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.

PEN-MVS		99.54 11	99.30 18	99.83 1	99.92 5	99.76 5	99.80 8	99.88 4	97.60 66	99.71 5	99.59 55	99.52 43	99.75 6	99.64 12	99.51 19	99.90 3	99.46 17

PS-CasMVS		99.50 14	99.23 21	99.82 2	99.92 5	99.75 7	99.78 11	99.89 2	97.30 85	99.71 5	99.60 53	99.23 75	99.71 9	99.65 10	99.55 18	99.90 3	99.56 8

DTE-MVSNet		99.52 13	99.27 19	99.82 2	99.93 3	99.77 4	99.79 10	99.87 7	97.89 45	99.70 10	99.55 62	99.21 79	99.77 2	99.65 10	99.43 23	99.90 3	99.36 21

WR-MVS		99.61 10	99.44 11	99.82 2	99.92 5	99.80 2	99.80 8	99.89 2	98.54 19	99.66 14	99.78 40	99.16 87	99.68 10	99.70 6	99.63 6	99.94 1	99.49 16

SixPastTwentyTwo		99.70 4	99.59 7	99.82 2	99.93 3	99.80 2	99.86 3	99.87 7	98.87 14	99.79 4	99.85 27	99.33 63	99.74 7	99.85 2	99.82 1	99.74 22	99.63 4

CP-MVSNet		99.39 20	99.04 29	99.80 6	99.91 9	99.70 10	99.75 15	99.88 4	96.82 108	99.68 11	99.32 76	98.86 121	99.68 10	99.57 21	99.47 21	99.89 6	99.52 10

Anonymous20231211		99.79 1	99.80 1	99.77 7	99.97 1	99.87 1	99.90 1	99.92 1	99.76 1	99.25 60	99.79 37	99.98 1	99.63 12	99.84 3	99.78 3	99.94 1	99.61 6

LTVRE_ROB	98.82 1	99.76 2	99.75 2	99.77 7	99.87 17	99.71 9	99.77 12	99.76 22	99.52 3	99.80 2	99.79 37	99.91 2	99.56 18	99.83 4	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
v7n		99.68 5	99.61 4	99.76 9	99.89 14	99.74 8	99.87 2	99.82 14	99.20 6	99.71 5	99.96 1	99.73 12	99.76 5	99.58 17	99.59 15	99.52 45	99.46 17

v52		99.67 6	99.59 7	99.76 9	99.91 9	99.69 11	99.85 4	99.79 16	99.12 9	99.68 11	99.95 2	99.72 14	99.77 2	99.58 17	99.61 11	99.54 39	99.50 13

V4		99.67 6	99.60 6	99.76 9	99.91 9	99.69 11	99.85 4	99.79 16	99.13 8	99.68 11	99.95 2	99.72 14	99.77 2	99.58 17	99.61 11	99.54 39	99.50 13

WR-MVS_H		99.48 15	99.23 21	99.76 9	99.91 9	99.76 5	99.75 15	99.88 4	97.27 88	99.58 19	99.56 59	99.24 73	99.56 18	99.60 15	99.60 14	99.88 8	99.58 7

v748		99.67 6	99.61 4	99.75 13	99.87 17	99.68 13	99.84 6	99.79 16	99.14 7	99.64 16	99.89 12	99.88 5	99.72 8	99.58 17	99.57 17	99.62 30	99.50 13

anonymousdsp		99.64 9	99.55 9	99.74 14	99.87 17	99.56 22	99.82 7	99.73 28	98.54 19	99.71 5	99.92 6	99.84 7	99.61 13	99.70 6	99.63 6	99.69 26	99.64 2

pmmvs6		99.74 3	99.75 2	99.73 15	99.92 5	99.67 15	99.76 14	99.84 11	99.59 2	99.52 26	99.87 18	99.91 2	99.43 39	99.87 1	99.81 2	99.89 6	99.52 10

Gipuma		99.22 29	98.86 42	99.64 16	99.70 63	99.24 58	99.17 96	99.63 47	99.52 3	99.89 1	96.54 180	99.14 93	99.93 1	99.42 29	99.15 39	99.52 45	99.04 46
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
TransMVSNet (Re)		99.45 18	99.32 16	99.61 17	99.88 16	99.60 18	99.75 15	99.63 47	99.11 10	99.28 56	99.83 31	98.35 141	99.27 62	99.70 6	99.62 10	99.84 10	99.03 48

TranMVSNet+NR-MVSNet		99.23 27	98.91 38	99.61 17	99.81 28	99.45 36	99.47 58	99.68 37	97.28 87	99.39 35	99.54 63	99.08 108	99.45 34	99.09 45	98.84 62	99.83 11	99.04 46

MIMVSNet1		99.46 17	99.34 13	99.60 19	99.83 23	99.68 13	99.74 18	99.71 33	98.20 27	99.41 34	99.86 22	99.66 27	99.41 42	99.50 23	99.39 25	99.50 51	99.10 41

TDRefinement		99.54 11	99.50 10	99.60 19	99.70 63	99.35 45	99.77 12	99.58 55	99.40 5	99.28 56	99.66 45	99.41 51	99.55 20	99.74 5	99.65 5	99.70 23	99.25 26

NR-MVSNet		99.10 39	98.68 56	99.58 21	99.89 14	99.23 60	99.35 72	99.63 47	96.58 123	99.36 37	99.05 95	98.67 133	99.46 32	99.63 13	98.73 75	99.80 15	98.88 69

pm-mvs1		99.47 16	99.38 12	99.57 22	99.82 25	99.49 32	99.63 29	99.65 43	98.88 13	99.31 46	99.85 27	99.02 113	99.23 65	99.60 15	99.58 16	99.80 15	99.22 31

UniMVSNet_NR-MVSNet		98.97 49	98.46 73	99.56 23	99.76 44	99.34 46	99.29 79	99.61 52	96.55 127	99.55 23	99.05 95	97.96 155	99.36 55	98.84 68	98.50 92	99.81 14	98.97 55

DU-MVS		99.04 43	98.59 61	99.56 23	99.74 51	99.23 60	99.29 79	99.63 47	96.58 123	99.55 23	99.05 95	98.68 131	99.36 55	99.03 54	98.60 85	99.77 19	98.97 55

ACMH	97.81 6	99.44 19	99.33 14	99.56 23	99.81 28	99.42 38	99.73 19	99.58 55	99.02 11	99.10 81	99.41 73	99.69 19	99.60 14	99.45 27	99.26 36	99.55 38	99.05 45
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tfpnnormal		99.19 31	98.90 39	99.54 26	99.81 28	99.55 26	99.60 35	99.54 66	98.53 21	99.23 61	98.40 120	98.23 144	99.40 43	99.29 34	99.36 28	99.63 29	98.95 61

