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	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

LTVRE_ROB	98.82 1	99.76 1	99.75 1	99.77 7	99.87 16	99.71 10	99.77 8	99.76 19	99.52 2	99.80 3	99.79 22	99.91 1	99.56 13	99.83 3	99.75 4	99.86 9	99.75 1
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
pmmvs6		99.74 2	99.75 1	99.73 11	99.92 5	99.67 15	99.76 10	99.84 11	99.59 1	99.52 24	99.87 11	99.91 1	99.43 27	99.87 1	99.81 2	99.89 6	99.52 12

SixPastTwentyTwo		99.70 3	99.59 4	99.82 2	99.93 3	99.80 1	99.86 2	99.87 6	98.87 12	99.79 5	99.85 14	99.33 86	99.74 5	99.85 2	99.82 1	99.74 24	99.63 5

v7n		99.68 4	99.61 3	99.76 8	99.89 12	99.74 7	99.87 1	99.82 13	99.20 6	99.71 6	99.96 1	99.73 23	99.76 3	99.58 20	99.59 16	99.52 47	99.46 17

anonymousdsp		99.64 5	99.55 6	99.74 10	99.87 16	99.56 26	99.82 3	99.73 23	98.54 28	99.71 6	99.92 4	99.84 7	99.61 9	99.70 9	99.63 9	99.69 33	99.64 3

UniMVSNet_ETH3D		99.61 6	99.59 4	99.63 13	99.96 1	99.70 11	99.53 37	99.86 8	99.28 5	99.48 32	99.44 70	99.86 5	99.01 71	99.78 4	99.76 3	99.90 2	99.33 23

WR-MVS		99.61 6	99.44 8	99.82 2	99.92 5	99.80 1	99.80 4	99.89 1	98.54 28	99.66 13	99.78 23	99.16 109	99.68 7	99.70 9	99.63 9	99.94 1	99.49 15

PEN-MVS		99.54 8	99.30 16	99.83 1	99.92 5	99.76 4	99.80 4	99.88 3	97.60 84	99.71 6	99.59 48	99.52 62	99.75 4	99.64 15	99.51 19	99.90 2	99.46 17

TDRefinement		99.54 8	99.50 7	99.60 17	99.70 82	99.35 47	99.77 8	99.58 51	99.40 4	99.28 50	99.66 35	99.41 75	99.55 15	99.74 8	99.65 8	99.70 30	99.25 28

DTE-MVSNet		99.52 10	99.27 17	99.82 2	99.93 3	99.77 3	99.79 6	99.87 6	97.89 63	99.70 11	99.55 58	99.21 99	99.77 2	99.65 13	99.43 23	99.90 2	99.36 21

PS-CasMVS		99.50 11	99.23 20	99.82 2	99.92 5	99.75 6	99.78 7	99.89 1	97.30 96	99.71 6	99.60 46	99.23 95	99.71 6	99.65 13	99.55 18	99.90 2	99.56 8

WR-MVS_H		99.48 12	99.23 20	99.76 8	99.91 9	99.76 4	99.75 12	99.88 3	97.27 99	99.58 17	99.56 54	99.24 94	99.56 13	99.60 18	99.60 15	99.88 8	99.58 7

pm-mvs1		99.47 13	99.38 9	99.57 21	99.82 29	99.49 30	99.63 24	99.65 39	98.88 11	99.31 44	99.85 14	99.02 129	99.23 47	99.60 18	99.58 17	99.80 15	99.22 35

MIMVSNet1		99.46 14	99.34 10	99.60 17	99.83 24	99.68 14	99.74 15	99.71 27	98.20 42	99.41 37	99.86 13	99.66 39	99.41 30	99.50 24	99.39 26	99.50 54	99.10 47

TransMVSNet (Re)		99.45 15	99.32 13	99.61 15	99.88 14	99.60 21	99.75 12	99.63 43	99.11 7	99.28 50	99.83 19	98.35 164	99.27 44	99.70 9	99.62 13	99.84 10	99.03 55

ACMH	97.81 6	99.44 16	99.33 11	99.56 22	99.81 33	99.42 37	99.73 16	99.58 51	99.02 8	99.10 78	99.41 75	99.69 31	99.60 10	99.45 28	99.26 37	99.55 43	99.05 52
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CP-MVSNet		99.39 17	99.04 31	99.80 6	99.91 9	99.70 11	99.75 12	99.88 3	96.82 124	99.68 12	99.32 82	98.86 138	99.68 7	99.57 21	99.47 20	99.89 6	99.52 12

COLMAP_ROB	98.29 2	99.37 18	99.25 18	99.51 31	99.74 69	99.12 94	99.56 34	99.39 92	98.96 10	99.17 66	99.44 70	99.63 47	99.58 11	99.48 26	99.27 36	99.60 40	98.81 81
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
DeepC-MVS	97.88 4	99.33 19	99.15 24	99.53 30	99.73 75	99.05 105	99.49 43	99.40 90	98.42 32	99.55 21	99.71 27	99.89 3	99.49 19	99.14 44	98.81 72	99.54 44	99.02 57
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
FC-MVSNet-test		99.32 20	99.33 11	99.31 58	99.87 16	99.65 18	99.63 24	99.75 21	97.76 68	97.29 227	99.87 11	99.63 47	99.52 16	99.66 12	99.63 9	99.77 20	99.12 43

UA-Net		99.30 21	99.22 22	99.39 45	99.94 2	99.66 17	98.91 136	99.86 8	97.74 74	98.74 122	99.00 113	99.60 53	99.17 56	99.50 24	99.39 26	99.70 30	99.64 3

ACMH+	97.53 7	99.29 22	99.20 23	99.40 44	99.81 33	99.22 72	99.59 31	99.50 72	98.64 25	98.29 172	99.21 96	99.69 31	99.57 12	99.53 23	99.33 31	99.66 34	98.81 81

FE-MVSNET2		99.25 23	99.00 32	99.55 26	99.77 50	99.40 39	99.76 10	99.54 59	98.10 47	99.50 28	99.71 27	99.81 12	99.39 33	98.44 106	99.00 53	99.36 74	98.50 111

Vis-MVSNet		99.25 23	99.32 13	99.17 73	99.65 99	99.55 28	99.63 24	99.33 111	98.16 44	99.29 47	99.65 39	99.77 20	97.56 179	99.44 30	99.14 42	99.58 41	99.51 14
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TranMVSNet+NR-MVSNet		99.23 25	98.91 42	99.61 15	99.81 33	99.45 34	99.47 46	99.68 30	97.28 98	99.39 38	99.54 59	99.08 124	99.45 22	99.09 50	98.84 68	99.83 11	99.04 53

CSCG		99.23 25	99.15 24	99.32 57	99.83 24	99.45 34	98.97 127	99.21 137	98.83 16	99.04 89	99.43 72	99.64 45	99.26 45	98.85 77	98.20 115	99.62 38	99.62 6

Gipuma		99.22 27	98.86 48	99.64 12	99.70 82	99.24 66	99.17 96	99.63 43	99.52 2	99.89 1	96.54 207	99.14 113	99.93 1	99.42 32	99.15 41	99.52 47	99.04 53
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
tfpnnormal		99.19 28	98.90 43	99.54 27	99.81 33	99.55 28	99.60 29	99.54 59	98.53 30	99.23 54	98.40 137	98.23 167	99.40 31	99.29 37	99.36 29	99.63 37	98.95 67

Baseline_NR-MVSNet		99.18 29	98.87 45	99.54 27	99.74 69	99.56 26	99.36 62	99.62 48	96.53 144	99.29 47	99.85 14	98.64 156	99.40 31	99.03 61	99.63 9	99.83 11	98.86 76

thisisatest0515		99.16 30	98.94 37	99.41 39	99.75 63	99.43 36	99.36 62	99.63 43	97.68 80	99.35 40	99.31 83	98.90 135	99.09 65	98.95 66	99.20 38	99.27 88	99.11 44

SPE-MVS-test		99.16 30	98.78 55	99.60 17	99.80 39	99.72 9	99.69 17	99.73 23	95.88 167	99.51 27	98.53 132	99.54 58	99.21 50	99.24 40	99.43 23	99.66 34	99.15 42

CS-MVS		99.15 32	98.75 60	99.62 14	99.76 58	99.73 8	99.60 29	99.75 21	95.67 174	99.50 28	98.53 132	99.39 80	99.29 41	99.21 42	99.46 22	99.79 18	99.29 26

