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.

EI-MVSNet-UG-set		99.58 4	99.57 1	99.64 77	99.78 44	99.14 128	99.60 75	99.45 182	99.01 18	99.90 3	99.83 42	98.98 23	99.93 69	99.59 1	99.95 6	99.86 11

APDe-MVS		99.66 1	99.57 1	99.92 1	99.77 49	99.89 3	99.75 28	99.56 56	99.02 15	99.88 5	99.85 29	99.18 8	99.96 19	99.22 39	99.92 11	99.90 1

EI-MVSNet-Vis-set		99.58 4	99.56 3	99.64 77	99.78 44	99.15 127	99.61 74	99.45 182	99.01 18	99.89 4	99.82 49	99.01 16	99.92 80	99.56 5	99.95 6	99.85 14

Regformer-4		99.59 3	99.54 4	99.73 58	99.76 52	99.41 98	99.58 88	99.49 130	99.02 15	99.88 5	99.80 76	99.00 22	99.94 54	99.45 19	99.92 11	99.84 18

Regformer-3		99.57 7	99.53 5	99.68 65	99.76 52	99.29 109	99.58 88	99.44 191	99.01 18	99.87 10	99.80 76	98.97 24	99.91 91	99.44 21	99.92 11	99.83 29

SED-MVS		99.61 2	99.52 6	99.88 6	99.84 32	99.90 1	99.60 75	99.48 142	99.08 11	99.91 1	99.81 62	99.20 5	99.96 19	98.91 71	99.85 58	99.79 53

SD-MVS		99.41 42	99.52 6	99.05 167	99.74 70	99.68 49	99.46 152	99.52 90	99.11 7	99.88 5	99.91 5	99.43 1	97.70 349	98.72 103	99.93 10	99.77 63
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
TSAR-MVS + MP.		99.58 4	99.50 8	99.81 38	99.91 1	99.66 54	99.63 62	99.39 213	98.91 38	99.78 31	99.85 29	99.36 2	99.94 54	98.84 85	99.88 36	99.82 36
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
DVP-MVS		99.57 7	99.47 9	99.88 6	99.85 25	99.89 3	99.57 93	99.37 228	99.10 8	99.81 22	99.80 76	98.94 31	99.96 19	98.93 68	99.86 51	99.81 41
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
Regformer-1		99.53 11	99.47 9	99.72 61	99.71 86	99.44 95	99.49 138	99.46 170	98.95 32	99.83 17	99.76 106	99.01 16	99.93 69	99.17 45	99.87 40	99.80 49

Regformer-2		99.54 9	99.47 9	99.75 51	99.71 86	99.52 84	99.49 138	99.49 130	98.94 33	99.83 17	99.76 106	99.01 16	99.94 54	99.15 48	99.87 40	99.80 49

MSLP-MVS++		99.46 24	99.47 9	99.44 121	99.60 134	99.16 123	99.41 172	99.71 13	98.98 27	99.45 113	99.78 95	99.19 7	99.54 232	99.28 34	99.84 65	99.63 124

XVS		99.53 11	99.42 13	99.87 11	99.85 25	99.83 14	99.69 37	99.68 19	98.98 27	99.37 137	99.74 117	98.81 45	99.94 54	98.79 94	99.86 51	99.84 18

SteuartSystems-ACMMP		99.54 9	99.42 13	99.87 11	99.82 37	99.81 24	99.59 81	99.51 103	98.62 59	99.79 26	99.83 42	99.28 3	99.97 11	98.48 139	99.90 23	99.84 18
Skip Steuart: Steuart Systems R&D Blog.
DELS-MVS		99.48 19	99.42 13	99.65 72	99.72 80	99.40 100	99.05 270	99.66 27	99.14 6	99.57 91	99.80 76	98.46 79	99.94 54	99.57 4	99.84 65	99.60 130
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
HPM-MVS_fast		99.51 14	99.40 16	99.85 25	99.91 1	99.79 30	99.76 27	99.56 56	97.72 156	99.76 37	99.75 111	99.13 10	99.92 80	99.07 55	99.92 11	99.85 14

MTAPA		99.52 13	99.39 17	99.89 4	99.90 3	99.86 10	99.66 50	99.47 160	98.79 49	99.68 53	99.81 62	98.43 81	99.97 11	98.88 74	99.90 23	99.83 29

DeepC-MVS_fast	98.69 1	99.49 15	99.39 17	99.77 47	99.63 120	99.59 69	99.36 196	99.46 170	99.07 13	99.79 26	99.82 49	98.85 41	99.92 80	98.68 110	99.87 40	99.82 36
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HFP-MVS		99.49 15	99.37 19	99.86 18	99.87 15	99.80 26	99.66 50	99.67 22	98.15 105	99.68 53	99.69 140	99.06 13	99.96 19	98.69 108	99.87 40	99.84 18

DeepPCF-MVS	98.18 3	98.81 133	99.37 19	97.12 317	99.60 134	91.75 352	98.61 329	99.44 191	99.35 1	99.83 17	99.85 29	98.70 62	99.81 156	99.02 59	99.91 16	99.81 41

zzz-MVS		99.49 15	99.36 21	99.89 4	99.90 3	99.86 10	99.36 196	99.47 160	98.79 49	99.68 53	99.81 62	98.43 81	99.97 11	98.88 74	99.90 23	99.83 29

ACMMPR		99.49 15	99.36 21	99.86 18	99.87 15	99.79 30	99.66 50	99.67 22	98.15 105	99.67 60	99.69 140	98.95 28	99.96 19	98.69 108	99.87 40	99.84 18

TSAR-MVS + GP.		99.36 50	99.36 21	99.36 129	99.67 101	98.61 189	99.07 265	99.33 245	99.00 22	99.82 20	99.81 62	99.06 13	99.84 136	99.09 53	99.42 136	99.65 113

region2R		99.48 19	99.35 24	99.87 11	99.88 11	99.80 26	99.65 57	99.66 27	98.13 107	99.66 65	99.68 146	98.96 25	99.96 19	98.62 117	99.87 40	99.84 18

APD-MVS_3200maxsize		99.48 19	99.35 24	99.85 25	99.76 52	99.83 14	99.63 62	99.54 73	98.36 81	99.79 26	99.82 49	98.86 40	99.95 43	98.62 117	99.81 80	99.78 61

DROMVSNet		99.40 45	99.35 24	99.55 92	99.52 149	99.50 87	99.84 6	99.58 49	98.35 82	99.68 53	99.64 166	98.19 98	99.71 196	99.59 1	99.80 84	99.43 171

RE-MVS-def			99.34 27		99.76 52	99.82 20	99.63 62	99.52 90	98.38 78	99.76 37	99.82 49	98.75 56		98.61 120	99.81 80	99.77 63

ACMMP_NAP		99.47 22	99.34 27	99.88 6	99.87 15	99.86 10	99.47 149	99.48 142	98.05 124	99.76 37	99.86 23	98.82 44	99.93 69	98.82 92	99.91 16	99.84 18

ZNCC-MVS		99.47 22	99.33 29	99.87 11	99.87 15	99.81 24	99.64 60	99.67 22	98.08 118	99.55 96	99.64 166	98.91 36	99.96 19	98.72 103	99.90 23	99.82 36

MVS_111021_LR		99.41 42	99.33 29	99.65 72	99.77 49	99.51 86	98.94 300	99.85 6	98.82 44	99.65 70	99.74 117	98.51 75	99.80 161	98.83 88	99.89 33	99.64 120

xxxxxxxxxxxxxcwj		99.43 33	99.32 31	99.75 51	99.76 52	99.59 69	99.14 253	99.53 84	99.00 22	99.71 46	99.80 76	98.95 28	99.93 69	98.19 163	99.84 65	99.74 74

DPE-MVS		99.46 24	99.32 31	99.91 2	99.78 44	99.88 7	99.36 196	99.51 103	98.73 53	99.88 5	99.84 38	98.72 60	99.96 19	98.16 168	99.87 40	99.88 5
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
PS-MVSNAJ		99.32 55	99.32 31	99.30 140	99.57 140	98.94 157	98.97 293	99.46 170	98.92 37	99.71 46	99.24 290	99.01 16	99.98 6	99.35 24	99.66 119	98.97 213

CP-MVS		99.45 26	99.32 31	99.85 25	99.83 36	99.75 38	99.69 37	99.52 90	98.07 119	99.53 99	99.63 173	98.93 35	99.97 11	98.74 99	99.91 16	99.83 29

MVS_111021_HR		99.41 42	99.32 31	99.66 68	99.72 80	99.47 91	98.95 298	99.85 6	98.82 44	99.54 97	99.73 124	98.51 75	99.74 179	98.91 71	99.88 36	99.77 63

CSCG		99.32 55	99.32 31	99.32 135	99.85 25	98.29 212	99.71 34	99.66 27	98.11 111	99.41 125	99.80 76	98.37 88	99.96 19	98.99 61	99.96 5	99.72 87

ACMMP		99.45 26	99.32 31	99.82 35	99.89 8	99.67 52	99.62 68	99.69 18	98.12 109	99.63 73	99.84 38	98.73 59	99.96 19	98.55 134	99.83 72	99.81 41
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
SR-MVS-dyc-post		99.45 26	99.31 38	99.85 25	99.76 52	99.82 20	99.63 62	99.52 90	98.38 78	99.76 37	99.82 49	98.53 72	99.95 43	98.61 120	99.81 80	99.77 63

CS-MVS		99.34 52	99.31 38	99.43 122	99.44 176	99.47 91	99.68 42	99.56 56	98.41 75	99.62 77	99.41 248	98.35 89	99.76 175	99.52 7	99.76 96	99.05 204

PGM-MVS		99.45 26	99.31 38	99.86 18	99.87 15	99.78 37	99.58 88	99.65 32	97.84 141	99.71 46	99.80 76	99.12 11	99.97 11	98.33 155	99.87 40	99.83 29

abl_6		99.44 30	99.31 38	99.83 33	99.85 25	99.75 38	99.66 50	99.59 43	98.13 107	99.82 20	99.81 62	98.60 69	99.96 19	98.46 143	99.88 36	99.79 53

SMA-MVS		99.44 30	99.30 42	99.85 25	99.73 75	99.83 14	99.56 100	99.47 160	97.45 185	99.78 31	99.82 49	99.18 8	99.91 91	98.79 94	99.89 33	99.81 41
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
MCST-MVS		99.43 33	99.30 42	99.82 35	99.79 42	99.74 41	99.29 215	99.40 209	98.79 49	99.52 101	99.62 179	98.91 36	99.90 106	98.64 115	99.75 98	99.82 36

mPP-MVS		99.44 30	99.30 42	99.86 18	99.88 11	99.79 30	99.69 37	99.48 142	98.12 109	99.50 104	99.75 111	98.78 48	99.97 11	98.57 128	99.89 33	99.83 29

CNVR-MVS		99.42 38	99.30 42	99.78 45	99.62 126	99.71 44	99.26 231	99.52 90	98.82 44	99.39 132	99.71 129	98.96 25	99.85 131	98.59 125	99.80 84	99.77 63

test1172		99.43 33	99.29 46	99.85 25	99.75 62	99.82 20	99.60 75	99.56 56	98.28 91	99.74 41	99.79 88	98.53 72	99.95 43	98.55 134	99.78 90	99.79 53

