	95.20 283	98.27 245	69.65 455	98.72 320	96.26 201	93.73 329	96.24 413

tpm cat1		93.36 365	92.80 367	95.07 380	97.58 310	87.97 444	96.76 432	97.86 333	82.17 462	93.53 351	96.04 416	86.13 317	99.13 258	89.24 405	95.87 302	98.10 296

JIA-IIPM		93.35 366	92.49 376	95.92 344	96.48 387	90.65 389	95.01 458	96.96 414	85.93 448	96.08 264	87.33 474	87.70 287	98.78 316	91.35 365	95.58 306	98.34 286

SixPastTwentyTwo		93.34 367	92.86 366	94.75 394	95.67 420	89.41 420	98.75 171	96.67 430	93.89 276	90.15 423	98.25 248	80.87 391	98.27 377	90.90 377	90.64 377	96.57 383

USDC		93.33 368	92.71 369	95.21 373	96.83 367	90.83 385	96.91 420	97.50 366	93.84 279	90.72 416	98.14 256	77.69 419	98.82 312	89.51 400	93.21 345	95.97 422

IB-MVS	91.98 17	93.27 369	91.97 384	97.19 241	97.47 321	93.41 320	97.09 409	95.99 442	93.32 314	92.47 391	95.73 426	78.06 414	99.53 182	94.59 268	82.98 446	98.62 266
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
MIMVSNet		93.26 370	92.21 381	96.41 319	97.73 298	93.13 336	95.65 453	97.03 408	91.27 391	94.04 329	96.06 414	75.33 438	97.19 434	86.56 428	96.23 294	98.92 230

ppachtmachnet_test		93.22 371	92.63 371	94.97 382	95.45 430	90.84 384	96.88 426	97.88 332	90.60 402	92.08 402	97.26 335	88.08 276	97.86 413	85.12 440	90.33 380	96.22 414

Patchmtry		93.22 371	92.35 379	95.84 350	96.77 370	93.09 339	94.66 466	97.56 356	87.37 439	92.90 376	96.24 405	88.15 273	97.90 408	87.37 425	90.10 385	96.53 390

testing3		93.19 373	92.48 377	95.30 372	98.07 258	92.27 351	98.64 207	97.17 398	93.94 275	93.98 332	97.04 361	67.97 460	96.01 457	88.40 414	97.14 255	97.63 310

FMVSNet1		93.19 373	92.07 382	96.56 301	97.54 315	95.00 246	98.82 149	98.18 289	90.38 408	92.27 396	97.07 353	73.68 450	97.95 404	89.36 403	91.30 368	96.72 362

LF4IMVS		93.14 375	92.79 368	94.20 412	95.88 415	88.67 433	97.66 362	97.07 404	93.81 282	91.71 406	97.65 303	77.96 416	98.81 313	91.47 364	91.92 361	95.12 437

mmtdpeth		93.12 376	92.61 372	94.63 399	97.60 308	89.68 413	99.21 44	97.32 384	94.02 266	97.72 180	94.42 445	77.01 429	99.44 202	99.05 32	77.18 469	94.78 447

testgi		93.06 377	92.45 378	94.88 387	96.43 390	89.90 405	98.75 171	97.54 362	95.60 163	91.63 409	97.91 276	74.46 446	97.02 436	86.10 431	93.67 330	97.72 307

PatchT		93.06 377	91.97 384	96.35 323	96.69 376	92.67 348	94.48 469	97.08 402	86.62 442	97.08 215	92.23 466	87.94 280	97.90 408	78.89 464	96.69 270	98.49 278

RPMNet		92.81 379	91.34 390	97.24 237	97.00 354	93.43 318	94.96 459	98.80 114	82.27 461	96.93 223	92.12 467	86.98 300	99.82 97	76.32 470	96.65 272	98.46 280