APDe-MVS		99.15 32	98.95 34	99.39 45	99.77 50	99.28 58	99.52 38	99.54 59	97.22 103	99.06 83	99.20 97	99.64 45	99.05 69	99.14 44	99.02 52	99.39 68	99.17 39
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
WB-MVS		99.14 34	99.31 15	98.95 109	99.81 33	99.61 20	98.85 144	99.51 69	99.01 9	97.37 221	99.33 80	99.56 56	98.70 96	99.44 30	99.29 33	99.45 59	98.96 66

FC-MVSNet-train		99.13 35	99.05 28	99.21 65	99.87 16	99.57 25	99.67 19	99.60 50	96.75 129	98.28 173	99.48 65	99.52 62	98.10 153	99.47 27	99.37 28	99.76 22	99.21 36

E6new		99.12 36	99.05 28	99.20 69	99.78 44	99.33 50	99.32 74	99.34 108	98.86 13	98.62 129	99.74 24	99.83 8	98.98 73	98.53 100	98.64 88	99.16 104	98.46 115

E6		99.12 36	99.05 28	99.20 69	99.78 44	99.33 50	99.32 74	99.34 108	98.86 13	98.62 129	99.74 24	99.83 8	98.98 73	98.53 100	98.64 88	99.16 104	98.46 115

NR-MVSNet		99.10 38	98.68 72	99.58 20	99.89 12	99.23 69	99.35 66	99.63 43	96.58 137	99.36 39	99.05 107	98.67 154	99.46 20	99.63 16	98.73 82	99.80 15	98.88 75

DVP-MVS++		99.09 39	99.25 18	98.90 117	99.53 131	99.37 45	99.17 96	99.48 77	98.28 40	97.95 198	99.54 59	99.88 4	98.13 152	99.08 51	98.94 57	99.15 107	99.65 2

DVP-MVS		99.09 39	99.07 27	99.12 80	99.55 122	99.40 39	99.36 62	99.44 89	97.75 71	98.23 176	99.23 93	99.80 16	98.97 75	99.08 51	98.96 54	99.19 97	99.25 28
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
UniMVSNet (Re)		99.08 41	98.69 70	99.54 27	99.75 63	99.33 50	99.29 78	99.64 42	96.75 129	99.48 32	99.30 85	98.69 149	99.26 45	98.94 68	98.76 78	99.78 19	99.02 57

casdiffseed414692147		99.06 42	98.93 41	99.21 65	99.79 40	99.26 60	99.49 43	99.35 104	98.20 42	98.46 156	99.68 30	99.82 10	98.84 86	98.72 91	98.36 108	99.34 76	98.45 119

ACMMPR		99.05 43	98.72 64	99.44 33	99.79 40	99.12 94	99.35 66	99.56 54	97.74 74	99.21 57	97.72 167	99.55 57	99.29 41	98.90 75	98.81 72	99.41 67	99.19 37

DU-MVS		99.04 44	98.59 77	99.56 22	99.74 69	99.23 69	99.29 78	99.63 43	96.58 137	99.55 21	99.05 107	98.68 151	99.36 36	99.03 61	98.60 91	99.77 20	98.97 62

usedtu_dtu_shiyan2		99.03 45	98.84 51	99.27 63	99.87 16	99.20 79	99.52 38	98.77 189	98.46 31	99.52 24	99.84 18	99.65 43	98.85 84	98.75 88	97.80 143	99.05 127	98.15 154

TSAR-MVS + MP.		99.02 46	98.95 34	99.11 84	99.23 183	98.79 142	99.51 40	98.73 193	97.50 88	98.56 139	99.03 110	99.59 54	99.16 58	99.29 37	99.17 40	99.50 54	99.24 32
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
v10		99.01 47	98.66 73	99.41 39	99.52 136	99.39 41	99.57 33	99.66 37	97.59 85	99.32 43	99.88 9	99.23 95	99.50 18	97.77 160	97.98 131	98.92 150	98.78 86

EG-PatchMatch MVS		99.01 47	98.77 59	99.28 62	99.64 103	98.90 134	98.81 153	99.27 122	96.55 141	99.71 6	99.31 83	99.66 39	99.17 56	99.28 39	99.11 44	99.10 110	98.57 103

viewmacassd2359aftdt		98.99 49	98.89 44	99.12 80	99.78 44	99.27 59	99.21 90	99.26 124	98.73 23	98.30 170	99.61 43	99.82 10	98.94 78	98.26 130	98.29 110	99.20 96	98.24 140

E4		98.98 50	98.87 45	99.11 84	99.78 44	99.26 60	99.20 92	99.27 122	98.81 17	98.57 137	99.68 30	99.81 12	98.69 98	98.08 140	98.23 112	99.15 107	98.24 140

PVSNet_Blended_VisFu		98.98 50	98.79 53	99.21 65	99.76 58	99.34 48	99.35 66	99.35 104	97.12 111	99.46 34	99.56 54	98.89 136	98.08 157	99.05 55	98.58 93	99.27 88	98.98 61

HFP-MVS		98.97 52	98.70 68	99.29 60	99.67 91	98.98 118	99.13 107	99.53 64	97.76 68	98.90 104	98.07 151	99.50 69	99.14 61	98.64 95	98.78 76	99.37 70	99.18 38

UniMVSNet_NR-MVSNet		98.97 52	98.46 89	99.56 22	99.76 58	99.34 48	99.29 78	99.61 49	96.55 141	99.55 21	99.05 107	97.96 175	99.36 36	98.84 78	98.50 100	99.81 14	98.97 62

casdiffmvs_mvg		98.96 54	98.87 45	99.07 88	99.82 29	99.36 46	99.36 62	99.22 134	98.13 46	97.74 205	99.42 73	99.46 73	98.59 106	98.39 111	98.95 56	99.71 29	98.39 125
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EC-MVSNet		98.96 54	98.45 92	99.56 22	99.88 14	99.70 11	99.68 18	99.78 16	94.15 215	98.97 93	98.26 143	99.21 99	99.35 38	99.30 36	99.14 42	99.73 25	99.40 20

SED-MVS		98.94 56	98.95 34	98.91 116	99.43 154	99.38 43	99.12 110	99.46 82	97.05 116	98.43 159	99.23 93	99.79 17	97.99 162	99.05 55	98.94 57	99.05 127	99.23 33

ACMMP_NAP		98.94 56	98.72 64	99.21 65	99.67 91	99.08 100	99.26 83	99.39 92	96.84 121	98.88 109	98.22 144	99.68 34	98.82 87	99.06 54	98.90 60	99.25 91	99.25 28

v1144		98.94 56	98.53 83	99.42 37	99.62 107	99.03 112	99.58 32	99.36 101	97.99 54	99.49 31	99.91 8	99.20 102	99.51 17	97.61 166	97.85 141	98.95 144	98.10 159

v8		98.94 56	98.60 75	99.35 54	99.54 128	99.39 41	99.55 35	99.67 34	97.48 89	99.13 74	99.81 20	99.10 120	99.39 33	97.86 152	97.89 139	98.81 161	98.66 96

SteuartSystems-ACMMP		98.94 56	98.52 85	99.43 36	99.79 40	99.13 92	99.33 72	99.55 56	96.17 160	99.04 89	97.53 173	99.65 43	99.46 20	99.04 60	98.76 78	99.44 62	99.35 22
Skip Steuart: Steuart Systems R&D Blog.
E5new		98.92 61	98.78 55	99.07 88	99.77 50	99.25 64	99.16 100	99.23 132	98.80 18	98.58 134	99.61 43	99.81 12	98.50 126	97.83 155	98.01 127	99.17 100	98.17 150

E5		98.92 61	98.78 55	99.07 88	99.77 50	99.25 64	99.16 100	99.23 132	98.80 18	98.58 134	99.61 43	99.81 12	98.50 126	97.83 155	98.01 127	99.17 100	98.17 150

viewdifsd2359ckpt11		98.92 61	98.94 37	98.90 117	99.71 80	99.16 86	99.16 100	98.82 184	98.78 21	98.12 186	99.68 30	99.78 18	98.52 121	98.80 83	98.11 120	99.05 127	98.25 138

viewmsd2359difaftdt		98.92 61	98.94 37	98.90 117	99.71 80	99.16 86	99.16 100	98.82 184	98.78 21	98.12 186	99.68 30	99.78 18	98.52 121	98.80 83	98.11 120	99.05 127	98.25 138

v1192		98.91 65	98.48 88	99.41 39	99.61 111	99.03 112	99.64 21	99.25 128	97.91 60	99.58 17	99.92 4	99.07 126	99.45 22	97.55 171	97.68 156	98.93 146	98.23 143

FMVSNet1		98.90 66	99.10 26	98.67 150	99.54 128	99.48 31	99.22 88	99.66 37	98.39 35	97.50 213	99.66 35	99.04 128	96.58 199	99.05 55	99.03 49	99.52 47	99.08 49