SR-MVS		99.43 33	99.29 46	99.86 18	99.75 62	99.83 14	99.59 81	99.62 33	98.21 100	99.73 43	99.79 88	98.68 63	99.96 19	98.44 145	99.77 93	99.79 53

UA-Net		99.42 38	99.29 46	99.80 40	99.62 126	99.55 76	99.50 128	99.70 15	98.79 49	99.77 33	99.96 1	97.45 118	99.96 19	98.92 70	99.90 23	99.89 2

#test#		99.43 33	99.29 46	99.86 18	99.87 15	99.80 26	99.55 109	99.67 22	97.83 142	99.68 53	99.69 140	99.06 13	99.96 19	98.39 147	99.87 40	99.84 18

HPM-MVS		99.42 38	99.28 50	99.83 33	99.90 3	99.72 42	99.81 13	99.54 73	97.59 168	99.68 53	99.63 173	98.91 36	99.94 54	98.58 126	99.91 16	99.84 18
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
PVSNet_Blended_VisFu		99.36 50	99.28 50	99.61 82	99.86 21	99.07 137	99.47 149	99.93 2	97.66 164	99.71 46	99.86 23	97.73 113	99.96 19	99.47 17	99.82 78	99.79 53

MSP-MVS		99.42 38	99.27 52	99.88 6	99.89 8	99.80 26	99.67 45	99.50 122	98.70 55	99.77 33	99.49 224	98.21 97	99.95 43	98.46 143	99.77 93	99.88 5
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
xiu_mvs_v1_base_debu		99.29 59	99.27 52	99.34 130	99.63 120	98.97 148	99.12 255	99.51 103	98.86 40	99.84 13	99.47 233	98.18 99	99.99 1	99.50 10	99.31 143	99.08 197

xiu_mvs_v1_base		99.29 59	99.27 52	99.34 130	99.63 120	98.97 148	99.12 255	99.51 103	98.86 40	99.84 13	99.47 233	98.18 99	99.99 1	99.50 10	99.31 143	99.08 197

xiu_mvs_v1_base_debi		99.29 59	99.27 52	99.34 130	99.63 120	98.97 148	99.12 255	99.51 103	98.86 40	99.84 13	99.47 233	98.18 99	99.99 1	99.50 10	99.31 143	99.08 197

xiu_mvs_v2_base		99.26 65	99.25 56	99.29 143	99.53 147	98.91 161	99.02 279	99.45 182	98.80 48	99.71 46	99.26 287	98.94 31	99.98 6	99.34 28	99.23 148	98.98 212

SF-MVS		99.38 48	99.24 57	99.79 43	99.79 42	99.68 49	99.57 93	99.54 73	97.82 147	99.71 46	99.80 76	98.95 28	99.93 69	98.19 163	99.84 65	99.74 74

GST-MVS		99.40 45	99.24 57	99.85 25	99.86 21	99.79 30	99.60 75	99.67 22	97.97 130	99.63 73	99.68 146	98.52 74	99.95 43	98.38 149	99.86 51	99.81 41

HPM-MVS++		99.39 47	99.23 59	99.87 11	99.75 62	99.84 13	99.43 163	99.51 103	98.68 57	99.27 159	99.53 211	98.64 68	99.96 19	98.44 145	99.80 84	99.79 53

CS-MVS-test		99.27 62	99.22 60	99.40 124	99.39 189	99.60 65	99.67 45	99.56 56	98.30 89	99.47 109	99.25 288	98.27 95	99.79 164	99.41 22	99.66 119	98.81 223

ETV-MVS		99.26 65	99.21 61	99.40 124	99.46 170	99.30 108	99.56 100	99.52 90	98.52 65	99.44 117	99.27 286	98.41 85	99.86 125	99.10 52	99.59 128	99.04 205

MP-MVS-pluss		99.37 49	99.20 62	99.88 6	99.90 3	99.87 9	99.30 211	99.52 90	97.18 211	99.60 84	99.79 88	98.79 47	99.95 43	98.83 88	99.91 16	99.83 29
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
NCCC		99.34 52	99.19 63	99.79 43	99.61 130	99.65 57	99.30 211	99.48 142	98.86 40	99.21 175	99.63 173	98.72 60	99.90 106	98.25 159	99.63 125	99.80 49

DeepC-MVS	98.35 2	99.30 57	99.19 63	99.64 77	99.82 37	99.23 116	99.62 68	99.55 66	98.94 33	99.63 73	99.95 2	95.82 174	99.94 54	99.37 23	99.97 3	99.73 81
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PHI-MVS		99.30 57	99.17 65	99.70 64	99.56 144	99.52 84	99.58 88	99.80 8	97.12 217	99.62 77	99.73 124	98.58 70	99.90 106	98.61 120	99.91 16	99.68 103

MP-MVS		99.33 54	99.15 66	99.87 11	99.88 11	99.82 20	99.66 50	99.46 170	98.09 114	99.48 108	99.74 117	98.29 93	99.96 19	97.93 186	99.87 40	99.82 36
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CANet		99.25 67	99.14 67	99.59 84	99.41 181	99.16 123	99.35 202	99.57 51	98.82 44	99.51 103	99.61 183	96.46 151	99.95 43	99.59 1	99.98 2	99.65 113

CHOSEN 280x420		99.12 87	99.13 68	99.08 163	99.66 110	97.89 233	98.43 339	99.71 13	98.88 39	99.62 77	99.76 106	96.63 146	99.70 203	99.46 18	99.99 1	99.66 109

MVSFormer		99.17 75	99.12 69	99.29 143	99.51 152	98.94 157	99.88 1	99.46 170	97.55 173	99.80 24	99.65 159	97.39 119	99.28 273	99.03 57	99.85 58	99.65 113

LS3D		99.27 62	99.12 69	99.74 56	99.18 240	99.75 38	99.56 100	99.57 51	98.45 71	99.49 107	99.85 29	97.77 112	99.94 54	98.33 155	99.84 65	99.52 148

9.14			99.10 71		99.72 80		99.40 180	99.51 103	97.53 178	99.64 72	99.78 95	98.84 42	99.91 91	97.63 213	99.82 78

CHOSEN 1792x2688		99.19 71	99.10 71	99.45 117	99.89 8	98.52 198	99.39 184	99.94 1	98.73 53	99.11 193	99.89 10	95.50 184	99.94 54	99.50 10	99.97 3	99.89 2

EIA-MVS		99.18 73	99.09 73	99.45 117	99.49 161	99.18 120	99.67 45	99.53 84	97.66 164	99.40 130	99.44 239	98.10 103	99.81 156	98.94 66	99.62 126	99.35 178

APD-MVS		99.27 62	99.08 74	99.84 32	99.75 62	99.79 30	99.50 128	99.50 122	97.16 213	99.77 33	99.82 49	98.78 48	99.94 54	97.56 222	99.86 51	99.80 49
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TAMVS		99.12 87	99.08 74	99.24 151	99.46 170	98.55 192	99.51 122	99.46 170	98.09 114	99.45 113	99.82 49	98.34 90	99.51 233	98.70 105	98.93 173	99.67 106

test_prior3		99.21 69	99.05 76	99.68 65	99.67 101	99.48 89	98.96 294	99.56 56	98.34 84	99.01 212	99.52 214	98.68 63	99.83 145	97.96 183	99.74 101	99.74 74

sss		99.17 75	99.05 76	99.53 99	99.62 126	98.97 148	99.36 196	99.62 33	97.83 142	99.67 60	99.65 159	97.37 123	99.95 43	99.19 42	99.19 151	99.68 103

3Dnovator	97.25 9	99.24 68	99.05 76	99.81 38	99.12 253	99.66 54	99.84 6	99.74 10	99.09 10	98.92 228	99.90 7	95.94 168	99.98 6	98.95 65	99.92 11	99.79 53

F-COLMAP		99.19 71	99.04 79	99.64 77	99.78 44	99.27 112	99.42 170	99.54 73	97.29 201	99.41 125	99.59 189	98.42 84	99.93 69	98.19 163	99.69 111	99.73 81

OMC-MVS		99.08 98	99.04 79	99.20 154	99.67 101	98.22 216	99.28 217	99.52 90	98.07 119	99.66 65	99.81 62	97.79 111	99.78 169	97.79 197	99.81 80	99.60 130

jason		99.13 81	99.03 81	99.45 117	99.46 170	98.87 164	99.12 255	99.26 268	98.03 127	99.79 26	99.65 159	97.02 133	99.85 131	99.02 59	99.90 23	99.65 113
jason: jason.
CDS-MVSNet		99.09 96	99.03 81	99.25 149	99.42 178	98.73 178	99.45 153	99.46 170	98.11 111	99.46 112	99.77 102	98.01 106	99.37 255	98.70 105	98.92 175	99.66 109
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
API-MVS		99.04 103	99.03 81	99.06 165	99.40 186	99.31 107	99.55 109	99.56 56	98.54 63	99.33 147	99.39 256	98.76 53	99.78 169	96.98 261	99.78 90	98.07 332

ETH3D-3000-0.1		99.21 69	99.02 84	99.77 47	99.73 75	99.69 47	99.38 189	99.51 103	97.45 185	99.61 80	99.75 111	98.51 75	99.91 91	97.45 234	99.83 72	99.71 94

diffmvs		99.14 79	99.02 84	99.51 107	99.61 130	98.96 152	99.28 217	99.49 130	98.46 70	99.72 45	99.71 129	96.50 150	99.88 119	99.31 31	99.11 157	99.67 106

baseline		99.15 78	99.02 84	99.53 99	99.66 110	99.14 128	99.72 32	99.48 142	98.35 82	99.42 121	99.84 38	96.07 162	99.79 164	99.51 9	99.14 155	99.67 106

MG-MVS		99.13 81	99.02 84	99.45 117	99.57 140	98.63 186	99.07 265	99.34 238	98.99 25	99.61 80	99.82 49	97.98 107	99.87 122	97.00 259	99.80 84	99.85 14

lupinMVS		99.13 81	99.01 88	99.46 116	99.51 152	98.94 157	99.05 270	99.16 283	97.86 137	99.80 24	99.56 199	97.39 119	99.86 125	98.94 66	99.85 58	99.58 138

mvs_anonymous		99.03 105	98.99 89	99.16 158	99.38 191	98.52 198	99.51 122	99.38 219	97.79 148	99.38 135	99.81 62	97.30 124	99.45 238	99.35 24	98.99 170	99.51 154

EPP-MVSNet		99.13 81	98.99 89	99.53 99	99.65 115	99.06 138	99.81 13	99.33 245	97.43 189	99.60 84	99.88 15	97.14 128	99.84 136	99.13 49	98.94 172	99.69 99

CNLPA		99.14 79	98.99 89	99.59 84	99.58 138	99.41 98	99.16 247	99.44 191	98.45 71	99.19 181	99.49 224	98.08 104	99.89 114	97.73 204	99.75 98	99.48 159

casdiffmvs		99.13 81	98.98 92	99.56 90	99.65 115	99.16 123	99.56 100	99.50 122	98.33 87	99.41 125	99.86 23	95.92 169	99.83 145	99.45 19	99.16 152	99.70 96