UniMVSNet (Re)		99.08 41	98.69 55	99.54 26	99.75 47	99.33 48	99.29 79	99.64 46	96.75 115	99.48 30	99.30 78	98.69 129	99.26 63	98.94 60	98.76 71	99.78 18	99.02 51

Baseline_NR-MVSNet		99.18 34	98.87 41	99.54 26	99.74 51	99.56 22	99.36 71	99.62 51	96.53 129	99.29 51	99.85 27	98.64 135	99.40 43	99.03 54	99.63 6	99.83 11	98.86 70

DeepC-MVS	97.88 4	99.33 22	99.15 25	99.53 29	99.73 56	99.05 90	99.49 56	99.40 92	98.42 22	99.55 23	99.71 43	99.89 4	99.49 29	99.14 39	98.81 65	99.54 39	99.02 51
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
COLMAP_ROB	98.29 2	99.37 21	99.25 20	99.51 30	99.74 51	99.12 82	99.56 40	99.39 94	98.96 12	99.17 68	99.44 70	99.63 33	99.58 15	99.48 25	99.27 34	99.60 35	98.81 76
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
v13		99.22 29	98.99 31	99.49 31	99.68 67	99.58 20	99.67 20	99.77 21	98.10 29	99.36 37	99.88 13	99.37 57	99.54 22	98.50 84	98.51 91	98.92 124	99.03 48

v12		99.19 31	98.95 32	99.48 32	99.67 70	99.56 22	99.66 22	99.76 22	98.06 31	99.33 42	99.88 13	99.34 62	99.53 23	98.42 91	98.43 96	98.91 127	98.97 55

v11		99.19 31	98.95 32	99.47 33	99.66 75	99.54 28	99.65 23	99.73 28	98.06 31	99.38 36	99.92 6	99.40 54	99.55 20	98.29 104	98.50 92	98.88 132	98.92 64

V9		99.16 35	98.90 39	99.46 34	99.66 75	99.54 28	99.65 23	99.75 25	98.01 34	99.31 46	99.87 18	99.31 67	99.51 25	98.34 98	98.34 99	98.90 129	98.91 65

V14		99.13 37	98.85 44	99.45 35	99.65 81	99.52 30	99.63 29	99.74 27	97.97 36	99.30 49	99.87 18	99.27 71	99.49 29	98.23 110	98.24 102	98.88 132	98.83 71

ACMMPR		99.05 42	98.72 51	99.44 36	99.79 33	99.12 82	99.35 72	99.56 58	97.74 55	99.21 62	97.72 146	99.55 41	99.29 60	98.90 66	98.81 65	99.41 66	99.19 33

LGP-MVS_train		98.84 73	98.33 95	99.44 36	99.78 36	98.98 107	99.39 67	99.55 60	95.41 158	98.90 109	97.51 153	99.68 22	99.44 37	99.03 54	98.81 65	99.57 37	98.91 65

ACMM	96.66 11	98.90 60	98.44 83	99.44 36	99.74 51	98.95 116	99.47 58	99.55 60	97.66 62	99.09 85	96.43 181	99.41 51	99.35 58	98.95 59	98.67 80	99.45 56	99.03 48
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
v15		99.09 40	98.79 46	99.43 39	99.64 89	99.50 31	99.61 33	99.73 28	97.92 40	99.28 56	99.86 22	99.24 73	99.47 31	98.12 121	98.14 107	98.87 134	98.76 83

SteuartSystems-ACMMP		98.94 53	98.52 69	99.43 39	99.79 33	99.13 80	99.33 76	99.55 60	96.17 143	99.04 93	97.53 152	99.65 30	99.46 32	99.04 53	98.76 71	99.44 58	99.35 22
Skip Steuart: Steuart Systems R&D Blog.
v1144		98.94 53	98.53 67	99.42 41	99.62 96	99.03 100	99.58 37	99.36 112	97.99 35	99.49 29	99.91 11	99.20 81	99.51 25	97.61 161	97.85 129	98.95 119	98.10 141

v1192		98.91 58	98.48 72	99.41 42	99.61 99	99.03 100	99.64 26	99.25 136	97.91 42	99.58 19	99.92 6	99.07 110	99.45 34	97.55 165	97.68 146	98.93 121	98.23 128

v10		99.01 45	98.66 57	99.41 42	99.52 124	99.39 41	99.57 38	99.66 41	97.59 67	99.32 44	99.88 13	99.23 75	99.50 27	97.77 149	97.98 117	98.92 124	98.78 81

ACMP	96.54 13	98.87 65	98.40 89	99.41 42	99.74 51	98.88 128	99.29 79	99.50 77	96.85 104	98.96 100	97.05 165	99.66 27	99.43 39	98.98 58	98.60 85	99.52 45	98.81 76
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMH+	97.53 7	99.29 25	99.20 24	99.40 45	99.81 28	99.22 63	99.59 36	99.50 77	98.64 18	98.29 156	99.21 85	99.69 19	99.57 16	99.53 22	99.33 30	99.66 28	98.81 76

v1921920		98.89 62	98.46 73	99.39 46	99.58 102	99.04 95	99.64 26	99.17 147	97.91 42	99.64 16	99.92 6	98.99 117	99.44 37	97.44 172	97.57 156	98.84 141	98.35 117

UA-Net		99.30 24	99.22 23	99.39 46	99.94 2	99.66 16	98.91 124	99.86 9	97.74 55	98.74 123	99.00 101	99.60 38	99.17 71	99.50 23	99.39 25	99.70 23	99.64 2

APDe-MVS		99.15 36	98.95 32	99.39 46	99.77 38	99.28 55	99.52 51	99.54 66	97.22 93	99.06 88	99.20 86	99.64 31	99.05 82	99.14 39	99.02 53	99.39 71	99.17 35

PGM-MVS		98.69 86	98.09 111	99.39 46	99.76 44	99.07 86	99.30 78	99.51 74	94.76 175	99.18 67	96.70 174	99.51 46	99.20 66	98.79 73	98.71 78	99.39 71	99.11 38