ACMM	96.66 11	98.90 66	98.44 94	99.44 33	99.74 69	98.95 124	99.47 46	99.55 56	97.66 82	99.09 79	96.43 209	99.41 75	99.35 38	98.95 66	98.67 85	99.45 59	99.03 55
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20231211		98.89 68	98.79 53	98.99 105	99.82 29	99.41 38	99.18 95	99.31 117	96.92 118	98.54 141	98.58 130	98.84 141	97.46 181	99.45 28	99.29 33	99.65 36	99.08 49

v1921920		98.89 68	98.46 89	99.39 45	99.58 115	99.04 110	99.64 21	99.17 145	97.91 60	99.64 15	99.92 4	98.99 133	99.44 25	97.44 180	97.57 165	98.84 159	98.35 128

GeoE		98.88 70	98.43 99	99.41 39	99.83 24	99.24 66	99.51 40	99.82 13	96.55 141	99.22 56	98.76 121	99.22 98	98.96 76	98.55 98	98.15 117	99.10 110	98.56 106

v144192		98.88 70	98.46 89	99.37 52	99.56 121	99.03 112	99.61 27	99.26 124	97.79 66	99.58 17	99.88 9	99.11 118	99.43 27	97.38 185	97.61 161	98.80 162	98.43 122

ME-MVS		98.87 72	98.78 55	98.98 107	99.67 91	99.13 92	99.34 70	98.89 176	97.44 91	98.49 149	99.59 48	99.54 58	98.49 128	98.48 104	98.52 99	99.01 136	98.74 88

SMA-MVS		98.87 72	98.73 63	99.04 96	99.72 78	99.05 105	98.64 166	99.17 145	96.31 155	98.80 116	99.07 104	99.70 30	98.67 99	98.93 71	98.82 69	99.23 94	99.23 33
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
ACMP	96.54 13	98.87 72	98.40 103	99.41 39	99.74 69	98.88 136	99.29 78	99.50 72	96.85 120	98.96 96	97.05 189	99.66 39	99.43 27	98.98 65	98.60 91	99.52 47	98.81 81
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DCV-MVSNet		98.86 75	98.57 81	99.19 71	99.86 21	99.67 15	99.39 56	99.71 27	97.53 87	98.69 126	95.85 220	98.48 159	97.75 173	99.57 21	99.41 25	99.72 26	99.48 16

v1240		98.86 75	98.41 101	99.38 50	99.59 113	99.05 105	99.65 20	99.14 150	97.68 80	99.66 13	99.93 3	98.72 148	99.45 22	97.38 185	97.72 154	98.79 163	98.35 128

CP-MVS		98.86 75	98.43 99	99.36 53	99.68 88	98.97 122	99.19 93	99.46 82	96.60 135	99.20 59	97.11 188	99.51 67	99.15 60	98.92 72	98.82 69	99.45 59	99.08 49

E3new		98.85 78	98.72 64	99.01 100	99.73 75	99.20 79	99.08 112	99.18 143	98.57 26	98.50 145	99.54 59	99.73 23	98.52 121	97.87 150	97.97 132	99.06 124	98.14 157

E3		98.85 78	98.72 64	99.01 100	99.73 75	99.20 79	99.08 112	99.18 143	98.57 26	98.51 144	99.54 59	99.73 23	98.52 121	97.86 152	97.97 132	99.06 124	98.14 157

v2v482		98.85 78	98.40 103	99.38 50	99.65 99	98.98 118	99.55 35	99.39 92	97.92 59	99.35 40	99.85 14	99.14 113	99.39 33	97.50 175	97.78 144	98.98 141	97.60 182

DPE-MVS		98.84 81	98.69 70	99.00 102	99.05 202	99.26 60	99.19 93	99.35 104	95.85 169	98.74 122	99.27 87	99.66 39	98.30 143	98.90 75	98.93 59	99.37 70	99.00 59
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
OPM-MVS		98.84 81	98.59 77	99.12 80	99.52 136	98.50 169	99.13 107	99.22 134	97.76 68	98.76 118	98.70 123	99.61 50	98.90 80	98.67 93	98.37 106	99.19 97	98.57 103
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
test20.03		98.84 81	98.74 62	98.95 109	99.77 50	99.33 50	99.21 90	99.46 82	97.29 97	98.88 109	99.65 39	99.10 120	97.07 191	99.11 47	98.76 78	99.32 81	97.98 168

casdiffmvs		98.84 81	98.75 60	98.94 113	99.75 63	99.21 73	99.33 72	99.04 163	98.04 50	97.46 216	99.72 26	99.72 27	98.60 104	98.30 123	98.37 106	99.48 56	97.92 171
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
LGP-MVS_train		98.84 81	98.33 109	99.44 33	99.78 44	98.98 118	99.39 56	99.55 56	95.41 179	98.90 104	97.51 174	99.68 34	99.44 25	99.03 61	98.81 72	99.57 42	98.91 71

RPSCF		98.84 81	98.81 52	98.89 122	99.37 162	98.95 124	98.51 178	98.85 182	97.73 76	98.33 167	98.97 115	99.14 113	98.95 77	99.18 43	98.68 84	99.31 82	98.99 60

ACMMP		98.82 87	98.33 109	99.39 45	99.77 50	99.14 90	99.37 59	99.54 59	96.47 148	99.03 91	96.26 213	99.52 62	99.28 43	98.92 72	98.80 75	99.37 70	99.16 40
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
FE-MVSNET		98.81 88	98.41 101	99.27 63	99.55 122	99.09 97	99.61 27	99.46 82	97.15 108	98.70 125	99.18 99	99.17 106	99.23 47	97.94 145	98.48 101	99.10 110	97.88 173

V42		98.81 88	98.49 87	99.18 72	99.52 136	98.92 129	99.50 42	99.29 119	97.43 93	98.97 93	99.81 20	99.00 132	99.30 40	97.93 146	98.01 127	98.51 188	98.34 132

viewdifsd2359ckpt07		98.79 90	98.85 50	98.72 142	99.74 69	99.14 90	98.97 127	98.91 174	98.84 15	98.32 169	99.48 65	99.73 23	98.40 133	98.29 124	98.12 118	97.96 208	98.31 134

LS3D		98.79 90	98.52 85	99.12 80	99.64 103	99.09 97	99.24 86	99.46 82	97.75 71	98.93 102	97.47 176	98.23 167	97.98 164	99.36 33	99.30 32	99.46 57	98.42 123

MP-MVS		98.78 92	98.30 111	99.34 56	99.75 63	98.95 124	99.26 83	99.46 82	95.78 173	99.17 66	96.98 193	99.72 27	99.06 68	98.84 78	98.74 81	99.33 78	99.11 44
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
viewmanbaseed2359cas		98.77 93	98.64 74	98.93 114	99.70 82	99.16 86	98.95 131	99.09 159	98.35 38	98.14 183	99.33 80	99.69 31	98.63 102	97.91 148	97.90 136	99.08 117	98.15 154

v148		98.77 93	98.45 92	99.15 76	99.68 88	98.94 128	99.49 43	99.31 117	97.95 56	98.91 103	99.65 39	99.62 49	99.18 53	97.99 143	97.64 160	98.33 193	97.38 188

test1111		98.75 95	98.14 125	99.46 32	99.86 21	99.63 19	99.47 46	99.68 30	98.34 39	98.76 118	99.66 35	90.92 227	99.23 47	99.77 5	99.71 5	99.75 23	98.95 67

viewcassd2359sk11		98.74 96	98.58 79	98.93 114	99.69 85	99.16 86	98.98 124	99.10 157	98.36 36	98.45 157	99.39 77	99.61 50	98.38 135	97.68 164	97.77 149	98.99 139	98.08 161

ECVR-MVS		98.74 96	98.15 123	99.42 37	99.83 24	99.58 23	99.37 59	99.67 34	98.02 52	98.85 113	99.59 48	91.66 225	99.10 63	99.77 5	99.70 6	99.72 26	98.73 89

SD-MVS		98.73 98	98.54 82	98.95 109	99.14 192	98.76 145	98.46 182	99.14 150	97.71 78	98.56 139	98.06 153	99.61 50	98.85 84	98.56 97	97.74 151	99.54 44	99.32 24
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
MSP-MVS		98.72 99	98.60 75	98.87 124	99.67 91	99.33 50	99.15 104	99.26 124	96.99 117	97.90 201	98.19 146	99.74 22	98.29 144	97.69 163	98.96 54	98.96 142	99.27 27
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
PGM-MVS		98.69 100	98.09 130	99.39 45	99.76 58	99.07 101	99.30 77	99.51 69	94.76 193	99.18 63	96.70 202	99.51 67	99.20 51	98.79 85	98.71 83	99.39 68	99.11 44

pmmvs-eth3d		98.68 101	98.14 125	99.29 60	99.49 141	98.45 172	99.45 51	99.38 97	97.21 104	99.50 28	99.65 39	99.21 99	99.16 58	97.11 193	97.56 166	98.79 163	97.82 176