UWE-MVS-28		92.79 380	92.51 375	93.62 420	96.46 388	86.28 452	97.93 331	92.71 474	94.17 259	94.78 294	97.16 343	81.05 388	96.43 451	81.45 456	96.86 263	98.14 295

myMVS_eth3d		92.73 381	92.01 383	94.89 386	97.39 331	90.94 380	97.91 334	97.46 370	93.16 322	93.42 359	95.37 435	68.09 459	96.12 455	88.34 415	96.99 259	97.60 311

TransMVSNet (Re)		92.67 382	91.51 389	96.15 331	96.58 381	94.65 265	98.90 116	96.73 426	90.86 399	89.46 430	97.86 281	85.62 327	98.09 391	86.45 429	81.12 455	95.71 427

ttmdpeth		92.61 383	91.96 386	94.55 401	94.10 448	90.60 393	98.52 236	97.29 387	92.67 341	90.18 421	97.92 275	79.75 401	97.79 415	91.09 370	86.15 434	95.26 433

Syy-MVS		92.55 384	92.61 372	92.38 435	97.39 331	83.41 461	97.91 334	97.46 370	93.16 322	93.42 359	95.37 435	84.75 345	96.12 455	77.00 469	96.99 259	97.60 311

K. test v3		92.55 384	91.91 387	94.48 405	95.64 421	89.24 421	99.07 71	94.88 457	94.04 264	86.78 447	97.59 310	77.64 422	97.64 422	92.08 346	89.43 397	96.57 383

DSMNet-mixed		92.52 386	92.58 374	92.33 436	94.15 447	82.65 464	98.30 276	94.26 464	89.08 429	92.65 384	95.73 426	85.01 339	95.76 459	86.24 430	97.76 234	98.59 271

TinyColmap		92.31 387	91.53 388	94.65 398	96.92 360	89.75 408	96.92 418	96.68 429	90.45 406	89.62 427	97.85 283	76.06 436	98.81 313	86.74 427	92.51 353	95.41 431

gg-mvs-nofinetune		92.21 388	90.58 396	97.13 246	96.75 373	95.09 242	95.85 448	89.40 482	85.43 452	94.50 300	81.98 477	80.80 393	98.40 362	92.16 344	98.33 208	97.88 300

FMVSNet5		91.81 389	90.92 392	94.49 404	97.21 341	92.09 359	98.00 323	97.55 361	89.31 427	90.86 415	95.61 432	74.48 445	95.32 463	85.57 435	89.70 389	96.07 420

pmmvs6		91.77 390	90.63 395	95.17 375	94.69 444	91.24 376	98.67 201	97.92 330	86.14 446	89.62 427	97.56 315	75.79 437	98.34 365	90.75 379	84.56 439	95.94 423

Anonymous20231206		91.66 391	91.10 391	93.33 425	94.02 452	87.35 448	98.58 220	97.26 391	90.48 404	90.16 422	96.31 403	83.83 368	96.53 449	79.36 462	89.90 387	96.12 418

Patchmatch-RL test		91.49 392	90.85 393	93.41 423	91.37 464	84.40 456	92.81 473	95.93 446	91.87 369	87.25 443	94.87 441	88.99 249	96.53 449	92.54 338	82.00 449	99.30 158

test_0402		91.32 393	90.27 399	94.48 405	96.60 380	91.12 377	98.50 244	97.22 393	86.10 447	88.30 439	96.98 368	77.65 421	97.99 402	78.13 466	92.94 347	94.34 449

test_vis1_rt		91.29 394	90.65 394	93.19 429	97.45 325	86.25 453	98.57 229	90.90 480	93.30 316	86.94 446	93.59 454	62.07 471	99.11 263	97.48 140	95.58 306	94.22 452

PVSNet_0	88.72 19	91.28 395	90.03 402	95.00 381	97.99 272	87.29 449	94.84 462	98.50 199	92.06 364	89.86 424	95.19 437	79.81 400	99.39 209	92.27 343	69.79 477	98.33 287

mvs5depth		91.23 396	90.17 400	94.41 409	92.09 460	89.79 407	95.26 457	96.50 434	90.73 400	91.69 407	97.06 357	76.12 435	98.62 328	88.02 419	84.11 442	94.82 444

