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.

APDe-MVS		89.15 9	89.63 8	87.73 31	94.49 22	71.69 54	93.83 4	93.96 18	75.70 111	91.06 19	96.03 1	76.84 17	97.03 21	89.09 21	95.65 31	94.47 54
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SMA-MVS		89.08 10	89.23 10	88.61 6	94.25 35	73.73 9	92.40 29	93.63 26	74.77 144	92.29 7	95.97 2	74.28 33	97.24 16	88.58 33	96.91 1	94.87 18
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
test0726					95.27 5	71.25 64	93.60 7	94.11 11	77.33 58	92.81 3	95.79 3	80.98 11

DVP-MVS		89.60 3	90.35 3	87.33 45	95.27 5	71.25 64	93.49 10	92.73 69	77.33 58	92.12 12	95.78 4	80.98 11	97.40 9	89.08 22	96.41 12	93.33 120
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
test_0728_THIRD									78.38 38	92.12 12	95.78 4	81.46 9	97.40 9	89.42 19	96.57 7	94.67 35

DVP-MVS++		90.23 1	91.01 1	87.89 24	94.34 31	71.25 64	95.06 1	94.23 7	78.38 38	92.78 4	95.74 6	82.45 3	97.49 4	89.42 19	96.68 2	94.95 12

test_one_0601					95.07 7	71.46 59		94.14 10	78.27 41	92.05 14	95.74 6	80.83 13

SED-MVS		90.08 2	90.85 2	87.77 28	95.30 2	70.98 71	93.57 8	94.06 15	77.24 61	93.10 1	95.72 8	82.99 1	97.44 7	89.07 25	96.63 4	94.88 16

test_241102_TWO								94.06 15	77.24 61	92.78 4	95.72 8	81.26 10	97.44 7	89.07 25	96.58 6	94.26 66

DPE-MVS		89.48 6	89.98 5	88.01 16	94.80 11	72.69 31	91.59 51	94.10 13	75.90 104	92.29 7	95.66 10	81.67 6	97.38 14	87.44 48	96.34 15	93.95 82
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
reproduce_model		87.28 35	87.39 33	86.95 54	93.10 62	71.24 68	91.60 50	93.19 40	74.69 145	88.80 33	95.61 11	70.29 81	96.44 43	86.20 56	93.08 75	93.16 130

reproduce-ours		87.47 27	87.61 27	87.07 50	93.27 54	71.60 55	91.56 54	93.19 40	74.98 135	88.96 30	95.54 12	71.20 70	96.54 40	86.28 54	93.49 71	93.06 137

our_new_method		87.47 27	87.61 27	87.07 50	93.27 54	71.60 55	91.56 54	93.19 40	74.98 135	88.96 30	95.54 12	71.20 70	96.54 40	86.28 54	93.49 71	93.06 137

lecture		88.09 17	88.59 16	86.58 62	93.26 56	69.77 96	93.70 6	94.16 9	77.13 66	89.76 26	95.52 14	72.26 53	96.27 48	86.87 50	94.65 52	93.70 98

fmvsm_s_conf0.5_n_9		87.39 33	87.95 23	85.70 81	89.48 137	67.88 153	88.59 146	89.05 231	80.19 12	90.70 20	95.40 15	74.56 28	93.92 151	91.54 2	92.07 92	95.31 5

test_241102_ONE					95.30 2	70.98 71		94.06 15	77.17 64	93.10 1	95.39 16	82.99 1	97.27 15

MP-MVS-pluss		87.67 25	87.72 25	87.54 40	93.64 48	72.04 50	89.80 90	93.50 30	75.17 131	86.34 68	95.29 17	70.86 74	96.00 59	88.78 31	96.04 16	94.58 44
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SF-MVS		88.46 15	88.74 15	87.64 38	92.78 70	71.95 51	92.40 29	94.74 2	75.71 109	89.16 29	95.10 18	75.65 24	96.19 51	87.07 49	96.01 17	94.79 23

ACMMP_NAP		88.05 20	88.08 21	87.94 19	93.70 45	73.05 22	90.86 65	93.59 28	76.27 97	88.14 41	95.09 19	71.06 72	96.67 33	87.67 44	96.37 14	94.09 74

MED-MVS test				87.86 26	94.57 17	71.43 60	93.28 12	94.36 3	75.24 123	92.25 9	95.03 20		97.39 11	88.15 39	95.96 19	94.75 30

MED-MVS		89.59 4	90.16 4	87.86 26	94.57 17	71.43 60	93.28 12	94.36 3	76.30 95	92.25 9	95.03 20	81.59 7	97.39 11	88.15 39	95.96 19	94.75 30

TestfortrainingZip a		89.27 7	89.82 7	87.60 39	94.57 17	70.90 77	93.28 12	94.36 3	75.24 123	92.25 9	95.03 20	81.59 7	97.39 11	86.12 57	95.96 19	94.52 51

ME-MVS		88.98 12	89.39 9	87.75 30	94.54 20	71.43 60	91.61 49	94.25 6	76.30 95	90.62 21	95.03 20	78.06 16	97.07 20	88.15 39	95.96 19	94.75 30

fmvsm_s_conf0.5_n_3		86.36 53	87.46 32	83.09 204	87.08 257	65.21 222	89.09 123	90.21 180	79.67 19	89.98 24	95.02 24	73.17 42	91.71 266	91.30 3	91.60 99	92.34 170

MM		89.16 8	89.23 10	88.97 4	90.79 102	73.65 10	92.66 28	91.17 146	86.57 1	87.39 57	94.97 25	71.70 62	97.68 1	92.19 1	95.63 32	95.57 1

fmvsm_s_conf0.5_n_8		86.56 47	87.17 38	84.73 120	87.76 221	65.62 212	89.20 114	92.21 99	79.94 17	89.74 27	94.86 26	68.63 111	94.20 136	90.83 5	91.39 104	94.38 58

MTAPA		87.23 36	87.00 39	87.90 22	94.18 39	74.25 5	86.58 225	92.02 108	79.45 22	85.88 70	94.80 27	68.07 119	96.21 50	86.69 52	95.34 36	93.23 123

SteuartSystems-ACMMP		88.72 14	88.86 14	88.32 9	92.14 78	72.96 25	93.73 5	93.67 25	80.19 12	88.10 42	94.80 27	73.76 37	97.11 18	87.51 46	95.82 25	94.90 15
Skip Steuart: Steuart Systems R&D Blog.
fmvsm_s_conf0.5_n_10		86.38 52	86.76 46	85.24 95	87.33 243	67.30 174	89.50 101	90.98 151	76.25 98	90.56 22	94.75 29	68.38 114	94.24 135	90.80 7	92.32 89	94.19 68

9.14			88.26 19		92.84 69		91.52 56	94.75 1	73.93 166	88.57 35	94.67 30	75.57 25	95.79 63	86.77 51	95.76 27

SR-MVS		86.73 43	86.67 48	86.91 55	94.11 41	72.11 49	92.37 33	92.56 80	74.50 149	86.84 64	94.65 31	67.31 128	95.77 64	84.80 68	92.85 78	92.84 151

region2R		87.42 31	87.20 37	88.09 14	94.63 14	73.55 13	93.03 19	93.12 45	76.73 80	84.45 94	94.52 32	69.09 102	96.70 31	84.37 74	94.83 49	94.03 77

ACMMPR		87.44 29	87.23 36	88.08 15	94.64 13	73.59 12	93.04 17	93.20 39	76.78 77	84.66 89	94.52 32	68.81 108	96.65 34	84.53 72	94.90 45	94.00 79

APD-MVS		87.44 29	87.52 30	87.19 47	94.24 36	72.39 41	91.86 45	92.83 65	73.01 195	88.58 34	94.52 32	73.36 38	96.49 42	84.26 75	95.01 41	92.70 153
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
APD-MVS_3200maxsize		85.97 61	85.88 65	86.22 67	92.69 72	69.53 99	91.93 42	92.99 54	73.54 177	85.94 69	94.51 35	65.80 151	95.61 67	83.04 89	92.51 83	93.53 113

CP-MVS		87.11 38	86.92 43	87.68 37	94.20 38	73.86 7	93.98 3	92.82 68	76.62 83	83.68 112	94.46 36	67.93 121	95.95 62	84.20 78	94.39 61	93.23 123

SR-MVS-dyc-post		85.77 67	85.61 72	86.23 66	93.06 64	70.63 82	91.88 43	92.27 90	73.53 178	85.69 73	94.45 37	65.00 159	95.56 68	82.75 94	91.87 95	92.50 163

RE-MVS-def			85.48 75		93.06 64	70.63 82	91.88 43	92.27 90	73.53 178	85.69 73	94.45 37	63.87 167		82.75 94	91.87 95	92.50 163

HFP-MVS		87.58 26	87.47 31	87.94 19	94.58 16	73.54 15	93.04 17	93.24 38	76.78 77	84.91 82	94.44 39	70.78 75	96.61 36	84.53 72	94.89 46	93.66 99

PGM-MVS		86.68 45	86.27 55	87.90 22	94.22 37	73.38 18	90.22 81	93.04 46	75.53 114	83.86 108	94.42 40	67.87 123	96.64 35	82.70 98	94.57 56	93.66 99

MP-MVS		87.71 23	87.64 26	87.93 21	94.36 30	73.88 6	92.71 27	92.65 75	77.57 49	83.84 109	94.40 41	72.24 54	96.28 47	85.65 59	95.30 39	93.62 106
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
fmvsm_l_conf0.5_n_3		86.02 57	86.32 53	85.14 98	87.20 248	68.54 130	89.57 99	90.44 169	75.31 122	87.49 54	94.39 42	72.86 47	92.72 222	89.04 27	90.56 118	94.16 69

fmvsm_s_conf0.1_n_2		83.80 103	83.79 103	83.83 176	85.62 294	64.94 235	87.03 204	86.62 302	74.32 154	87.97 47	94.33 43	60.67 225	92.60 225	89.72 14	87.79 172	93.96 80

fmvsm_l_conf0.5_n_9		85.84 66	86.63 49	83.46 187	87.12 256	66.01 199	88.56 148	89.43 207	75.59 113	89.32 28	94.32 44	72.89 46	91.21 291	90.11 11	92.33 87	93.16 130

ZNCC-MVS		87.94 22	87.85 24	88.20 12	94.39 28	73.33 19	93.03 19	93.81 22	76.81 75	85.24 77	94.32 44	71.76 60	96.93 23	85.53 61	95.79 26	94.32 63

MGCNet		87.69 24	87.55 29	88.12 13	89.45 138	71.76 53	91.47 57	89.54 203	82.14 3	86.65 66	94.28 46	68.28 117	97.46 6	90.81 6	95.31 38	95.15 8

test_fmvsmconf0.01_n		84.73 89	84.52 91	85.34 92	80.25 408	69.03 110	89.47 102	89.65 199	73.24 189	86.98 62	94.27 47	66.62 135	93.23 192	90.26 10	89.95 130	93.78 95

HPM-MVS++		89.02 11	89.15 12	88.63 5	95.01 9	76.03 1	92.38 32	92.85 64	80.26 11	87.78 48	94.27 47	75.89 22	96.81 27	87.45 47	96.44 9	93.05 139

mPP-MVS		86.67 46	86.32 53	87.72 33	94.41 26	73.55 13	92.74 25	92.22 97	76.87 74	82.81 133	94.25 49	66.44 139	96.24 49	82.88 92	94.28 64	93.38 116

fmvsm_s_conf0.5_n_2		84.04 96	84.11 96	83.81 178	86.17 281	65.00 230	86.96 207	87.28 284	74.35 153	88.25 39	94.23 50	61.82 201	92.60 225	89.85 12	88.09 165	93.84 89

DeepC-MVS	79.81 2	87.08 40	86.88 45	87.69 36	91.16 91	72.32 45	90.31 79	93.94 19	77.12 67	82.82 132	94.23 50	72.13 56	97.09 19	84.83 67	95.37 35	93.65 103
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
fmvsm_s_conf0.5_n_11		86.06 56	86.75 47	84.00 169	87.78 218	66.09 196	89.96 86	90.80 159	77.37 57	86.72 65	94.20 52	72.51 51	92.78 221	89.08 22	92.33 87	93.13 134

XVS		87.18 37	86.91 44	88.00 17	94.42 24	73.33 19	92.78 23	92.99 54	79.14 26	83.67 113	94.17 53	67.45 126	96.60 37	83.06 87	94.50 57	94.07 75

MSP-MVS		89.51 5	89.91 6	88.30 10	94.28 34	73.46 17	92.90 21	94.11 11	80.27 10	91.35 17	94.16 54	78.35 15	96.77 28	89.59 17	94.22 66	94.67 35
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
test_fmvsmconf0.1_n		85.61 71	85.65 71	85.50 88	82.99 366	69.39 107	89.65 95	90.29 178	73.31 185	87.77 49	94.15 55	71.72 61	93.23 192	90.31 9	90.67 117	93.89 86

DeepPCF-MVS	80.84 1	88.10 16	88.56 17	86.73 59	92.24 77	69.03 110	89.57 99	93.39 35	77.53 53	89.79 25	94.12 56	78.98 14	96.58 39	85.66 58	95.72 28	94.58 44

HPM-MVS_fast		85.35 79	84.95 85	86.57 63	93.69 46	70.58 84	92.15 40	91.62 131	73.89 167	82.67 135	94.09 57	62.60 185	95.54 70	80.93 111	92.93 77	93.57 109

ZD-MVS					94.38 29	72.22 46		92.67 72	70.98 236	87.75 50	94.07 58	74.01 36	96.70 31	84.66 70	94.84 48

fmvsm_s_conf0.1_n_a		83.32 123	82.99 120	84.28 143	83.79 339	68.07 145	89.34 111	82.85 362	69.80 270	87.36 58	94.06 59	68.34 116	91.56 272	87.95 42	83.46 257	93.21 126

CNVR-MVS		88.93 13	89.13 13	88.33 8	94.77 12	73.82 8	90.51 70	93.00 51	80.90 7	88.06 43	94.06 59	76.43 19	96.84 25	88.48 36	95.99 18	94.34 61

test_fmvsmconf_n		85.92 62	86.04 63	85.57 87	85.03 313	69.51 100	89.62 98	90.58 164	73.42 181	87.75 50	94.02 61	72.85 48	93.24 191	90.37 8	90.75 115	93.96 80

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 8				94.02 61	82.45 3	96.87 24	83.77 82	96.48 8	94.88 16

PC_three_1452									68.21 309	92.02 15	94.00 63	82.09 5	95.98 61	84.58 71	96.68 2	94.95 12