EU-MVSNet		98.68 101	98.94 37	98.37 173	99.14 192	98.74 148	99.64 21	98.20 218	98.21 41	99.17 66	99.66 35	99.18 105	99.08 66	99.11 47	98.86 63	95.00 239	98.83 78

PMVS	92.51 17	98.66 103	98.86 48	98.43 169	99.26 178	98.98 118	98.60 172	98.59 202	97.73 76	99.45 35	99.38 78	98.54 158	95.24 218	99.62 17	99.61 14	99.42 64	98.17 150
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
DeepC-MVS_fast	97.38 8	98.65 104	98.34 108	99.02 99	99.33 166	98.29 179	98.99 121	98.71 195	97.40 94	99.31 44	98.20 145	99.40 78	98.54 119	98.33 120	98.18 116	99.23 94	98.58 101
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
3Dnovator	98.16 3	98.65 104	98.35 107	99.00 102	99.59 113	98.70 151	98.90 140	99.36 101	97.97 55	99.09 79	96.55 206	99.09 122	97.97 165	98.70 92	98.65 87	99.12 109	98.81 81

TSAR-MVS + ACMM		98.64 106	98.58 79	98.72 142	99.17 190	98.63 158	98.69 161	99.10 157	97.69 79	98.30 170	99.12 102	99.38 81	98.70 96	98.45 105	97.51 169	98.35 192	99.25 28

E2		98.63 107	98.44 94	98.86 127	99.65 99	99.12 94	98.88 142	99.03 164	98.10 47	98.40 160	99.27 87	99.48 72	98.24 147	97.51 174	97.56 166	98.93 146	98.05 162

DELS-MVS		98.63 107	98.70 68	98.55 165	99.24 182	99.04 110	98.96 129	98.52 205	96.83 123	98.38 162	99.58 52	99.68 34	97.06 192	98.74 90	98.44 103	99.10 110	98.59 100
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
QAPM		98.62 109	98.40 103	98.89 122	99.57 120	98.80 141	98.63 167	99.35 104	96.82 124	98.60 132	98.85 120	99.08 124	98.09 155	98.31 121	98.21 113	99.08 117	98.72 90

EPP-MVSNet		98.61 110	98.19 120	99.11 84	99.86 21	99.60 21	99.44 52	99.53 64	97.37 95	96.85 239	98.69 124	93.75 218	99.18 53	99.22 41	99.35 30	99.82 13	99.32 24

3Dnovator+	97.85 5	98.61 110	98.14 125	99.15 76	99.62 107	98.37 176	99.10 111	99.51 69	98.04 50	98.98 92	96.07 217	98.75 147	98.55 116	98.51 102	98.40 104	99.17 100	98.82 79

viewdifsd2359ckpt13		98.60 112	98.39 106	98.85 131	99.67 91	99.05 105	98.77 157	99.05 162	97.89 63	98.19 178	99.25 90	99.54 58	98.37 136	97.55 171	97.45 172	99.04 132	97.99 165

X-MVS		98.59 113	97.99 137	99.30 59	99.75 63	99.07 101	99.17 96	99.50 72	96.62 133	98.95 98	93.95 236	99.37 82	99.11 62	98.94 68	98.86 63	99.35 75	99.09 48

MVS_111021_HR		98.58 114	98.26 114	98.96 108	99.32 169	98.81 139	98.48 180	98.99 169	96.81 126	99.16 69	98.07 151	99.23 95	98.89 82	98.43 108	98.27 111	98.90 152	98.24 140

MGCNet		98.57 115	98.44 94	98.71 145	99.76 58	99.31 56	99.43 53	99.24 130	97.79 66	98.35 165	98.48 134	96.64 195	96.30 207	98.91 74	98.82 69	99.18 99	99.16 40

PM-MVS		98.57 115	98.24 117	98.95 109	99.26 178	98.59 161	99.03 117	98.74 192	96.84 121	99.44 36	99.13 101	98.31 166	98.75 92	98.03 141	98.21 113	98.48 189	98.58 101

PHI-MVS		98.57 115	98.20 119	99.00 102	99.48 143	98.91 131	98.68 162	99.17 145	94.97 188	99.27 52	98.33 139	99.33 86	98.05 159	98.82 81	98.62 90	99.34 76	98.38 126

diffmvs_AUTHOR		98.56 118	98.53 83	98.60 157	99.69 85	98.90 134	99.01 120	98.86 181	98.36 36	97.21 229	99.70 29	99.67 38	98.08 157	97.61 166	97.45 172	98.77 165	98.00 164

HPM-MVS++		98.56 118	98.08 131	99.11 84	99.53 131	98.61 160	99.02 119	99.32 115	96.29 157	99.06 83	97.23 183	99.50 69	98.77 90	98.15 136	97.90 136	98.96 142	98.90 72

TSAR-MVS + GP.		98.54 120	98.29 113	98.82 135	99.28 176	98.59 161	97.73 223	99.24 130	95.93 166	98.59 133	99.07 104	99.17 106	98.86 83	98.44 106	98.10 122	99.26 90	98.72 90

viewdifsd2359ckpt09		98.53 121	98.25 116	98.86 127	99.68 88	99.09 97	98.73 159	99.12 154	97.85 65	98.38 162	99.07 104	99.28 92	98.25 146	97.06 195	97.39 175	98.99 139	98.02 163

UGNet		98.52 122	99.00 32	97.96 197	99.58 115	99.26 60	99.27 82	99.40 90	98.07 49	98.28 173	98.76 121	99.71 29	92.24 249	98.94 68	98.85 65	99.00 138	99.43 19
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
Anonymous20231206		98.50 123	98.03 134	99.05 94	99.50 139	99.01 115	99.15 104	99.26 124	96.38 152	99.12 76	99.50 64	99.12 116	98.60 104	97.68 164	97.24 184	98.66 172	97.30 192

CLD-MVS		98.48 124	98.15 123	98.86 127	99.53 131	98.35 177	98.55 175	97.83 227	96.02 165	98.97 93	99.08 103	99.75 21	99.03 70	98.10 139	97.33 180	99.28 86	98.44 121
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CANet		98.47 125	98.30 111	98.67 150	99.65 99	98.87 137	98.82 149	99.01 167	96.14 161	99.29 47	98.86 118	99.01 130	96.54 200	98.36 115	98.08 124	98.72 168	98.80 85

APD-MVS		98.47 125	97.97 138	99.05 94	99.64 103	98.91 131	98.94 132	99.45 88	94.40 208	98.77 117	97.26 182	99.41 75	98.21 149	98.67 93	98.57 96	99.31 82	98.57 103
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
Vis-MVSNet (Re-imp)		98.46 127	98.23 118	98.73 141	99.81 33	99.29 57	98.79 154	99.50 72	96.20 159	96.03 246	98.29 141	96.98 190	98.54 119	99.11 47	99.08 45	99.70 30	98.62 98

Fast-Effi-MVS+		98.42 128	97.79 146	99.15 76	99.69 85	98.66 156	98.94 132	99.68 30	94.49 202	99.05 85	98.06 153	98.86 138	98.48 129	98.18 133	97.78 144	99.05 127	98.54 109

ETV-MVS		98.41 129	97.76 147	99.17 73	99.58 115	99.01 115	98.91 136	99.50 72	93.33 228	99.31 44	96.82 199	98.42 162	98.17 151	99.13 46	99.08 45	99.54 44	98.56 106

MVS_111021_LR		98.39 130	98.11 128	98.71 145	99.08 199	98.54 167	98.23 205	98.56 204	96.57 139	99.13 74	98.41 136	98.86 138	98.65 101	98.23 131	97.87 140	98.65 174	98.28 135

pmmvs5		98.37 131	97.81 145	99.03 97	99.46 145	98.97 122	99.03 117	98.96 171	95.85 169	99.05 85	99.45 69	98.66 155	98.79 89	96.02 212	97.52 168	98.87 154	98.21 146

OMC-MVS		98.35 132	98.10 129	98.64 156	98.85 210	97.99 198	98.56 174	98.21 216	97.26 101	98.87 111	98.54 131	99.27 93	98.43 131	98.34 118	97.66 157	98.92 150	97.65 181

sasdasda		98.34 133	97.92 141	98.83 132	99.45 147	99.21 73	98.37 190	99.53 64	97.06 113	97.74 205	96.95 196	95.05 208	98.36 137	98.77 86	98.85 65	99.51 52	99.53 10

canonicalmvs		98.34 133	97.92 141	98.83 132	99.45 147	99.21 73	98.37 190	99.53 64	97.06 113	97.74 205	96.95 196	95.05 208	98.36 137	98.77 86	98.85 65	99.51 52	99.53 10