MVS_Test		99.10 95	98.97 93	99.48 111	99.49 161	99.14 128	99.67 45	99.34 238	97.31 199	99.58 89	99.76 106	97.65 115	99.82 152	98.87 78	99.07 163	99.46 166

PVSNet_Blended		99.08 98	98.97 93	99.42 123	99.76 52	98.79 175	98.78 315	99.91 3	96.74 246	99.67 60	99.49 224	97.53 116	99.88 119	98.98 62	99.85 58	99.60 130

Vis-MVSNet		99.12 87	98.97 93	99.56 90	99.78 44	99.10 133	99.68 42	99.66 27	98.49 67	99.86 11	99.87 20	94.77 213	99.84 136	99.19 42	99.41 137	99.74 74
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
3Dnovator+	97.12 13	99.18 73	98.97 93	99.82 35	99.17 246	99.68 49	99.81 13	99.51 103	99.20 4	98.72 254	99.89 10	95.68 179	99.97 11	98.86 81	99.86 51	99.81 41

DP-MVS Recon		99.12 87	98.95 97	99.65 72	99.74 70	99.70 46	99.27 222	99.57 51	96.40 276	99.42 121	99.68 146	98.75 56	99.80 161	97.98 182	99.72 105	99.44 169

DP-MVS		99.16 77	98.95 97	99.78 45	99.77 49	99.53 81	99.41 172	99.50 122	97.03 228	99.04 209	99.88 15	97.39 119	99.92 80	98.66 113	99.90 23	99.87 10

PS-MVSNAJss		98.92 116	98.92 99	98.90 192	98.78 302	98.53 194	99.78 22	99.54 73	98.07 119	99.00 217	99.76 106	99.01 16	99.37 255	99.13 49	97.23 252	98.81 223

HyFIR lowres test		99.11 92	98.92 99	99.65 72	99.90 3	99.37 101	99.02 279	99.91 3	97.67 163	99.59 87	99.75 111	95.90 171	99.73 186	99.53 6	99.02 168	99.86 11

CDPH-MVS		99.13 81	98.91 101	99.80 40	99.75 62	99.71 44	99.15 251	99.41 203	96.60 259	99.60 84	99.55 202	98.83 43	99.90 106	97.48 229	99.83 72	99.78 61

VNet		99.11 92	98.90 102	99.73 58	99.52 149	99.56 74	99.41 172	99.39 213	99.01 18	99.74 41	99.78 95	95.56 182	99.92 80	99.52 7	98.18 210	99.72 87

CPTT-MVS		99.11 92	98.90 102	99.74 56	99.80 41	99.46 93	99.59 81	99.49 130	97.03 228	99.63 73	99.69 140	97.27 126	99.96 19	97.82 195	99.84 65	99.81 41

Effi-MVS+-dtu		98.78 137	98.89 104	98.47 247	99.33 201	96.91 279	99.57 93	99.30 260	98.47 68	99.41 125	98.99 316	96.78 140	99.74 179	98.73 101	99.38 138	98.74 239

WTY-MVS		99.06 100	98.88 105	99.61 82	99.62 126	99.16 123	99.37 192	99.56 56	98.04 125	99.53 99	99.62 179	96.84 138	99.94 54	98.85 83	98.49 197	99.72 87

testtj		99.12 87	98.87 106	99.86 18	99.72 80	99.79 30	99.44 157	99.51 103	97.29 201	99.59 87	99.74 117	98.15 102	99.96 19	96.74 274	99.69 111	99.81 41

CANet_DTU		98.97 113	98.87 106	99.25 149	99.33 201	98.42 209	99.08 264	99.30 260	99.16 5	99.43 118	99.75 111	95.27 192	99.97 11	98.56 131	99.95 6	99.36 177

1121		99.09 96	98.87 106	99.75 51	99.74 70	99.60 65	99.27 222	99.48 142	96.82 244	99.25 166	99.65 159	98.38 86	99.93 69	97.53 225	99.67 118	99.73 81

IS-MVSNet		99.05 102	98.87 106	99.57 88	99.73 75	99.32 104	99.75 28	99.20 278	98.02 128	99.56 92	99.86 23	96.54 149	99.67 208	98.09 172	99.13 156	99.73 81

canonicalmvs		99.02 106	98.86 110	99.51 107	99.42 178	99.32 104	99.80 17	99.48 142	98.63 58	99.31 149	98.81 325	97.09 130	99.75 178	99.27 36	97.90 220	99.47 164

PLC	97.94 4	99.02 106	98.85 111	99.53 99	99.66 110	99.01 143	99.24 235	99.52 90	96.85 240	99.27 159	99.48 230	98.25 96	99.91 91	97.76 200	99.62 126	99.65 113
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
ETH3D cwj APD-0.16		99.06 100	98.84 112	99.72 61	99.51 152	99.60 65	99.23 236	99.44 191	97.04 226	99.39 132	99.67 152	98.30 92	99.92 80	97.27 241	99.69 111	99.64 120

mvs-test1		98.86 121	98.84 112	98.89 195	99.33 201	97.77 239	99.44 157	99.30 260	98.47 68	99.10 196	99.43 241	96.78 140	99.95 43	98.73 101	99.02 168	98.96 215

PAPM_NR		99.04 103	98.84 112	99.66 68	99.74 70	99.44 95	99.39 184	99.38 219	97.70 158	99.28 156	99.28 283	98.34 90	99.85 131	96.96 263	99.45 134	99.69 99

PVSNet	96.02 17	98.85 129	98.84 112	98.89 195	99.73 75	97.28 252	98.32 345	99.60 40	97.86 137	99.50 104	99.57 196	96.75 143	99.86 125	98.56 131	99.70 110	99.54 143

Fast-Effi-MVS+-dtu		98.77 139	98.83 116	98.60 228	99.41 181	96.99 273	99.52 118	99.49 130	98.11 111	99.24 167	99.34 269	96.96 136	99.79 164	97.95 185	99.45 134	99.02 208

PVSNet_BlendedMVS		98.86 121	98.80 117	99.03 170	99.76 52	98.79 175	99.28 217	99.91 3	97.42 191	99.67 60	99.37 260	97.53 116	99.88 119	98.98 62	97.29 251	98.42 315

AdaColmap		99.01 109	98.80 117	99.66 68	99.56 144	99.54 78	99.18 245	99.70 15	98.18 104	99.35 143	99.63 173	96.32 156	99.90 106	97.48 229	99.77 93	99.55 141

MSDG		98.98 111	98.80 117	99.53 99	99.76 52	99.19 118	98.75 318	99.55 66	97.25 205	99.47 109	99.77 102	97.82 110	99.87 122	96.93 266	99.90 23	99.54 143

train_agg		99.02 106	98.77 120	99.77 47	99.67 101	99.65 57	99.05 270	99.41 203	96.28 280	98.95 223	99.49 224	98.76 53	99.91 91	97.63 213	99.72 105	99.75 69

1112_ss		98.98 111	98.77 120	99.59 84	99.68 100	99.02 141	99.25 233	99.48 142	97.23 208	99.13 189	99.58 192	96.93 137	99.90 106	98.87 78	98.78 184	99.84 18

agg_prior1		99.01 109	98.76 122	99.76 50	99.67 101	99.62 61	98.99 286	99.40 209	96.26 283	98.87 236	99.49 224	98.77 51	99.91 91	97.69 210	99.72 105	99.75 69

COLMAP_ROB	97.56 6	98.86 121	98.75 123	99.17 157	99.88 11	98.53 194	99.34 205	99.59 43	97.55 173	98.70 261	99.89 10	95.83 173	99.90 106	98.10 171	99.90 23	99.08 197
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
AllTest		98.87 118	98.72 124	99.31 136	99.86 21	98.48 204	99.56 100	99.61 35	97.85 139	99.36 140	99.85 29	95.95 166	99.85 131	96.66 280	99.83 72	99.59 134

Vis-MVSNet (Re-imp)		98.87 118	98.72 124	99.31 136	99.71 86	98.88 163	99.80 17	99.44 191	97.91 135	99.36 140	99.78 95	95.49 185	99.43 247	97.91 187	99.11 157	99.62 126

DPM-MVS		98.95 114	98.71 126	99.66 68	99.63 120	99.55 76	98.64 328	99.10 289	97.93 133	99.42 121	99.55 202	98.67 66	99.80 161	95.80 296	99.68 116	99.61 128

EPNet		98.86 121	98.71 126	99.30 140	97.20 348	98.18 217	99.62 68	98.91 311	99.28 2	98.63 272	99.81 62	95.96 165	99.99 1	99.24 38	99.72 105	99.73 81
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
UGNet		98.87 118	98.69 128	99.40 124	99.22 231	98.72 179	99.44 157	99.68 19	99.24 3	99.18 184	99.42 244	92.74 267	99.96 19	99.34 28	99.94 9	99.53 147
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
XVG-OURS		98.73 141	98.68 129	98.88 198	99.70 93	97.73 241	98.92 301	99.55 66	98.52 65	99.45 113	99.84 38	95.27 192	99.91 91	98.08 176	98.84 180	99.00 209

EI-MVSNet		98.67 146	98.67 130	98.68 225	99.35 196	97.97 227	99.50 128	99.38 219	96.93 237	99.20 178	99.83 42	97.87 108	99.36 259	98.38 149	97.56 232	98.71 243

CVMVSNet		98.57 152	98.67 130	98.30 265	99.35 196	95.59 312	99.50 128	99.55 66	98.60 61	99.39 132	99.83 42	94.48 227	99.45 238	98.75 98	98.56 193	99.85 14

114514_t		98.93 115	98.67 130	99.72 61	99.85 25	99.53 81	99.62 68	99.59 43	92.65 340	99.71 46	99.78 95	98.06 105	99.90 106	98.84 85	99.91 16	99.74 74

Test_1112_low_res		98.89 117	98.66 133	99.57 88	99.69 96	98.95 154	99.03 276	99.47 160	96.98 230	99.15 187	99.23 291	96.77 142	99.89 114	98.83 88	98.78 184	99.86 11

HY-MVS	97.30 7	98.85 129	98.64 134	99.47 114	99.42 178	99.08 135	99.62 68	99.36 229	97.39 194	99.28 156	99.68 146	96.44 153	99.92 80	98.37 151	98.22 206	99.40 175

test_yl		98.86 121	98.63 135	99.54 93	99.49 161	99.18 120	99.50 128	99.07 294	98.22 98	99.61 80	99.51 218	95.37 188	99.84 136	98.60 123	98.33 200	99.59 134

DCV-MVSNet		98.86 121	98.63 135	99.54 93	99.49 161	99.18 120	99.50 128	99.07 294	98.22 98	99.61 80	99.51 218	95.37 188	99.84 136	98.60 123	98.33 200	99.59 134

FIs		98.78 137	98.63 135	99.23 153	99.18 240	99.54 78	99.83 10	99.59 43	98.28 91	98.79 248	99.81 62	96.75 143	99.37 255	99.08 54	96.38 270	98.78 227

ab-mvs		98.86 121	98.63 135	99.54 93	99.64 117	99.19 118	99.44 157	99.54 73	97.77 150	99.30 151	99.81 62	94.20 235	99.93 69	99.17 45	98.82 181	99.49 158