SD-MVS		88.06 18	88.50 18	86.71 60	92.60 75	72.71 29	91.81 46	93.19 40	77.87 42	90.32 23	94.00 63	74.83 26	93.78 158	87.63 45	94.27 65	93.65 103
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
GST-MVS		87.42 31	87.26 34	87.89 24	94.12 40	72.97 24	92.39 31	93.43 33	76.89 73	84.68 86	93.99 65	70.67 77	96.82 26	84.18 79	95.01 41	93.90 85

test_fmvsm_n_1920		85.29 80	85.34 77	85.13 101	86.12 283	69.93 92	88.65 144	90.78 160	69.97 266	88.27 38	93.98 66	71.39 67	91.54 276	88.49 35	90.45 120	93.91 83

fmvsm_s_conf0.1_n		83.56 114	83.38 113	84.10 152	84.86 315	67.28 175	89.40 108	83.01 357	70.67 243	87.08 60	93.96 67	68.38 114	91.45 282	88.56 34	84.50 231	93.56 110

HPM-MVS		87.11 38	86.98 41	87.50 43	93.88 43	72.16 47	92.19 38	93.33 36	76.07 101	83.81 110	93.95 68	69.77 92	96.01 58	85.15 62	94.66 51	94.32 63
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
fmvsm_s_conf0.5_n_7		83.34 121	84.03 97	81.28 263	85.73 291	65.13 225	85.40 266	89.90 190	74.96 137	82.13 141	93.89 69	66.65 134	87.92 355	86.56 53	91.05 109	90.80 226

fmvsm_s_conf0.5_n_5		85.22 81	85.55 73	84.25 148	86.26 277	67.40 170	89.18 115	89.31 216	72.50 200	88.31 37	93.86 70	69.66 93	91.96 254	89.81 13	91.05 109	93.38 116

TSAR-MVS + MP.		88.02 21	88.11 20	87.72 33	93.68 47	72.13 48	91.41 58	92.35 87	74.62 148	88.90 32	93.85 71	75.75 23	96.00 59	87.80 43	94.63 54	95.04 10
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
ACMMP		85.89 65	85.39 76	87.38 44	93.59 49	72.63 33	92.74 25	93.18 44	76.78 77	80.73 169	93.82 72	64.33 163	96.29 46	82.67 99	90.69 116	93.23 123
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
fmvsm_s_conf0.5_n_a		83.63 112	83.41 112	84.28 143	86.14 282	68.12 143	89.43 104	82.87 361	70.27 259	87.27 59	93.80 73	69.09 102	91.58 269	88.21 38	83.65 251	93.14 133

fmvsm_s_conf0.5_n_4		85.39 77	85.75 70	84.30 141	86.70 268	65.83 205	88.77 136	89.78 192	75.46 117	88.35 36	93.73 74	69.19 101	93.06 207	91.30 3	88.44 159	94.02 78

fmvsm_s_conf0.5_n		83.80 103	83.71 105	84.07 158	86.69 269	67.31 173	89.46 103	83.07 356	71.09 231	86.96 63	93.70 75	69.02 107	91.47 281	88.79 30	84.62 230	93.44 115

test_prior2							88.85 132		75.41 118	84.91 82	93.54 76	74.28 33		83.31 85	95.86 24

fmvsm_l_conf0.5_n		84.47 90	84.54 89	84.27 145	85.42 300	68.81 116	88.49 150	87.26 286	68.08 310	88.03 44	93.49 77	72.04 57	91.77 262	88.90 29	89.14 146	92.24 177

VDDNet		81.52 161	80.67 161	84.05 164	90.44 108	64.13 257	89.73 93	85.91 313	71.11 230	83.18 123	93.48 78	50.54 331	93.49 177	73.40 207	88.25 162	94.54 50

CDPH-MVS		85.76 68	85.29 81	87.17 48	93.49 51	71.08 69	88.58 147	92.42 85	68.32 308	84.61 91	93.48 78	72.32 52	96.15 53	79.00 137	95.43 34	94.28 65

NCCC		88.06 18	88.01 22	88.24 11	94.41 26	73.62 11	91.22 62	92.83 65	81.50 5	85.79 72	93.47 80	73.02 45	97.00 22	84.90 64	94.94 44	94.10 73

fmvsm_s_conf0.5_n_6		85.55 72	86.20 56	83.60 182	87.32 245	65.13 225	88.86 130	91.63 130	75.41 118	88.23 40	93.45 81	68.56 112	92.47 233	89.52 18	92.78 79	93.20 128

fmvsm_l_conf0.5_n_a		84.13 94	84.16 94	84.06 161	85.38 301	68.40 133	88.34 158	86.85 296	67.48 317	87.48 55	93.40 82	70.89 73	91.61 267	88.38 37	89.22 143	92.16 184

3Dnovator+	77.84 4	85.48 73	84.47 92	88.51 7	91.08 93	73.49 16	93.18 16	93.78 23	80.79 8	76.66 251	93.37 83	60.40 233	96.75 30	77.20 159	93.73 70	95.29 6

DeepC-MVS_fast	79.65 3	86.91 41	86.62 50	87.76 29	93.52 50	72.37 43	91.26 59	93.04 46	76.62 83	84.22 100	93.36 84	71.44 66	96.76 29	80.82 113	95.33 37	94.16 69
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
VDD-MVS		83.01 131	82.36 133	84.96 107	91.02 95	66.40 191	88.91 128	88.11 260	77.57 49	84.39 96	93.29 85	52.19 305	93.91 152	77.05 162	88.70 154	94.57 46

test_fmvsmvis_n_1920		84.02 97	83.87 99	84.49 128	84.12 331	69.37 108	88.15 166	87.96 267	70.01 264	83.95 107	93.23 86	68.80 109	91.51 279	88.61 32	89.96 129	92.57 158

UA-Net		85.08 84	84.96 84	85.45 89	92.07 79	68.07 145	89.78 91	90.86 157	82.48 2	84.60 92	93.20 87	69.35 97	95.22 88	71.39 231	90.88 114	93.07 136

TEST9					93.26 56	72.96 25	88.75 138	91.89 116	68.44 306	85.00 80	93.10 88	74.36 32	95.41 80

train_agg		86.43 49	86.20 56	87.13 49	93.26 56	72.96 25	88.75 138	91.89 116	68.69 301	85.00 80	93.10 88	74.43 30	95.41 80	84.97 63	95.71 29	93.02 141

test_8					93.13 60	72.57 35	88.68 143	91.84 120	68.69 301	84.87 84	93.10 88	74.43 30	95.16 90

LFMVS		81.82 151	81.23 151	83.57 185	91.89 82	63.43 280	89.84 87	81.85 373	77.04 70	83.21 120	93.10 88	52.26 304	93.43 183	71.98 226	89.95 130	93.85 87

旧先验1					91.96 80	65.79 208		86.37 306			93.08 92	69.31 99			92.74 80	88.74 316

dcpmvs_2		85.63 70	86.15 60	84.06 161	91.71 84	64.94 235	86.47 229	91.87 118	73.63 173	86.60 67	93.02 93	76.57 18	91.87 260	83.36 84	92.15 90	95.35 3

testdata				79.97 295	90.90 98	64.21 255		84.71 327	59.27 410	85.40 75	92.91 94	62.02 198	89.08 336	68.95 259	91.37 105	86.63 370

MCST-MVS		87.37 34	87.25 35	87.73 31	94.53 21	72.46 40	89.82 88	93.82 21	73.07 193	84.86 85	92.89 95	76.22 20	96.33 45	84.89 66	95.13 40	94.40 57

Vis-MVSNet		83.46 117	82.80 124	85.43 90	90.25 112	68.74 121	90.30 80	90.13 183	76.33 94	80.87 166	92.89 95	61.00 220	94.20 136	72.45 223	90.97 111	93.35 119
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CPTT-MVS		83.73 107	83.33 115	84.92 111	93.28 53	70.86 78	92.09 41	90.38 171	68.75 300	79.57 184	92.83 97	60.60 229	93.04 210	80.92 112	91.56 102	90.86 225

3Dnovator	76.31 5	83.38 120	82.31 134	86.59 61	87.94 208	72.94 28	90.64 68	92.14 107	77.21 63	75.47 277	92.83 97	58.56 245	94.72 115	73.24 210	92.71 81	92.13 185

MSLP-MVS++		85.43 75	85.76 69	84.45 129	91.93 81	70.24 85	90.71 67	92.86 63	77.46 55	84.22 100	92.81 99	67.16 130	92.94 212	80.36 119	94.35 63	90.16 255

test2506		77.30 275	76.49 272	79.74 301	90.08 116	52.02 424	87.86 178	63.10 467	74.88 140	80.16 178	92.79 100	38.29 430	92.35 240	68.74 262	92.50 84	94.86 19

ECVR-MVS		79.61 209	79.26 202	80.67 280	90.08 116	54.69 406	87.89 176	77.44 420	74.88 140	80.27 175	92.79 100	48.96 354	92.45 234	68.55 263	92.50 84	94.86 19

test1111		79.43 216	79.18 205	80.15 292	89.99 121	53.31 419	87.33 196	77.05 424	75.04 133	80.23 177	92.77 102	48.97 353	92.33 242	68.87 260	92.40 86	94.81 22

MG-MVS		83.41 118	83.45 111	83.28 194	92.74 71	62.28 305	88.17 164	89.50 205	75.22 125	81.49 153	92.74 103	66.75 133	95.11 94	72.85 213	91.58 101	92.45 167

casdiffmvs_mvg		85.99 59	86.09 62	85.70 81	87.65 229	67.22 179	88.69 142	93.04 46	79.64 21	85.33 76	92.54 104	73.30 39	94.50 124	83.49 83	91.14 108	95.37 2
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
patch_mono-2		83.65 110	84.54 89	80.99 272	90.06 120	65.83 205	84.21 300	88.74 249	71.60 219	85.01 79	92.44 105	74.51 29	83.50 401	82.15 101	92.15 90	93.64 105

casdiffmvs		85.11 83	85.14 82	85.01 105	87.20 248	65.77 209	87.75 180	92.83 65	77.84 43	84.36 99	92.38 106	72.15 55	93.93 150	81.27 109	90.48 119	95.33 4
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CS-MVS		86.69 44	86.95 42	85.90 78	90.76 103	67.57 164	92.83 22	93.30 37	79.67 19	84.57 93	92.27 107	71.47 65	95.02 100	84.24 77	93.46 73	95.13 9

E6		84.22 92	84.12 95	84.52 125	87.60 231	65.36 220	87.45 190	92.30 89	76.51 85	83.53 116	92.26 108	69.26 100	93.49 177	79.88 125	88.26 161	94.69 33

baseline		84.93 86	84.98 83	84.80 117	87.30 246	65.39 218	87.30 197	92.88 62	77.62 47	84.04 105	92.26 108	71.81 59	93.96 144	81.31 107	90.30 122	95.03 11

NormalMVS		86.29 54	85.88 65	87.52 41	93.26 56	72.47 38	91.65 47	92.19 102	79.31 24	84.39 96	92.18 110	64.64 161	95.53 71	80.70 116	94.65 52	94.56 48

SymmetryMVS		85.38 78	84.81 86	87.07 50	91.47 87	72.47 38	91.65 47	88.06 264	79.31 24	84.39 96	92.18 110	64.64 161	95.53 71	80.70 116	90.91 113	93.21 126

QAPM		80.88 172	79.50 195	85.03 104	88.01 206	68.97 114	91.59 51	92.00 110	66.63 330	75.15 295	92.16 112	57.70 252	95.45 75	63.52 302	88.76 152	90.66 234

IS-MVSNet		83.15 126	82.81 123	84.18 150	89.94 123	63.30 282	91.59 51	88.46 257	79.04 30	79.49 185	92.16 112	65.10 156	94.28 130	67.71 269	91.86 97	94.95 12

viewmacassd2359aftdt		83.76 106	83.66 107	84.07 158	86.59 272	64.56 244	86.88 212	91.82 121	75.72 108	83.34 119	92.15 114	68.24 118	92.88 215	79.05 133	89.15 145	94.77 25

BP-MVS1		84.32 91	83.71 105	86.17 68	87.84 213	67.85 154	89.38 109	89.64 200	77.73 45	83.98 106	92.12 115	56.89 263	95.43 77	84.03 80	91.75 98	95.24 7

E4		84.10 95	83.99 98	84.45 129	87.58 236	64.99 231	86.54 227	92.25 93	76.38 91	83.37 118	92.09 116	69.88 90	93.58 166	79.78 127	88.03 168	94.77 25

新几何1				83.42 189	93.13 60	70.71 80		85.48 319	57.43 428	81.80 147	91.98 117	63.28 171	92.27 243	64.60 297	92.99 76	87.27 351

OpenMVS	72.83 10	79.77 207	78.33 223	84.09 156	85.17 306	69.91 93	90.57 69	90.97 152	66.70 324	72.17 341	91.91 118	54.70 281	93.96 144	61.81 324	90.95 112	88.41 325

PHI-MVS		86.43 49	86.17 59	87.24 46	90.88 99	70.96 73	92.27 37	94.07 14	72.45 201	85.22 78	91.90 119	69.47 95	96.42 44	83.28 86	95.94 23	94.35 60

VNet		82.21 142	82.41 131	81.62 252	90.82 100	60.93 321	84.47 290	89.78 192	76.36 93	84.07 104	91.88 120	64.71 160	90.26 312	70.68 238	88.89 148	93.66 99

EC-MVSNet		86.01 58	86.38 52	84.91 112	89.31 147	66.27 194	92.32 35	93.63 26	79.37 23	84.17 102	91.88 120	69.04 106	95.43 77	83.93 81	93.77 69	93.01 142

GDP-MVS		83.52 115	82.64 127	86.16 69	88.14 197	68.45 132	89.13 121	92.69 70	72.82 199	83.71 111	91.86 122	55.69 271	95.35 86	80.03 122	89.74 134	94.69 33

KinetiMVS		83.31 124	82.61 128	85.39 91	87.08 257	67.56 165	88.06 168	91.65 129	77.80 44	82.21 140	91.79 123	57.27 258	94.07 142	77.77 152	89.89 132	94.56 48

E2		84.00 98	83.87 99	84.39 132	87.70 226	64.95 232	86.40 234	92.23 94	75.85 105	83.21 120	91.78 124	70.09 85	93.55 171	79.52 130	88.05 166	94.66 38

E3		84.00 98	83.87 99	84.39 132	87.70 226	64.95 232	86.40 234	92.23 94	75.85 105	83.21 120	91.78 124	70.09 85	93.55 171	79.52 130	88.05 166	94.66 38

OPM-MVS		83.50 116	82.95 121	85.14 98	88.79 172	70.95 74	89.13 121	91.52 135	77.55 52	80.96 163	91.75 126	60.71 223	94.50 124	79.67 129	86.51 197	89.97 271
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
MVSMamba_PlusPlus		85.99 59	85.96 64	86.05 73	91.09 92	67.64 161	89.63 97	92.65 75	72.89 198	84.64 90	91.71 127	71.85 58	96.03 55	84.77 69	94.45 60	94.49 53

viewmanbaseed2359cas		83.66 109	83.55 109	84.00 169	86.81 264	64.53 245	86.65 222	91.75 126	74.89 139	83.15 125	91.68 128	68.74 110	92.83 219	79.02 135	89.24 142	94.63 41