CHOSEN 1792x2688		98.31 135	98.02 135	98.66 152	99.55 122	98.57 164	99.38 58	99.25 128	98.42 32	98.48 152	99.58 52	99.85 6	98.31 142	95.75 215	95.71 210	96.96 221	98.27 137

viewmambaseed2359dif		98.30 136	98.05 133	98.58 159	99.55 122	98.69 152	98.99 121	98.76 191	97.06 113	97.32 224	99.40 76	99.52 62	97.99 162	97.22 191	96.54 198	98.85 158	97.95 169

CPTT-MVS		98.28 137	97.51 161	99.16 75	99.54 128	98.78 143	98.96 129	99.36 101	96.30 156	98.89 108	93.10 240	99.30 89	99.20 51	98.35 117	97.96 134	99.03 134	98.82 79

usedtu_dtu_shiyan1		98.27 138	97.72 151	98.90 117	98.96 205	98.75 147	99.17 96	98.96 171	96.35 153	98.90 104	98.69 124	99.05 127	98.55 116	96.31 207	97.36 178	98.86 156	97.55 185

TinyColmap		98.27 138	97.62 158	99.03 97	99.29 174	97.79 207	98.92 135	98.95 173	97.48 89	99.52 24	98.65 127	97.86 177	98.90 80	98.34 118	97.27 182	98.64 175	95.97 218

diffmvs		98.26 140	98.16 121	98.39 171	99.61 111	98.78 143	98.79 154	98.61 200	97.94 57	97.11 232	99.51 63	99.52 62	97.61 177	96.55 203	96.93 190	98.61 177	97.87 174
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
USDC		98.26 140	97.57 159	99.06 91	99.42 157	97.98 200	98.83 146	98.85 182	97.57 86	99.59 16	99.15 100	98.59 157	98.99 72	97.42 181	96.08 209	98.69 171	96.23 215

SF-MVS		98.25 142	98.16 121	98.35 174	99.43 154	98.42 175	97.05 245	99.09 159	96.42 150	98.13 184	97.73 166	99.20 102	97.22 187	98.36 115	98.38 105	99.16 104	98.62 98

MCST-MVS		98.25 142	97.57 159	99.06 91	99.53 131	98.24 185	98.63 167	99.17 145	95.88 167	98.58 134	96.11 215	99.09 122	99.18 53	97.58 170	97.31 181	99.25 91	98.75 87

MGCFI-Net		98.23 144	97.93 140	98.58 159	99.44 151	99.20 79	98.37 190	99.54 59	97.14 109	96.70 243	96.98 193	95.04 210	97.92 169	98.75 88	98.89 61	99.52 47	99.55 9

IterMVS-LS		98.23 144	97.66 154	98.90 117	99.63 106	99.38 43	99.07 114	99.48 77	97.75 71	98.81 115	99.37 79	94.57 212	97.88 170	96.54 204	97.04 187	98.53 185	98.97 62
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TAPA-MVS	96.65 12	98.23 144	97.96 139	98.55 165	98.81 212	98.16 189	98.40 187	97.94 225	96.68 131	98.49 149	98.61 128	98.89 136	98.57 114	97.45 178	97.59 163	99.09 116	98.35 128
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CNVR-MVS		98.22 147	97.76 147	98.76 139	99.33 166	98.26 183	98.48 180	98.88 179	96.22 158	98.47 154	95.79 221	99.33 86	98.35 139	98.37 114	97.99 130	99.03 134	98.38 126

IS_MVSNet		98.20 148	98.00 136	98.44 168	99.82 29	99.48 31	99.25 85	99.56 54	95.58 176	93.93 258	97.56 172	96.52 196	98.27 145	99.08 51	99.20 38	99.80 15	98.56 106

DeepPCF-MVS	96.68 10	98.20 148	98.26 114	98.12 187	97.03 256	98.11 192	98.44 184	97.70 229	96.77 128	98.52 143	98.91 116	99.17 106	98.58 113	98.41 110	98.02 126	98.46 190	98.46 115

MSDG		98.20 148	97.88 144	98.56 163	99.33 166	97.74 208	98.27 202	98.10 219	97.20 106	98.06 191	98.59 129	99.16 109	98.76 91	98.39 111	97.71 155	98.86 156	96.38 212

testgi		98.18 151	98.44 94	97.89 199	99.78 44	99.23 69	98.78 156	99.21 137	97.26 101	97.41 218	97.39 179	99.36 85	92.85 245	98.82 81	98.66 86	99.31 82	98.35 128

Effi-MVS+		98.11 152	97.29 167	99.06 91	99.62 107	98.55 165	98.16 208	99.80 15	94.64 198	99.15 72	96.59 204	97.43 183	98.44 130	97.46 177	97.90 136	99.17 100	98.45 119

FA-MVS(training)		98.08 153	97.68 152	98.56 163	99.14 192	98.69 152	98.41 185	99.83 12	95.85 169	98.57 137	97.95 160	96.92 192	96.85 194	98.51 102	98.09 123	98.54 183	97.74 177

HyFIR lowres test		98.08 153	97.16 176	99.14 79	99.72 78	98.91 131	99.41 54	99.58 51	97.93 58	98.82 114	99.24 91	95.81 202	98.73 94	95.16 226	95.13 219	98.60 179	97.94 170

EIA-MVS		98.03 155	97.20 173	98.99 105	99.66 96	99.24 66	98.53 177	99.52 68	91.56 244	99.25 53	95.34 225	98.78 144	97.72 174	98.38 113	98.58 93	99.28 86	98.54 109

train_agg		97.99 156	97.26 168	98.83 132	99.43 154	98.22 187	98.91 136	99.07 161	94.43 206	97.96 197	96.42 210	99.30 89	98.81 88	97.39 183	96.62 196	98.82 160	98.47 113

MSLP-MVS++		97.99 156	97.64 157	98.40 170	98.91 208	98.47 171	97.12 243	98.78 188	96.49 146	98.48 152	93.57 238	99.12 116	98.51 125	98.31 121	98.58 93	98.58 181	98.95 67

CDPH-MVS		97.99 156	97.23 171	98.87 124	99.58 115	98.29 179	98.83 146	99.20 139	93.76 222	98.11 188	96.11 215	99.16 109	98.23 148	97.80 158	97.22 185	99.29 85	98.28 135

FMVSNet2		97.94 159	98.08 131	97.77 207	98.71 217	99.21 73	98.62 169	99.47 79	96.62 133	96.37 245	99.20 97	97.70 179	94.39 230	97.39 183	97.75 150	99.08 117	98.70 93

PVSNet_BlendedMVS		97.93 160	97.66 154	98.25 180	99.30 171	98.67 154	98.31 197	97.95 223	94.30 212	98.75 120	97.63 169	98.76 145	96.30 207	98.29 124	97.78 144	98.93 146	98.18 148

PVSNet_Blended		97.93 160	97.66 154	98.25 180	99.30 171	98.67 154	98.31 197	97.95 223	94.30 212	98.75 120	97.63 169	98.76 145	96.30 207	98.29 124	97.78 144	98.93 146	98.18 148

OpenMVS	97.26 9	97.88 162	97.17 175	98.70 147	99.50 139	98.55 165	98.34 195	99.11 155	93.92 220	98.90 104	95.04 230	98.23 167	97.38 184	98.11 138	98.12 118	98.95 144	98.23 143

pmmvs4		97.87 163	97.02 180	98.86 127	99.20 184	97.68 211	98.89 141	99.03 164	96.57 139	99.12 76	99.03 110	97.26 187	98.42 132	95.16 226	96.34 201	98.53 185	97.10 199

NCCC		97.84 164	96.96 182	98.87 124	99.39 160	98.27 182	98.46 182	99.02 166	96.78 127	98.73 124	91.12 244	98.91 134	98.57 114	97.83 155	97.49 170	99.04 132	98.33 133

Effi-MVS+-dtu		97.78 165	97.37 165	98.26 178	99.25 180	98.50 169	97.89 217	99.19 142	94.51 200	98.16 181	95.93 218	98.80 143	95.97 211	98.27 129	97.38 176	99.10 110	98.23 143

MDA-MVSNet-bldmvs		97.75 166	97.26 168	98.33 175	99.35 165	98.45 172	99.32 74	97.21 234	97.90 62	99.05 85	99.01 112	96.86 193	99.08 66	99.36 33	92.97 229	95.97 235	96.25 214