MAR-MVS		98.86 121	98.63 135	99.54 93	99.37 193	99.66 54	99.45 153	99.54 73	96.61 257	99.01 212	99.40 252	97.09 130	99.86 125	97.68 212	99.53 132	99.10 192
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
GeoE		98.85 129	98.62 140	99.53 99	99.61 130	99.08 135	99.80 17	99.51 103	97.10 221	99.31 149	99.78 95	95.23 196	99.77 171	98.21 161	99.03 166	99.75 69

FC-MVSNet-test		98.75 140	98.62 140	99.15 160	99.08 262	99.45 94	99.86 5	99.60 40	98.23 97	98.70 261	99.82 49	96.80 139	99.22 283	99.07 55	96.38 270	98.79 226

XVG-OURS-SEG-HR		98.69 144	98.62 140	98.89 195	99.71 86	97.74 240	99.12 255	99.54 73	98.44 74	99.42 121	99.71 129	94.20 235	99.92 80	98.54 136	98.90 177	99.00 209

RPSCF		98.22 173	98.62 140	96.99 318	99.82 37	91.58 353	99.72 32	99.44 191	96.61 257	99.66 65	99.89 10	95.92 169	99.82 152	97.46 232	99.10 160	99.57 139

PatchMatch-RL		98.84 132	98.62 140	99.52 105	99.71 86	99.28 110	99.06 268	99.77 9	97.74 155	99.50 104	99.53 211	95.41 186	99.84 136	97.17 252	99.64 123	99.44 169

PMMVS		98.80 136	98.62 140	99.34 130	99.27 219	98.70 180	98.76 317	99.31 256	97.34 196	99.21 175	99.07 307	97.20 127	99.82 152	98.56 131	98.87 178	99.52 148

Effi-MVS+		98.81 133	98.59 146	99.48 111	99.46 170	99.12 132	98.08 351	99.50 122	97.50 181	99.38 135	99.41 248	96.37 155	99.81 156	99.11 51	98.54 194	99.51 154

test_djsdf		98.67 146	98.57 147	98.98 176	98.70 313	98.91 161	99.88 1	99.46 170	97.55 173	99.22 172	99.88 15	95.73 177	99.28 273	99.03 57	97.62 227	98.75 235

alignmvs		98.81 133	98.56 148	99.58 87	99.43 177	99.42 97	99.51 122	98.96 304	98.61 60	99.35 143	98.92 322	94.78 210	99.77 171	99.35 24	98.11 216	99.54 143

1314		98.68 145	98.54 149	99.11 162	98.89 286	98.65 184	99.27 222	99.49 130	96.89 238	97.99 309	99.56 199	97.72 114	99.83 145	97.74 203	99.27 146	98.84 222

D2MVS		98.41 160	98.50 150	98.15 276	99.26 221	96.62 289	99.40 180	99.61 35	97.71 157	98.98 219	99.36 263	96.04 163	99.67 208	98.70 105	97.41 247	98.15 330

tpmrst		98.33 166	98.48 151	97.90 292	99.16 248	94.78 332	99.31 209	99.11 288	97.27 203	99.45 113	99.59 189	95.33 190	99.84 136	98.48 139	98.61 187	99.09 196

RRT_MVS		98.60 151	98.44 152	99.05 167	98.88 287	99.14 128	99.49 138	99.38 219	97.76 151	99.29 154	99.86 23	95.38 187	99.36 259	98.81 93	97.16 256	98.64 275

Fast-Effi-MVS+		98.70 142	98.43 153	99.51 107	99.51 152	99.28 110	99.52 118	99.47 160	96.11 298	99.01 212	99.34 269	96.20 160	99.84 136	97.88 189	98.82 181	99.39 176

nrg030		98.64 149	98.42 154	99.28 146	99.05 268	99.69 47	99.81 13	99.46 170	98.04 125	99.01 212	99.82 49	96.69 145	99.38 252	99.34 28	94.59 310	98.78 227

IterMVS-LS		98.46 155	98.42 154	98.58 232	99.59 136	98.00 225	99.37 192	99.43 199	96.94 236	99.07 203	99.59 189	97.87 108	99.03 310	98.32 157	95.62 290	98.71 243
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
BH-untuned		98.42 158	98.36 156	98.59 229	99.49 161	96.70 285	99.27 222	99.13 287	97.24 207	98.80 246	99.38 257	95.75 176	99.74 179	97.07 257	99.16 152	99.33 181

PatchmatchNet		98.31 167	98.36 156	98.19 273	99.16 248	95.32 321	99.27 222	98.92 308	97.37 195	99.37 137	99.58 192	94.90 204	99.70 203	97.43 236	99.21 149	99.54 143
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ETH3 D test6400		98.70 142	98.35 158	99.73 58	99.69 96	99.60 65	99.16 247	99.45 182	95.42 309	99.27 159	99.60 186	97.39 119	99.91 91	95.36 307	99.83 72	99.70 96

PAPR		98.63 150	98.34 159	99.51 107	99.40 186	99.03 140	98.80 313	99.36 229	96.33 277	99.00 217	99.12 305	98.46 79	99.84 136	95.23 309	99.37 142	99.66 109

ACMM	97.58 5	98.37 164	98.34 159	98.48 243	99.41 181	97.10 260	99.56 100	99.45 182	98.53 64	99.04 209	99.85 29	93.00 259	99.71 196	98.74 99	97.45 243	98.64 275
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVSTER		98.49 153	98.32 161	99.00 174	99.35 196	99.02 141	99.54 112	99.38 219	97.41 192	99.20 178	99.73 124	93.86 247	99.36 259	98.87 78	97.56 232	98.62 285

MDTV_nov1_ep13			98.32 161		99.11 255	94.44 335	99.27 222	98.74 325	97.51 180	99.40 130	99.62 179	94.78 210	99.76 175	97.59 216	98.81 183

QAPM		98.67 146	98.30 163	99.80 40	99.20 235	99.67 52	99.77 24	99.72 11	94.74 321	98.73 253	99.90 7	95.78 175	99.98 6	96.96 263	99.88 36	99.76 68

anonymousdsp		98.44 156	98.28 164	98.94 182	98.50 328	98.96 152	99.77 24	99.50 122	97.07 223	98.87 236	99.77 102	94.76 214	99.28 273	98.66 113	97.60 228	98.57 300

jajsoiax		98.43 157	98.28 164	98.88 198	98.60 323	98.43 207	99.82 11	99.53 84	98.19 101	98.63 272	99.80 76	93.22 257	99.44 243	99.22 39	97.50 238	98.77 231

mvs_tets		98.40 162	98.23 166	98.91 190	98.67 316	98.51 200	99.66 50	99.53 84	98.19 101	98.65 270	99.81 62	92.75 265	99.44 243	99.31 31	97.48 242	98.77 231

HQP_MVS		98.27 172	98.22 167	98.44 252	99.29 214	96.97 275	99.39 184	99.47 160	98.97 30	99.11 193	99.61 183	92.71 270	99.69 206	97.78 198	97.63 225	98.67 263

SCA		98.19 177	98.16 168	98.27 270	99.30 210	95.55 313	99.07 265	98.97 302	97.57 171	99.43 118	99.57 196	92.72 268	99.74 179	97.58 217	99.20 150	99.52 148

LCM-MVSNet-Re		97.83 228	98.15 169	96.87 323	99.30 210	92.25 351	99.59 81	98.26 340	97.43 189	96.20 338	99.13 302	96.27 158	98.73 333	98.17 167	98.99 170	99.64 120

tttt0517		98.42 158	98.14 170	99.28 146	99.66 110	98.38 210	99.74 31	96.85 356	97.68 160	99.79 26	99.74 117	91.39 303	99.89 114	98.83 88	99.56 129	99.57 139

LPG-MVS_test		98.22 173	98.13 171	98.49 241	99.33 201	97.05 266	99.58 88	99.55 66	97.46 182	99.24 167	99.83 42	92.58 275	99.72 190	98.09 172	97.51 236	98.68 256

OpenMVS	96.50 16	98.47 154	98.12 172	99.52 105	99.04 269	99.53 81	99.82 11	99.72 11	94.56 324	98.08 304	99.88 15	94.73 216	99.98 6	97.47 231	99.76 96	99.06 203

miper_ehance_all_eth		98.18 179	98.10 173	98.41 254	99.23 227	97.72 242	98.72 321	99.31 256	96.60 259	98.88 234	99.29 281	97.29 125	99.13 297	97.60 215	95.99 279	98.38 320

OPM-MVS		98.19 177	98.10 173	98.45 249	98.88 287	97.07 264	99.28 217	99.38 219	98.57 62	99.22 172	99.81 62	92.12 286	99.66 211	98.08 176	97.54 234	98.61 294

CLD-MVS		98.16 181	98.10 173	98.33 261	99.29 214	96.82 282	98.75 318	99.44 191	97.83 142	99.13 189	99.55 202	92.92 261	99.67 208	98.32 157	97.69 224	98.48 306
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
XXY-MVS		98.38 163	98.09 176	99.24 151	99.26 221	99.32 104	99.56 100	99.55 66	97.45 185	98.71 255	99.83 42	93.23 255	99.63 223	98.88 74	96.32 272	98.76 233

miper_enhance_ethall		98.16 181	98.08 177	98.41 254	98.96 281	97.72 242	98.45 338	99.32 253	96.95 234	98.97 221	99.17 297	97.06 132	99.22 283	97.86 191	95.99 279	98.29 323

ADS-MVSNet		98.20 176	98.08 177	98.56 235	99.33 201	96.48 293	99.23 236	99.15 284	96.24 285	99.10 196	99.67 152	94.11 239	99.71 196	96.81 271	99.05 164	99.48 159

BH-RMVSNet		98.41 160	98.08 177	99.40 124	99.41 181	98.83 171	99.30 211	98.77 321	97.70 158	98.94 225	99.65 159	92.91 263	99.74 179	96.52 282	99.55 131	99.64 120

ADS-MVSNet2		98.02 200	98.07 180	97.87 293	99.33 201	95.19 324	99.23 236	99.08 292	96.24 285	99.10 196	99.67 152	94.11 239	98.93 327	96.81 271	99.05 164	99.48 159

cl_fuxian		98.12 187	98.04 181	98.38 258	99.30 210	97.69 245	98.81 312	99.33 245	96.67 251	98.83 242	99.34 269	97.11 129	98.99 316	97.58 217	95.34 296	98.48 306

thisisatest0530		98.35 165	98.03 182	99.31 136	99.63 120	98.56 191	99.54 112	96.75 358	97.53 178	99.73 43	99.65 159	91.25 306	99.89 114	98.62 117	99.56 129	99.48 159

EU-MVSNet		97.98 207	98.03 182	97.81 298	98.72 310	96.65 288	99.66 50	99.66 27	98.09 114	98.35 293	99.82 49	95.25 195	98.01 342	97.41 237	95.30 297	98.78 227

tpmvs		97.98 207	98.02 184	97.84 295	99.04 269	94.73 333	99.31 209	99.20 278	96.10 302	98.76 251	99.42 244	94.94 200	99.81 156	96.97 262	98.45 198	98.97 213

UniMVSNet (Re)		98.29 170	98.00 185	99.13 161	99.00 274	99.36 102	99.49 138	99.51 103	97.95 131	98.97 221	99.13 302	96.30 157	99.38 252	98.36 153	93.34 326	98.66 271