Anonymous20240521		91.18 397	90.44 397	93.42 422	93.70 453	88.47 437	98.94 105	97.56 356	88.46 433	89.56 429	95.08 440	77.15 427	96.97 437	83.92 447	89.55 393	94.82 444

EG-PatchMatch MVS		91.13 398	90.12 401	94.17 414	94.73 443	89.00 426	98.13 304	97.81 337	89.22 428	85.32 457	96.46 399	67.71 461	98.42 349	87.89 423	93.82 328	95.08 439

TDRefinement		91.06 399	89.68 404	95.21 373	85.35 482	91.49 372	98.51 243	97.07 404	91.47 379	88.83 436	97.84 284	77.31 423	99.09 268	92.79 328	77.98 467	95.04 441

sc_t1		91.01 400	89.39 406	95.85 349	95.99 409	90.39 398	98.43 259	97.64 348	78.79 466	92.20 399	97.94 273	66.00 465	98.60 332	91.59 362	85.94 436	98.57 274

UnsupCasMVSNet_eth		90.99 401	89.92 403	94.19 413	94.08 449	89.83 406	97.13 408	98.67 151	93.69 293	85.83 453	96.19 410	75.15 440	96.74 442	89.14 406	79.41 462	96.00 421

test20.03		90.89 402	90.38 398	92.43 434	93.48 454	88.14 443	98.33 268	97.56 356	93.40 311	87.96 440	96.71 389	80.69 394	94.13 469	79.15 463	86.17 432	95.01 443

usedtu_blend_shiyan5		90.87 403	89.15 410	96.01 338	91.33 465	93.35 326	98.12 305	97.36 382	81.93 463	92.36 394	91.75 469	81.83 379	98.09 391	92.88 326	74.82 474	96.59 380

blend_shiyan4		90.76 404	89.01 413	95.99 339	91.69 463	93.35 326	97.44 375	97.83 335	86.93 441	92.23 397	91.98 468	75.19 439	98.09 391	92.88 326	74.96 472	96.52 393

MDA-MVSNet_test_wron		90.71 405	89.38 408	94.68 396	94.83 440	90.78 386	97.19 400	97.46 370	87.60 437	72.41 477	95.72 428	86.51 306	96.71 445	85.92 433	86.80 429	96.56 385

YYNet1		90.70 406	89.39 406	94.62 400	94.79 442	90.65 389	97.20 398	97.46 370	87.54 438	72.54 476	95.74 424	86.51 306	96.66 446	86.00 432	86.76 430	96.54 388

KD-MVS_self_test		90.38 407	89.38 408	93.40 424	92.85 457	88.94 429	97.95 327	97.94 328	90.35 409	90.25 420	93.96 451	79.82 399	95.94 458	84.62 446	76.69 470	95.33 432

pmmvs-eth3d		90.36 408	89.05 412	94.32 411	91.10 467	92.12 356	97.63 367	96.95 415	88.86 431	84.91 458	93.13 459	78.32 410	96.74 442	88.70 411	81.81 451	94.09 455

FE-MVSNET2		90.29 409	88.94 415	94.36 410	90.48 469	92.27 351	98.45 251	97.82 336	91.59 377	84.90 459	93.10 460	73.92 448	96.42 452	87.92 422	82.26 447	94.39 448

tt0320		90.26 410	88.73 417	94.86 388	96.12 403	90.62 391	98.17 297	97.63 349	77.46 469	89.68 426	96.04 416	69.19 457	97.79 415	88.98 408	85.29 438	96.16 417