CDS-MVSNet		97.75 166	97.68 152	97.83 205	99.08 199	98.20 188	98.68 162	98.61 200	95.63 175	97.80 203	99.24 91	96.93 191	94.09 236	97.96 144	97.82 142	98.71 169	97.99 165
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CNLPA		97.75 166	97.26 168	98.32 177	98.58 225	97.86 203	97.80 219	98.09 220	96.49 146	98.49 149	96.15 214	98.08 170	98.35 139	98.00 142	97.03 188	98.61 177	97.21 196

PLC	95.63 15	97.73 169	97.01 181	98.57 162	99.10 196	97.80 206	97.72 224	98.77 189	96.34 154	98.38 162	93.46 239	98.06 171	98.66 100	97.90 149	97.65 159	98.77 165	97.90 172
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MVS_Test		97.69 170	97.15 177	98.33 175	99.27 177	98.43 174	98.25 203	99.29 119	95.00 187	97.39 220	98.86 118	98.00 174	97.14 189	95.38 221	96.22 203	98.62 176	98.15 154

GBi-Net		97.69 170	97.75 149	97.62 208	98.71 217	99.21 73	98.62 169	99.33 111	94.09 216	95.60 248	98.17 148	95.97 199	94.39 230	99.05 55	99.03 49	99.08 117	98.70 93

test1		97.69 170	97.75 149	97.62 208	98.71 217	99.21 73	98.62 169	99.33 111	94.09 216	95.60 248	98.17 148	95.97 199	94.39 230	99.05 55	99.03 49	99.08 117	98.70 93

CANet_DTU		97.65 173	97.50 163	97.82 206	99.19 187	98.08 194	98.41 185	98.67 197	94.40 208	99.16 69	98.32 140	98.69 149	93.96 239	97.87 150	97.61 161	97.51 214	97.56 184

IterMVS-SCA-FT		97.63 174	96.86 184	98.52 167	99.48 143	98.71 150	98.84 145	98.91 174	96.44 149	99.16 69	99.56 54	95.54 204	97.95 166	95.68 218	95.07 222	96.76 227	97.03 202

TSAR-MVS + COLMAP		97.62 175	97.31 166	97.98 195	98.47 233	97.39 215	98.29 199	98.25 215	96.68 131	97.54 212	98.87 117	98.04 173	97.08 190	96.78 198	96.26 202	98.26 196	97.12 198

MS-PatchMatch		97.60 176	97.22 172	98.04 194	98.67 221	97.18 220	97.91 215	98.28 214	95.82 172	98.34 166	97.66 168	98.38 163	97.77 172	97.10 194	97.25 183	97.27 216	97.18 197

PCF-MVS	95.58 16	97.60 176	96.67 185	98.69 148	99.44 151	98.23 186	98.37 190	98.81 186	93.01 232	98.22 177	97.97 159	99.59 54	98.20 150	95.72 217	95.08 220	99.08 117	97.09 201
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
HQP-MVS		97.58 178	96.65 188	98.66 152	99.30 171	97.99 198	97.88 218	98.65 198	94.58 199	98.66 127	94.65 234	99.15 112	98.59 106	96.10 210	95.59 211	98.90 152	98.50 111

DI_MVS_pp		97.57 179	96.55 190	98.77 138	99.55 122	98.76 145	99.22 88	99.00 168	97.08 112	97.95 198	97.78 165	91.35 226	98.02 160	96.20 208	96.81 192	98.87 154	97.87 174

AdaColmap		97.57 179	96.57 189	98.74 140	99.25 180	98.01 196	98.36 194	98.98 170	94.44 205	98.47 154	92.44 241	97.91 176	98.62 103	98.19 132	97.74 151	98.73 167	97.28 193

baseline		97.50 181	97.51 161	97.50 212	99.18 188	97.38 216	98.00 211	98.00 222	96.52 145	97.49 214	99.28 86	99.43 74	95.31 217	95.27 223	96.22 203	96.99 219	98.47 113

IterMVS		97.40 182	96.67 185	98.25 180	99.45 147	98.66 156	98.87 143	98.73 193	96.40 151	98.94 101	99.56 54	95.26 206	97.58 178	95.38 221	94.70 224	95.90 236	96.72 205
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
dmvs_re		97.38 183	96.15 198	98.82 135	99.39 160	98.34 178	98.65 165	98.88 179	90.80 251	98.86 112	92.35 242	95.13 207	98.09 155	98.84 78	98.88 62	99.06 124	98.71 92

CVMVSNet		97.38 183	97.39 164	97.37 216	98.58 225	97.72 209	98.70 160	97.42 232	97.21 104	95.95 247	99.46 68	93.31 221	97.38 184	97.60 168	97.78 144	96.18 232	98.66 96

new-patchmatchnet		97.26 185	96.12 199	98.58 159	99.55 122	98.63 158	99.14 106	97.04 236	98.80 18	99.19 61	99.92 4	99.19 104	98.92 79	95.51 220	87.04 246	97.66 211	93.73 237

MIMVSNet		97.24 186	97.15 177	97.36 217	99.03 203	98.52 168	98.55 175	99.73 23	94.94 191	94.94 255	97.98 158	97.37 185	93.66 240	97.60 168	97.34 179	98.23 199	96.29 213

PatchMatch-RL		97.24 186	96.45 193	98.17 184	98.70 220	97.57 214	97.31 238	98.48 208	94.42 207	98.39 161	95.74 222	96.35 198	97.88 170	97.75 161	97.48 171	98.24 198	95.87 221

thisisatest0530		97.20 188	95.95 203	98.66 152	99.46 145	98.84 138	98.29 199	99.20 139	94.51 200	98.25 175	97.42 177	85.03 242	97.68 175	98.43 108	98.56 97	99.08 117	98.89 74

tttt0517		97.18 189	95.92 204	98.65 155	99.49 141	98.92 129	98.29 199	99.20 139	94.37 210	98.17 179	97.37 180	84.72 245	97.68 175	98.55 98	98.56 97	99.10 110	98.95 67

MDTV_nov1_ep13_2view		97.12 190	96.19 197	98.22 183	99.13 195	98.05 195	99.24 86	99.47 79	97.61 83	99.15 72	99.59 48	99.01 130	98.40 133	94.87 229	90.14 232	93.91 245	94.04 236

MAR-MVS		97.12 190	96.28 196	98.11 188	98.94 206	97.22 218	97.65 228	99.38 97	90.93 250	98.15 182	95.17 227	97.13 188	96.48 203	97.71 162	97.40 174	98.06 203	98.40 124
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
Fast-Effi-MVS+-dtu		96.99 192	96.46 192	97.61 210	98.98 204	97.89 201	97.54 232	99.76 19	93.43 226	96.55 244	94.93 231	98.06 171	94.32 233	96.93 196	96.50 199	98.53 185	97.47 186

FPMVS		96.97 193	97.20 173	96.70 234	97.75 248	96.11 240	97.72 224	95.47 243	97.13 110	98.02 193	97.57 171	96.67 194	92.97 244	99.00 64	98.34 109	98.28 195	95.58 223

TAMVS		96.95 194	96.94 183	96.97 228	99.07 201	97.67 213	97.98 213	97.12 235	95.04 186	95.41 251	99.27 87	95.57 203	94.09 236	97.32 187	97.11 186	98.16 201	96.59 206

FMVSNet3		96.85 195	96.67 185	97.06 222	97.56 251	99.01 115	97.99 212	99.33 111	94.09 216	95.60 248	98.17 148	95.97 199	93.26 243	94.76 231	96.22 203	98.59 180	98.46 115

GA-MVS		96.84 196	95.86 206	97.98 195	99.16 191	98.29 179	97.91 215	98.64 199	95.14 182	97.71 208	98.04 155	88.90 230	96.50 202	96.41 206	96.61 197	97.97 207	97.60 182

CHOSEN 280x420		96.80 197	96.30 195	97.39 214	99.09 197	96.52 232	98.76 158	99.29 119	93.88 221	97.65 209	98.34 138	93.66 219	96.29 210	98.28 127	97.73 153	93.27 248	95.70 222

gg-mvs-nofinetune		96.77 198	96.52 191	97.06 222	99.66 96	97.82 205	97.54 232	99.86 8	98.69 24	98.61 131	99.94 2	89.62 228	88.37 257	97.55 171	96.67 194	98.30 194	95.35 224