XVG-OURS-SEG-HR		80.81 175	79.76 186	83.96 173	85.60 295	68.78 118	83.54 319	90.50 167	70.66 246	76.71 250	91.66 129	60.69 224	91.26 288	76.94 163	81.58 280	91.83 190

EPNet		83.72 108	82.92 122	86.14 72	84.22 329	69.48 101	91.05 64	85.27 320	81.30 6	76.83 246	91.65 130	66.09 146	95.56 68	76.00 178	93.85 68	93.38 116
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
OMC-MVS		82.69 135	81.97 144	84.85 114	88.75 174	67.42 168	87.98 170	90.87 156	74.92 138	79.72 182	91.65 130	62.19 195	93.96 144	75.26 189	86.42 198	93.16 130

viewdifsd2359ckpt07		82.83 134	82.78 126	82.99 211	86.51 274	62.58 296	85.09 274	90.83 158	75.22 125	82.28 137	91.63 132	69.43 96	92.03 250	77.71 153	86.32 199	94.34 61

balanced_conf03		86.78 42	86.99 40	86.15 70	91.24 90	67.61 162	90.51 70	92.90 61	77.26 60	87.44 56	91.63 132	71.27 69	96.06 54	85.62 60	95.01 41	94.78 24

test222					91.50 86	68.26 137	84.16 303	83.20 354	54.63 439	79.74 181	91.63 132	58.97 241			91.42 103	86.77 365

MVS_111021_HR		85.14 82	84.75 87	86.32 65	91.65 85	72.70 30	85.98 247	90.33 175	76.11 100	82.08 142	91.61 135	71.36 68	94.17 139	81.02 110	92.58 82	92.08 186

原ACMM1				84.35 136	93.01 66	68.79 117		92.44 82	63.96 366	81.09 160	91.57 136	66.06 147	95.45 75	67.19 276	94.82 50	88.81 311

viewcassd2359sk11		83.89 100	83.74 104	84.34 137	87.76 221	64.91 238	86.30 238	92.22 97	75.47 116	83.04 126	91.52 137	70.15 83	93.53 174	79.26 132	87.96 169	94.57 46

LPG-MVS_test		82.08 144	81.27 150	84.50 126	89.23 152	68.76 119	90.22 81	91.94 114	75.37 120	76.64 252	91.51 138	54.29 284	94.91 102	78.44 143	83.78 244	89.83 276

LGP-MVS_train				84.50 126	89.23 152	68.76 119		91.94 114	75.37 120	76.64 252	91.51 138	54.29 284	94.91 102	78.44 143	83.78 244	89.83 276

XVG-OURS		80.41 192	79.23 203	83.97 172	85.64 293	69.02 112	83.03 332	90.39 170	71.09 231	77.63 228	91.49 140	54.62 283	91.35 285	75.71 181	83.47 256	91.54 201

alignmvs		85.48 73	85.32 79	85.96 77	89.51 134	69.47 102	89.74 92	92.47 81	76.17 99	87.73 52	91.46 141	70.32 80	93.78 158	81.51 104	88.95 147	94.63 41

CANet		86.45 48	86.10 61	87.51 42	90.09 115	70.94 75	89.70 94	92.59 79	81.78 4	81.32 155	91.43 142	70.34 79	97.23 17	84.26 75	93.36 74	94.37 59

h-mvs33		83.15 126	82.19 137	86.02 76	90.56 105	70.85 79	88.15 166	89.16 226	76.02 102	84.67 87	91.39 143	61.54 206	95.50 73	82.71 96	75.48 363	91.72 197

MGCFI-Net		85.06 85	85.51 74	83.70 180	89.42 139	63.01 288	89.43 104	92.62 78	76.43 86	87.53 53	91.34 144	72.82 49	93.42 184	81.28 108	88.74 153	94.66 38

nrg030		83.88 101	83.53 110	84.96 107	86.77 266	69.28 109	90.46 75	92.67 72	74.79 143	82.95 127	91.33 145	72.70 50	93.09 205	80.79 115	79.28 311	92.50 163

E3new		83.78 105	83.60 108	84.31 139	87.76 221	64.89 239	86.24 241	92.20 100	75.15 132	82.87 129	91.23 146	70.11 84	93.52 176	79.05 133	87.79 172	94.51 52

sasdasda		85.91 63	85.87 67	86.04 74	89.84 125	69.44 105	90.45 76	93.00 51	76.70 81	88.01 45	91.23 146	73.28 40	93.91 152	81.50 105	88.80 150	94.77 25

canonicalmvs		85.91 63	85.87 67	86.04 74	89.84 125	69.44 105	90.45 76	93.00 51	76.70 81	88.01 45	91.23 146	73.28 40	93.91 152	81.50 105	88.80 150	94.77 25

DPM-MVS		84.93 86	84.29 93	86.84 56	90.20 113	73.04 23	87.12 201	93.04 46	69.80 270	82.85 131	91.22 149	73.06 44	96.02 57	76.72 171	94.63 54	91.46 207

Anonymous202405211		78.25 247	77.01 258	81.99 246	91.03 94	60.67 327	84.77 281	83.90 340	70.65 247	80.00 179	91.20 150	41.08 415	91.43 283	65.21 291	85.26 222	93.85 87

SPE-MVS-test		86.29 54	86.48 51	85.71 80	91.02 95	67.21 180	92.36 34	93.78 23	78.97 33	83.51 117	91.20 150	70.65 78	95.15 91	81.96 102	94.89 46	94.77 25

Anonymous20240529		80.19 202	78.89 211	84.10 152	90.60 104	64.75 242	88.95 127	90.90 154	65.97 338	80.59 171	91.17 152	49.97 338	93.73 164	69.16 257	82.70 269	93.81 91

EPP-MVSNet		83.40 119	83.02 119	84.57 123	90.13 114	64.47 250	92.32 35	90.73 161	74.45 152	79.35 190	91.10 153	69.05 105	95.12 92	72.78 214	87.22 183	94.13 71

TAPA-MVS	73.13 9	79.15 225	77.94 231	82.79 225	89.59 130	62.99 292	88.16 165	91.51 136	65.77 339	77.14 243	91.09 154	60.91 221	93.21 194	50.26 412	87.05 187	92.17 183
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CSCG		86.41 51	86.19 58	87.07 50	92.91 67	72.48 37	90.81 66	93.56 29	73.95 164	83.16 124	91.07 155	75.94 21	95.19 89	79.94 124	94.38 62	93.55 111

FIs		82.07 145	82.42 130	81.04 271	88.80 171	58.34 351	88.26 161	93.49 31	76.93 72	78.47 208	91.04 156	69.92 89	92.34 241	69.87 250	84.97 224	92.44 168

MVS_111021_LR		82.61 137	82.11 138	84.11 151	88.82 166	71.58 57	85.15 271	86.16 310	74.69 145	80.47 174	91.04 156	62.29 192	90.55 309	80.33 120	90.08 127	90.20 254

DP-MVS Recon		83.11 129	82.09 140	86.15 70	94.44 23	70.92 76	88.79 135	92.20 100	70.53 248	79.17 192	91.03 158	64.12 165	96.03 55	68.39 266	90.14 125	91.50 203

mamv4		76.81 283	78.23 227	72.54 404	86.12 283	65.75 210	78.76 390	82.07 370	64.12 360	72.97 329	91.02 159	67.97 120	68.08 469	83.04 89	78.02 325	83.80 414

HQP_MVS		83.64 111	83.14 116	85.14 98	90.08 116	68.71 123	91.25 60	92.44 82	79.12 28	78.92 196	91.00 160	60.42 231	95.38 82	78.71 141	86.32 199	91.33 208

plane_prior4											91.00 160

FC-MVSNet-test		81.52 161	82.02 142	80.03 294	88.42 187	55.97 391	87.95 172	93.42 34	77.10 68	77.38 232	90.98 162	69.96 88	91.79 261	68.46 265	84.50 231	92.33 171

diffmvs_AUTHOR		82.38 140	82.27 136	82.73 230	83.26 353	63.80 264	83.89 307	89.76 194	73.35 184	82.37 136	90.84 163	66.25 142	90.79 303	82.77 93	87.93 170	93.59 108

Vis-MVSNet (Re-imp)		78.36 246	78.45 218	78.07 337	88.64 178	51.78 430	86.70 220	79.63 402	74.14 161	75.11 296	90.83 164	61.29 214	89.75 322	58.10 360	91.60 99	92.69 155

114514_t		80.68 183	79.51 194	84.20 149	94.09 42	67.27 176	89.64 96	91.11 149	58.75 417	74.08 314	90.72 165	58.10 248	95.04 99	69.70 251	89.42 140	90.30 251

viewdifsd2359ckpt13		82.91 132	82.29 135	84.77 118	86.96 260	66.90 187	87.47 187	91.62 131	72.19 206	81.68 150	90.71 166	66.92 132	93.28 187	75.90 179	87.15 185	94.12 72

viewdifsd2359ckpt09		83.34 121	82.55 129	85.70 81	87.64 230	67.72 159	88.43 151	91.68 128	71.91 213	81.65 151	90.68 167	67.10 131	94.75 113	76.17 174	87.70 175	94.62 43

PAPM_NR		83.02 130	82.41 131	84.82 115	92.47 76	66.37 192	87.93 174	91.80 122	73.82 168	77.32 234	90.66 168	67.90 122	94.90 104	70.37 241	89.48 139	93.19 129

viewdifsd2359ckpt11		80.37 196	79.73 187	82.30 239	83.70 343	62.39 300	84.20 301	86.67 298	73.22 190	80.90 164	90.62 169	63.00 182	91.56 272	76.81 168	78.44 318	92.95 146

viewmsd2359difaftdt		80.37 196	79.73 187	82.30 239	83.70 343	62.39 300	84.20 301	86.67 298	73.22 190	80.90 164	90.62 169	63.00 182	91.56 272	76.81 168	78.44 318	92.95 146

LS3D		76.95 281	74.82 300	83.37 192	90.45 107	67.36 172	89.15 120	86.94 293	61.87 390	69.52 371	90.61 171	51.71 318	94.53 122	46.38 434	86.71 194	88.21 330

AstraMVS		80.81 175	80.14 176	82.80 222	86.05 286	63.96 259	86.46 230	85.90 314	73.71 171	80.85 167	90.56 172	54.06 288	91.57 271	79.72 128	83.97 242	92.86 149

VPNet		78.69 238	78.66 214	78.76 320	88.31 190	55.72 395	84.45 293	86.63 301	76.79 76	78.26 212	90.55 173	59.30 239	89.70 324	66.63 280	77.05 336	90.88 224

UniMVSNet_ETH3D		79.10 227	78.24 225	81.70 251	86.85 262	60.24 334	87.28 198	88.79 243	74.25 158	76.84 245	90.53 174	49.48 344	91.56 272	67.98 267	82.15 273	93.29 121

ACMP	74.13 6	81.51 163	80.57 163	84.36 135	89.42 139	68.69 126	89.97 85	91.50 139	74.46 151	75.04 299	90.41 175	53.82 290	94.54 121	77.56 155	82.91 264	89.86 275
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
SSM_0407		81.58 158	80.48 166	84.87 113	88.81 167	67.96 149	87.37 193	89.25 221	71.06 233	79.48 186	90.39 176	59.57 236	94.48 126	72.45 223	85.93 210	92.18 180

SSM_0404		81.91 148	80.84 159	85.13 101	89.24 151	68.26 137	87.84 179	89.25 221	71.06 233	80.62 170	90.39 176	59.57 236	94.65 119	72.45 223	87.19 184	92.47 166

viewmambaseed2359dif		80.41 192	79.84 184	82.12 241	82.95 368	62.50 299	83.39 320	88.06 264	67.11 319	80.98 162	90.31 178	66.20 144	91.01 299	74.62 193	84.90 225	92.86 149

RRT-MVS		82.60 139	82.10 139	84.10 152	87.98 207	62.94 293	87.45 190	91.27 142	77.42 56	79.85 180	90.28 179	56.62 266	94.70 117	79.87 126	88.15 164	94.67 35

PCF-MVS	73.52 7	80.38 194	78.84 212	85.01 105	87.71 224	68.99 113	83.65 313	91.46 140	63.00 374	77.77 226	90.28 179	66.10 145	95.09 98	61.40 327	88.22 163	90.94 223
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
NP-MVS					89.62 129	68.32 135					90.24 181

HQP-MVS		82.61 137	82.02 142	84.37 134	89.33 144	66.98 183	89.17 116	92.19 102	76.41 87	77.23 237	90.23 182	60.17 234	95.11 94	77.47 156	85.99 208	91.03 218

PS-MVSNAJss		82.07 145	81.31 149	84.34 137	86.51 274	67.27 176	89.27 112	91.51 136	71.75 214	79.37 189	90.22 183	63.15 177	94.27 131	77.69 154	82.36 272	91.49 204

TSAR-MVS + GP.		85.71 69	85.33 78	86.84 56	91.34 88	72.50 36	89.07 124	87.28 284	76.41 87	85.80 71	90.22 183	74.15 35	95.37 85	81.82 103	91.88 94	92.65 157

SDMVSNet		80.38 194	80.18 173	80.99 272	89.03 161	64.94 235	80.45 365	89.40 208	75.19 129	76.61 254	89.98 185	60.61 228	87.69 359	76.83 167	83.55 253	90.33 249

sd_testset		77.70 266	77.40 251	78.60 323	89.03 161	60.02 336	79.00 386	85.83 315	75.19 129	76.61 254	89.98 185	54.81 276	85.46 384	62.63 313	83.55 253	90.33 249

TranMVSNet+NR-MVSNet		80.84 173	80.31 170	82.42 236	87.85 212	62.33 303	87.74 181	91.33 141	80.55 9	77.99 220	89.86 187	65.23 155	92.62 223	67.05 278	75.24 373	92.30 173

diffmvs		82.10 143	81.88 145	82.76 228	83.00 363	63.78 266	83.68 312	89.76 194	72.94 196	82.02 143	89.85 188	65.96 150	90.79 303	82.38 100	87.30 182	93.71 97
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Elysia		81.53 159	80.16 174	85.62 84	85.51 297	68.25 139	88.84 133	92.19 102	71.31 224	80.50 172	89.83 189	46.89 365	94.82 108	76.85 164	89.57 136	93.80 93

StellarMVS		81.53 159	80.16 174	85.62 84	85.51 297	68.25 139	88.84 133	92.19 102	71.31 224	80.50 172	89.83 189	46.89 365	94.82 108	76.85 164	89.57 136	93.80 93

mamba_0408		79.37 221	77.52 248	84.93 110	88.81 167	67.96 149	65.03 465	88.66 251	70.96 237	79.48 186	89.80 191	58.69 242	94.65 119	70.35 242	85.93 210	92.18 180

SSM_04072		77.67 268	77.52 248	78.12 335	88.81 167	67.96 149	65.03 465	88.66 251	70.96 237	79.48 186	89.80 191	58.69 242	74.23 457	70.35 242	85.93 210	92.18 180