ACMMP		98.82 80	98.33 95	99.39 46	99.77 38	99.14 79	99.37 69	99.54 66	96.47 133	99.03 95	96.26 185	99.52 43	99.28 61	98.92 64	98.80 68	99.37 73	99.16 36
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
v1240		98.86 70	98.41 87	99.38 51	99.59 100	99.05 90	99.65 23	99.14 152	97.68 61	99.66 14	99.93 5	98.72 128	99.45 34	97.38 176	97.72 144	98.79 150	98.35 117

v2v482		98.85 72	98.40 89	99.38 51	99.65 81	98.98 107	99.55 43	99.39 94	97.92 40	99.35 40	99.85 27	99.14 93	99.39 53	97.50 167	97.78 132	98.98 116	97.60 160

zzz-MVS		98.94 53	98.57 64	99.37 53	99.77 38	99.15 78	99.24 87	99.55 60	97.38 82	99.16 71	96.64 176	99.69 19	99.15 75	99.09 45	98.92 56	99.37 73	99.11 38

v144192		98.88 64	98.46 73	99.37 53	99.56 107	99.03 100	99.61 33	99.26 133	97.79 49	99.58 19	99.88 13	99.11 101	99.43 39	97.38 176	97.61 152	98.80 148	98.43 112

v1141		98.87 65	98.45 77	99.36 55	99.65 81	99.04 95	99.56 40	99.38 101	97.83 46	99.29 51	99.86 22	99.16 87	99.40 43	97.68 155	97.78 132	98.86 137	97.82 153

divwei89l23v2f112		98.87 65	98.45 77	99.36 55	99.65 81	99.04 95	99.56 40	99.38 101	97.83 46	99.29 51	99.86 22	99.15 91	99.40 43	97.68 155	97.78 132	98.86 137	97.82 153

v7		98.91 58	98.53 67	99.36 55	99.53 119	98.99 106	99.57 38	99.36 112	97.58 69	99.32 44	99.88 13	99.23 75	99.50 27	97.77 149	97.98 117	98.91 127	98.26 126

v1		98.87 65	98.45 77	99.36 55	99.65 81	99.04 95	99.55 43	99.38 101	97.83 46	99.30 49	99.86 22	99.17 84	99.40 43	97.68 155	97.77 139	98.86 137	97.82 153

CP-MVS		98.86 70	98.43 86	99.36 55	99.68 67	98.97 114	99.19 95	99.46 86	96.60 121	99.20 63	97.11 164	99.51 46	99.15 75	98.92 64	98.82 63	99.45 56	99.08 43

v17		98.96 51	98.63 58	99.35 60	99.54 112	99.41 39	99.55 43	99.70 34	97.40 80	99.10 81	99.79 37	99.10 102	99.40 43	97.96 128	97.99 115	98.80 148	98.77 82

v8		98.94 53	98.60 60	99.35 60	99.54 112	99.39 41	99.55 43	99.67 40	97.48 73	99.13 76	99.81 32	99.10 102	99.39 53	97.86 138	97.89 123	98.81 143	98.66 94

v16		98.95 52	98.62 59	99.34 62	99.53 119	99.41 39	99.54 47	99.70 34	97.34 84	99.07 87	99.76 41	99.10 102	99.40 43	97.96 128	98.00 114	98.79 150	98.76 83

MP-MVS		98.78 83	98.30 97	99.34 62	99.75 47	98.95 116	99.26 84	99.46 86	95.78 154	99.17 68	96.98 169	99.72 14	99.06 81	98.84 68	98.74 74	99.33 79	99.11 38
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CSCG		99.23 27	99.15 25	99.32 64	99.83 23	99.45 36	98.97 116	99.21 141	98.83 15	99.04 93	99.43 71	99.64 31	99.26 63	98.85 67	98.20 105	99.62 30	99.62 5

FC-MVSNet-test		99.32 23	99.33 14	99.31 65	99.87 17	99.65 17	99.63 29	99.75 25	97.76 50	97.29 204	99.87 18	99.63 33	99.52 24	99.66 9	99.63 6	99.77 19	99.12 37

v18		98.89 62	98.54 65	99.30 66	99.50 127	99.37 44	99.51 52	99.68 37	97.25 92	99.00 96	99.76 41	99.04 111	99.36 55	97.81 145	97.86 128	98.77 153	98.68 93

X-MVS		98.59 98	97.99 120	99.30 66	99.75 47	99.07 86	99.17 96	99.50 77	96.62 119	98.95 102	93.95 209	99.37 57	99.11 78	98.94 60	98.86 58	99.35 77	99.09 42

v6		98.84 73	98.46 73	99.30 66	99.54 112	98.98 107	99.54 47	99.37 109	97.49 72	99.11 80	99.81 32	99.13 96	99.40 43	97.86 138	97.89 123	98.81 143	98.04 144

pmmvs-eth3d		98.68 87	98.14 107	99.29 69	99.49 130	98.45 161	99.45 62	99.38 101	97.21 94	99.50 28	99.65 49	99.21 79	99.16 73	97.11 184	97.56 157	98.79 150	97.82 153

HFP-MVS		98.97 49	98.70 53	99.29 69	99.67 70	98.98 107	99.13 100	99.53 71	97.76 50	98.90 109	98.07 134	99.50 48	99.14 77	98.64 79	98.78 69	99.37 73	99.18 34

v1neww		98.84 73	98.45 77	99.29 69	99.54 112	98.98 107	99.54 47	99.37 109	97.48 73	99.10 81	99.80 35	99.12 97	99.40 43	97.85 141	97.89 123	98.81 143	98.04 144

v7new		98.84 73	98.45 77	99.29 69	99.54 112	98.98 107	99.54 47	99.37 109	97.48 73	99.10 81	99.80 35	99.12 97	99.40 43	97.85 141	97.89 123	98.81 143	98.04 144

EG-PatchMatch MVS		99.01 45	98.77 48	99.28 73	99.64 89	98.90 126	98.81 136	99.27 132	96.55 127	99.71 5	99.31 77	99.66 27	99.17 71	99.28 36	99.11 43	99.10 99	98.57 101

ACMMP_Plus		98.94 53	98.72 51	99.21 74	99.67 70	99.08 85	99.26 84	99.39 94	96.84 105	98.88 113	98.22 127	99.68 22	98.82 92	99.06 48	98.90 57	99.25 90	99.25 26

FC-MVSNet-train		99.13 37	99.05 28	99.21 74	99.87 17	99.57 21	99.67 20	99.60 54	96.75 115	98.28 157	99.48 67	99.52 43	98.10 135	99.47 26	99.37 27	99.76 21	99.21 32

PVSNet_Blended_VisFu		98.98 48	98.79 46	99.21 74	99.76 44	99.34 46	99.35 72	99.35 117	97.12 99	99.46 31	99.56 59	98.89 119	98.08 138	99.05 49	98.58 87	99.27 88	98.98 54

conf0.05thres1000		97.44 162	95.93 184	99.20 77	99.82 25	99.56 22	99.41 64	99.61 52	97.42 79	98.01 172	94.34 208	82.73 223	98.68 100	99.33 33	99.42 24	99.67 27	98.74 86