DPM-MVS		96.73 199	95.70 209	97.95 198	98.93 207	97.26 217	97.39 237	98.44 210	95.47 178	97.62 210	90.71 245	98.47 161	97.03 193	95.02 228	95.27 216	98.26 196	97.67 179

baseline1		96.72 200	95.40 211	98.26 178	99.53 131	98.81 139	98.32 196	98.80 187	94.96 189	96.78 242	96.50 208	84.87 244	96.68 198	97.42 181	97.91 135	99.46 57	97.33 191

N_pmnet		96.68 201	95.70 209	97.84 204	99.42 157	98.00 197	99.35 66	98.21 216	98.40 34	98.13 184	99.42 73	99.30 89	97.44 183	94.00 235	88.79 233	94.47 242	91.96 245

pmnet_mix02		96.61 202	95.32 212	98.11 188	99.41 159	97.68 211	99.05 115	97.59 230	98.16 44	99.05 85	99.48 65	99.11 118	98.32 141	92.36 239	87.67 241	95.26 238	92.80 243

new_pmnet		96.59 203	96.40 194	96.81 231	98.24 244	95.46 249	97.71 226	94.75 250	96.92 118	96.80 241	99.23 93	97.81 178	96.69 196	96.58 202	95.16 218	96.69 228	93.64 238

PMMVS		96.47 204	95.81 207	97.23 218	97.38 253	95.96 244	97.31 238	96.91 237	93.21 229	97.93 200	97.14 186	97.64 181	95.70 213	95.24 224	96.18 206	98.17 200	95.33 225

EPNet		96.44 205	96.08 200	96.86 230	99.32 169	97.15 221	97.69 227	99.32 115	93.67 223	98.11 188	95.64 223	93.44 220	89.07 255	96.86 197	96.83 191	97.67 210	98.97 62
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
thres600view7		96.35 206	94.27 216	98.79 137	99.66 96	99.18 83	98.94 132	99.38 97	94.37 210	97.21 229	87.19 250	84.10 246	98.10 153	98.16 134	99.47 20	99.42 64	97.43 187

EPNet_dtu		96.31 207	95.96 202	96.72 233	99.18 188	95.39 250	97.03 246	99.13 153	93.02 231	99.35 40	97.23 183	97.07 189	90.70 254	95.74 216	95.08 220	94.94 240	98.16 153
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
pmmvs3		96.30 208	95.87 205	96.80 232	97.66 250	96.48 233	97.93 214	93.80 252	93.40 227	98.54 141	98.27 142	97.50 182	97.37 186	97.49 176	93.11 228	95.52 237	94.85 229

PMMVS2		96.29 209	97.05 179	95.40 244	98.32 243	96.16 237	98.18 207	97.46 231	97.20 106	84.51 264	99.60 46	98.68 151	96.37 204	98.59 96	97.38 176	97.58 213	91.76 246

thres200		96.23 210	94.13 217	98.69 148	99.44 151	99.18 83	98.58 173	99.38 97	93.52 225	97.35 222	86.33 255	85.83 240	97.93 167	98.16 134	98.78 76	99.42 64	97.10 199

thres400		96.22 211	94.08 220	98.72 142	99.58 115	99.05 105	98.83 146	99.22 134	94.01 219	97.40 219	86.34 254	84.91 243	97.93 167	97.85 154	99.08 45	99.37 70	97.28 193

tfpn200view9		96.17 212	94.08 220	98.60 157	99.37 162	99.18 83	98.68 162	99.39 92	92.02 238	97.30 225	86.53 252	86.34 237	97.45 182	98.15 136	99.08 45	99.43 63	97.28 193

CMPMVS	74.71 19	96.17 212	96.06 201	96.30 238	97.41 252	94.52 253	94.83 258	95.46 244	91.57 243	97.26 228	94.45 235	98.33 165	94.98 220	98.28 127	97.59 163	97.86 209	97.68 178
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test2506		96.12 214	93.35 232	99.35 54	99.83 24	99.58 23	99.37 59	99.67 34	98.02 52	98.44 158	97.51 174	60.03 266	99.10 63	99.77 5	99.70 6	99.72 26	98.86 76

blended_shiyan8		96.02 215	94.28 215	98.05 192	98.55 231	97.09 222	98.98 124	95.56 241	95.13 183	99.23 54	98.03 157	94.19 214	98.73 94	90.28 242	88.65 234	97.22 217	96.56 209

blended_shiyan6		96.02 215	94.29 214	98.05 192	98.56 228	97.09 222	98.99 121	95.56 241	95.11 184	99.21 57	98.04 155	94.28 213	98.74 93	90.26 243	88.64 235	97.22 217	96.57 207

gbinet_0.2-2-1-0.02		95.92 217	94.09 218	98.06 190	98.81 212	97.08 224	99.13 107	96.47 238	94.88 192	99.08 81	98.47 135	94.16 215	98.02 160	90.43 241	87.61 242	96.86 222	95.99 217

IB-MVS	95.85 14	95.87 218	94.88 213	97.02 225	99.09 197	98.25 184	97.16 240	97.38 233	91.97 241	97.77 204	83.61 260	97.29 186	92.03 252	97.16 192	97.66 157	98.66 172	98.20 147
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
test0.0.03 1		95.81 219	95.77 208	95.85 243	99.20 184	98.15 191	97.49 236	98.50 206	92.24 234	92.74 261	96.82 199	92.70 222	88.60 256	97.31 189	97.01 189	98.57 182	96.19 216

thres100view900		95.74 220	93.66 231	98.17 184	99.37 162	98.59 161	98.10 209	98.33 213	92.02 238	97.30 225	86.53 252	86.34 237	96.69 196	96.77 199	98.47 102	99.24 93	96.89 203

wanda-best-256-512		95.72 221	93.88 225	97.86 202	98.45 234	96.92 225	98.82 149	95.29 246	94.75 194	99.18 63	97.92 162	94.13 216	98.59 106	89.77 245	87.74 237	96.86 222	95.95 219

FE-blended-shiyan7		95.72 221	93.88 225	97.86 202	98.45 234	96.92 225	98.82 149	95.29 246	94.75 194	99.18 63	97.92 162	94.13 216	98.59 106	89.77 245	87.74 237	96.86 222	95.95 219

ET-MVSNet_ETH3D		95.72 221	93.85 227	97.89 199	97.30 254	98.09 193	98.19 206	98.40 211	94.46 204	98.01 196	96.71 201	77.85 262	96.76 195	96.08 211	96.39 200	98.70 170	97.36 189

baseline2		95.58 224	94.04 222	97.38 215	98.80 214	98.16 189	97.14 241	97.80 228	91.45 245	97.49 214	95.22 226	83.63 247	94.98 220	96.42 205	96.66 195	98.06 203	96.76 204

PatchT		95.49 225	93.29 233	98.06 190	98.65 222	96.20 236	98.91 136	99.73 23	92.00 240	98.50 145	96.67 203	83.25 248	96.34 205	94.40 232	95.50 212	96.21 231	95.04 227

CR-MVSNet		95.38 226	93.01 234	98.16 186	98.63 223	95.85 246	97.64 229	99.78 16	91.27 247	98.50 145	96.84 198	82.16 249	96.34 205	94.40 232	95.50 212	98.05 205	95.04 227

MVSTER		95.38 226	93.99 224	97.01 226	98.83 211	98.95 124	96.62 247	99.14 150	92.17 236	97.44 217	97.29 181	77.88 261	91.63 253	97.45 178	96.18 206	98.41 191	97.99 165

MVS-HIRNet		94.86 228	93.83 228	96.07 239	97.07 255	94.00 255	94.31 259	99.17 145	91.23 249	98.17 179	98.69 124	97.43 183	95.66 214	94.05 234	91.92 230	92.04 255	89.46 254

test-LLR		94.79 229	93.71 229	96.06 240	99.20 184	96.16 237	96.31 249	98.50 206	89.98 252	94.08 256	97.01 190	86.43 235	92.20 250	96.76 200	95.31 214	96.05 233	94.31 233

RPMNet		94.72 230	92.01 239	97.88 201	98.56 228	95.85 246	97.78 220	99.70 29	91.27 247	98.33 167	93.69 237	81.88 250	94.91 223	92.60 237	94.34 226	98.01 206	94.46 232

gm-plane-assit		94.62 231	91.39 241	98.39 171	99.90 11	99.47 33	99.40 55	99.65 39	97.44 91	99.56 20	99.68 30	59.40 267	94.23 234	96.17 209	94.77 223	97.61 212	92.79 244

test-mter		94.62 231	94.02 223	95.32 245	97.72 249	96.75 229	96.23 251	95.67 240	89.83 255	93.23 260	96.99 192	85.94 239	92.66 248	97.32 187	96.11 208	96.44 229	95.22 226