BH-RMVSNet		79.61 209	78.44 219	83.14 202	89.38 143	65.93 202	84.95 278	87.15 289	73.56 176	78.19 214	89.79 193	56.67 265	93.36 185	59.53 343	86.74 193	90.13 257

GeoE		81.71 153	81.01 156	83.80 179	89.51 134	64.45 251	88.97 126	88.73 250	71.27 227	78.63 202	89.76 194	66.32 141	93.20 197	69.89 249	86.02 207	93.74 96

guyue		81.13 168	80.64 162	82.60 233	86.52 273	63.92 262	86.69 221	87.73 275	73.97 163	80.83 168	89.69 195	56.70 264	91.33 287	78.26 150	85.40 221	92.54 160

AdaColmap		80.58 190	79.42 196	84.06 161	93.09 63	68.91 115	89.36 110	88.97 237	69.27 283	75.70 273	89.69 195	57.20 260	95.77 64	63.06 307	88.41 160	87.50 345

ACMM	73.20 8	80.78 182	79.84 184	83.58 184	89.31 147	68.37 134	89.99 84	91.60 133	70.28 258	77.25 235	89.66 197	53.37 295	93.53 174	74.24 199	82.85 265	88.85 309
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CNLPA		78.08 253	76.79 265	81.97 247	90.40 109	71.07 70	87.59 184	84.55 330	66.03 337	72.38 338	89.64 198	57.56 254	86.04 376	59.61 342	83.35 258	88.79 312

test_yl		81.17 166	80.47 167	83.24 197	89.13 156	63.62 267	86.21 242	89.95 188	72.43 204	81.78 148	89.61 199	57.50 255	93.58 166	70.75 236	86.90 189	92.52 161

DCV-MVSNet		81.17 166	80.47 167	83.24 197	89.13 156	63.62 267	86.21 242	89.95 188	72.43 204	81.78 148	89.61 199	57.50 255	93.58 166	70.75 236	86.90 189	92.52 161

EI-MVSNet-Vis-set		84.19 93	83.81 102	85.31 93	88.18 194	67.85 154	87.66 182	89.73 197	80.05 15	82.95 127	89.59 201	70.74 76	94.82 108	80.66 118	84.72 228	93.28 122

PAPR		81.66 156	80.89 158	83.99 171	90.27 111	64.00 258	86.76 219	91.77 125	68.84 299	77.13 244	89.50 202	67.63 124	94.88 106	67.55 271	88.52 157	93.09 135

jajsoiax		79.29 222	77.96 230	83.27 195	84.68 320	66.57 190	89.25 113	90.16 182	69.20 288	75.46 279	89.49 203	45.75 382	93.13 203	76.84 166	80.80 290	90.11 259

MVSFormer		82.85 133	82.05 141	85.24 95	87.35 238	70.21 86	90.50 72	90.38 171	68.55 303	81.32 155	89.47 204	61.68 203	93.46 181	78.98 138	90.26 123	92.05 187

jason		81.39 164	80.29 171	84.70 121	86.63 271	69.90 94	85.95 248	86.77 297	63.24 370	81.07 161	89.47 204	61.08 219	92.15 247	78.33 146	90.07 128	92.05 187
jason: jason.
mvs_tets		79.13 226	77.77 240	83.22 199	84.70 319	66.37 192	89.17 116	90.19 181	69.38 280	75.40 282	89.46 206	44.17 394	93.15 201	76.78 170	80.70 292	90.14 256

UGNet		80.83 174	79.59 193	84.54 124	88.04 203	68.09 144	89.42 106	88.16 259	76.95 71	76.22 263	89.46 206	49.30 348	93.94 147	68.48 264	90.31 121	91.60 198
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
VPA-MVSNet		80.60 187	80.55 164	80.76 278	88.07 202	60.80 324	86.86 213	91.58 134	75.67 112	80.24 176	89.45 208	63.34 170	90.25 313	70.51 240	79.22 312	91.23 211

MVS_Test		83.15 126	83.06 118	83.41 191	86.86 261	63.21 284	86.11 245	92.00 110	74.31 155	82.87 129	89.44 209	70.03 87	93.21 194	77.39 158	88.50 158	93.81 91

EI-MVSNet-UG-set		83.81 102	83.38 113	85.09 103	87.87 211	67.53 166	87.44 192	89.66 198	79.74 18	82.23 139	89.41 210	70.24 82	94.74 114	79.95 123	83.92 243	92.99 144

RPSCF		73.23 338	71.46 342	78.54 326	82.50 377	59.85 337	82.18 338	82.84 363	58.96 413	71.15 353	89.41 210	45.48 386	84.77 391	58.82 352	71.83 403	91.02 220

UniMVSNet_NR-MVSNet		81.88 149	81.54 148	82.92 215	88.46 184	63.46 278	87.13 200	92.37 86	80.19 12	78.38 209	89.14 212	71.66 64	93.05 208	70.05 246	76.46 346	92.25 175

tttt0517		79.40 218	77.91 232	83.90 175	88.10 200	63.84 263	88.37 157	84.05 338	71.45 222	76.78 248	89.12 213	49.93 341	94.89 105	70.18 245	83.18 262	92.96 145

DU-MVS		81.12 169	80.52 165	82.90 216	87.80 215	63.46 278	87.02 205	91.87 118	79.01 31	78.38 209	89.07 214	65.02 157	93.05 208	70.05 246	76.46 346	92.20 178

NR-MVSNet		80.23 200	79.38 197	82.78 226	87.80 215	63.34 281	86.31 237	91.09 150	79.01 31	72.17 341	89.07 214	67.20 129	92.81 220	66.08 285	75.65 359	92.20 178

icg_test_0407_2		78.92 233	78.93 210	78.90 318	87.13 251	63.59 271	76.58 412	89.33 211	70.51 249	77.82 222	89.03 216	61.84 199	81.38 416	72.56 219	85.56 217	91.74 193

IMVS_0407		80.61 185	79.90 182	82.75 229	87.13 251	63.59 271	85.33 267	89.33 211	70.51 249	77.82 222	89.03 216	61.84 199	92.91 213	72.56 219	85.56 217	91.74 193

IMVS_0404		77.16 277	76.42 275	79.37 309	87.13 251	63.59 271	77.12 410	89.33 211	70.51 249	66.22 410	89.03 216	50.36 333	82.78 406	72.56 219	85.56 217	91.74 193

IMVS_0403		80.80 178	80.12 177	82.87 218	87.13 251	63.59 271	85.19 268	89.33 211	70.51 249	78.49 206	89.03 216	63.26 173	93.27 189	72.56 219	85.56 217	91.74 193

DELS-MVS		85.41 76	85.30 80	85.77 79	88.49 182	67.93 152	85.52 265	93.44 32	78.70 34	83.63 115	89.03 216	74.57 27	95.71 66	80.26 121	94.04 67	93.66 99
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
mvsmamba		80.60 187	79.38 197	84.27 145	89.74 128	67.24 178	87.47 187	86.95 292	70.02 263	75.38 283	88.93 221	51.24 322	92.56 228	75.47 187	89.22 143	93.00 143

baseline1		76.98 280	76.75 268	77.66 345	88.13 198	55.66 396	85.12 272	81.89 371	73.04 194	76.79 247	88.90 222	62.43 190	87.78 358	63.30 306	71.18 407	89.55 285

DP-MVS		76.78 284	74.57 303	83.42 189	93.29 52	69.46 104	88.55 149	83.70 342	63.98 365	70.20 359	88.89 223	54.01 289	94.80 111	46.66 431	81.88 278	86.01 380

ab-mvs		79.51 212	78.97 209	81.14 268	88.46 184	60.91 322	83.84 308	89.24 223	70.36 254	79.03 193	88.87 224	63.23 175	90.21 314	65.12 292	82.57 270	92.28 174

PEN-MVS		77.73 263	77.69 244	77.84 341	87.07 259	53.91 413	87.91 175	91.18 145	77.56 51	73.14 326	88.82 225	61.23 215	89.17 334	59.95 338	72.37 397	90.43 244

tt0805		78.73 236	77.83 236	81.43 257	85.17 306	60.30 333	89.41 107	90.90 154	71.21 228	77.17 242	88.73 226	46.38 371	93.21 194	72.57 217	78.96 313	90.79 227

test_djsdf		80.30 199	79.32 200	83.27 195	83.98 335	65.37 219	90.50 72	90.38 171	68.55 303	76.19 264	88.70 227	56.44 267	93.46 181	78.98 138	80.14 300	90.97 221

PAPM		77.68 267	76.40 276	81.51 255	87.29 247	61.85 310	83.78 309	89.59 202	64.74 352	71.23 351	88.70 227	62.59 186	93.66 165	52.66 396	87.03 188	89.01 301

DTE-MVSNet		76.99 279	76.80 264	77.54 350	86.24 278	53.06 422	87.52 185	90.66 162	77.08 69	72.50 335	88.67 229	60.48 230	89.52 326	57.33 367	70.74 409	90.05 266

PS-CasMVS		78.01 257	78.09 228	77.77 343	87.71 224	54.39 410	88.02 169	91.22 143	77.50 54	73.26 324	88.64 230	60.73 222	88.41 350	61.88 322	73.88 386	90.53 240

cdsmvs_eth3d_5k		19.96 448	26.61 450	0.00 469	0.00 492	0.00 494	0.00 481	89.26 220	0.00 487	0.00 488	88.61 231	61.62 205	0.00 488	0.00 487	0.00 486	0.00 484

lupinMVS		81.39 164	80.27 172	84.76 119	87.35 238	70.21 86	85.55 261	86.41 304	62.85 377	81.32 155	88.61 231	61.68 203	92.24 245	78.41 145	90.26 123	91.83 190

F-COLMAP		76.38 295	74.33 309	82.50 235	89.28 149	66.95 186	88.41 153	89.03 232	64.05 363	66.83 399	88.61 231	46.78 367	92.89 214	57.48 364	78.55 315	87.67 339

mvs_anonymous		79.42 217	79.11 206	80.34 287	84.45 326	57.97 357	82.59 334	87.62 277	67.40 318	76.17 267	88.56 234	68.47 113	89.59 325	70.65 239	86.05 206	93.47 114

CP-MVSNet		78.22 248	78.34 222	77.84 341	87.83 214	54.54 408	87.94 173	91.17 146	77.65 46	73.48 322	88.49 235	62.24 194	88.43 349	62.19 318	74.07 382	90.55 239

PVSNet_Blended_VisFu		82.62 136	81.83 146	84.96 107	90.80 101	69.76 97	88.74 140	91.70 127	69.39 279	78.96 194	88.46 236	65.47 153	94.87 107	74.42 196	88.57 155	90.24 253

CANet_DTU		80.61 185	79.87 183	82.83 219	85.60 295	63.17 287	87.36 194	88.65 253	76.37 92	75.88 270	88.44 237	53.51 293	93.07 206	73.30 208	89.74 134	92.25 175

PLC	70.83 11	78.05 255	76.37 277	83.08 206	91.88 83	67.80 156	88.19 163	89.46 206	64.33 358	69.87 368	88.38 238	53.66 291	93.58 166	58.86 351	82.73 267	87.86 336
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
WR-MVS		79.49 213	79.22 204	80.27 289	88.79 172	58.35 350	85.06 275	88.61 255	78.56 35	77.65 227	88.34 239	63.81 169	90.66 308	64.98 294	77.22 334	91.80 192

XXY-MVS		75.41 309	75.56 286	74.96 376	83.59 346	57.82 361	80.59 362	83.87 341	66.54 331	74.93 302	88.31 240	63.24 174	80.09 422	62.16 319	76.85 340	86.97 361

Effi-MVS+		83.62 113	83.08 117	85.24 95	88.38 188	67.45 167	88.89 129	89.15 227	75.50 115	82.27 138	88.28 241	69.61 94	94.45 127	77.81 151	87.84 171	93.84 89

API-MVS		81.99 147	81.23 151	84.26 147	90.94 97	70.18 91	91.10 63	89.32 215	71.51 221	78.66 201	88.28 241	65.26 154	95.10 97	64.74 296	91.23 107	87.51 344

thisisatest0530		79.40 218	77.76 241	84.31 139	87.69 228	65.10 228	87.36 194	84.26 336	70.04 262	77.42 231	88.26 243	49.94 339	94.79 112	70.20 244	84.70 229	93.03 140

hse-mvs2		81.72 152	80.94 157	84.07 158	88.72 175	67.68 160	85.87 251	87.26 286	76.02 102	84.67 87	88.22 244	61.54 206	93.48 179	82.71 96	73.44 391	91.06 216

xiu_mvs_v1_base_debu		80.80 178	79.72 189	84.03 166	87.35 238	70.19 88	85.56 258	88.77 244	69.06 292	81.83 144	88.16 245	50.91 325	92.85 216	78.29 147	87.56 176	89.06 296

xiu_mvs_v1_base		80.80 178	79.72 189	84.03 166	87.35 238	70.19 88	85.56 258	88.77 244	69.06 292	81.83 144	88.16 245	50.91 325	92.85 216	78.29 147	87.56 176	89.06 296

xiu_mvs_v1_base_debi		80.80 178	79.72 189	84.03 166	87.35 238	70.19 88	85.56 258	88.77 244	69.06 292	81.83 144	88.16 245	50.91 325	92.85 216	78.29 147	87.56 176	89.06 296

UniMVSNet (Re)		81.60 157	81.11 153	83.09 204	88.38 188	64.41 252	87.60 183	93.02 50	78.42 37	78.56 204	88.16 245	69.78 91	93.26 190	69.58 253	76.49 345	91.60 198

AUN-MVS		79.21 224	77.60 246	84.05 164	88.71 176	67.61 162	85.84 253	87.26 286	69.08 291	77.23 237	88.14 249	53.20 297	93.47 180	75.50 186	73.45 390	91.06 216

Anonymous20231211		78.97 231	77.69 244	82.81 221	90.54 106	64.29 254	90.11 83	91.51 136	65.01 350	76.16 268	88.13 250	50.56 330	93.03 211	69.68 252	77.56 332	91.11 214

pm-mvs1		77.25 276	76.68 270	78.93 317	84.22 329	58.62 348	86.41 231	88.36 258	71.37 223	73.31 323	88.01 251	61.22 216	89.15 335	64.24 300	73.01 394	89.03 300

LuminaMVS		80.68 183	79.62 192	83.83 176	85.07 312	68.01 148	86.99 206	88.83 241	70.36 254	81.38 154	87.99 252	50.11 336	92.51 232	79.02 135	86.89 191	90.97 221

SD_0403		74.65 317	74.77 301	74.29 385	86.20 280	47.42 449	83.71 311	85.12 322	69.30 282	68.50 382	87.95 253	59.40 238	86.05 375	49.38 416	83.35 258	89.40 288