CL-MVSNet_self_test		90.11 411	89.14 411	93.02 430	91.86 462	88.23 442	96.51 440	98.07 315	90.49 403	90.49 419	94.41 446	84.75 345	95.34 462	80.79 458	74.95 473	95.50 430

new_pmnet		90.06 412	89.00 414	93.22 428	94.18 446	88.32 440	96.42 442	96.89 420	86.19 445	85.67 454	93.62 453	77.18 426	97.10 435	81.61 455	89.29 399	94.23 451

MDA-MVSNet-bldmvs		89.97 413	88.35 419	94.83 392	95.21 434	91.34 373	97.64 364	97.51 365	88.36 435	71.17 478	96.13 412	79.22 404	96.63 447	83.65 448	86.27 431	96.52 393

tt0320-xc		89.79 414	88.11 421	94.84 391	96.19 398	90.61 392	98.16 298	97.22 393	77.35 470	88.75 437	96.70 390	65.94 466	97.63 423	89.31 404	83.39 444	96.28 412

CMPMVS	66.06 21	89.70 415	89.67 405	89.78 443	93.19 455	76.56 469	97.00 414	98.35 249	80.97 464	81.57 465	97.75 292	74.75 443	98.61 329	89.85 392	93.63 332	94.17 453
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MIMVSNet1		89.67 416	88.28 420	93.82 417	92.81 458	91.08 378	98.01 321	97.45 374	87.95 436	87.90 441	95.87 422	67.63 462	94.56 468	78.73 465	88.18 412	95.83 425

KD-MVS_2432*1600		89.61 417	87.96 425	94.54 402	94.06 450	91.59 370	95.59 454	97.63 349	89.87 416	88.95 433	94.38 448	78.28 411	96.82 440	84.83 442	68.05 478	95.21 435

miper_refine_blended		89.61 417	87.96 425	94.54 402	94.06 450	91.59 370	95.59 454	97.63 349	89.87 416	88.95 433	94.38 448	78.28 411	96.82 440	84.83 442	68.05 478	95.21 435

MVStest1		89.53 419	87.99 424	94.14 416	94.39 445	90.42 396	98.25 283	96.84 425	82.81 458	81.18 467	97.33 331	77.09 428	96.94 438	85.27 439	78.79 463	95.06 440

MVS-HIRNet		89.46 420	88.40 418	92.64 433	97.58 310	82.15 465	94.16 472	93.05 473	75.73 473	90.90 414	82.52 476	79.42 403	98.33 367	83.53 449	98.68 173	97.43 314

OpenMVS_ROB	86.42 20	89.00 421	87.43 429	93.69 419	93.08 456	89.42 419	97.91 334	96.89 420	78.58 467	85.86 452	94.69 442	69.48 456	98.29 375	77.13 468	93.29 344	93.36 463

mvsany_test3		88.80 422	88.04 422	91.09 442	89.78 472	81.57 467	97.83 349	95.49 451	93.81 282	87.53 442	93.95 452	56.14 474	97.43 430	94.68 261	83.13 445	94.26 450

FE-MVSNET		88.56 423	87.09 430	92.99 431	89.93 471	89.99 404	98.15 301	95.59 449	88.42 434	84.87 460	92.90 461	74.82 442	94.99 466	77.88 467	81.21 454	93.99 458

new-patchmatchnet		88.50 424	87.45 428	91.67 440	90.31 470	85.89 454	97.16 406	97.33 383	89.47 423	83.63 462	92.77 463	76.38 432	95.06 465	82.70 451	77.29 468	94.06 457

APD_test1		88.22 425	88.01 423	88.86 445	95.98 410	74.66 477	97.21 397	96.44 436	83.96 457	86.66 449	97.90 277	60.95 472	97.84 414	82.73 450	90.23 383	94.09 455

PM-MVS		87.77 426	86.55 432	91.40 441	91.03 468	83.36 463	96.92 418	95.18 455	91.28 390	86.48 451	93.42 455	53.27 475	96.74 442	89.43 402	81.97 450	94.11 454

dmvs_testset		87.64 427	88.93 416	83.79 454	95.25 433	63.36 486	97.20 398	91.17 478	93.07 326	85.64 455	95.98 421	85.30 336	91.52 476	69.42 475	87.33 421	96.49 400

test_fmvs3		87.17 428	87.06 431	87.50 447	91.21 466	75.66 472	99.05 74	96.61 433	92.79 338	88.85 435	92.78 462	43.72 478	93.49 470	93.95 291	84.56 439	93.34 464