ACMH	97.28 8	98.10 188	97.99 186	98.44 252	99.41 181	96.96 277	99.60 75	99.56 56	98.09 114	98.15 302	99.91 5	90.87 310	99.70 203	98.88 74	97.45 243	98.67 263
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous202405211		98.30 169	97.98 187	99.26 148	99.57 140	98.16 218	99.41 172	98.55 337	96.03 303	99.19 181	99.74 117	91.87 290	99.92 80	99.16 47	98.29 205	99.70 96

bset_n11_16_dypcd		98.16 181	97.97 188	98.73 220	98.26 333	98.28 214	97.99 353	98.01 346	97.68 160	99.10 196	99.63 173	95.68 179	99.15 293	98.78 97	96.55 265	98.75 235

UniMVSNet_NR-MVSNet		98.22 173	97.97 188	98.96 179	98.92 284	98.98 145	99.48 144	99.53 84	97.76 151	98.71 255	99.46 237	96.43 154	99.22 283	98.57 128	92.87 333	98.69 251

eth_miper_zixun_eth		98.05 197	97.96 190	98.33 261	99.26 221	97.38 250	98.56 334	99.31 256	96.65 253	98.88 234	99.52 214	96.58 147	99.12 301	97.39 238	95.53 293	98.47 308

EPNet_dtu		98.03 198	97.96 190	98.23 271	98.27 332	95.54 315	99.23 236	98.75 322	99.02 15	97.82 314	99.71 129	96.11 161	99.48 234	93.04 334	99.65 122	99.69 99
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
VPA-MVSNet		98.29 170	97.95 192	99.30 140	99.16 248	99.54 78	99.50 128	99.58 49	98.27 93	99.35 143	99.37 260	92.53 277	99.65 215	99.35 24	94.46 311	98.72 241

baseline1		98.31 167	97.95 192	99.38 128	99.50 159	98.74 177	99.59 81	98.93 306	98.41 75	99.14 188	99.60 186	94.59 222	99.79 164	98.48 139	93.29 327	99.61 128

ACMP	97.20 11	98.06 192	97.94 194	98.45 249	99.37 193	97.01 271	99.44 157	99.49 130	97.54 176	98.45 285	99.79 88	91.95 289	99.72 190	97.91 187	97.49 241	98.62 285
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
CR-MVSNet		98.17 180	97.93 195	98.87 202	99.18 240	98.49 202	99.22 241	99.33 245	96.96 232	99.56 92	99.38 257	94.33 231	99.00 315	94.83 315	98.58 190	99.14 189

miper_lstm_enhance		98.00 205	97.91 196	98.28 269	99.34 200	97.43 249	98.88 305	99.36 229	96.48 269	98.80 246	99.55 202	95.98 164	98.91 328	97.27 241	95.50 294	98.51 304

pmmvs4		98.13 185	97.90 197	98.81 213	98.61 322	98.87 164	98.99 286	99.21 277	96.44 272	99.06 207	99.58 192	95.90 171	99.11 302	97.18 251	96.11 276	98.46 312

test-LLR		98.06 192	97.90 197	98.55 237	98.79 299	97.10 260	98.67 324	97.75 349	97.34 196	98.61 275	98.85 323	94.45 228	99.45 238	97.25 243	99.38 138	99.10 192

HQP-MVS		98.02 200	97.90 197	98.37 259	99.19 237	96.83 280	98.98 290	99.39 213	98.24 94	98.66 264	99.40 252	92.47 279	99.64 218	97.19 249	97.58 230	98.64 275

LTVRE_ROB	97.16 12	98.02 200	97.90 197	98.40 256	99.23 227	96.80 283	99.70 35	99.60 40	97.12 217	98.18 301	99.70 133	91.73 295	99.72 190	98.39 147	97.45 243	98.68 256
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
BH-w/o		98.00 205	97.89 201	98.32 263	99.35 196	96.20 302	99.01 284	98.90 313	96.42 274	98.38 290	99.00 315	95.26 194	99.72 190	96.06 290	98.61 187	99.03 206

WR-MVS_H		98.13 185	97.87 202	98.90 192	99.02 272	98.84 168	99.70 35	99.59 43	97.27 203	98.40 289	99.19 296	95.53 183	99.23 280	98.34 154	93.78 322	98.61 294

cl-mvsnet1		98.01 203	97.85 203	98.48 243	99.24 226	97.95 231	98.71 322	99.35 234	96.50 264	98.60 277	99.54 207	95.72 178	99.03 310	97.21 245	95.77 285	98.46 312

cl-mvsnet____		98.01 203	97.84 204	98.55 237	99.25 225	97.97 227	98.71 322	99.34 238	96.47 271	98.59 278	99.54 207	95.65 181	99.21 288	97.21 245	95.77 285	98.46 312

dp		97.75 242	97.80 205	97.59 305	99.10 258	93.71 342	99.32 207	98.88 315	96.48 269	99.08 202	99.55 202	92.67 273	99.82 152	96.52 282	98.58 190	99.24 185

thisisatest0515		98.14 184	97.79 206	99.19 155	99.50 159	98.50 201	98.61 329	96.82 357	96.95 234	99.54 97	99.43 241	91.66 299	99.86 125	98.08 176	99.51 133	99.22 186

V42		98.06 192	97.79 206	98.86 205	98.98 278	98.84 168	99.69 37	99.34 238	96.53 263	99.30 151	99.37 260	94.67 219	99.32 268	97.57 221	94.66 308	98.42 315

DU-MVS		98.08 191	97.79 206	98.96 179	98.87 291	98.98 145	99.41 172	99.45 182	97.87 136	98.71 255	99.50 221	94.82 207	99.22 283	98.57 128	92.87 333	98.68 256

CP-MVSNet		98.09 189	97.78 209	99.01 172	98.97 280	99.24 115	99.67 45	99.46 170	97.25 205	98.48 284	99.64 166	93.79 248	99.06 306	98.63 116	94.10 318	98.74 239

ACMH+	97.24 10	97.92 215	97.78 209	98.32 263	99.46 170	96.68 287	99.56 100	99.54 73	98.41 75	97.79 316	99.87 20	90.18 317	99.66 211	98.05 180	97.18 255	98.62 285

v2v482		98.06 192	97.77 211	98.92 186	98.90 285	98.82 172	99.57 93	99.36 229	96.65 253	99.19 181	99.35 266	94.20 235	99.25 278	97.72 206	94.97 304	98.69 251

OurMVSNet-221017-0		97.88 218	97.77 211	98.19 273	98.71 312	96.53 291	99.88 1	99.00 299	97.79 148	98.78 249	99.94 3	91.68 296	99.35 263	97.21 245	96.99 259	98.69 251

IterMVS		97.83 228	97.77 211	98.02 283	99.58 138	96.27 300	99.02 279	99.48 142	97.22 209	98.71 255	99.70 133	92.75 265	99.13 297	97.46 232	96.00 278	98.67 263
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FMVSNet3		98.03 198	97.76 214	98.84 209	99.39 189	98.98 145	99.40 180	99.38 219	96.67 251	99.07 203	99.28 283	92.93 260	98.98 317	97.10 254	96.65 261	98.56 301

IterMVS-SCA-FT		97.82 231	97.75 215	98.06 280	99.57 140	96.36 297	99.02 279	99.49 130	97.18 211	98.71 255	99.72 128	92.72 268	99.14 294	97.44 235	95.86 284	98.67 263

MVP-Stereo		97.81 233	97.75 215	97.99 286	97.53 341	96.60 290	98.96 294	98.85 317	97.22 209	97.23 325	99.36 263	95.28 191	99.46 237	95.51 302	99.78 90	97.92 344
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
WR-MVS		98.06 192	97.73 217	99.06 165	98.86 294	99.25 114	99.19 244	99.35 234	97.30 200	98.66 264	99.43 241	93.94 244	99.21 288	98.58 126	94.28 315	98.71 243

CostFormer		97.72 248	97.73 217	97.71 302	99.15 251	94.02 339	99.54 112	99.02 298	94.67 322	99.04 209	99.35 266	92.35 285	99.77 171	98.50 138	97.94 219	99.34 180

XVG-ACMP-BASELINE		97.83 228	97.71 219	98.20 272	99.11 255	96.33 298	99.41 172	99.52 90	98.06 123	99.05 208	99.50 221	89.64 323	99.73 186	97.73 204	97.38 249	98.53 302

v1144		97.98 207	97.69 220	98.85 208	98.87 291	98.66 183	99.54 112	99.35 234	96.27 282	99.23 171	99.35 266	94.67 219	99.23 280	96.73 275	95.16 300	98.68 256

Anonymous20240529		98.09 189	97.68 221	99.34 130	99.66 110	98.44 206	99.40 180	99.43 199	93.67 331	99.22 172	99.89 10	90.23 316	99.93 69	99.26 37	98.33 200	99.66 109

our_test_3		97.65 261	97.68 221	97.55 307	98.62 320	94.97 328	98.84 309	99.30 260	96.83 243	98.19 300	99.34 269	97.01 134	99.02 312	95.00 313	96.01 277	98.64 275

TranMVSNet+NR-MVSNet		97.93 212	97.66 223	98.76 219	98.78 302	98.62 187	99.65 57	99.49 130	97.76 151	98.49 283	99.60 186	94.23 234	98.97 324	98.00 181	92.90 331	98.70 247

Patchmatch-test		97.93 212	97.65 224	98.77 218	99.18 240	97.07 264	99.03 276	99.14 286	96.16 293	98.74 252	99.57 196	94.56 224	99.72 190	93.36 330	99.11 157	99.52 148

EPMVS		97.82 231	97.65 224	98.35 260	98.88 287	95.98 305	99.49 138	94.71 364	97.57 171	99.26 164	99.48 230	92.46 282	99.71 196	97.87 190	99.08 162	99.35 178

cl-mvsnet2		97.85 223	97.64 226	98.48 243	99.09 260	97.87 234	98.60 331	99.33 245	97.11 220	98.87 236	99.22 292	92.38 284	99.17 292	98.21 161	95.99 279	98.42 315

v8		97.95 211	97.63 227	98.93 184	98.95 282	98.81 174	99.80 17	99.41 203	96.03 303	99.10 196	99.42 244	94.92 203	99.30 271	96.94 265	94.08 319	98.66 271

NR-MVSNet		97.97 210	97.61 228	99.02 171	98.87 291	99.26 113	99.47 149	99.42 201	97.63 166	97.08 330	99.50 221	95.07 199	99.13 297	97.86 191	93.59 324	98.68 256

v144192		97.92 215	97.60 229	98.87 202	98.83 297	98.65 184	99.55 109	99.34 238	96.20 288	99.32 148	99.40 252	94.36 230	99.26 277	96.37 287	95.03 303	98.70 247

RRT_test8_iter05		97.72 248	97.60 229	98.08 278	99.23 227	96.08 304	99.63 62	99.49 130	97.54 176	98.94 225	99.81 62	87.99 340	99.35 263	99.21 41	96.51 267	98.81 223