LTVRE_ROB	69.57 13	76.25 296	74.54 305	81.41 258	88.60 179	64.38 253	79.24 381	89.12 230	70.76 242	69.79 370	87.86 254	49.09 351	93.20 197	56.21 379	80.16 298	86.65 369
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
testing3-2		75.12 314	75.19 296	74.91 377	90.40 109	45.09 460	80.29 368	78.42 412	78.37 40	76.54 256	87.75 255	44.36 392	87.28 364	57.04 370	83.49 255	92.37 169

WTY-MVS		75.65 304	75.68 283	75.57 367	86.40 276	56.82 376	77.92 404	82.40 366	65.10 347	76.18 265	87.72 256	63.13 180	80.90 419	60.31 336	81.96 276	89.00 303

TAMVS		78.89 234	77.51 250	83.03 209	87.80 215	67.79 157	84.72 282	85.05 325	67.63 313	76.75 249	87.70 257	62.25 193	90.82 302	58.53 355	87.13 186	90.49 242

BH-untuned		79.47 214	78.60 215	82.05 244	89.19 154	65.91 203	86.07 246	88.52 256	72.18 207	75.42 281	87.69 258	61.15 217	93.54 173	60.38 335	86.83 192	86.70 367

COLMAP_ROB	66.92 17	73.01 341	70.41 357	80.81 277	87.13 251	65.63 211	88.30 160	84.19 337	62.96 375	63.80 428	87.69 258	38.04 431	92.56 228	46.66 431	74.91 376	84.24 407
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
OurMVSNet-221017-0		74.26 320	72.42 333	79.80 299	83.76 341	59.59 341	85.92 250	86.64 300	66.39 332	66.96 397	87.58 260	39.46 421	91.60 268	65.76 288	69.27 415	88.22 329

FA-MVS(test-final)		80.96 171	79.91 181	84.10 152	88.30 191	65.01 229	84.55 289	90.01 186	73.25 188	79.61 183	87.57 261	58.35 247	94.72 115	71.29 232	86.25 202	92.56 159

Baseline_NR-MVSNet		78.15 252	78.33 223	77.61 347	85.79 289	56.21 389	86.78 217	85.76 316	73.60 175	77.93 221	87.57 261	65.02 157	88.99 337	67.14 277	75.33 370	87.63 340

WR-MVS_H		78.51 243	78.49 217	78.56 325	88.02 204	56.38 385	88.43 151	92.67 72	77.14 65	73.89 316	87.55 263	66.25 142	89.24 332	58.92 350	73.55 389	90.06 265

EI-MVSNet		80.52 191	79.98 179	82.12 241	84.28 327	63.19 286	86.41 231	88.95 238	74.18 160	78.69 199	87.54 264	66.62 135	92.43 235	72.57 217	80.57 294	90.74 231

CVMVSNet		72.99 342	72.58 331	74.25 386	84.28 327	50.85 438	86.41 231	83.45 348	44.56 458	73.23 325	87.54 264	49.38 346	85.70 379	65.90 286	78.44 318	86.19 375

ACMH+	68.96 14	76.01 300	74.01 311	82.03 245	88.60 179	65.31 221	88.86 130	87.55 278	70.25 260	67.75 386	87.47 266	41.27 413	93.19 199	58.37 357	75.94 356	87.60 341

TransMVSNet (Re)		75.39 311	74.56 304	77.86 340	85.50 299	57.10 373	86.78 217	86.09 312	72.17 208	71.53 348	87.34 267	63.01 181	89.31 330	56.84 373	61.83 440	87.17 353

GBi-Net		78.40 244	77.40 251	81.40 259	87.60 231	63.01 288	88.39 154	89.28 217	71.63 216	75.34 285	87.28 268	54.80 277	91.11 292	62.72 309	79.57 304	90.09 261

test1		78.40 244	77.40 251	81.40 259	87.60 231	63.01 288	88.39 154	89.28 217	71.63 216	75.34 285	87.28 268	54.80 277	91.11 292	62.72 309	79.57 304	90.09 261

FMVSNet2		78.20 250	77.21 255	81.20 266	87.60 231	62.89 294	87.47 187	89.02 233	71.63 216	75.29 291	87.28 268	54.80 277	91.10 295	62.38 315	79.38 309	89.61 283

FMVSNet1		77.44 271	76.12 279	81.40 259	86.81 264	63.01 288	88.39 154	89.28 217	70.49 253	74.39 311	87.28 268	49.06 352	91.11 292	60.91 331	78.52 316	90.09 261

v2v482		80.23 200	79.29 201	83.05 208	83.62 345	64.14 256	87.04 203	89.97 187	73.61 174	78.18 215	87.22 272	61.10 218	93.82 156	76.11 175	76.78 342	91.18 212

ITE_SJBPF				78.22 332	81.77 387	60.57 328		83.30 349	69.25 285	67.54 388	87.20 273	36.33 438	87.28 364	54.34 387	74.62 379	86.80 364

anonymousdsp		78.60 240	77.15 256	82.98 213	80.51 406	67.08 181	87.24 199	89.53 204	65.66 341	75.16 294	87.19 274	52.52 299	92.25 244	77.17 160	79.34 310	89.61 283

MVSTER		79.01 229	77.88 235	82.38 237	83.07 360	64.80 241	84.08 306	88.95 238	69.01 295	78.69 199	87.17 275	54.70 281	92.43 235	74.69 192	80.57 294	89.89 274

thres100view900		76.50 288	75.55 287	79.33 310	89.52 133	56.99 374	85.83 254	83.23 351	73.94 165	76.32 261	87.12 276	51.89 314	91.95 255	48.33 422	83.75 247	89.07 294

thres600view7		76.50 288	75.44 288	79.68 303	89.40 141	57.16 371	85.53 263	83.23 351	73.79 169	76.26 262	87.09 277	51.89 314	91.89 258	48.05 427	83.72 250	90.00 267

XVG-ACMP-BASELINE		76.11 298	74.27 310	81.62 252	83.20 356	64.67 243	83.60 316	89.75 196	69.75 273	71.85 344	87.09 277	32.78 445	92.11 248	69.99 248	80.43 296	88.09 332

HY-MVS	69.67 12	77.95 258	77.15 256	80.36 286	87.57 237	60.21 335	83.37 322	87.78 274	66.11 334	75.37 284	87.06 279	63.27 172	90.48 310	61.38 328	82.43 271	90.40 246

CHOSEN 1792x2688		77.63 269	75.69 282	83.44 188	89.98 122	68.58 129	78.70 391	87.50 280	56.38 433	75.80 272	86.84 280	58.67 244	91.40 284	61.58 326	85.75 215	90.34 248

v8		79.97 206	79.02 208	82.80 222	84.09 332	64.50 249	87.96 171	90.29 178	74.13 162	75.24 292	86.81 281	62.88 184	93.89 155	74.39 197	75.40 368	90.00 267

AllTest		70.96 360	68.09 375	79.58 306	85.15 308	63.62 267	84.58 288	79.83 399	62.31 384	60.32 441	86.73 282	32.02 446	88.96 340	50.28 410	71.57 405	86.15 376

TestCases				79.58 306	85.15 308	63.62 267		79.83 399	62.31 384	60.32 441	86.73 282	32.02 446	88.96 340	50.28 410	71.57 405	86.15 376

LCM-MVSNet-Re		77.05 278	76.94 261	77.36 351	87.20 248	51.60 431	80.06 371	80.46 390	75.20 128	67.69 387	86.72 284	62.48 188	88.98 338	63.44 304	89.25 141	91.51 202

1112_ss		77.40 273	76.43 274	80.32 288	89.11 160	60.41 332	83.65 313	87.72 276	62.13 387	73.05 327	86.72 284	62.58 187	89.97 318	62.11 321	80.80 290	90.59 238

ab-mvs-re		7.23 451	9.64 454	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	86.72 284	0.00 491	0.00 488	0.00 487	0.00 486	0.00 484

IterMVS-LS		80.06 203	79.38 197	82.11 243	85.89 287	63.20 285	86.79 216	89.34 210	74.19 159	75.45 280	86.72 284	66.62 135	92.39 237	72.58 216	76.86 339	90.75 230
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ACMH	67.68 16	75.89 301	73.93 313	81.77 250	88.71 176	66.61 189	88.62 145	89.01 234	69.81 269	66.78 400	86.70 288	41.95 410	91.51 279	55.64 380	78.14 324	87.17 353
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Test_1112_low_res		76.40 294	75.44 288	79.27 311	89.28 149	58.09 353	81.69 344	87.07 290	59.53 408	72.48 336	86.67 289	61.30 213	89.33 329	60.81 333	80.15 299	90.41 245

FMVSNet3		77.88 260	76.85 263	80.97 274	86.84 263	62.36 302	86.52 228	88.77 244	71.13 229	75.34 285	86.66 290	54.07 287	91.10 295	62.72 309	79.57 304	89.45 287

pmmvs6		74.69 316	73.39 320	78.61 322	81.38 395	57.48 368	86.64 223	87.95 268	64.99 351	70.18 360	86.61 291	50.43 332	89.52 326	62.12 320	70.18 412	88.83 310

ET-MVSNet_ETH3D		78.63 239	76.63 271	84.64 122	86.73 267	69.47 102	85.01 276	84.61 329	69.54 277	66.51 407	86.59 292	50.16 335	91.75 263	76.26 173	84.24 239	92.69 155

testgi		66.67 400	66.53 396	67.08 435	75.62 441	41.69 470	75.93 415	76.50 427	66.11 334	65.20 418	86.59 292	35.72 440	74.71 454	43.71 443	73.38 392	84.84 401

CLD-MVS		82.31 141	81.65 147	84.29 142	88.47 183	67.73 158	85.81 255	92.35 87	75.78 107	78.33 211	86.58 294	64.01 166	94.35 128	76.05 177	87.48 179	90.79 227
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
v10		79.74 208	78.67 213	82.97 214	84.06 333	64.95 232	87.88 177	90.62 163	73.11 192	75.11 296	86.56 295	61.46 209	94.05 143	73.68 202	75.55 361	89.90 273

CDS-MVSNet		79.07 228	77.70 243	83.17 201	87.60 231	68.23 141	84.40 297	86.20 309	67.49 316	76.36 260	86.54 296	61.54 206	90.79 303	61.86 323	87.33 181	90.49 242
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
xiu_mvs_v2_base		81.69 154	81.05 154	83.60 182	89.15 155	68.03 147	84.46 292	90.02 185	70.67 243	81.30 158	86.53 297	63.17 176	94.19 138	75.60 184	88.54 156	88.57 321

TR-MVS		77.44 271	76.18 278	81.20 266	88.24 192	63.24 283	84.61 287	86.40 305	67.55 315	77.81 224	86.48 298	54.10 286	93.15 201	57.75 363	82.72 268	87.20 352

EIA-MVS		83.31 124	82.80 124	84.82 115	89.59 130	65.59 213	88.21 162	92.68 71	74.66 147	78.96 194	86.42 299	69.06 104	95.26 87	75.54 185	90.09 126	93.62 106

tfpn200view9		76.42 293	75.37 292	79.55 308	89.13 156	57.65 365	85.17 269	83.60 343	73.41 182	76.45 257	86.39 300	52.12 306	91.95 255	48.33 422	83.75 247	89.07 294

thres400		76.50 288	75.37 292	79.86 297	89.13 156	57.65 365	85.17 269	83.60 343	73.41 182	76.45 257	86.39 300	52.12 306	91.95 255	48.33 422	83.75 247	90.00 267

v7n		78.97 231	77.58 247	83.14 202	83.45 349	65.51 214	88.32 159	91.21 144	73.69 172	72.41 337	86.32 302	57.93 249	93.81 157	69.18 256	75.65 359	90.11 259

MAR-MVS		81.84 150	80.70 160	85.27 94	91.32 89	71.53 58	89.82 88	90.92 153	69.77 272	78.50 205	86.21 303	62.36 191	94.52 123	65.36 290	92.05 93	89.77 279
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
v1144		80.03 204	79.03 207	83.01 210	83.78 340	64.51 247	87.11 202	90.57 166	71.96 212	78.08 218	86.20 304	61.41 210	93.94 147	74.93 191	77.23 333	90.60 237

test_vis1_n_1920		75.52 306	75.78 281	74.75 381	79.84 414	57.44 369	83.26 324	85.52 318	62.83 378	79.34 191	86.17 305	45.10 387	79.71 423	78.75 140	81.21 284	87.10 359

V42		79.38 220	78.24 225	82.83 219	81.10 400	65.50 215	85.55 261	89.82 191	71.57 220	78.21 213	86.12 306	60.66 226	93.18 200	75.64 182	75.46 365	89.81 278

PVSNet_BlendedMVS		80.60 187	80.02 178	82.36 238	88.85 163	65.40 216	86.16 244	92.00 110	69.34 281	78.11 216	86.09 307	66.02 148	94.27 131	71.52 228	82.06 275	87.39 346

v1192		79.59 211	78.43 220	83.07 207	83.55 347	64.52 246	86.93 210	90.58 164	70.83 239	77.78 225	85.90 308	59.15 240	93.94 147	73.96 201	77.19 335	90.76 229

SixPastTwentyTwo		73.37 333	71.26 348	79.70 302	85.08 311	57.89 359	85.57 257	83.56 345	71.03 235	65.66 412	85.88 309	42.10 408	92.57 227	59.11 348	63.34 435	88.65 318

EPNet_dtu		75.46 307	74.86 299	77.23 354	82.57 376	54.60 407	86.89 211	83.09 355	71.64 215	66.25 409	85.86 310	55.99 269	88.04 354	54.92 384	86.55 196	89.05 299
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
sss		73.60 330	73.64 318	73.51 393	82.80 370	55.01 404	76.12 414	81.69 374	62.47 383	74.68 306	85.85 311	57.32 257	78.11 430	60.86 332	80.93 286	87.39 346

ETV-MVS		84.90 88	84.67 88	85.59 86	89.39 142	68.66 127	88.74 140	92.64 77	79.97 16	84.10 103	85.71 312	69.32 98	95.38 82	80.82 113	91.37 105	92.72 152

test_cas_vis1_n_1920		73.76 328	73.74 317	73.81 391	75.90 437	59.77 338	80.51 363	82.40 366	58.30 419	81.62 152	85.69 313	44.35 393	76.41 441	76.29 172	78.61 314	85.23 393

v1240		78.99 230	77.78 239	82.64 231	83.21 355	63.54 275	86.62 224	90.30 177	69.74 275	77.33 233	85.68 314	57.04 261	93.76 161	73.13 211	76.92 337	90.62 235

v144192		79.47 214	78.37 221	82.78 226	83.35 350	63.96 259	86.96 207	90.36 174	69.99 265	77.50 229	85.67 315	60.66 226	93.77 160	74.27 198	76.58 343	90.62 235

tfpnnormal		74.39 318	73.16 324	78.08 336	86.10 285	58.05 354	84.65 286	87.53 279	70.32 257	71.22 352	85.63 316	54.97 275	89.86 319	43.03 446	75.02 375	86.32 372