V42		98.81 81	98.49 71	99.18 78	99.52 124	98.92 122	99.50 55	99.29 129	97.43 78	98.97 98	99.81 32	99.00 116	99.30 59	97.93 131	98.01 113	98.51 173	98.34 121

Vis-MVSNet		99.25 26	99.32 16	99.17 79	99.65 81	99.55 26	99.63 29	99.33 121	98.16 28	99.29 51	99.65 49	99.77 8	97.56 154	99.44 28	99.14 40	99.58 36	99.51 12
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CPTT-MVS		98.28 120	97.51 139	99.16 80	99.54 112	98.78 133	98.96 117	99.36 112	96.30 139	98.89 112	93.10 214	99.30 68	99.20 66	98.35 97	97.96 120	99.03 112	98.82 73

Fast-Effi-MVS+		98.42 113	97.79 127	99.15 81	99.69 66	98.66 144	98.94 119	99.68 37	94.49 179	99.05 90	98.06 136	98.86 121	98.48 115	98.18 113	97.78 132	99.05 110	98.54 105

v148		98.77 84	98.45 77	99.15 81	99.68 67	98.94 120	99.49 56	99.31 128	97.95 38	98.91 108	99.65 49	99.62 35	99.18 68	97.99 127	97.64 150	98.33 178	97.38 169

3Dnovator+	97.85 5	98.61 95	98.14 107	99.15 81	99.62 96	98.37 164	99.10 104	99.51 74	98.04 33	98.98 97	96.07 189	98.75 127	98.55 110	98.51 83	98.40 97	99.17 96	98.82 73

HyFIR lowres test		98.08 132	97.16 152	99.14 84	99.72 58	98.91 123	99.41 64	99.58 55	97.93 39	98.82 116	99.24 80	95.81 183	98.73 98	95.16 214	95.13 206	98.60 165	97.94 150

OPM-MVS		98.84 73	98.59 61	99.12 85	99.52 124	98.50 158	99.13 100	99.22 139	97.76 50	98.76 120	98.70 110	99.61 36	98.90 87	98.67 77	98.37 98	99.19 95	98.57 101

LS3D		98.79 82	98.52 69	99.12 85	99.64 89	99.09 84	99.24 87	99.46 86	97.75 53	98.93 106	97.47 154	98.23 144	97.98 141	99.36 30	99.30 32	99.46 55	98.42 113

TSAR-MVS + MP.		99.02 44	98.95 32	99.11 87	99.23 171	98.79 132	99.51 52	98.73 182	97.50 71	98.56 132	99.03 98	99.59 39	99.16 73	99.29 34	99.17 38	99.50 51	99.24 29

HPM-MVS++		98.56 103	98.08 112	99.11 87	99.53 119	98.61 148	99.02 112	99.32 126	96.29 140	99.06 88	97.23 159	99.50 48	98.77 95	98.15 117	97.90 121	98.96 117	98.90 67

EPP-MVSNet		98.61 95	98.19 105	99.11 87	99.86 22	99.60 18	99.44 63	99.53 71	97.37 83	96.85 212	98.69 111	93.75 189	99.18 68	99.22 37	99.35 29	99.82 13	99.32 23

no-one		99.01 45	98.94 36	99.09 90	98.97 194	98.55 153	99.37 69	99.04 164	97.59 67	99.36 37	99.66 45	99.75 9	99.57 16	98.47 85	99.27 34	98.21 184	99.30 25

Effi-MVS+		98.11 131	97.29 144	99.06 91	99.62 96	98.55 153	98.16 190	99.80 15	94.64 176	99.15 74	96.59 177	97.43 165	98.44 116	97.46 169	97.90 121	99.17 96	98.45 110

MCST-MVS		98.25 123	97.57 137	99.06 91	99.53 119	98.24 172	98.63 154	99.17 147	95.88 151	98.58 131	96.11 187	99.09 106	99.18 68	97.58 164	97.31 167	99.25 90	98.75 85

USDC		98.26 122	97.57 137	99.06 91	99.42 139	97.98 187	98.83 132	98.85 175	97.57 70	99.59 18	99.15 88	98.59 136	98.99 84	97.42 173	96.08 197	98.69 158	96.23 193

Anonymous20231206		98.50 106	98.03 117	99.05 94	99.50 127	99.01 104	99.15 98	99.26 133	96.38 135	99.12 78	99.50 66	99.12 97	98.60 105	97.68 155	97.24 170	98.66 159	97.30 171

APD-MVS		98.47 109	97.97 121	99.05 94	99.64 89	98.91 123	98.94 119	99.45 90	94.40 186	98.77 119	97.26 158	99.41 51	98.21 132	98.67 77	98.57 89	99.31 83	98.57 101
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SMA-MVS		98.87 65	98.73 50	99.04 96	99.72 58	99.05 90	98.64 153	99.17 147	96.31 138	98.80 118	99.07 93	99.70 18	98.67 101	98.93 63	98.82 63	99.23 93	99.23 30

HSP-MVS		98.50 106	98.05 115	99.03 97	99.67 70	99.33 48	99.51 52	99.26 133	95.28 160	98.51 138	98.19 129	99.74 11	98.29 125	97.69 154	96.70 182	98.96 117	99.41 20

pmmvs5		98.37 116	97.81 126	99.03 97	99.46 132	98.97 114	99.03 108	98.96 171	95.85 152	99.05 90	99.45 69	98.66 134	98.79 94	96.02 202	97.52 158	98.87 134	98.21 131

TinyColmap		98.27 121	97.62 136	99.03 97	99.29 160	97.79 193	98.92 122	98.95 172	97.48 73	99.52 26	98.65 113	97.86 157	98.90 87	98.34 98	97.27 168	98.64 162	95.97 196

DeepC-MVS_fast	97.38 8	98.65 90	98.34 94	99.02 100	99.33 151	98.29 166	98.99 113	98.71 184	97.40 80	99.31 46	98.20 128	99.40 54	98.54 112	98.33 101	98.18 106	99.23 93	98.58 99
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
tfpn_n400		97.59 154	96.36 172	99.01 101	99.66 75	99.19 69	99.21 92	99.55 60	97.62 63	97.77 179	94.60 203	87.78 202	98.27 127	98.44 87	98.72 76	99.62 30	98.21 131

tfpnconf		97.59 154	96.36 172	99.01 101	99.66 75	99.19 69	99.21 92	99.55 60	97.62 63	97.77 179	94.60 203	87.78 202	98.27 127	98.44 87	98.72 76	99.62 30	98.21 131