UnsupCasMVSNet_bld		87.17 428	85.12 435	93.31 426	91.94 461	88.77 430	94.92 461	98.30 266	84.30 456	82.30 463	90.04 471	63.96 469	97.25 433	85.85 434	74.47 476	93.93 460

N_pmnet		87.12 430	87.77 427	85.17 451	95.46 429	61.92 487	97.37 383	70.66 492	85.83 449	88.73 438	96.04 416	85.33 334	97.76 418	80.02 459	90.48 378	95.84 424

pmmvs3		86.67 431	84.86 436	92.11 439	88.16 476	87.19 450	96.63 436	94.75 459	79.88 465	87.22 444	92.75 464	66.56 464	95.20 464	81.24 457	76.56 471	93.96 459

test_f		86.07 432	85.39 433	88.10 446	89.28 474	75.57 473	97.73 357	96.33 438	89.41 426	85.35 456	91.56 470	43.31 480	95.53 460	91.32 366	84.23 441	93.21 465

WB-MVS		84.86 433	85.33 434	83.46 455	89.48 473	69.56 481	98.19 291	96.42 437	89.55 422	81.79 464	94.67 443	84.80 343	90.12 477	52.44 481	80.64 459	90.69 468

SSC-MVS		84.27 434	84.71 437	82.96 459	89.19 475	68.83 482	98.08 313	96.30 439	89.04 430	81.37 466	94.47 444	84.60 350	89.89 478	49.80 483	79.52 461	90.15 469

dongtai		82.47 435	81.88 438	84.22 453	95.19 435	76.03 470	94.59 468	74.14 491	82.63 459	87.19 445	96.09 413	64.10 468	87.85 481	58.91 479	84.11 442	88.78 473

test_vis3_rt		79.22 436	77.40 443	84.67 452	86.44 480	74.85 476	97.66 362	81.43 487	84.98 453	67.12 480	81.91 478	28.09 488	97.60 424	88.96 409	80.04 460	81.55 478

test_method		79.03 437	78.17 439	81.63 460	86.06 481	54.40 492	82.75 481	96.89 420	39.54 484	80.98 468	95.57 433	58.37 473	94.73 467	84.74 445	78.61 464	95.75 426

testf1		79.02 438	77.70 440	82.99 457	88.10 477	66.90 483	94.67 464	93.11 470	71.08 475	74.02 473	93.41 456	34.15 484	93.25 471	72.25 473	78.50 465	88.82 471

APD_test2		79.02 438	77.70 440	82.99 457	88.10 477	66.90 483	94.67 464	93.11 470	71.08 475	74.02 473	93.41 456	34.15 484	93.25 471	72.25 473	78.50 465	88.82 471

LCM-MVSNet		78.70 440	76.24 446	86.08 449	77.26 488	71.99 479	94.34 470	96.72 427	61.62 479	76.53 471	89.33 472	33.91 486	92.78 474	81.85 454	74.60 475	93.46 462

kuosan		78.45 441	77.69 442	80.72 461	92.73 459	75.32 474	94.63 467	74.51 490	75.96 471	80.87 469	93.19 458	63.23 470	79.99 485	42.56 485	81.56 453	86.85 477

Gipuma		78.40 442	76.75 445	83.38 456	95.54 424	80.43 468	79.42 482	97.40 378	64.67 478	73.46 475	80.82 479	45.65 477	93.14 473	66.32 477	87.43 419	76.56 481
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		77.95 443	75.44 447	85.46 450	82.54 483	74.95 475	94.23 471	93.08 472	72.80 474	74.68 472	87.38 473	36.36 483	91.56 475	73.95 471	63.94 480	89.87 470