PS-MVSNAJ		81.69 154	81.02 155	83.70 180	89.51 134	68.21 142	84.28 299	90.09 184	70.79 240	81.26 159	85.62 317	63.15 177	94.29 129	75.62 183	88.87 149	88.59 320

SSC-MVS3.2		73.35 336	73.39 320	73.23 394	85.30 304	49.01 445	74.58 429	81.57 375	75.21 127	73.68 319	85.58 318	52.53 298	82.05 411	54.33 388	77.69 330	88.63 319

v1921920		79.22 223	78.03 229	82.80 222	83.30 352	63.94 261	86.80 215	90.33 175	69.91 268	77.48 230	85.53 319	58.44 246	93.75 162	73.60 203	76.85 340	90.71 233

test_0402		72.79 345	70.44 356	79.84 298	88.13 198	65.99 201	85.93 249	84.29 334	65.57 342	67.40 393	85.49 320	46.92 364	92.61 224	35.88 460	74.38 381	80.94 439

v148		78.72 237	77.80 238	81.47 256	82.73 372	61.96 309	86.30 238	88.08 262	73.26 187	76.18 265	85.47 321	62.46 189	92.36 239	71.92 227	73.82 387	90.09 261

USDC		70.33 369	68.37 370	76.21 361	80.60 404	56.23 388	79.19 383	86.49 303	60.89 395	61.29 436	85.47 321	31.78 448	89.47 328	53.37 393	76.21 354	82.94 425

VortexMVS		78.57 242	77.89 234	80.59 281	85.89 287	62.76 295	85.61 256	89.62 201	72.06 210	74.99 300	85.38 323	55.94 270	90.77 306	74.99 190	76.58 343	88.23 328

MVP-Stereo		76.12 297	74.46 307	81.13 269	85.37 302	69.79 95	84.42 296	87.95 268	65.03 349	67.46 390	85.33 324	53.28 296	91.73 265	58.01 361	83.27 260	81.85 434
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MVS		78.19 251	76.99 260	81.78 249	85.66 292	66.99 182	84.66 284	90.47 168	55.08 438	72.02 343	85.27 325	63.83 168	94.11 141	66.10 284	89.80 133	84.24 407

DIV-MVS_self_test		77.72 264	76.76 266	80.58 282	82.48 379	60.48 330	83.09 328	87.86 271	69.22 286	74.38 312	85.24 326	62.10 196	91.53 277	71.09 233	75.40 368	89.74 280

FE-MVS		77.78 262	75.68 283	84.08 157	88.09 201	66.00 200	83.13 327	87.79 273	68.42 307	78.01 219	85.23 327	45.50 385	95.12 92	59.11 348	85.83 214	91.11 214

cl____		77.72 264	76.76 266	80.58 282	82.49 378	60.48 330	83.09 328	87.87 270	69.22 286	74.38 312	85.22 328	62.10 196	91.53 277	71.09 233	75.41 367	89.73 281

HyFIR lowres test		77.53 270	75.40 290	83.94 174	89.59 130	66.62 188	80.36 366	88.64 254	56.29 434	76.45 257	85.17 329	57.64 253	93.28 187	61.34 329	83.10 263	91.91 189

pmmvs4		74.03 326	71.91 337	80.39 285	81.96 384	68.32 135	81.45 348	82.14 368	59.32 409	69.87 368	85.13 330	52.40 302	88.13 353	60.21 337	74.74 378	84.73 403

TDRefinement		67.49 392	64.34 404	76.92 356	73.47 453	61.07 320	84.86 280	82.98 359	59.77 405	58.30 448	85.13 330	26.06 456	87.89 356	47.92 428	60.59 445	81.81 435

Fast-Effi-MVS+		80.81 175	79.92 180	83.47 186	88.85 163	64.51 247	85.53 263	89.39 209	70.79 240	78.49 206	85.06 332	67.54 125	93.58 166	67.03 279	86.58 195	92.32 172

PVSNet_Blended		80.98 170	80.34 169	82.90 216	88.85 163	65.40 216	84.43 294	92.00 110	67.62 314	78.11 216	85.05 333	66.02 148	94.27 131	71.52 228	89.50 138	89.01 301

ttmdpeth		59.91 420	57.10 424	68.34 430	67.13 467	46.65 454	74.64 428	67.41 457	48.30 453	62.52 434	85.04 334	20.40 466	75.93 446	42.55 448	45.90 468	82.44 428

test_fmvs1_n		70.86 362	70.24 359	72.73 402	72.51 460	55.28 401	81.27 351	79.71 401	51.49 449	78.73 198	84.87 335	27.54 455	77.02 435	76.06 176	79.97 302	85.88 384

WBMVS		73.43 332	72.81 328	75.28 373	87.91 209	50.99 437	78.59 394	81.31 380	65.51 345	74.47 310	84.83 336	46.39 370	86.68 368	58.41 356	77.86 326	88.17 331

CMPMVS	51.72 21	70.19 371	68.16 373	76.28 360	73.15 456	57.55 367	79.47 378	83.92 339	48.02 454	56.48 454	84.81 337	43.13 400	86.42 372	62.67 312	81.81 279	84.89 400
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EU-MVSNet		68.53 387	67.61 386	71.31 414	78.51 428	47.01 452	84.47 290	84.27 335	42.27 461	66.44 408	84.79 338	40.44 418	83.76 397	58.76 353	68.54 420	83.17 419

BH-w/o		78.21 249	77.33 254	80.84 276	88.81 167	65.13 225	84.87 279	87.85 272	69.75 273	74.52 309	84.74 339	61.34 212	93.11 204	58.24 359	85.84 213	84.27 406

pmmvs5		71.55 355	70.20 360	75.61 366	77.83 430	56.39 384	81.74 342	80.89 381	57.76 424	67.46 390	84.49 340	49.26 349	85.32 386	57.08 369	75.29 371	85.11 397

reproduce_monomvs		75.40 310	74.38 308	78.46 330	83.92 337	57.80 362	83.78 309	86.94 293	73.47 180	72.25 340	84.47 341	38.74 426	89.27 331	75.32 188	70.53 410	88.31 326

thres200		75.55 305	74.47 306	78.82 319	87.78 218	57.85 360	83.07 330	83.51 346	72.44 203	75.84 271	84.42 342	52.08 309	91.75 263	47.41 429	83.64 252	86.86 363

test_fmvs1		70.93 361	70.52 354	72.16 406	73.71 449	55.05 403	80.82 354	78.77 410	51.21 450	78.58 203	84.41 343	31.20 450	76.94 436	75.88 180	80.12 301	84.47 405

testing3		68.56 386	67.67 385	71.22 415	87.33 243	42.87 465	83.06 331	71.54 445	70.36 254	69.08 376	84.38 344	30.33 452	85.69 380	37.50 458	75.45 366	85.09 398

test_fmvs2		68.35 389	67.48 388	70.98 417	69.50 463	51.95 426	80.05 372	76.38 428	49.33 452	74.65 307	84.38 344	23.30 464	75.40 452	74.51 195	75.17 374	85.60 387

eth_miper_zixun_eth		77.92 259	76.69 269	81.61 254	83.00 363	61.98 308	83.15 326	89.20 225	69.52 278	74.86 303	84.35 346	61.76 202	92.56 228	71.50 230	72.89 395	90.28 252

myMVS_eth3d28		73.62 329	73.53 319	73.90 390	88.20 193	47.41 450	78.06 401	79.37 404	74.29 157	73.98 315	84.29 347	44.67 388	83.54 400	51.47 402	87.39 180	90.74 231

testing91		76.54 286	75.66 285	79.18 314	88.43 186	55.89 392	81.08 352	83.00 358	73.76 170	75.34 285	84.29 347	46.20 376	90.07 316	64.33 298	84.50 231	91.58 200

c3_l		78.75 235	77.91 232	81.26 264	82.89 369	61.56 314	84.09 305	89.13 229	69.97 266	75.56 275	84.29 347	66.36 140	92.09 249	73.47 206	75.48 363	90.12 258

testing99		76.09 299	75.12 298	79.00 315	88.16 195	55.50 398	80.79 356	81.40 378	73.30 186	75.17 293	84.27 350	44.48 391	90.02 317	64.28 299	84.22 240	91.48 205

UWE-MVS		72.13 352	71.49 341	74.03 388	86.66 270	47.70 447	81.40 350	76.89 426	63.60 369	75.59 274	84.22 351	39.94 420	85.62 381	48.98 419	86.13 205	88.77 313

FE-MVSNET3		76.43 292	75.32 294	79.76 300	83.00 363	60.72 325	81.74 342	88.76 248	68.99 296	72.98 328	84.19 352	56.41 268	90.27 311	62.39 314	79.40 308	88.31 326

Fast-Effi-MVS+-dtu		78.02 256	76.49 272	82.62 232	83.16 359	66.96 185	86.94 209	87.45 282	72.45 201	71.49 349	84.17 353	54.79 280	91.58 269	67.61 270	80.31 297	89.30 292

IterMVS-SCA-FT		75.43 308	73.87 315	80.11 293	82.69 373	64.85 240	81.57 346	83.47 347	69.16 289	70.49 356	84.15 354	51.95 312	88.15 352	69.23 255	72.14 401	87.34 348

1314		76.53 287	75.30 295	80.21 291	83.93 336	62.32 304	84.66 284	88.81 242	60.23 401	70.16 362	84.07 355	55.30 274	90.73 307	67.37 273	83.21 261	87.59 343

cl22		78.07 254	77.01 258	81.23 265	82.37 381	61.83 311	83.55 317	87.98 266	68.96 297	75.06 298	83.87 356	61.40 211	91.88 259	73.53 204	76.39 348	89.98 270

EG-PatchMatch MVS		74.04 324	71.82 338	80.71 279	84.92 314	67.42 168	85.86 252	88.08 262	66.04 336	64.22 423	83.85 357	35.10 441	92.56 228	57.44 365	80.83 289	82.16 432

thisisatest0515		77.33 274	75.38 291	83.18 200	85.27 305	63.80 264	82.11 339	83.27 350	65.06 348	75.91 269	83.84 358	49.54 343	94.27 131	67.24 275	86.19 203	91.48 205

test20.03		67.45 393	66.95 394	68.94 424	75.48 442	44.84 461	77.50 406	77.67 416	66.66 325	63.01 430	83.80 359	47.02 363	78.40 428	42.53 449	68.86 419	83.58 416

miper_ehance_all_eth		78.59 241	77.76 241	81.08 270	82.66 374	61.56 314	83.65 313	89.15 227	68.87 298	75.55 276	83.79 360	66.49 138	92.03 250	73.25 209	76.39 348	89.64 282

MSDG		73.36 335	70.99 350	80.49 284	84.51 325	65.80 207	80.71 360	86.13 311	65.70 340	65.46 413	83.74 361	44.60 389	90.91 301	51.13 405	76.89 338	84.74 402

MonoMVSNet		76.49 291	75.80 280	78.58 324	81.55 391	58.45 349	86.36 236	86.22 308	74.87 142	74.73 305	83.73 362	51.79 317	88.73 343	70.78 235	72.15 400	88.55 322

testing11		75.14 313	74.01 311	78.53 327	88.16 195	56.38 385	80.74 359	80.42 392	70.67 243	72.69 334	83.72 363	43.61 398	89.86 319	62.29 317	83.76 246	89.36 290

IterMVS		74.29 319	72.94 327	78.35 331	81.53 392	63.49 277	81.58 345	82.49 365	68.06 311	69.99 365	83.69 364	51.66 319	85.54 382	65.85 287	71.64 404	86.01 380
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tpm		72.37 348	71.71 339	74.35 384	82.19 382	52.00 425	79.22 382	77.29 422	64.56 354	72.95 330	83.68 365	51.35 320	83.26 404	58.33 358	75.80 357	87.81 337

UWE-MVS-28		65.32 407	64.93 401	66.49 436	78.70 426	38.55 473	77.86 405	64.39 465	62.00 389	64.13 424	83.60 366	41.44 411	76.00 445	31.39 465	80.89 287	84.92 399

sc_t1		72.19 351	69.51 362	80.23 290	84.81 316	61.09 319	84.68 283	80.22 396	60.70 397	71.27 350	83.58 367	36.59 436	89.24 332	60.41 334	63.31 436	90.37 247

testing222		74.04 324	72.66 330	78.19 333	87.89 210	55.36 399	81.06 353	79.20 407	71.30 226	74.65 307	83.57 368	39.11 425	88.67 345	51.43 404	85.75 215	90.53 240

Effi-MVS+-dtu		80.03 204	78.57 216	84.42 131	85.13 310	68.74 121	88.77 136	88.10 261	74.99 134	74.97 301	83.49 369	57.27 258	93.36 185	73.53 204	80.88 288	91.18 212

baseline2		75.70 303	73.83 316	81.30 262	83.26 353	61.79 312	82.57 335	80.65 385	66.81 321	66.88 398	83.42 370	57.86 251	92.19 246	63.47 303	79.57 304	89.91 272

mvs5depth		69.45 378	67.45 389	75.46 371	73.93 447	55.83 393	79.19 383	83.23 351	66.89 320	71.63 347	83.32 371	33.69 444	85.09 387	59.81 340	55.34 455	85.46 389

TinyColmap		67.30 395	64.81 402	74.76 380	81.92 386	56.68 380	80.29 368	81.49 377	60.33 399	56.27 455	83.22 372	24.77 460	87.66 360	45.52 439	69.47 414	79.95 444

mvsany_test1		62.30 416	61.26 420	65.41 438	69.52 462	54.86 405	66.86 457	49.78 478	46.65 455	68.50 382	83.21 373	49.15 350	66.28 470	56.93 372	60.77 443	75.11 454

test_vis1_n		69.85 376	69.21 365	71.77 408	72.66 459	55.27 402	81.48 347	76.21 429	52.03 446	75.30 290	83.20 374	28.97 453	76.22 443	74.60 194	78.41 322	83.81 413

CostFormer		75.24 312	73.90 314	79.27 311	82.65 375	58.27 352	80.80 355	82.73 364	61.57 391	75.33 289	83.13 375	55.52 272	91.07 298	64.98 294	78.34 323	88.45 323

MVStest1		56.63 424	52.76 430	68.25 431	61.67 473	53.25 421	71.67 438	68.90 455	38.59 466	50.59 462	83.05 376	25.08 458	70.66 463	36.76 459	38.56 469	80.83 440

WB-MVSnew		71.96 354	71.65 340	72.89 400	84.67 323	51.88 428	82.29 337	77.57 417	62.31 384	73.67 320	83.00 377	53.49 294	81.10 418	45.75 438	82.13 274	85.70 386

ETVMVS		72.25 350	71.05 349	75.84 363	87.77 220	51.91 427	79.39 379	74.98 433	69.26 284	73.71 318	82.95 378	40.82 417	86.14 374	46.17 435	84.43 236	89.47 286

miper_lstm_enhance		74.11 323	73.11 325	77.13 355	80.11 410	59.62 340	72.23 436	86.92 295	66.76 323	70.40 357	82.92 379	56.93 262	82.92 405	69.06 258	72.63 396	88.87 308