PHI-MVS		98.57 100	98.20 104	99.00 103	99.48 131	98.91 123	98.68 144	99.17 147	94.97 170	99.27 59	98.33 122	99.33 63	98.05 139	98.82 70	98.62 84	99.34 78	98.38 115

3Dnovator	98.16 3	98.65 90	98.35 93	99.00 103	99.59 100	98.70 140	98.90 127	99.36 112	97.97 36	99.09 85	96.55 179	99.09 106	97.97 142	98.70 76	98.65 83	99.12 98	98.81 76

tfpnview11		97.49 159	96.22 176	98.97 105	99.63 94	99.24 58	99.12 102	99.54 66	96.76 113	97.77 179	94.60 203	87.78 202	98.25 130	97.93 131	99.14 40	99.52 45	98.08 143

MVS_111021_HR		98.58 99	98.26 100	98.96 106	99.32 154	98.81 130	98.48 168	98.99 169	96.81 110	99.16 71	98.07 134	99.23 75	98.89 89	98.43 90	98.27 101	98.90 129	98.24 127

SD-MVS		98.73 85	98.54 65	98.95 107	99.14 180	98.76 134	98.46 170	99.14 152	97.71 59	98.56 132	98.06 136	99.61 36	98.85 91	98.56 81	97.74 141	99.54 39	99.32 23

test20.03		98.84 73	98.74 49	98.95 107	99.77 38	99.33 48	99.21 92	99.46 86	97.29 86	98.88 113	99.65 49	99.10 102	97.07 170	99.11 42	98.76 71	99.32 82	97.98 149

PM-MVS		98.57 100	98.24 102	98.95 107	99.26 165	98.59 149	99.03 108	98.74 181	96.84 105	99.44 33	99.13 89	98.31 143	98.75 97	98.03 125	98.21 103	98.48 174	98.58 99

tfpn		94.97 206	91.60 219	98.90 110	99.73 56	99.33 48	99.11 103	99.51 74	95.05 165	97.19 209	89.03 224	62.62 241	98.37 120	98.53 82	98.97 55	99.48 54	97.70 157

IterMVS-LS		98.23 124	97.66 132	98.90 110	99.63 94	99.38 43	99.07 105	99.48 82	97.75 53	98.81 117	99.37 75	94.57 188	97.88 145	96.54 195	97.04 176	98.53 170	98.97 55
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
QAPM		98.62 94	98.40 89	98.89 112	99.57 106	98.80 131	98.63 154	99.35 117	96.82 108	98.60 129	98.85 108	99.08 108	98.09 137	98.31 102	98.21 103	99.08 104	98.72 87

RPSCF		98.84 73	98.81 45	98.89 112	99.37 142	98.95 116	98.51 167	98.85 175	97.73 57	98.33 153	98.97 103	99.14 93	98.95 85	99.18 38	98.68 79	99.31 83	98.99 53

view800		96.48 182	94.42 195	98.87 114	99.70 63	99.26 56	99.05 106	99.45 90	94.77 174	97.32 200	88.21 225	83.40 221	98.28 126	98.37 94	99.33 30	99.44 58	97.58 162

CDPH-MVS		97.99 133	97.23 148	98.87 114	99.58 102	98.29 166	98.83 132	99.20 145	93.76 198	98.11 165	96.11 187	99.16 87	98.23 131	97.80 146	97.22 171	99.29 86	98.28 123

NCCC		97.84 141	96.96 158	98.87 114	99.39 141	98.27 169	98.46 170	99.02 166	96.78 111	98.73 124	91.12 220	98.91 118	98.57 108	97.83 144	97.49 160	99.04 111	98.33 122

Anonymous20240521		98.42 113	98.05 115	98.86 117	99.67 70	99.16 76	98.79 137	99.21 141	95.11 164	98.54 135	97.87 142	97.47 164	97.39 162	99.14 39	99.01 54	99.54 39	98.60 97

pmmvs4		97.87 140	97.02 156	98.86 117	99.20 172	97.68 199	98.89 128	99.03 165	96.57 125	99.12 78	99.03 98	97.26 169	98.42 118	95.16 214	96.34 189	98.53 170	97.10 181

CLD-MVS		98.48 108	98.15 106	98.86 117	99.53 119	98.35 165	98.55 165	97.83 217	96.02 148	98.97 98	99.08 92	99.75 9	99.03 83	98.10 123	97.33 166	99.28 87	98.44 111
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
casdiffmvs		98.43 112	98.08 112	98.85 120	99.37 142	98.89 127	98.66 151	99.54 66	97.07 101	98.68 125	98.53 117	99.33 63	97.83 149	96.89 188	97.11 173	99.01 114	98.70 89

ESAPD		98.60 97	98.41 87	98.83 121	99.56 107	99.21 64	98.66 151	99.47 83	95.22 161	98.35 151	98.48 118	99.67 26	97.84 148	98.80 72	98.57 89	99.10 99	98.93 63

train_agg		97.99 133	97.26 145	98.83 121	99.43 138	98.22 174	98.91 124	99.07 161	94.43 184	97.96 174	96.42 182	99.30 68	98.81 93	97.39 174	96.62 185	98.82 142	98.47 107

canonicalmvs		98.34 118	97.92 123	98.83 121	99.45 133	99.21 64	98.37 177	99.53 71	97.06 102	97.74 183	96.95 171	95.05 186	98.36 121	98.77 74	98.85 60	99.51 50	99.53 9

view600		96.39 186	94.30 196	98.82 124	99.65 81	99.16 76	98.98 114	99.36 112	94.46 182	97.39 196	87.28 226	84.16 219	98.16 134	98.16 114	99.48 20	99.40 68	97.42 167

MVS_0304		98.57 100	98.36 92	98.82 124	99.72 58	98.94 120	98.92 122	99.14 152	96.76 113	99.33 42	98.30 124	99.73 12	96.74 173	98.05 124	97.79 131	99.08 104	98.97 55

TSAR-MVS + GP.		98.54 104	98.29 99	98.82 124	99.28 163	98.59 149	97.73 206	99.24 138	95.93 150	98.59 130	99.07 93	99.17 84	98.86 90	98.44 87	98.10 109	99.26 89	98.72 87

thres600view7		96.35 187	94.27 197	98.79 127	99.66 75	99.18 71	98.94 119	99.38 101	94.37 188	97.21 206	87.19 228	84.10 220	98.10 135	98.16 114	99.47 21	99.42 63	97.43 166

DI_MVS_plusplus_trai		97.57 157	96.55 167	98.77 128	99.55 109	98.76 134	99.22 90	99.00 168	97.08 100	97.95 175	97.78 145	91.35 196	98.02 140	96.20 198	96.81 181	98.87 134	97.87 152