FMVSNet5		94.57 233	92.77 235	96.67 235	97.88 246	98.72 149	97.54 232	98.70 196	88.64 256	95.11 253	86.90 251	81.77 251	93.27 242	97.92 147	98.07 125	97.50 215	97.34 190

SCA		94.53 234	91.95 240	97.55 211	98.58 225	97.86 203	98.49 179	99.68 30	95.11 184	99.07 82	95.87 219	87.24 233	96.53 201	89.77 245	87.08 245	92.96 250	90.69 249

MDTV_nov1_ep13		94.47 235	92.15 237	97.17 219	98.54 232	96.42 234	98.10 209	98.89 176	94.49 202	98.02 193	97.41 178	86.49 234	95.56 215	90.85 240	87.95 236	93.91 245	91.45 248

TESTMET0.1,1		94.44 236	93.71 229	95.30 246	97.84 247	96.16 237	96.31 249	95.32 245	89.98 252	94.08 256	97.01 190	86.43 235	92.20 250	96.76 200	95.31 214	96.05 233	94.31 233

ADS-MVSNet		94.41 237	92.13 238	97.07 221	98.86 209	96.60 231	98.38 189	98.47 209	96.13 163	98.02 193	96.98 193	87.50 232	95.87 212	89.89 244	87.58 243	92.79 252	90.27 251

tpm		93.89 238	91.21 242	97.03 224	98.36 241	96.07 241	97.53 235	99.65 39	92.24 234	98.64 128	97.23 183	74.67 265	94.64 228	92.68 236	90.73 231	93.37 247	94.82 230

PatchmatchNet		93.88 239	91.08 243	97.14 220	98.75 216	96.01 243	98.25 203	99.39 92	94.95 190	98.96 96	96.32 211	85.35 241	95.50 216	88.89 250	85.89 249	91.99 256	90.15 252
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EPMVS		93.67 240	90.82 244	96.99 227	98.62 224	96.39 235	98.40 187	99.11 155	95.54 177	97.87 202	97.14 186	81.27 253	94.97 222	88.54 252	86.80 247	92.95 251	90.06 253

FE-MVSNET3		93.58 241	90.22 245	97.50 212	98.45 234	96.92 225	98.82 149	95.29 246	94.75 194	96.98 234	86.26 256	79.50 256	98.59 106	89.77 245	87.74 237	96.86 222	96.57 207

usedtu_blend_shiyan5		93.31 242	90.20 246	96.93 229	98.45 234	96.92 225	95.44 255	95.29 246	94.75 194	96.98 234	86.26 256	79.50 256	98.59 106	89.77 245	87.74 237	96.86 222	96.46 210

MVE	82.47 18	93.12 243	94.09 218	91.99 253	90.79 260	82.50 262	93.93 260	96.30 239	96.06 164	88.81 262	98.19 146	96.38 197	97.56 179	97.24 190	95.18 217	84.58 262	93.07 240
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
CostFormer		92.75 244	89.49 248	96.55 236	98.78 215	95.83 248	97.55 231	98.59 202	91.83 242	97.34 223	96.31 212	78.53 260	94.50 229	86.14 254	84.92 250	92.54 253	92.84 242

tpmrst		92.45 245	89.48 249	95.92 242	98.43 239	95.03 251	97.14 241	97.92 226	94.16 214	97.56 211	97.86 164	81.63 252	93.56 241	85.89 255	82.86 254	90.91 260	88.95 256

dps		92.35 246	88.78 251	96.52 237	98.21 245	95.94 245	97.78 220	98.38 212	89.88 254	96.81 240	95.07 229	75.31 264	94.70 226	88.62 251	86.21 248	93.21 249	90.41 250

E-PMN		92.28 247	90.12 247	94.79 248	98.56 228	90.90 259	95.16 257	93.68 253	95.36 180	95.10 254	96.56 205	89.05 229	95.24 218	95.21 225	81.84 256	90.98 258	81.94 258

EMVS		91.84 248	89.39 250	94.70 249	98.44 238	90.84 260	95.27 256	93.53 254	95.18 181	95.26 252	95.62 224	87.59 231	94.77 225	94.87 229	80.72 257	90.95 259	80.88 259

tpm cat1		91.52 249	87.70 253	95.97 241	98.33 242	94.98 252	97.06 244	98.03 221	92.11 237	98.03 192	94.77 233	77.19 263	92.71 246	83.56 256	82.24 255	91.67 257	89.04 255

blend_shiyan4		91.30 250	88.16 252	94.96 247	89.60 261	96.63 230	93.72 261	93.90 251	82.52 260	96.98 234	86.26 256	79.50 256	98.59 106	88.21 253	87.51 244	96.99 219	96.46 210

0.4-1-1-0.1		90.20 251	87.09 254	93.83 250	91.98 257	94.48 254	96.12 252	88.26 255	84.35 257	97.04 233	88.99 246	79.83 254	94.68 227	83.11 257	84.34 251	94.87 241	94.55 231

0.3-1-1-0.015		89.53 252	86.18 255	93.43 251	91.67 259	93.80 256	95.70 253	87.54 256	83.38 258	96.98 234	87.42 248	79.50 256	94.21 235	81.99 259	83.67 252	94.46 243	93.50 239

0.4-1-1-0.2		89.46 253	86.17 256	93.30 252	91.74 258	93.59 258	95.48 254	87.42 257	83.04 259	96.95 238	88.20 247	79.80 255	93.99 238	82.16 258	83.38 253	94.21 244	93.03 241

test_method		77.69 254	85.40 257	68.69 254	42.66 263	55.39 264	82.17 264	52.05 259	92.83 233	84.52 263	94.88 232	95.41 205	65.37 258	92.49 238	79.32 258	85.36 261	87.50 257

GG-mvs-BLEND		65.66 255	92.62 236	34.20 256	1.45 266	93.75 257	85.40 263	1.64 263	91.37 246	17.21 266	87.25 249	94.78 211	3.25 262	95.64 219	93.80 227	96.27 230	91.74 247

testmvs		9.73 256	13.38 258	5.48 258	3.62 264	4.12 265	6.40 267	3.19 262	14.92 261	7.68 268	22.10 261	13.89 269	6.83 260	13.47 260	10.38 260	5.14 265	14.81 260

test123		9.37 257	12.26 259	6.00 257	3.32 265	4.06 266	6.39 268	3.41 261	13.20 262	10.48 267	16.43 262	16.22 268	6.76 261	11.37 261	10.40 259	5.62 264	14.10 261

uanet_test		0.00 258	0.00 260	0.00 259	0.00 267	0.00 267	0.00 269	0.00 264	0.00 263	0.00 269	0.00 263	0.00 270	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

sosnet-low-res		0.00 258	0.00 260	0.00 259	0.00 267	0.00 267	0.00 269	0.00 264	0.00 263	0.00 269	0.00 263	0.00 270	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

sosnet		0.00 258	0.00 260	0.00 259	0.00 267	0.00 267	0.00 269	0.00 264	0.00 263	0.00 269	0.00 263	0.00 270	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

TestfortrainingZip							99.34 70	98.89 176		98.10 190						99.01 136

TPM-MVS					98.38 240	97.20 219	96.44 248			97.17 231	95.17 227	98.68 151	92.69 247			98.11 202	97.67 179
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										99.88 2

9.14												98.83 142

SR-MVS					99.62 107			99.47 79				99.40 78

Anonymous202405211			98.44 94		99.79 40	99.32 55	99.05 115	99.34 108	96.59 136		97.95 160	97.68 180	97.16 188	99.36 33	99.28 35	99.61 39	98.90 72

our_test_3					99.29 174	97.72 209	98.98 124

ambc			97.89 143		99.45 147	97.88 202	97.78 220		97.27 99	99.80 3	98.99 114	98.48 159	98.55 116	97.80 158	96.68 193	98.54 183	98.10 159

MTAPA										99.19 61		99.68 34

MTMP										99.20 59		99.54 58

Patchmatch-RL test							32.47 266

tmp_tt				65.28 255	82.24 262	71.50 263	70.81 265	23.21 260	96.14 161	81.70 265	85.98 259	92.44 223	49.84 259	95.81 214	94.36 225	83.86 263

XVS					99.77 50	99.07 101	99.46 49			98.95 98		99.37 82				99.33 78

X-MVStestdata					99.77 50	99.07 101	99.46 49			98.95 98		99.37 82				99.33 78

mPP-MVS					99.75 63							99.49 71

NP-MVS									93.07 230

Patchmtry						96.05 242	97.64 229	99.78 16		98.50 145

DeepMVS_CX						87.86 261	92.27 262	61.98 258	93.64 224	93.62 259	91.17 243	91.67 224	94.90 224	95.99 213		92.48 254	94.18 235

High-resolution multi-view benchmark