PS-CasMVS		97.93 212	97.59 231	98.95 181	98.99 275	99.06 138	99.68 42	99.52 90	97.13 215	98.31 295	99.68 146	92.44 283	99.05 307	98.51 137	94.08 319	98.75 235

v148		97.79 236	97.55 232	98.50 240	98.74 307	97.72 242	99.54 112	99.33 245	96.26 283	98.90 231	99.51 218	94.68 218	99.14 294	97.83 194	93.15 330	98.63 283

baseline2		97.87 220	97.55 232	98.82 211	99.18 240	98.02 224	99.41 172	96.58 360	96.97 231	96.51 335	99.17 297	93.43 252	99.57 228	97.71 207	99.03 166	98.86 220

tpm		97.67 259	97.55 232	98.03 281	99.02 272	95.01 327	99.43 163	98.54 338	96.44 272	99.12 191	99.34 269	91.83 292	99.60 226	97.75 202	96.46 268	99.48 159

Anonymous20231211		97.88 218	97.54 235	98.90 192	99.71 86	98.53 194	99.48 144	99.57 51	94.16 327	98.81 244	99.68 146	93.23 255	99.42 248	98.84 85	94.42 313	98.76 233

v7n		97.87 220	97.52 236	98.92 186	98.76 306	98.58 190	99.84 6	99.46 170	96.20 288	98.91 229	99.70 133	94.89 205	99.44 243	96.03 291	93.89 321	98.75 235

v10		97.85 223	97.52 236	98.86 205	98.99 275	98.67 182	99.75 28	99.41 203	95.70 306	98.98 219	99.41 248	94.75 215	99.23 280	96.01 292	94.63 309	98.67 263

thres600view7		97.86 222	97.51 238	98.92 186	99.72 80	97.95 231	99.59 81	98.74 325	97.94 132	99.27 159	98.62 332	91.75 293	99.86 125	93.73 326	98.19 209	98.96 215

testgi		97.65 261	97.50 239	98.13 277	99.36 195	96.45 294	99.42 170	99.48 142	97.76 151	97.87 312	99.45 238	91.09 307	98.81 331	94.53 317	98.52 195	99.13 191

GBi-Net		97.68 256	97.48 240	98.29 266	99.51 152	97.26 255	99.43 163	99.48 142	96.49 265	99.07 203	99.32 276	90.26 313	98.98 317	97.10 254	96.65 261	98.62 285

test1		97.68 256	97.48 240	98.29 266	99.51 152	97.26 255	99.43 163	99.48 142	96.49 265	99.07 203	99.32 276	90.26 313	98.98 317	97.10 254	96.65 261	98.62 285

tfpnnormal		97.84 226	97.47 242	98.98 176	99.20 235	99.22 117	99.64 60	99.61 35	96.32 278	98.27 298	99.70 133	93.35 254	99.44 243	95.69 298	95.40 295	98.27 324

GA-MVS		97.85 223	97.47 242	99.00 174	99.38 191	97.99 226	98.57 332	99.15 284	97.04 226	98.90 231	99.30 279	89.83 319	99.38 252	96.70 277	98.33 200	99.62 126

LF4IMVS		97.52 268	97.46 244	97.70 303	98.98 278	95.55 313	99.29 215	98.82 320	98.07 119	98.66 264	99.64 166	89.97 318	99.61 225	97.01 258	96.68 260	97.94 342

ppachtmachnet_test		97.49 274	97.45 245	97.61 304	98.62 320	95.24 322	98.80 313	99.46 170	96.11 298	98.22 299	99.62 179	96.45 152	98.97 324	93.77 325	95.97 282	98.61 294

thres100view900		97.76 238	97.45 245	98.69 224	99.72 80	97.86 236	99.59 81	98.74 325	97.93 133	99.26 164	98.62 332	91.75 293	99.83 145	93.22 331	98.18 210	98.37 321

v1921920		97.80 235	97.45 245	98.84 209	98.80 298	98.53 194	99.52 118	99.34 238	96.15 295	99.24 167	99.47 233	93.98 243	99.29 272	95.40 305	95.13 301	98.69 251

Baseline_NR-MVSNet		97.76 238	97.45 245	98.68 225	99.09 260	98.29 212	99.41 172	98.85 317	95.65 307	98.63 272	99.67 152	94.82 207	99.10 304	98.07 179	92.89 332	98.64 275

MIMVSNet		97.73 246	97.45 245	98.57 233	99.45 175	97.50 247	99.02 279	98.98 301	96.11 298	99.41 125	99.14 301	90.28 312	98.74 332	95.74 297	98.93 173	99.47 164

v1192		97.81 233	97.44 250	98.91 190	98.88 287	98.68 181	99.51 122	99.34 238	96.18 290	99.20 178	99.34 269	94.03 242	99.36 259	95.32 308	95.18 299	98.69 251

VPNet		97.84 226	97.44 250	99.01 172	99.21 233	98.94 157	99.48 144	99.57 51	98.38 78	99.28 156	99.73 124	88.89 329	99.39 250	99.19 42	93.27 328	98.71 243

PEN-MVS		97.76 238	97.44 250	98.72 222	98.77 305	98.54 193	99.78 22	99.51 103	97.06 225	98.29 297	99.64 166	92.63 274	98.89 330	98.09 172	93.16 329	98.72 241

cascas		97.69 254	97.43 253	98.48 243	98.60 323	97.30 251	98.18 350	99.39 213	92.96 339	98.41 288	98.78 328	93.77 249	99.27 276	98.16 168	98.61 187	98.86 220

test0.0.03 1		97.71 252	97.42 254	98.56 235	98.41 331	97.82 237	98.78 315	98.63 334	97.34 196	98.05 308	98.98 319	94.45 228	98.98 317	95.04 312	97.15 257	98.89 219

TR-MVS		97.76 238	97.41 255	98.82 211	99.06 265	97.87 234	98.87 307	98.56 336	96.63 256	98.68 263	99.22 292	92.49 278	99.65 215	95.40 305	97.79 222	98.95 218

DWT-MVSNet_test		97.53 267	97.40 256	97.93 289	99.03 271	94.86 331	99.57 93	98.63 334	96.59 261	98.36 292	98.79 326	89.32 325	99.74 179	98.14 170	98.16 214	99.20 188

Patchmtry		97.75 242	97.40 256	98.81 213	99.10 258	98.87 164	99.11 261	99.33 245	94.83 319	98.81 244	99.38 257	94.33 231	99.02 312	96.10 289	95.57 291	98.53 302

tfpn200view9		97.72 248	97.38 258	98.72 222	99.69 96	97.96 229	99.50 128	98.73 330	97.83 142	99.17 185	98.45 337	91.67 297	99.83 145	93.22 331	98.18 210	98.37 321

thres400		97.77 237	97.38 258	98.92 186	99.69 96	97.96 229	99.50 128	98.73 330	97.83 142	99.17 185	98.45 337	91.67 297	99.83 145	93.22 331	98.18 210	98.96 215

tpm cat1		97.39 277	97.36 260	97.50 309	99.17 246	93.73 341	99.43 163	99.31 256	91.27 344	98.71 255	99.08 306	94.31 233	99.77 171	96.41 286	98.50 196	99.00 209

FMVSNet2		97.72 248	97.36 260	98.80 215	99.51 152	98.84 168	99.45 153	99.42 201	96.49 265	98.86 241	99.29 281	90.26 313	98.98 317	96.44 284	96.56 264	98.58 299

LFMVS		97.90 217	97.35 262	99.54 93	99.52 149	99.01 143	99.39 184	98.24 341	97.10 221	99.65 70	99.79 88	84.79 351	99.91 91	99.28 34	98.38 199	99.69 99

VDD-MVS		97.73 246	97.35 262	98.88 198	99.47 169	97.12 259	99.34 205	98.85 317	98.19 101	99.67 60	99.85 29	82.98 353	99.92 80	99.49 14	98.32 204	99.60 130

DSMNet-mixed		97.25 281	97.35 262	96.95 321	97.84 338	93.61 345	99.57 93	96.63 359	96.13 297	98.87 236	98.61 334	94.59 222	97.70 349	95.08 311	98.86 179	99.55 141

tpm2		97.44 276	97.34 265	97.74 301	99.15 251	94.36 336	99.45 153	98.94 305	93.45 336	98.90 231	99.44 239	91.35 304	99.59 227	97.31 239	98.07 217	99.29 183

TAPA-MVS	97.07 15	97.74 245	97.34 265	98.94 182	99.70 93	97.53 246	99.25 233	99.51 103	91.90 342	99.30 151	99.63 173	98.78 48	99.64 218	88.09 353	99.87 40	99.65 113
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SixPastTwentyTwo		97.50 271	97.33 267	98.03 281	98.65 317	96.23 301	99.77 24	98.68 333	97.14 214	97.90 311	99.93 4	90.45 311	99.18 291	97.00 259	96.43 269	98.67 263

MS-PatchMatch		97.24 282	97.32 268	96.99 318	98.45 330	93.51 346	98.82 311	99.32 253	97.41 192	98.13 303	99.30 279	88.99 328	99.56 229	95.68 299	99.80 84	97.90 345

v1240		97.69 254	97.32 268	98.79 216	98.85 295	98.43 207	99.48 144	99.36 229	96.11 298	99.27 159	99.36 263	93.76 250	99.24 279	94.46 318	95.23 298	98.70 247

pmmvs5		97.52 268	97.30 270	98.16 275	98.57 325	96.73 284	99.27 222	98.90 313	96.14 296	98.37 291	99.53 211	91.54 302	99.14 294	97.51 227	95.87 283	98.63 283

hse-mvs3		97.70 253	97.28 271	98.97 178	99.70 93	97.27 253	99.36 196	99.45 182	98.94 33	99.66 65	99.64 166	94.93 201	99.99 1	99.48 15	84.36 350	99.65 113

pm-mvs1		97.68 256	97.28 271	98.88 198	99.06 265	98.62 187	99.50 128	99.45 182	96.32 278	97.87 312	99.79 88	92.47 279	99.35 263	97.54 224	93.54 325	98.67 263

thres200		97.61 263	97.28 271	98.62 227	99.64 117	98.03 223	99.26 231	98.74 325	97.68 160	99.09 201	98.32 341	91.66 299	99.81 156	92.88 335	98.22 206	98.03 335

TESTMET0.1,1		97.55 265	97.27 274	98.40 256	98.93 283	96.53 291	98.67 324	97.61 352	96.96 232	98.64 271	99.28 283	88.63 333	99.45 238	97.30 240	99.38 138	99.21 187

test_part1		97.75 242	97.24 275	99.29 143	99.59 136	99.63 60	99.65 57	99.49 130	96.17 291	98.44 286	99.69 140	89.80 320	99.47 235	98.68 110	93.66 323	98.78 227

USDC		97.34 278	97.20 276	97.75 300	99.07 263	95.20 323	98.51 336	99.04 297	97.99 129	98.31 295	99.86 23	89.02 327	99.55 231	95.67 300	97.36 250	98.49 305

DTE-MVSNet		97.51 270	97.19 277	98.46 248	98.63 319	98.13 221	99.84 6	99.48 142	96.68 250	97.97 310	99.67 152	92.92 261	98.56 334	96.88 270	92.60 336	98.70 247

hse-mvs2		97.50 271	97.14 278	98.59 229	99.49 161	97.05 266	99.28 217	99.22 274	98.94 33	99.66 65	99.42 244	94.93 201	99.65 215	99.48 15	83.80 352	99.08 197

test-mter		97.49 274	97.13 279	98.55 237	98.79 299	97.10 260	98.67 324	97.75 349	96.65 253	98.61 275	98.85 323	88.23 337	99.45 238	97.25 243	99.38 138	99.10 192