CNVR-MVS		98.22 126	97.76 128	98.76 129	99.33 151	98.26 170	98.48 168	98.88 174	96.22 141	98.47 146	95.79 191	99.33 63	98.35 122	98.37 94	97.99 115	99.03 112	98.38 115

AdaColmap		97.57 157	96.57 166	98.74 130	99.25 168	98.01 182	98.36 179	98.98 170	94.44 183	98.47 146	92.44 218	97.91 156	98.62 104	98.19 112	97.74 141	98.73 155	97.28 172

Vis-MVSNet (Re-imp)		98.46 111	98.23 103	98.73 131	99.81 28	99.29 54	98.79 137	99.50 77	96.20 142	96.03 217	98.29 125	96.98 172	98.54 112	99.11 42	99.08 44	99.70 23	98.62 96

TSAR-MVS + ACMM		98.64 92	98.58 63	98.72 132	99.17 177	98.63 146	98.69 143	99.10 159	97.69 60	98.30 155	99.12 91	99.38 56	98.70 99	98.45 86	97.51 159	98.35 177	99.25 26

thres400		96.22 192	94.08 200	98.72 132	99.58 102	99.05 90	98.83 132	99.22 139	94.01 195	97.40 194	86.34 234	84.91 218	97.93 143	97.85 141	99.08 44	99.37 73	97.28 172

MVS_111021_LR		98.39 115	98.11 109	98.71 134	99.08 187	98.54 156	98.23 187	98.56 193	96.57 125	99.13 76	98.41 119	98.86 121	98.65 103	98.23 110	97.87 127	98.65 161	98.28 123

thresconf0.02		95.49 201	92.74 213	98.70 135	99.32 154	98.70 140	98.87 130	99.21 141	95.95 149	97.57 188	90.63 221	73.55 235	97.86 147	96.09 201	97.03 177	99.40 68	97.22 177

OpenMVS	97.26 9	97.88 139	97.17 151	98.70 135	99.50 127	98.55 153	98.34 180	99.11 157	93.92 196	98.90 109	95.04 199	98.23 144	97.38 163	98.11 122	98.12 108	98.95 119	98.23 128

thres200		96.23 191	94.13 198	98.69 137	99.44 136	99.18 71	98.58 163	99.38 101	93.52 201	97.35 198	86.33 235	85.83 215	97.93 143	98.16 114	98.78 69	99.42 63	97.10 181

PCF-MVS	95.58 16	97.60 152	96.67 162	98.69 137	99.44 136	98.23 173	98.37 177	98.81 178	93.01 208	98.22 159	97.97 140	99.59 39	98.20 133	95.72 207	95.08 207	99.08 104	97.09 183
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CANet		98.47 109	98.30 97	98.67 139	99.65 81	98.87 129	98.82 135	99.01 167	96.14 144	99.29 51	98.86 106	99.01 114	96.54 177	98.36 96	98.08 110	98.72 156	98.80 80

FMVSNet1		98.90 60	99.10 27	98.67 139	99.54 112	99.48 33	99.22 90	99.66 41	98.39 25	97.50 191	99.66 45	99.04 111	96.58 176	99.05 49	99.03 50	99.52 45	99.08 43

CHOSEN 1792x2688		98.31 119	98.02 118	98.66 141	99.55 109	98.57 152	99.38 68	99.25 136	98.42 22	98.48 144	99.58 57	99.85 6	98.31 124	95.75 205	95.71 198	96.96 205	98.27 125

HQP-MVS		97.58 156	96.65 165	98.66 141	99.30 157	97.99 185	97.88 201	98.65 187	94.58 177	98.66 126	94.65 202	99.15 91	98.59 106	96.10 200	95.59 199	98.90 129	98.50 106

OMC-MVS		98.35 117	98.10 110	98.64 143	98.85 198	97.99 185	98.56 164	98.21 205	97.26 90	98.87 115	98.54 116	99.27 71	98.43 117	98.34 98	97.66 147	98.92 124	97.65 159

tfpn200view9		96.17 193	94.08 200	98.60 144	99.37 142	99.18 71	98.68 144	99.39 94	92.02 217	97.30 202	86.53 231	86.34 210	97.45 156	98.15 117	99.08 44	99.43 60	97.28 172

tfpn111		96.48 182	94.67 194	98.59 145	99.37 142	99.18 71	98.68 144	99.39 94	92.02 217	97.21 206	90.63 221	86.34 210	97.45 156	98.15 117	99.08 44	99.43 60	97.28 172

conf200view11		96.16 195	94.08 200	98.59 145	99.37 142	99.18 71	98.68 144	99.39 94	92.02 217	97.21 206	86.53 231	86.34 210	97.45 156	98.15 117	99.08 44	99.43 60	97.28 172

new-patchmatchnet		97.26 165	96.12 179	98.58 147	99.55 109	98.63 146	99.14 99	97.04 225	98.80 16	99.19 65	99.92 6	99.19 82	98.92 86	95.51 209	87.04 225	97.66 194	93.73 214

PLC	95.63 15	97.73 146	97.01 157	98.57 148	99.10 184	97.80 192	97.72 207	98.77 180	96.34 136	98.38 149	93.46 213	98.06 150	98.66 102	97.90 134	97.65 149	98.77 153	97.90 151
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MSDG		98.20 127	97.88 125	98.56 149	99.33 151	97.74 196	98.27 184	98.10 208	97.20 96	98.06 167	98.59 115	99.16 87	98.76 96	98.39 93	97.71 145	98.86 137	96.38 190

DELS-MVS		98.63 93	98.70 53	98.55 150	99.24 170	99.04 95	98.96 117	98.52 194	96.83 107	98.38 149	99.58 57	99.68 22	97.06 171	98.74 75	98.44 95	99.10 99	98.59 98
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
TAPA-MVS	96.65 12	98.23 124	97.96 122	98.55 150	98.81 200	98.16 176	98.40 174	97.94 214	96.68 117	98.49 142	98.61 114	98.89 119	98.57 108	97.45 170	97.59 154	99.09 103	98.35 117
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
conf0.01		94.53 213	91.09 222	98.53 152	99.29 160	99.05 90	98.68 144	99.35 117	92.02 217	97.04 210	84.45 237	68.52 237	97.45 156	97.79 148	99.08 44	99.41 66	96.70 187

conf0.002		93.97 218	90.06 226	98.52 153	99.26 165	99.02 103	98.68 144	99.33 121	92.02 217	97.01 211	83.82 238	63.41 240	97.45 156	97.73 152	97.98 117	99.40 68	96.47 189