FPMVS		77.62 444	77.14 444	79.05 463	79.25 486	60.97 488	95.79 449	95.94 445	65.96 477	67.93 479	94.40 447	37.73 482	88.88 480	68.83 476	88.46 409	87.29 474

EGC-MVSNET		75.22 445	69.54 448	92.28 437	94.81 441	89.58 415	97.64 364	96.50 434	1.82 489	5.57 490	95.74 424	68.21 458	96.26 454	73.80 472	91.71 363	90.99 467

ANet_high		69.08 446	65.37 450	80.22 462	65.99 490	71.96 480	90.91 477	90.09 481	82.62 460	49.93 485	78.39 480	29.36 487	81.75 482	62.49 478	38.52 484	86.95 476

tmp_tt		68.90 447	66.97 449	74.68 465	50.78 492	59.95 489	87.13 478	83.47 486	38.80 485	62.21 481	96.23 407	64.70 467	76.91 487	88.91 410	30.49 485	87.19 475

PMVS	61.03 23	65.95 448	63.57 452	73.09 466	57.90 491	51.22 493	85.05 480	93.93 468	54.45 480	44.32 486	83.57 475	13.22 489	89.15 479	58.68 480	81.00 456	78.91 480
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		64.94 449	64.25 451	67.02 467	82.28 484	59.36 490	91.83 476	85.63 484	52.69 481	60.22 482	77.28 481	41.06 481	80.12 484	46.15 484	41.14 482	61.57 483

EMVS		64.07 450	63.26 453	66.53 468	81.73 485	58.81 491	91.85 475	84.75 485	51.93 483	59.09 483	75.13 482	43.32 479	79.09 486	42.03 486	39.47 483	61.69 482

MVE	62.14 22	63.28 451	59.38 454	74.99 464	74.33 489	65.47 485	85.55 479	80.50 488	52.02 482	51.10 484	75.00 483	10.91 492	80.50 483	51.60 482	53.40 481	78.99 479
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		30.17 452	30.18 456	30.16 469	78.61 487	43.29 494	66.79 483	14.21 493	17.31 486	14.82 489	11.93 489	11.55 491	41.43 488	37.08 487	19.30 486	5.76 486

cdsmvs_eth3d_5k		23.98 453	31.98 455	0.00 472	0.00 495	0.00 497	0.00 484	98.59 172	0.00 490	0.00 491	98.61 205	90.60 201	0.00 491	0.00 490	0.00 489	0.00 487

testmvs		21.48 454	24.95 457	11.09 471	14.89 493	6.47 496	96.56 438	9.87 494	7.55 487	17.93 487	39.02 485	9.43 493	5.90 490	16.56 489	12.72 487	20.91 485

test123		20.95 455	23.72 458	12.64 470	13.54 494	8.19 495	96.55 439	6.13 495	7.48 488	16.74 488	37.98 486	12.97 490	6.05 489	16.69 488	5.43 488	23.68 484

ab-mvs-re		8.20 456	10.94 459	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	98.43 223	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

pcd_1.5k_mvsjas		7.88 457	10.50 460	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	94.51 91	0.00 491	0.00 490	0.00 489	0.00 487

mmdepth		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

monomultidepth		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

test_blank		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

uanet_test		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

DCPMVS		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

sosnet-low-res		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

sosnet		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

uncertanet		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

Regformer		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

uanet		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

MED-MVS test				99.52 13	99.77 2	98.86 22	99.32 22	99.24 20	96.41 121	99.30 50	99.35 60		99.92 43	98.30 75	99.80 25	99.79 28

TestfortrainingZip							99.32 22

WAC-MVS						90.94 380								88.66 412

FOURS1					99.82 1	98.66 28	99.69 1	98.95 61	97.46 55	99.39 44

MSC_two_6792asdad				99.62 7	99.17 111	99.08 12		98.63 162					99.94 14	98.53 55	99.80 25	99.86 12