GA-MVS		76.87 282	75.17 297	81.97 247	82.75 371	62.58 296	81.44 349	86.35 307	72.16 209	74.74 304	82.89 380	46.20 376	92.02 252	68.85 261	81.09 285	91.30 210

K. test v3		71.19 357	68.51 369	79.21 313	83.04 362	57.78 363	84.35 298	76.91 425	72.90 197	62.99 431	82.86 381	39.27 422	91.09 297	61.65 325	52.66 458	88.75 314

MS-PatchMatch		73.83 327	72.67 329	77.30 353	83.87 338	66.02 198	81.82 340	84.66 328	61.37 394	68.61 380	82.82 382	47.29 360	88.21 351	59.27 345	84.32 238	77.68 449

lessismore_v0				78.97 316	81.01 401	57.15 372		65.99 460		61.16 437	82.82 382	39.12 424	91.34 286	59.67 341	46.92 465	88.43 324

D2MVS		74.82 315	73.21 323	79.64 305	79.81 415	62.56 298	80.34 367	87.35 283	64.37 357	68.86 377	82.66 384	46.37 372	90.10 315	67.91 268	81.24 283	86.25 373

Anonymous20231206		68.60 384	67.80 382	71.02 416	80.23 409	50.75 439	78.30 399	80.47 389	56.79 431	66.11 411	82.63 385	46.35 373	78.95 426	43.62 444	75.70 358	83.36 418

MIMVSNet		70.69 364	69.30 363	74.88 378	84.52 324	56.35 387	75.87 418	79.42 403	64.59 353	67.76 385	82.41 386	41.10 414	81.54 414	46.64 433	81.34 281	86.75 366

UBG		73.08 340	72.27 335	75.51 369	88.02 204	51.29 435	78.35 398	77.38 421	65.52 343	73.87 317	82.36 387	45.55 383	86.48 371	55.02 383	84.39 237	88.75 314

OpenMVS_ROB	64.09 19	70.56 366	68.19 372	77.65 346	80.26 407	59.41 344	85.01 276	82.96 360	58.76 416	65.43 414	82.33 388	37.63 433	91.23 290	45.34 441	76.03 355	82.32 429

miper_enhance_ethall		77.87 261	76.86 262	80.92 275	81.65 388	61.38 316	82.68 333	88.98 235	65.52 343	75.47 277	82.30 389	65.76 152	92.00 253	72.95 212	76.39 348	89.39 289

test0.0.03 1		68.00 391	67.69 384	68.90 425	77.55 431	47.43 448	75.70 419	72.95 444	66.66 325	66.56 403	82.29 390	48.06 357	75.87 447	44.97 442	74.51 380	83.41 417

PVSNet	64.34 18	72.08 353	70.87 352	75.69 365	86.21 279	56.44 383	74.37 430	80.73 384	62.06 388	70.17 361	82.23 391	42.86 402	83.31 403	54.77 385	84.45 235	87.32 349

MIMVSNet1		68.58 385	66.78 395	73.98 389	80.07 411	51.82 429	80.77 357	84.37 331	64.40 356	59.75 444	82.16 392	36.47 437	83.63 399	42.73 447	70.33 411	86.48 371

CL-MVSNet_self_test		72.37 348	71.46 342	75.09 375	79.49 421	53.53 415	80.76 358	85.01 326	69.12 290	70.51 355	82.05 393	57.92 250	84.13 395	52.27 398	66.00 429	87.60 341

tpm2		73.26 337	71.46 342	78.63 321	83.34 351	56.71 379	80.65 361	80.40 393	56.63 432	73.55 321	82.02 394	51.80 316	91.24 289	56.35 378	78.42 321	87.95 333

PatchMatch-RL		72.38 347	70.90 351	76.80 358	88.60 179	67.38 171	79.53 377	76.17 430	62.75 380	69.36 373	82.00 395	45.51 384	84.89 390	53.62 391	80.58 293	78.12 448

FE-MVSNET2		72.88 344	71.28 346	77.67 344	78.30 429	57.78 363	84.43 294	88.92 240	69.56 276	64.61 420	81.67 396	46.73 369	88.54 348	59.33 344	67.99 421	86.69 368

FMVSNet5		69.50 377	67.96 377	74.15 387	82.97 367	55.35 400	80.01 373	82.12 369	62.56 382	63.02 429	81.53 397	36.92 434	81.92 412	48.42 421	74.06 383	85.17 396

CR-MVSNet		73.37 333	71.27 347	79.67 304	81.32 398	65.19 223	75.92 416	80.30 394	59.92 404	72.73 332	81.19 398	52.50 300	86.69 367	59.84 339	77.71 328	87.11 357

Patchmtry		70.74 363	69.16 366	75.49 370	80.72 402	54.07 412	74.94 427	80.30 394	58.34 418	70.01 363	81.19 398	52.50 300	86.54 369	53.37 393	71.09 408	85.87 385

IB-MVS	68.01 15	75.85 302	73.36 322	83.31 193	84.76 318	66.03 197	83.38 321	85.06 324	70.21 261	69.40 372	81.05 400	45.76 381	94.66 118	65.10 293	75.49 362	89.25 293
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
cascas		76.72 285	74.64 302	82.99 211	85.78 290	65.88 204	82.33 336	89.21 224	60.85 396	72.74 331	81.02 401	47.28 361	93.75 162	67.48 272	85.02 223	89.34 291

LF4IMVS		64.02 412	62.19 416	69.50 422	70.90 461	53.29 420	76.13 413	77.18 423	52.65 444	58.59 446	80.98 402	23.55 463	76.52 439	53.06 395	66.66 425	78.68 447

Anonymous20240521		68.80 383	67.22 392	73.55 392	74.33 445	54.11 411	83.18 325	85.61 317	58.15 420	61.68 435	80.94 403	30.71 451	81.27 417	57.00 371	73.34 393	85.28 392

gm-plane-assit					81.40 394	53.83 414			62.72 381		80.94 403		92.39 237	63.40 305

UnsupCasMVSNet_eth		67.33 394	65.99 398	71.37 411	73.48 452	51.47 433	75.16 423	85.19 321	65.20 346	60.78 438	80.93 405	42.35 404	77.20 434	57.12 368	53.69 457	85.44 390

dmvs_re		71.14 358	70.58 353	72.80 401	81.96 384	59.68 339	75.60 420	79.34 405	68.55 303	69.27 375	80.72 406	49.42 345	76.54 438	52.56 397	77.79 327	82.19 431

MDTV_nov1_ep13			69.97 361		83.18 357	53.48 416	77.10 411	80.18 398	60.45 398	69.33 374	80.44 407	48.89 355	86.90 366	51.60 401	78.51 317

pmmvs-eth3d		70.50 367	67.83 381	78.52 328	77.37 433	66.18 195	81.82 340	81.51 376	58.90 414	63.90 427	80.42 408	42.69 403	86.28 373	58.56 354	65.30 431	83.11 421

tt0320		70.49 368	68.03 376	77.89 339	84.78 317	59.12 345	83.55 317	80.44 391	58.13 421	67.43 392	80.41 409	39.26 423	87.54 361	55.12 382	63.18 437	86.99 360

mmtdpeth		74.16 322	73.01 326	77.60 349	83.72 342	61.13 317	85.10 273	85.10 323	72.06 210	77.21 241	80.33 410	43.84 396	85.75 378	77.14 161	52.61 459	85.91 383

tt0320-xc		70.11 372	67.45 389	78.07 337	85.33 303	59.51 343	83.28 323	78.96 409	58.77 415	67.10 396	80.28 411	36.73 435	87.42 362	56.83 374	59.77 447	87.29 350

PM-MVS		66.41 402	64.14 405	73.20 397	73.92 448	56.45 382	78.97 387	64.96 464	63.88 367	64.72 419	80.24 412	19.84 468	83.44 402	66.24 281	64.52 433	79.71 445

SCA		74.22 321	72.33 334	79.91 296	84.05 334	62.17 306	79.96 374	79.29 406	66.30 333	72.38 338	80.13 413	51.95 312	88.60 346	59.25 346	77.67 331	88.96 305

Patchmatch-test		64.82 410	63.24 411	69.57 421	79.42 422	49.82 443	63.49 469	69.05 453	51.98 447	59.95 443	80.13 413	50.91 325	70.98 462	40.66 452	73.57 388	87.90 335

tpmrst		72.39 346	72.13 336	73.18 398	80.54 405	49.91 442	79.91 375	79.08 408	63.11 372	71.69 346	79.95 415	55.32 273	82.77 407	65.66 289	73.89 385	86.87 362

DSMNet-mixed		57.77 423	56.90 425	60.38 444	67.70 465	35.61 475	69.18 449	53.97 476	32.30 474	57.49 451	79.88 416	40.39 419	68.57 468	38.78 456	72.37 397	76.97 450

MDA-MVSNet-bldmvs		66.68 399	63.66 409	75.75 364	79.28 423	60.56 329	73.92 432	78.35 413	64.43 355	50.13 463	79.87 417	44.02 395	83.67 398	46.10 436	56.86 449	83.03 423

PatchmatchNet		73.12 339	71.33 345	78.49 329	83.18 357	60.85 323	79.63 376	78.57 411	64.13 359	71.73 345	79.81 418	51.20 323	85.97 377	57.40 366	76.36 353	88.66 317
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
FE-MVSNET		67.25 396	65.33 400	73.02 399	75.86 438	52.54 423	80.26 370	80.56 387	63.80 368	60.39 439	79.70 419	41.41 412	84.66 393	43.34 445	62.62 438	81.86 433

Syy-MVS		68.05 390	67.85 379	68.67 428	84.68 320	40.97 471	78.62 392	73.08 442	66.65 328	66.74 401	79.46 420	52.11 308	82.30 409	32.89 463	76.38 351	82.75 426

myMVS_eth3d		67.02 397	66.29 397	69.21 423	84.68 320	42.58 466	78.62 392	73.08 442	66.65 328	66.74 401	79.46 420	31.53 449	82.30 409	39.43 455	76.38 351	82.75 426

ppachtmachnet_test		70.04 373	67.34 391	78.14 334	79.80 416	61.13 317	79.19 383	80.59 386	59.16 411	65.27 415	79.29 422	46.75 368	87.29 363	49.33 417	66.72 424	86.00 382

EPMVS		69.02 381	68.16 373	71.59 409	79.61 419	49.80 444	77.40 407	66.93 458	62.82 379	70.01 363	79.05 423	45.79 380	77.86 432	56.58 376	75.26 372	87.13 356

PMMVS		69.34 379	68.67 368	71.35 413	75.67 440	62.03 307	75.17 422	73.46 440	50.00 451	68.68 378	79.05 423	52.07 310	78.13 429	61.16 330	82.77 266	73.90 455

test-LLR		72.94 343	72.43 332	74.48 382	81.35 396	58.04 355	78.38 395	77.46 418	66.66 325	69.95 366	79.00 425	48.06 357	79.24 424	66.13 282	84.83 226	86.15 376

test-mter		71.41 356	70.39 358	74.48 382	81.35 396	58.04 355	78.38 395	77.46 418	60.32 400	69.95 366	79.00 425	36.08 439	79.24 424	66.13 282	84.83 226	86.15 376

KD-MVS_self_test		68.81 382	67.59 387	72.46 405	74.29 446	45.45 455	77.93 403	87.00 291	63.12 371	63.99 426	78.99 427	42.32 405	84.77 391	56.55 377	64.09 434	87.16 355

test_fmvs3		63.36 414	61.82 417	67.98 432	62.51 472	46.96 453	77.37 408	74.03 439	45.24 457	67.50 389	78.79 428	12.16 476	72.98 461	72.77 215	66.02 428	83.99 411

KD-MVS_2432*1600		66.22 404	63.89 407	73.21 395	75.47 443	53.42 417	70.76 443	84.35 332	64.10 361	66.52 405	78.52 429	34.55 442	84.98 388	50.40 408	50.33 462	81.23 437

miper_refine_blended		66.22 404	63.89 407	73.21 395	75.47 443	53.42 417	70.76 443	84.35 332	64.10 361	66.52 405	78.52 429	34.55 442	84.98 388	50.40 408	50.33 462	81.23 437

tpmvs		71.09 359	69.29 364	76.49 359	82.04 383	56.04 390	78.92 388	81.37 379	64.05 363	67.18 395	78.28 431	49.74 342	89.77 321	49.67 415	72.37 397	83.67 415

our_test_3		69.14 380	67.00 393	75.57 367	79.80 416	58.80 346	77.96 402	77.81 415	59.55 407	62.90 432	78.25 432	47.43 359	83.97 396	51.71 400	67.58 423	83.93 412

MDA-MVSNet_test_wron		65.03 408	62.92 412	71.37 411	75.93 436	56.73 377	69.09 452	74.73 436	57.28 429	54.03 458	77.89 433	45.88 378	74.39 456	49.89 414	61.55 441	82.99 424

YYNet1		65.03 408	62.91 413	71.38 410	75.85 439	56.60 381	69.12 451	74.66 438	57.28 429	54.12 457	77.87 434	45.85 379	74.48 455	49.95 413	61.52 442	83.05 422

ambc				75.24 374	73.16 455	50.51 440	63.05 470	87.47 281		64.28 422	77.81 435	17.80 470	89.73 323	57.88 362	60.64 444	85.49 388

tpm cat1		70.57 365	68.31 371	77.35 352	82.41 380	57.95 358	78.08 400	80.22 396	52.04 445	68.54 381	77.66 436	52.00 311	87.84 357	51.77 399	72.07 402	86.25 373

dp		66.80 398	65.43 399	70.90 418	79.74 418	48.82 446	75.12 425	74.77 435	59.61 406	64.08 425	77.23 437	42.89 401	80.72 420	48.86 420	66.58 426	83.16 420

TESTMET0.1,1		69.89 375	69.00 367	72.55 403	79.27 424	56.85 375	78.38 395	74.71 437	57.64 425	68.09 384	77.19 438	37.75 432	76.70 437	63.92 301	84.09 241	84.10 410

CHOSEN 280x420		66.51 401	64.71 403	71.90 407	81.45 393	63.52 276	57.98 472	68.95 454	53.57 441	62.59 433	76.70 439	46.22 375	75.29 453	55.25 381	79.68 303	76.88 451

PatchT		68.46 388	67.85 379	70.29 419	80.70 403	43.93 463	72.47 435	74.88 434	60.15 402	70.55 354	76.57 440	49.94 339	81.59 413	50.58 406	74.83 377	85.34 391

mvsany_test3		53.99 427	51.45 432	61.61 443	55.51 477	44.74 462	63.52 468	45.41 482	43.69 460	58.11 449	76.45 441	17.99 469	63.76 473	54.77 385	47.59 464	76.34 452