IS_MVSNet		98.20 127	98.00 119	98.44 154	99.82 25	99.48 33	99.25 86	99.56 58	95.58 156	93.93 234	97.56 151	96.52 176	98.27 127	99.08 47	99.20 37	99.80 15	98.56 104

PMVS	92.51 17	98.66 89	98.86 42	98.43 155	99.26 165	98.98 107	98.60 160	98.59 191	97.73 57	99.45 32	99.38 74	98.54 138	95.24 197	99.62 14	99.61 11	99.42 63	98.17 137
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tfpn1000		97.10 170	95.97 182	98.41 156	99.64 89	99.30 53	98.89 128	99.49 81	96.49 130	95.97 219	95.31 195	85.62 216	96.92 172	97.86 138	99.13 42	99.53 44	98.11 140

MSLP-MVS++		97.99 133	97.64 135	98.40 157	98.91 196	98.47 160	97.12 225	98.78 179	96.49 130	98.48 144	93.57 212	99.12 97	98.51 114	98.31 102	98.58 87	98.58 167	98.95 61

gm-plane-assit		94.62 210	91.39 220	98.39 158	99.90 13	99.47 35	99.40 66	99.65 43	97.44 77	99.56 22	99.68 44	59.40 244	94.23 212	96.17 199	94.77 209	97.61 195	92.79 219

abl_6				98.38 159	99.03 191	98.04 181	98.08 193	98.65 187	93.23 204	98.56 132	94.58 206	98.57 137	97.17 166			98.81 143	97.42 167

EU-MVSNet		98.68 87	98.94 36	98.37 160	99.14 180	98.74 138	99.64 26	98.20 207	98.21 26	99.17 68	99.66 45	99.18 83	99.08 79	99.11 42	98.86 58	95.00 216	98.83 71

MVS_Test		97.69 147	97.15 153	98.33 161	99.27 164	98.43 163	98.25 185	99.29 129	95.00 169	97.39 196	98.86 106	98.00 153	97.14 168	95.38 210	96.22 191	98.62 163	98.15 139

MDA-MVSNet-bldmvs		97.75 143	97.26 145	98.33 161	99.35 150	98.45 161	99.32 77	97.21 223	97.90 44	99.05 90	99.01 100	96.86 174	99.08 79	99.36 30	92.97 217	95.97 213	96.25 192

CNLPA		97.75 143	97.26 145	98.32 163	98.58 212	97.86 190	97.80 202	98.09 209	96.49 130	98.49 142	96.15 186	98.08 149	98.35 122	98.00 126	97.03 177	98.61 164	97.21 178

Effi-MVS+-dtu		97.78 142	97.37 142	98.26 164	99.25 168	98.50 158	97.89 200	99.19 146	94.51 178	98.16 162	95.93 190	98.80 124	95.97 188	98.27 109	97.38 163	99.10 99	98.23 128

PVSNet_BlendedMVS		97.93 137	97.66 132	98.25 165	99.30 157	98.67 142	98.31 181	97.95 212	94.30 189	98.75 121	97.63 148	98.76 125	96.30 184	98.29 104	97.78 132	98.93 121	98.18 135

PVSNet_Blended		97.93 137	97.66 132	98.25 165	99.30 157	98.67 142	98.31 181	97.95 212	94.30 189	98.75 121	97.63 148	98.76 125	96.30 184	98.29 104	97.78 132	98.93 121	98.18 135

IterMVS		97.40 163	96.67 162	98.25 165	99.45 133	98.66 144	98.87 130	98.73 182	96.40 134	98.94 105	99.56 59	95.26 185	97.58 153	95.38 210	94.70 211	95.90 214	96.72 186
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testmv		97.48 161	96.83 161	98.24 168	99.37 142	97.79 193	98.59 161	99.07 161	92.40 211	97.59 186	99.24 80	98.11 148	97.66 151	97.64 159	97.11 173	97.17 201	95.54 201

test1235678		97.49 159	96.84 160	98.24 168	99.37 142	97.79 193	98.59 161	99.07 161	92.41 210	97.59 186	99.24 80	98.15 147	97.66 151	97.64 159	97.12 172	97.17 201	95.55 200

MDTV_nov1_ep13_2view		97.12 168	96.19 178	98.22 170	99.13 182	98.05 180	99.24 87	99.47 83	97.61 65	99.15 74	99.59 55	99.01 114	98.40 119	94.87 216	90.14 220	93.91 221	94.04 213

thres100view900		95.74 199	93.66 208	98.17 171	99.37 142	98.59 149	98.10 191	98.33 201	92.02 217	97.30 202	86.53 231	86.34 210	96.69 174	96.77 191	98.47 94	99.24 92	96.89 184

PatchMatch-RL		97.24 166	96.45 170	98.17 171	98.70 206	97.57 201	97.31 221	98.48 197	94.42 185	98.39 148	95.74 192	96.35 179	97.88 145	97.75 151	97.48 161	98.24 182	95.87 197

CR-MVSNet		95.38 203	93.01 211	98.16 173	98.63 210	95.85 225	97.64 212	99.78 19	91.27 228	98.50 139	96.84 172	82.16 224	96.34 182	94.40 219	95.50 200	98.05 188	95.04 205

DeepPCF-MVS	96.68 10	98.20 127	98.26 100	98.12 174	97.03 238	98.11 178	98.44 172	97.70 218	96.77 112	98.52 137	98.91 104	99.17 84	98.58 107	98.41 92	98.02 112	98.46 175	98.46 108

MAR-MVS		97.12 168	96.28 175	98.11 175	98.94 195	97.22 204	97.65 211	99.38 101	90.93 232	98.15 163	95.17 196	97.13 170	96.48 180	97.71 153	97.40 162	98.06 187	98.40 114
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
tfpn_ndepth		96.69 179	95.49 191	98.09 176	99.17 177	99.13 80	98.61 159	99.38 101	94.90 173	95.85 221	92.85 216	88.19 201	96.07 187	97.28 181	98.67 80	99.49 53	97.44 165

PatchT		95.49 201	93.29 210	98.06 177	98.65 209	96.20 215	98.91 124	99.73 28	92.00 223	98.50 139	96.67 175	83.25 222	96.34 182	94.40 219	95.50 200	96.21 209	95.04 205

MS-PatchMatch		97.60 152	97.22 149	98.04 178	98.67 208	97.18 205	97.91 198	98.28 202	95.82 153	98.34 152	97.66 147	98.38 140	97.77 150	97.10 185	97.25 169	97.27 200	97.18 179

diffmvs		97.05 171	96.20 177	98.04 178	99.08 187	98.01 182	98.20 188	99.10 159	94.48 181	97.31 201	95.15 197	97.82 158	96.53 178	94.32 221	94.76 210	98.05 188	98.82 73