PC_three_1452									95.08 208	99.60 32	99.16 105	97.86 2	98.47 343	97.52 133	99.72 68	99.74 50

No_MVS				99.62 7	99.17 111	99.08 12		98.63 162					99.94 14	98.53 55	99.80 25	99.86 12

test_one_0601					99.66 31	99.25 3		98.86 91	97.55 47	99.20 59	99.47 35	97.57 8

eth-test2					0.00 495

eth-test					0.00 495

ZD-MVS					99.46 58	98.70 27		98.79 119	93.21 319	98.67 104	98.97 146	95.70 52	99.83 90	96.07 205	99.58 99

RE-MVS-def			98.34 54		99.49 52	97.86 74	99.11 65	98.80 114	96.49 116	99.17 62	99.35 60	95.29 69		97.72 110	99.65 82	99.71 63

IU-MVS					99.71 24	99.23 8		98.64 159	95.28 191	99.63 31				98.35 72	99.81 16	99.83 18

OPU-MVS				99.37 27	99.24 103	99.05 15	99.02 84				99.16 105	97.81 3	99.37 210	97.24 155	99.73 63	99.70 67

test_241102_TWO								98.87 85	97.65 39	99.53 37	99.48 33	97.34 13	99.94 14	98.43 67	99.80 25	99.83 18

test_241102_ONE					99.71 24	99.24 6		98.87 85	97.62 41	99.73 22	99.39 48	97.53 9	99.74 134

9.14			98.06 79		99.47 56		98.71 186	98.82 101	94.36 254	99.16 66	99.29 75	96.05 40	99.81 102	97.00 162	99.71 70

save fliter					99.46 58	98.38 40	98.21 286	98.71 137	97.95 28

test_0728_THIRD									97.32 63	99.45 39	99.46 40	97.88 1	99.94 14	98.47 63	99.86 2	99.85 15

test_0728_SECOND				99.71 1	99.72 17	99.35 1	98.97 95	98.88 78					99.94 14	98.47 63	99.81 16	99.84 17

test0726					99.72 17	99.25 3	99.06 72	98.88 78	97.62 41	99.56 34	99.50 29	97.42 11

GSMVS																99.20 182

test_part2					99.63 34	99.18 11				99.27 56

sam_mvs1												89.45 233				99.20 182

sam_mvs												88.99 249

ambc				89.49 444	86.66 479	75.78 471	92.66 474	96.72 427		86.55 450	92.50 465	46.01 476	97.90 408	90.32 383	82.09 448	94.80 446

MTGPA								98.74 129

test_post1							96.68 435				30.43 488	87.85 284	98.69 321	92.59 334

test_post											31.83 487	88.83 256	98.91 297

patchmatchnet-post											95.10 439	89.42 234	98.89 301

GG-mvs-BLEND				96.59 297	96.34 393	94.98 250	96.51 440	88.58 483		93.10 373	94.34 450	80.34 398	98.05 396	89.53 399	96.99 259	96.74 359

MTMP							98.89 120	94.14 466

gm-plane-assit					95.88 415	87.47 447			89.74 419		96.94 374		99.19 246	93.32 310

test9_res														96.39 199	99.57 100	99.69 70

TEST9					99.31 79	98.50 34	97.92 332	98.73 132	92.63 342	97.74 177	98.68 200	96.20 35	99.80 109

test_8					99.29 88	98.44 36	97.89 340	98.72 134	92.98 330	97.70 182	98.66 203	96.20 35	99.80 109

agg_prior2														95.87 215	99.57 100	99.68 75

agg_prior					99.30 83	98.38 40		98.72 134		97.57 198			99.81 102

TestCases				96.99 257	99.25 96	93.21 334		98.18 289	91.36 383	93.52 352	98.77 187	84.67 348	99.72 136	89.70 396	97.87 229	98.02 298

test_prior4						98.01 70	97.86 344

test_prior2							97.80 351		96.12 137	97.89 165	98.69 199	95.96 44		96.89 172	99.60 94

test_prior				99.19 50	99.31 79	98.22 57		98.84 96					99.70 142			99.65 83

旧先验2							97.57 370		91.30 388	98.67 104			99.80 109	95.70 226

新几何2							97.64 364

新几何1				99.16 55	99.34 71	98.01 70		98.69 143	90.06 413	98.13 134	98.95 153	94.60 89	99.89 68	91.97 353	99.47 122	99.59 94