PAPM		97.59 264	97.09 280	99.07 164	99.06 265	98.26 215	98.30 346	99.10 289	94.88 318	98.08 304	99.34 269	96.27 158	99.64 218	89.87 347	98.92 175	99.31 182

PCF-MVS	97.08 14	97.66 260	97.06 281	99.47 114	99.61 130	99.09 134	98.04 352	99.25 270	91.24 345	98.51 281	99.70 133	94.55 225	99.91 91	92.76 338	99.85 58	99.42 172
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
VDDNet		97.55 265	97.02 282	99.16 158	99.49 161	98.12 222	99.38 189	99.30 260	95.35 310	99.68 53	99.90 7	82.62 355	99.93 69	99.31 31	98.13 215	99.42 172

JIA-IIPM		97.50 271	97.02 282	98.93 184	98.73 308	97.80 238	99.30 211	98.97 302	91.73 343	98.91 229	94.86 356	95.10 198	99.71 196	97.58 217	97.98 218	99.28 184

TinyColmap		97.12 284	96.89 284	97.83 296	99.07 263	95.52 316	98.57 332	98.74 325	97.58 170	97.81 315	99.79 88	88.16 338	99.56 229	95.10 310	97.21 253	98.39 319

UniMVSNet_ETH3D		97.32 279	96.81 285	98.87 202	99.40 186	97.46 248	99.51 122	99.53 84	95.86 305	98.54 280	99.77 102	82.44 356	99.66 211	98.68 110	97.52 235	99.50 157

K. test v3		97.10 285	96.79 286	98.01 284	98.72 310	96.33 298	99.87 4	97.05 355	97.59 168	96.16 339	99.80 76	88.71 330	99.04 308	96.69 278	96.55 265	98.65 273

TransMVSNet (Re)		97.15 283	96.58 287	98.86 205	99.12 253	98.85 167	99.49 138	98.91 311	95.48 308	97.16 328	99.80 76	93.38 253	99.11 302	94.16 323	91.73 338	98.62 285

MVS		97.28 280	96.55 288	99.48 111	98.78 302	98.95 154	99.27 222	99.39 213	83.53 355	98.08 304	99.54 207	96.97 135	99.87 122	94.23 321	99.16 152	99.63 124

MVS_0304		96.79 289	96.52 289	97.59 305	99.22 231	94.92 330	99.04 275	99.59 43	96.49 265	98.43 287	98.99 316	80.48 359	99.39 250	97.15 253	99.27 146	98.47 308

PatchT		97.03 286	96.44 290	98.79 216	98.99 275	98.34 211	99.16 247	99.07 294	92.13 341	99.52 101	97.31 351	94.54 226	98.98 317	88.54 351	98.73 186	99.03 206

FMVSNet1		96.84 288	96.36 291	98.29 266	99.32 208	97.26 255	99.43 163	99.48 142	95.11 313	98.55 279	99.32 276	83.95 352	98.98 317	95.81 295	96.26 273	98.62 285

AUN-MVS		96.88 287	96.31 292	98.59 229	99.48 168	97.04 269	99.27 222	99.22 274	97.44 188	98.51 281	99.41 248	91.97 288	99.66 211	97.71 207	83.83 351	99.07 202

test_0402		96.64 291	96.24 293	97.85 294	98.85 295	96.43 295	99.44 157	99.26 268	93.52 333	96.98 332	99.52 214	88.52 334	99.20 290	92.58 340	97.50 238	97.93 343

FMVSNet5		96.43 296	96.19 294	97.15 314	99.11 255	95.89 307	99.32 207	99.52 90	94.47 326	98.34 294	99.07 307	87.54 344	97.07 353	92.61 339	95.72 288	98.47 308

UnsupCasMVSNet_eth		96.44 295	96.12 295	97.40 311	98.65 317	95.65 310	99.36 196	99.51 103	97.13 215	96.04 341	98.99 316	88.40 335	98.17 338	96.71 276	90.27 341	98.40 318

pmmvs6		96.53 293	96.09 296	97.82 297	98.69 314	95.47 317	99.37 192	99.47 160	93.46 335	97.41 321	99.78 95	87.06 345	99.33 267	96.92 268	92.70 335	98.65 273

Anonymous20231206		96.22 298	96.03 297	96.79 325	97.31 346	94.14 338	99.63 62	99.08 292	96.17 291	97.04 331	99.06 309	93.94 244	97.76 348	86.96 356	95.06 302	98.47 308

new_pmnet		96.38 297	96.03 297	97.41 310	98.13 336	95.16 326	99.05 270	99.20 278	93.94 328	97.39 322	98.79 326	91.61 301	99.04 308	90.43 345	95.77 285	98.05 334

test20.03		96.12 302	95.96 299	96.63 326	97.44 342	95.45 318	99.51 122	99.38 219	96.55 262	96.16 339	99.25 288	93.76 250	96.17 358	87.35 355	94.22 316	98.27 324

RPMNet		96.72 290	95.90 300	99.19 155	99.18 240	98.49 202	99.22 241	99.52 90	88.72 351	99.56 92	97.38 348	94.08 241	99.95 43	86.87 357	98.58 190	99.14 189

Anonymous20240521		96.20 300	95.89 301	97.13 316	97.72 340	94.96 329	99.79 21	99.29 265	93.01 338	97.20 327	99.03 312	89.69 322	98.36 336	91.16 343	96.13 275	98.07 332

N_pmnet		94.95 314	95.83 302	92.31 337	98.47 329	79.33 362	99.12 255	92.81 369	93.87 329	97.68 317	99.13 302	93.87 246	99.01 314	91.38 342	96.19 274	98.59 298

Patchmatch-RL test		95.84 305	95.81 303	95.95 331	95.61 354	90.57 354	98.24 347	98.39 339	95.10 315	95.20 344	98.67 331	94.78 210	97.77 347	96.28 288	90.02 342	99.51 154

EG-PatchMatch MVS		95.97 304	95.69 304	96.81 324	97.78 339	92.79 349	99.16 247	98.93 306	96.16 293	94.08 348	99.22 292	82.72 354	99.47 235	95.67 300	97.50 238	98.17 329

ET-MVSNet_ETH3D		96.49 294	95.64 305	99.05 167	99.53 147	98.82 172	98.84 309	97.51 353	97.63 166	84.77 356	99.21 295	92.09 287	98.91 328	98.98 62	92.21 337	99.41 174

PVSNet_0	94.43 19	96.09 303	95.47 306	97.94 288	99.31 209	94.34 337	97.81 354	99.70 15	97.12 217	97.46 320	98.75 329	89.71 321	99.79 164	97.69 210	81.69 354	99.68 103

X-MVStestdata		96.55 292	95.45 307	99.87 11	99.85 25	99.83 14	99.69 37	99.68 19	98.98 27	99.37 137	64.01 368	98.81 45	99.94 54	98.79 94	99.86 51	99.84 18

IB-MVS	95.67 18	96.22 298	95.44 308	98.57 233	99.21 233	96.70 285	98.65 327	97.74 351	96.71 248	97.27 324	98.54 335	86.03 347	99.92 80	98.47 142	86.30 348	99.10 192
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
gg-mvs-nofinetune		96.17 301	95.32 309	98.73 220	98.79 299	98.14 220	99.38 189	94.09 365	91.07 347	98.07 307	91.04 361	89.62 324	99.35 263	96.75 273	99.09 161	98.68 256

MVS-HIRNet		95.75 306	95.16 310	97.51 308	99.30 210	93.69 343	98.88 305	95.78 361	85.09 354	98.78 249	92.65 358	91.29 305	99.37 255	94.85 314	99.85 58	99.46 166

MIMVSNet1		95.51 307	95.04 311	96.92 322	97.38 343	95.60 311	99.52 118	99.50 122	93.65 332	96.97 333	99.17 297	85.28 350	96.56 357	88.36 352	95.55 292	98.60 297

CMPMVS	69.68 23	94.13 320	94.90 312	91.84 338	97.24 347	80.01 361	98.52 335	99.48 142	89.01 349	91.99 353	99.67 152	85.67 349	99.13 297	95.44 303	97.03 258	96.39 353
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs-eth3d		95.34 311	94.73 313	97.15 314	95.53 356	95.94 306	99.35 202	99.10 289	95.13 311	93.55 349	97.54 346	88.15 339	97.91 344	94.58 316	89.69 344	97.61 347

MDA-MVSNet_test_wron		95.45 308	94.60 314	98.01 284	98.16 335	97.21 258	99.11 261	99.24 272	93.49 334	80.73 361	98.98 319	93.02 258	98.18 337	94.22 322	94.45 312	98.64 275

TDRefinement		95.42 309	94.57 315	97.97 287	89.83 363	96.11 303	99.48 144	98.75 322	96.74 246	96.68 334	99.88 15	88.65 332	99.71 196	98.37 151	82.74 353	98.09 331

YYNet1		95.36 310	94.51 316	97.92 290	97.89 337	97.10 260	99.10 263	99.23 273	93.26 337	80.77 360	99.04 311	92.81 264	98.02 341	94.30 319	94.18 317	98.64 275

DIV-MVS_2432*1600		95.00 312	94.34 317	96.96 320	97.07 351	95.39 320	99.56 100	99.44 191	95.11 313	97.13 329	97.32 350	91.86 291	97.27 352	90.35 346	81.23 355	98.23 328

new-patchmatchnet		94.48 318	94.08 318	95.67 332	95.08 357	92.41 350	99.18 245	99.28 267	94.55 325	93.49 350	97.37 349	87.86 343	97.01 354	91.57 341	88.36 345	97.61 347

MDA-MVSNet-bldmvs		94.96 313	93.98 319	97.92 290	98.24 334	97.27 253	99.15 251	99.33 245	93.80 330	80.09 362	99.03 312	88.31 336	97.86 346	93.49 329	94.36 314	98.62 285

CL-MVSNet_2432*1600		94.49 317	93.97 320	96.08 330	96.16 352	93.67 344	98.33 344	99.38 219	95.13 311	97.33 323	98.15 343	92.69 272	96.57 356	88.67 350	79.87 356	97.99 339

KD-MVS_2432*1600		94.62 315	93.72 321	97.31 312	97.19 349	95.82 308	98.34 342	99.20 278	95.00 316	97.57 318	98.35 339	87.95 341	98.10 339	92.87 336	77.00 358	98.01 336

miper_refine_blended		94.62 315	93.72 321	97.31 312	97.19 349	95.82 308	98.34 342	99.20 278	95.00 316	97.57 318	98.35 339	87.95 341	98.10 339	92.87 336	77.00 358	98.01 336

OpenMVS_ROB	92.34 20	94.38 319	93.70 323	96.41 329	97.38 343	93.17 347	99.06 268	98.75 322	86.58 352	94.84 347	98.26 342	81.53 357	99.32 268	89.01 349	97.87 221	96.76 351

pmmvs3		94.09 321	93.25 324	96.60 327	94.76 358	94.49 334	98.92 301	98.18 344	89.66 348	96.48 336	98.06 344	86.28 346	97.33 351	89.68 348	87.20 347	97.97 341