RPMNet		73.51 331	70.49 355	82.58 234	81.32 398	65.19 223	75.92 416	92.27 90	57.60 426	72.73 332	76.45 441	52.30 303	95.43 77	48.14 426	77.71 328	87.11 357

dmvs_testset		62.63 415	64.11 406	58.19 446	78.55 427	24.76 484	75.28 421	65.94 461	67.91 312	60.34 440	76.01 443	53.56 292	73.94 459	31.79 464	67.65 422	75.88 453

ADS-MVSNet2		66.20 406	63.33 410	74.82 379	79.92 412	58.75 347	67.55 455	75.19 432	53.37 442	65.25 416	75.86 444	42.32 405	80.53 421	41.57 450	68.91 417	85.18 394

ADS-MVSNet		64.36 411	62.88 414	68.78 427	79.92 412	47.17 451	67.55 455	71.18 446	53.37 442	65.25 416	75.86 444	42.32 405	73.99 458	41.57 450	68.91 417	85.18 394

EGC-MVSNET		52.07 433	47.05 437	67.14 434	83.51 348	60.71 326	80.50 364	67.75 456	0.07 484	0.43 485	75.85 446	24.26 461	81.54 414	28.82 467	62.25 439	59.16 467

new-patchmatchnet		61.73 417	61.73 418	61.70 442	72.74 458	24.50 485	69.16 450	78.03 414	61.40 392	56.72 453	75.53 447	38.42 428	76.48 440	45.95 437	57.67 448	84.13 409

N_pmnet		52.79 431	53.26 429	51.40 456	78.99 425	7.68 490	69.52 447	3.89 489	51.63 448	57.01 452	74.98 448	40.83 416	65.96 471	37.78 457	64.67 432	80.56 443

WB-MVS		54.94 425	54.72 426	55.60 452	73.50 451	20.90 486	74.27 431	61.19 469	59.16 411	50.61 461	74.15 449	47.19 362	75.78 448	17.31 477	35.07 471	70.12 459

patchmatchnet-post											74.00 450	51.12 324	88.60 346

GG-mvs-BLEND				75.38 372	81.59 390	55.80 394	79.32 380	69.63 450		67.19 394	73.67 451	43.24 399	88.90 342	50.41 407	84.50 231	81.45 436

SSC-MVS		53.88 428	53.59 428	54.75 454	72.87 457	19.59 487	73.84 433	60.53 471	57.58 427	49.18 465	73.45 452	46.34 374	75.47 451	16.20 480	32.28 473	69.20 460

Patchmatch-RL test		70.24 370	67.78 383	77.61 347	77.43 432	59.57 342	71.16 440	70.33 447	62.94 376	68.65 379	72.77 453	50.62 329	85.49 383	69.58 253	66.58 426	87.77 338

FPMVS		53.68 429	51.64 431	59.81 445	65.08 469	51.03 436	69.48 448	69.58 451	41.46 462	40.67 469	72.32 454	16.46 472	70.00 466	24.24 473	65.42 430	58.40 469

UnsupCasMVSNet_bld		63.70 413	61.53 419	70.21 420	73.69 450	51.39 434	72.82 434	81.89 371	55.63 436	57.81 450	71.80 455	38.67 427	78.61 427	49.26 418	52.21 460	80.63 441

APD_test1		53.31 430	49.93 435	63.42 441	65.68 468	50.13 441	71.59 439	66.90 459	34.43 471	40.58 470	71.56 456	8.65 481	76.27 442	34.64 462	55.36 454	63.86 465

test_f		52.09 432	50.82 433	55.90 450	53.82 480	42.31 469	59.42 471	58.31 474	36.45 469	56.12 456	70.96 457	12.18 475	57.79 476	53.51 392	56.57 451	67.60 461

PVSNet_0	57.27 20	61.67 418	59.27 421	68.85 426	79.61 419	57.44 369	68.01 453	73.44 441	55.93 435	58.54 447	70.41 458	44.58 390	77.55 433	47.01 430	35.91 470	71.55 458

pmmvs3		57.79 422	54.26 427	68.37 429	64.02 471	56.72 378	75.12 425	65.17 462	40.20 463	52.93 459	69.86 459	20.36 467	75.48 450	45.45 440	55.25 456	72.90 457

test_vis1_rt		60.28 419	58.42 422	65.84 437	67.25 466	55.60 397	70.44 445	60.94 470	44.33 459	59.00 445	66.64 460	24.91 459	68.67 467	62.80 308	69.48 413	73.25 456

new_pmnet		50.91 434	50.29 434	52.78 455	68.58 464	34.94 477	63.71 467	56.63 475	39.73 464	44.95 466	65.47 461	21.93 465	58.48 475	34.98 461	56.62 450	64.92 463

gg-mvs-nofinetune		69.95 374	67.96 377	75.94 362	83.07 360	54.51 409	77.23 409	70.29 448	63.11 372	70.32 358	62.33 462	43.62 397	88.69 344	53.88 390	87.76 174	84.62 404

JIA-IIPM		66.32 403	62.82 415	76.82 357	77.09 434	61.72 313	65.34 463	75.38 431	58.04 423	64.51 421	62.32 463	42.05 409	86.51 370	51.45 403	69.22 416	82.21 430

LCM-MVSNet		54.25 426	49.68 436	67.97 433	53.73 481	45.28 458	66.85 458	80.78 383	35.96 470	39.45 471	62.23 464	8.70 480	78.06 431	48.24 425	51.20 461	80.57 442

PMMVS2		40.82 442	38.86 446	46.69 457	53.84 479	16.45 488	48.61 475	49.92 477	37.49 467	31.67 472	60.97 465	8.14 482	56.42 477	28.42 468	30.72 474	67.19 462

testf1		45.72 437	41.96 441	57.00 447	56.90 475	45.32 456	66.14 460	59.26 472	26.19 475	30.89 474	60.96 466	4.14 484	70.64 464	26.39 471	46.73 466	55.04 470

APD_test2		45.72 437	41.96 441	57.00 447	56.90 475	45.32 456	66.14 460	59.26 472	26.19 475	30.89 474	60.96 466	4.14 484	70.64 464	26.39 471	46.73 466	55.04 470

MVS-HIRNet		59.14 421	57.67 423	63.57 440	81.65 388	43.50 464	71.73 437	65.06 463	39.59 465	51.43 460	57.73 468	38.34 429	82.58 408	39.53 453	73.95 384	64.62 464

ANet_high		50.57 435	46.10 439	63.99 439	48.67 484	39.13 472	70.99 442	80.85 382	61.39 393	31.18 473	57.70 469	17.02 471	73.65 460	31.22 466	15.89 481	79.18 446

PMVS	37.38 22	44.16 441	40.28 445	55.82 451	40.82 486	42.54 468	65.12 464	63.99 466	34.43 471	24.48 477	57.12 470	3.92 486	76.17 444	17.10 478	55.52 453	48.75 472
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
dongtai		45.42 439	45.38 440	45.55 458	73.36 454	26.85 482	67.72 454	34.19 484	54.15 440	49.65 464	56.41 471	25.43 457	62.94 474	19.45 475	28.09 475	46.86 474

test_vis3_rt		49.26 436	47.02 438	56.00 449	54.30 478	45.27 459	66.76 459	48.08 479	36.83 468	44.38 467	53.20 472	7.17 483	64.07 472	56.77 375	55.66 452	58.65 468

test_method		31.52 445	29.28 449	38.23 460	27.03 488	6.50 491	20.94 480	62.21 468	4.05 482	22.35 480	52.50 473	13.33 473	47.58 480	27.04 470	34.04 472	60.62 466

kuosan		39.70 443	40.40 444	37.58 461	64.52 470	26.98 480	65.62 462	33.02 485	46.12 456	42.79 468	48.99 474	24.10 462	46.56 482	12.16 483	26.30 476	39.20 475

DeepMVS_CX				27.40 464	40.17 487	26.90 481		24.59 488	17.44 480	23.95 478	48.61 475	9.77 478	26.48 483	18.06 476	24.47 477	28.83 477

MVE	26.22 23	30.37 447	25.89 451	43.81 459	44.55 485	35.46 476	28.87 479	39.07 483	18.20 479	18.58 481	40.18 476	2.68 487	47.37 481	17.07 479	23.78 478	48.60 473
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
Gipuma		45.18 440	41.86 443	55.16 453	77.03 435	51.52 432	32.50 478	80.52 388	32.46 473	27.12 476	35.02 477	9.52 479	75.50 449	22.31 474	60.21 446	38.45 476
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
E-PMN		31.77 444	30.64 447	35.15 462	52.87 482	27.67 479	57.09 473	47.86 480	24.64 477	16.40 482	33.05 478	11.23 477	54.90 478	14.46 481	18.15 479	22.87 478

EMVS		30.81 446	29.65 448	34.27 463	50.96 483	25.95 483	56.58 474	46.80 481	24.01 478	15.53 483	30.68 479	12.47 474	54.43 479	12.81 482	17.05 480	22.43 479

tmp_tt		18.61 449	21.40 452	10.23 466	4.82 489	10.11 489	34.70 477	30.74 487	1.48 483	23.91 479	26.07 480	28.42 454	13.41 485	27.12 469	15.35 482	7.17 480

X-MVStestdata		80.37 196	77.83 236	88.00 17	94.42 24	73.33 19	92.78 23	92.99 54	79.14 26	83.67 113	12.47 481	67.45 126	96.60 37	83.06 87	94.50 57	94.07 75

test_post											5.46 482	50.36 333	84.24 394

test_post1							78.90 389				5.43 483	48.81 356	85.44 385	59.25 346

wuyk23d		16.82 450	15.94 453	19.46 465	58.74 474	31.45 478	39.22 476	3.74 490	6.84 481	6.04 484	2.70 484	1.27 488	24.29 484	10.54 484	14.40 483	2.63 481

testmvs		6.04 453	8.02 456	0.10 468	0.08 490	0.03 493	69.74 446	0.04 491	0.05 485	0.31 486	1.68 485	0.02 490	0.04 486	0.24 485	0.02 484	0.25 483

test123		6.12 452	8.11 455	0.14 467	0.06 491	0.09 492	71.05 441	0.03 492	0.04 486	0.25 487	1.30 486	0.05 489	0.03 487	0.21 486	0.01 485	0.29 482

mmdepth		0.00 455	0.00 458	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	0.00 487	0.00 491	0.00 488	0.00 487	0.00 486	0.00 484

monomultidepth		0.00 455	0.00 458	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	0.00 487	0.00 491	0.00 488	0.00 487	0.00 486	0.00 484

test_blank		0.00 455	0.00 458	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	0.00 487	0.00 491	0.00 488	0.00 487	0.00 486	0.00 484

uanet_test		0.00 455	0.00 458	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	0.00 487	0.00 491	0.00 488	0.00 487	0.00 486	0.00 484

DCPMVS		0.00 455	0.00 458	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	0.00 487	0.00 491	0.00 488	0.00 487	0.00 486	0.00 484

pcd_1.5k_mvsjas		5.26 454	7.02 457	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	0.00 487	63.15 177	0.00 488	0.00 487	0.00 486	0.00 484

sosnet-low-res		0.00 455	0.00 458	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	0.00 487	0.00 491	0.00 488	0.00 487	0.00 486	0.00 484

sosnet		0.00 455	0.00 458	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	0.00 487	0.00 491	0.00 488	0.00 487	0.00 486	0.00 484

uncertanet		0.00 455	0.00 458	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	0.00 487	0.00 491	0.00 488	0.00 487	0.00 486	0.00 484

Regformer		0.00 455	0.00 458	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	0.00 487	0.00 491	0.00 488	0.00 487	0.00 486	0.00 484

uanet		0.00 455	0.00 458	0.00 469	0.00 492	0.00 494	0.00 481	0.00 493	0.00 487	0.00 488	0.00 487	0.00 491	0.00 488	0.00 487	0.00 486	0.00 484

TestfortrainingZip							93.28 12

WAC-MVS						42.58 466								39.46 454

FOURS1					95.00 10	72.39 41	95.06 1	93.84 20	74.49 150	91.30 18

MSC_two_6792asdad				89.16 1	94.34 31	75.53 2		92.99 54					97.53 2	89.67 15	96.44 9	94.41 55

No_MVS				89.16 1	94.34 31	75.53 2		92.99 54					97.53 2	89.67 15	96.44 9	94.41 55

eth-test2					0.00 492

eth-test					0.00 492

IU-MVS					95.30 2	71.25 64		92.95 60	66.81 321	92.39 6				88.94 28	96.63 4	94.85 21

save fliter					93.80 44	72.35 44	90.47 74	91.17 146	74.31 155

test_0728_SECOND				87.71 35	95.34 1	71.43 60	93.49 10	94.23 7					97.49 4	89.08 22	96.41 12	94.21 67

GSMVS																88.96 305

test_part2					95.06 8	72.65 32				91.80 16

sam_mvs1												51.32 321				88.96 305

sam_mvs												50.01 337

MTGPA								92.02 108

MTMP							92.18 39	32.83 486

test9_res														84.90 64	95.70 30	92.87 148

agg_prior2														82.91 91	95.45 33	92.70 153

agg_prior					92.85 68	71.94 52		91.78 124		84.41 95			94.93 101

test_prior4						72.60 34	89.01 125

test_prior				86.33 64	92.61 74	69.59 98		92.97 59					95.48 74			93.91 83

旧先验2							86.56 226		58.10 422	87.04 61			88.98 338	74.07 200

新几何2							86.29 240

无先验							87.48 186	88.98 235	60.00 403				94.12 140	67.28 274		88.97 304

原ACMM2							86.86 213

testdata2													91.01 299	62.37 316

segment_acmp												73.08 43

testdata1							84.14 304		75.71 109

test12				86.80 58	92.63 73	70.70 81		91.79 123		82.71 134		71.67 63	96.16 52		94.50 57	93.54 112

plane_prior7					90.08 116	68.51 131

plane_prior6					89.84 125	68.70 125						60.42 231

plane_prior5								92.44 82					95.38 82	78.71 141	86.32 199	91.33 208

plane_prior3						68.60 128			78.44 36	78.92 196

plane_prior2							91.25 60		79.12 28

plane_prior1					89.90 124

plane_prior						68.71 123	90.38 78		77.62 47						86.16 204

n2								0.00 493

nn								0.00 493

door-mid								69.98 449

test11								92.23 94

door								69.44 452

HQP5-MVS						66.98 183

HQP-NCC					89.33 144		89.17 116		76.41 87	77.23 237

ACMP_Plane					89.33 144		89.17 116		76.41 87	77.23 237

BP-MVS														77.47 156

HQP4-MVS										77.24 236			95.11 94			91.03 218

HQP3-MVS								92.19 102							85.99 208

HQP2-MVS												60.17 234

MDTV_nov1_ep13_2view						37.79 474	75.16 423		55.10 437	66.53 404		49.34 347		53.98 389		87.94 334

ACMMP++_ref															81.95 277

ACMMP++															81.25 282

Test By Simon												64.33 163

High-resolution multi-view benchmark