旧先验1					99.29 88	97.48 89		98.70 141			99.09 128	95.56 55			99.47 122	99.61 90

无先验							97.58 369	98.72 134	91.38 382				99.87 79	93.36 309		99.60 92

原ACMM2							97.67 361

原ACMM1				98.65 97	99.32 77	96.62 140		98.67 151	93.27 318	97.81 170	98.97 146	95.18 76	99.83 90	93.84 295	99.46 125	99.50 106

test222					99.23 104	97.17 116	97.40 379	98.66 154	88.68 432	98.05 142	98.96 151	94.14 102			99.53 113	99.61 90

testdata2													99.89 68	91.65 361

segment_acmp												96.85 16

testdata				98.26 141	99.20 109	95.36 227		98.68 146	91.89 368	98.60 112	99.10 120	94.44 96	99.82 97	94.27 279	99.44 126	99.58 98

testdata1							97.32 389		96.34 127

test12				99.18 52	99.16 115	98.19 59		98.53 188		98.07 138		95.13 79	99.72 136		99.56 108	99.63 88

plane_prior7					97.42 327	94.63 267

plane_prior6					97.35 334	94.61 270						87.09 297

plane_prior5								98.56 182					99.03 277	96.07 205	94.27 312	96.92 335

plane_prior4											98.28 242

plane_prior3						94.61 270			97.02 87	95.34 278

plane_prior2							98.80 158		97.28 67

plane_prior1					97.37 333

plane_prior						94.60 272	98.44 257		96.74 103						94.22 314

n2								0.00 496

nn								0.00 496

door-mid								94.37 462

lessismore_v0				94.45 408	94.93 439	88.44 438		91.03 479		86.77 448	97.64 306	76.23 434	98.42 349	90.31 384	85.64 437	96.51 397

LGP-MVS_train				96.47 312	97.46 322	93.54 313		98.54 186	94.67 236	94.36 310	98.77 187	85.39 330	99.11 263	95.71 224	94.15 318	96.76 357

test11								98.66 154

door								94.64 460

HQP5-MVS						94.25 289

HQP-NCC					97.20 342		98.05 316		96.43 118	94.45 302

ACMP_Plane					97.20 342		98.05 316		96.43 118	94.45 302

BP-MVS														95.30 238

HQP4-MVS										94.45 302			98.96 288			96.87 347

HQP3-MVS								98.46 207							94.18 316

HQP2-MVS												86.75 303

NP-MVS					97.28 336	94.51 275					97.73 293

MDTV_nov1_ep13_2view						84.26 457	96.89 425		90.97 397	97.90 164		89.89 219		93.91 293		99.18 191

MDTV_nov1_ep13			95.40 230		97.48 320	88.34 439	96.85 428	97.29 387	93.74 286	97.48 200	97.26 335	89.18 242	99.05 273	91.92 354	97.43 250

ACMMP++_ref															92.97 346

ACMMP++															93.61 333

Test By Simon												94.64 88

ITE_SJBPF				95.44 367	97.42 327	91.32 374		97.50 366	95.09 207	93.59 347	98.35 233	81.70 380	98.88 303	89.71 395	93.39 339	96.12 418

DeepMVS_CX				86.78 448	97.09 352	72.30 478		95.17 456	75.92 472	84.34 461	95.19 437	70.58 454	95.35 461	79.98 461	89.04 403	92.68 466

High-resolution multi-view benchmark