UnsupCasMVSNet_bld		93.53 322	92.51 325	96.58 328	97.38 343	93.82 340	98.24 347	99.48 142	91.10 346	93.10 351	96.66 352	74.89 360	98.37 335	94.03 324	87.71 346	97.56 349

PM-MVS		92.96 323	92.23 326	95.14 333	95.61 354	89.98 356	99.37 192	98.21 342	94.80 320	95.04 346	97.69 345	65.06 362	97.90 345	94.30 319	89.98 343	97.54 350

test_method		91.10 324	91.36 327	90.31 341	95.85 353	73.72 367	94.89 359	99.25 270	68.39 361	95.82 342	99.02 314	80.50 358	98.95 326	93.64 327	94.89 307	98.25 326

Gipuma		90.99 325	90.15 328	93.51 334	98.73 308	90.12 355	93.98 360	99.45 182	79.32 357	92.28 352	94.91 355	69.61 361	97.98 343	87.42 354	95.67 289	92.45 357
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
FPMVS		84.93 328	85.65 329	82.75 346	86.77 365	63.39 369	98.35 341	98.92 308	74.11 358	83.39 358	98.98 319	50.85 366	92.40 362	84.54 359	94.97 304	92.46 356

PMMVS2		86.87 326	85.37 330	91.35 340	90.21 362	83.80 357	98.89 304	97.45 354	83.13 356	91.67 354	95.03 354	48.49 367	94.70 360	85.86 358	77.62 357	95.54 354

LCM-MVSNet		86.80 327	85.22 331	91.53 339	87.81 364	80.96 360	98.23 349	98.99 300	71.05 359	90.13 355	96.51 353	48.45 368	96.88 355	90.51 344	85.30 349	96.76 351

tmp_tt		82.80 329	81.52 332	86.66 342	66.61 370	68.44 368	92.79 362	97.92 347	68.96 360	80.04 363	99.85 29	85.77 348	96.15 359	97.86 191	43.89 364	95.39 355

E-PMN		80.61 330	79.88 333	82.81 345	90.75 361	76.38 365	97.69 355	95.76 362	66.44 363	83.52 357	92.25 359	62.54 364	87.16 364	68.53 363	61.40 361	84.89 362

EMVS		80.02 331	79.22 334	82.43 347	91.19 360	76.40 364	97.55 357	92.49 370	66.36 364	83.01 359	91.27 360	64.63 363	85.79 365	65.82 364	60.65 362	85.08 361

PMVS	70.75 22	75.98 334	74.97 335	79.01 348	70.98 369	55.18 370	93.37 361	98.21 342	65.08 365	61.78 366	93.83 357	21.74 373	92.53 361	78.59 360	91.12 340	89.34 360
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
ANet_high		77.30 332	74.86 336	84.62 344	75.88 368	77.61 363	97.63 356	93.15 368	88.81 350	64.27 365	89.29 362	36.51 369	83.93 366	75.89 361	52.31 363	92.33 358

MVE	76.82 21	76.91 333	74.31 337	84.70 343	85.38 367	76.05 366	96.88 358	93.17 367	67.39 362	71.28 364	89.01 363	21.66 374	87.69 363	71.74 362	72.29 360	90.35 359
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testmvs		39.17 336	43.78 338	25.37 351	36.04 372	16.84 373	98.36 340	26.56 371	20.06 367	38.51 368	67.32 364	29.64 371	15.30 369	37.59 366	39.90 365	43.98 364

test123		39.01 337	42.50 339	28.53 350	39.17 371	20.91 372	98.75 318	19.17 373	19.83 368	38.57 367	66.67 365	33.16 370	15.42 368	37.50 367	29.66 366	49.26 363

wuyk23d		40.18 335	41.29 340	36.84 349	86.18 366	49.12 371	79.73 363	22.81 372	27.64 366	25.46 369	28.45 369	21.98 372	48.89 367	55.80 365	23.56 367	12.51 365

cdsmvs_eth3d_5k		24.64 338	32.85 341	0.00 352	0.00 373	0.00 374	0.00 364	99.51 103	0.00 369	0.00 370	99.56 199	96.58 147	0.00 370	0.00 368	0.00 368	0.00 366

ab-mvs-re		8.30 339	11.06 342	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	99.58 192	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

pcd_1.5k_mvsjas		8.27 340	11.03 343	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.27 370	99.01 16	0.00 370	0.00 368	0.00 368	0.00 366

uanet_test		0.02 341	0.03 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.27 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

sosnet-low-res		0.02 341	0.03 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.27 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

sosnet		0.02 341	0.03 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.27 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

uncertanet		0.02 341	0.03 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.27 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

Regformer		0.02 341	0.03 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.27 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

uanet		0.02 341	0.03 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.27 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

eth-test2					0.00 373

eth-test					0.00 373

ZD-MVS					99.71 86	99.79 30		99.61 35	96.84 241	99.56 92	99.54 207	98.58 70	99.96 19	96.93 266	99.75 98

IU-MVS					99.84 32	99.88 7		99.32 253	98.30 89	99.84 13				98.86 81	99.85 58	99.89 2

OPU-MVS				99.64 77	99.56 144	99.72 42	99.60 75				99.70 133	99.27 4	99.42 248	98.24 160	99.80 84	99.79 53

test_241102_TWO								99.48 142	99.08 11	99.88 5	99.81 62	98.94 31	99.96 19	98.91 71	99.84 65	99.88 5

test_241102_ONE					99.84 32	99.90 1		99.48 142	99.07 13	99.91 1	99.74 117	99.20 5	99.76 175

save fliter					99.76 52	99.59 69	99.14 253	99.40 209	99.00 22

test_0728_THIRD									98.99 25	99.81 22	99.80 76	99.09 12	99.96 19	98.85 83	99.90 23	99.88 5

test_0728_SECOND				99.91 2	99.84 32	99.89 3	99.57 93	99.51 103					99.96 19	98.93 68	99.86 51	99.88 5

test0726					99.85 25	99.89 3	99.62 68	99.50 122	99.10 8	99.86 11	99.82 49	98.94 31

GSMVS																99.52 148

test_part2					99.81 40	99.83 14				99.77 33

sam_mvs1												94.86 206				99.52 148

sam_mvs												94.72 217

ambc				93.06 336	92.68 359	82.36 358	98.47 337	98.73 330		95.09 345	97.41 347	55.55 365	99.10 304	96.42 285	91.32 339	97.71 346

MTGPA								99.47 160

test_post1							99.23 236				65.14 367	94.18 238	99.71 196	97.58 217

test_post											65.99 366	94.65 221	99.73 186

patchmatchnet-post											98.70 330	94.79 209	99.74 179

GG-mvs-BLEND				98.45 249	98.55 326	98.16 218	99.43 163	93.68 366		97.23 325	98.46 336	89.30 326	99.22 283	95.43 304	98.22 206	97.98 340

MTMP							99.54 112	98.88 315

gm-plane-assit					98.54 327	92.96 348			94.65 323		99.15 300		99.64 218	97.56 222

test9_res														97.49 228	99.72 105	99.75 69

TEST9					99.67 101	99.65 57	99.05 270	99.41 203	96.22 287	98.95 223	99.49 224	98.77 51	99.91 91

test_8					99.67 101	99.61 63	99.03 276	99.41 203	96.28 280	98.93 227	99.48 230	98.76 53	99.91 91

agg_prior2														97.21 245	99.73 104	99.75 69

agg_prior					99.67 101	99.62 61		99.40 209		98.87 236			99.91 91

TestCases				99.31 136	99.86 21	98.48 204		99.61 35	97.85 139	99.36 140	99.85 29	95.95 166	99.85 131	96.66 280	99.83 72	99.59 134

test_prior4						99.56 74	98.99 286

test_prior2							98.96 294		98.34 84	99.01 212	99.52 214	98.68 63		97.96 183	99.74 101

test_prior				99.68 65	99.67 101	99.48 89		99.56 56					99.83 145			99.74 74

旧先验2							98.96 294		96.70 249	99.47 109			99.94 54	98.19 163

新几何2							99.01 284

新几何1				99.75 51	99.75 62	99.59 69		99.54 73	96.76 245	99.29 154	99.64 166	98.43 81	99.94 54	96.92 268	99.66 119	99.72 87

旧先验1					99.74 70	99.59 69		99.54 73			99.69 140	98.47 78			99.68 116	99.73 81

无先验							98.99 286	99.51 103	96.89 238				99.93 69	97.53 225		99.72 87

原ACMM2							98.95 298

原ACMM1				99.65 72	99.73 75	99.33 103		99.47 160	97.46 182	99.12 191	99.66 158	98.67 66	99.91 91	97.70 209	99.69 111	99.71 94

test222					99.75 62	99.49 88	98.91 303	99.49 130	96.42 274	99.34 146	99.65 159	98.28 94			99.69 111	99.72 87

testdata2													99.95 43	96.67 279

segment_acmp												98.96 25

testdata				99.54 93	99.75 62	98.95 154		99.51 103	97.07 223	99.43 118	99.70 133	98.87 39	99.94 54	97.76 200	99.64 123	99.72 87

testdata1							98.85 308		98.32 88

test12				99.75 51	99.64 117	99.61 63		99.29 265		99.21 175		98.38 86	99.89 114		99.74 101	99.74 74

plane_prior7					99.29 214	97.03 270

plane_prior6					99.27 219	96.98 274						92.71 270

plane_prior5								99.47 160					99.69 206	97.78 198	97.63 225	98.67 263

plane_prior4											99.61 183

plane_prior3						97.00 272			98.69 56	99.11 193

plane_prior2							99.39 184		98.97 30

plane_prior1					99.26 221

plane_prior						96.97 275	99.21 243		98.45 71						97.60 228

n2								0.00 374

nn								0.00 374

door-mid								98.05 345

lessismore_v0				97.79 299	98.69 314	95.44 319		94.75 363		95.71 343	99.87 20	88.69 331	99.32 268	95.89 293	94.93 306	98.62 285

LGP-MVS_train				98.49 241	99.33 201	97.05 266		99.55 66	97.46 182	99.24 167	99.83 42	92.58 275	99.72 190	98.09 172	97.51 236	98.68 256

test11								99.35 234

door								97.92 347

HQP5-MVS						96.83 280

HQP-NCC					99.19 237		98.98 290		98.24 94	98.66 264

ACMP_Plane					99.19 237		98.98 290		98.24 94	98.66 264

BP-MVS														97.19 249

HQP4-MVS										98.66 264			99.64 218			98.64 275

HQP3-MVS								99.39 213							97.58 230

HQP2-MVS												92.47 279

NP-MVS					99.23 227	96.92 278					99.40 252

MDTV_nov1_ep13_2view						95.18 325	99.35 202		96.84 241	99.58 89		95.19 197		97.82 195		99.46 166

ACMMP++_ref															97.19 254

ACMMP++															97.43 246

Test By Simon												98.75 56

ITE_SJBPF				98.08 278	99.29 214	96.37 296		98.92 308	98.34 84	98.83 242	99.75 111	91.09 307	99.62 224	95.82 294	97.40 248	98.25 326

DeepMVS_CX				93.34 335	99.29 214	82.27 359		99.22 274	85.15 353	96.33 337	99.05 310	90.97 309	99.73 186	93.57 328	97.77 223	98.01 336

High-resolution multi-view benchmark