GA-MVS		96.84 176	95.86 186	97.98 180	99.16 179	98.29 166	97.91 198	98.64 189	95.14 163	97.71 184	98.04 138	88.90 199	96.50 179	96.41 196	96.61 186	97.97 191	97.60 160

TSAR-MVS + COLMAP		97.62 151	97.31 143	97.98 180	98.47 218	97.39 203	98.29 183	98.25 203	96.68 117	97.54 190	98.87 105	98.04 152	97.08 169	96.78 190	96.26 190	98.26 181	97.12 180

UGNet		98.52 105	99.00 30	97.96 182	99.58 102	99.26 56	99.27 83	99.40 92	98.07 30	98.28 157	98.76 109	99.71 17	92.24 226	98.94 60	98.85 60	99.00 115	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
testgi		98.18 130	98.44 83	97.89 183	99.78 36	99.23 60	98.78 139	99.21 141	97.26 90	97.41 193	97.39 156	99.36 61	92.85 222	98.82 70	98.66 82	99.31 83	98.35 117

RPMNet		94.72 209	92.01 218	97.88 184	98.56 214	95.85 225	97.78 203	99.70 34	91.27 228	98.33 153	93.69 210	81.88 225	94.91 202	92.60 227	94.34 213	98.01 190	94.46 209

N_pmnet		96.68 180	95.70 189	97.84 185	99.42 139	98.00 184	99.35 72	98.21 205	98.40 24	98.13 164	99.42 72	99.30 68	97.44 161	94.00 224	88.79 222	94.47 220	91.96 222

CDS-MVSNet		97.75 143	97.68 131	97.83 186	99.08 187	98.20 175	98.68 144	98.61 190	95.63 155	97.80 178	99.24 80	96.93 173	94.09 213	97.96 128	97.82 130	98.71 157	97.99 147
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CANet_DTU		97.65 150	97.50 140	97.82 187	99.19 175	98.08 179	98.41 173	98.67 186	94.40 186	99.16 71	98.32 123	98.69 129	93.96 215	97.87 137	97.61 152	97.51 197	97.56 163

FMVSNet2		97.94 136	98.08 112	97.77 188	98.71 203	99.21 64	98.62 156	99.47 83	96.62 119	96.37 216	99.20 86	97.70 160	94.39 208	97.39 174	97.75 140	99.08 104	98.70 89

GBi-Net		97.69 147	97.75 129	97.62 189	98.71 203	99.21 64	98.62 156	99.33 121	94.09 192	95.60 223	98.17 131	95.97 180	94.39 208	99.05 49	99.03 50	99.08 104	98.70 89

test1		97.69 147	97.75 129	97.62 189	98.71 203	99.21 64	98.62 156	99.33 121	94.09 192	95.60 223	98.17 131	95.97 180	94.39 208	99.05 49	99.03 50	99.08 104	98.70 89

Fast-Effi-MVS+-dtu		96.99 172	96.46 169	97.61 191	98.98 193	97.89 188	97.54 216	99.76 22	93.43 202	96.55 215	94.93 200	98.06 150	94.32 211	96.93 187	96.50 188	98.53 170	97.47 164

LP		95.33 205	93.45 209	97.54 192	98.68 207	97.40 202	98.73 141	98.41 199	96.33 137	98.92 107	97.84 144	88.30 200	95.92 189	92.98 225	89.38 221	94.56 219	91.90 223

CHOSEN 280x420		96.80 177	96.30 174	97.39 193	99.09 185	96.52 210	98.76 140	99.29 129	93.88 197	97.65 185	98.34 121	93.66 190	96.29 186	98.28 107	97.73 143	93.27 225	95.70 198

CVMVSNet		97.38 164	97.39 141	97.37 194	98.58 212	97.72 197	98.70 142	97.42 220	97.21 94	95.95 220	99.46 68	93.31 192	97.38 163	97.60 162	97.78 132	96.18 210	98.66 94

MIMVSNet		97.24 166	97.15 153	97.36 195	99.03 191	98.52 157	98.55 165	99.73 28	94.94 172	94.94 231	97.98 139	97.37 167	93.66 217	97.60 162	97.34 165	98.23 183	96.29 191

testus		96.13 196	95.13 192	97.28 196	99.13 182	97.00 207	96.84 229	97.89 216	90.48 233	97.40 194	93.60 211	96.47 177	95.39 195	96.21 197	96.19 193	97.05 203	95.99 195

PMMVS		96.47 184	95.81 187	97.23 197	97.38 236	95.96 223	97.31 221	96.91 226	93.21 205	97.93 176	97.14 162	97.64 162	95.70 191	95.24 212	96.18 194	98.17 185	95.33 203

MDTV_nov1_ep13		94.47 214	92.15 216	97.17 198	98.54 216	96.42 213	98.10 191	98.89 173	94.49 179	98.02 169	97.41 155	86.49 207	95.56 193	90.85 228	87.95 223	93.91 221	91.45 226

PatchmatchNet		93.88 220	91.08 223	97.14 199	98.75 202	96.01 222	98.25 185	99.39 94	94.95 171	98.96 100	96.32 183	85.35 217	95.50 194	88.89 231	85.89 229	91.99 233	90.15 229
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ADS-MVSNet		94.41 216	92.13 217	97.07 200	98.86 197	96.60 209	98.38 176	98.47 198	96.13 146	98.02 169	96.98 169	87.50 206	95.87 190	89.89 229	87.58 224	92.79 229	90.27 228

gg-mvs-nofinetune		96.77 178	96.52 168	97.06 201	99.66 75	97.82 191	97.54 216	99.86 9	98.69 17	98.61 128	99.94 4	89.62 197	88.37 236	97.55 165	96.67 184	98.30 179	95.35 202

FMVSNet3		96.85 175	96.67 162	97.06 201	97.56 234	99.01 104	97.99 195	99.33 121	94.09 192	95.60 223	98.17 131	95.97 180	93.26 220	94.76 218	96.22 191	98.59 166	98.46 108

tpm		93.89 219	91.21 221	97.03 203	98.36 222	96.07 220	97.53 219	99.65 43	92.24 212	98.64 127	97.23 159	74.67 234	94.64 206	92.68 226	90.73 219	93.37 224	94.82 208

IB-MVS	95.85 14	95.87 197	94.88 193	97.02 204	99.09 185	98.25 171	97.16 223	97.38 221	91.97 224	97.77 179	83.61 239	97.29 168	92.03 229	97.16 183	97.66 147	98.66 159	98.20 134
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
MVSTER		95.38 203	93.99 204	97.01 205	98.83 199	98.95 116	96.62 230	99.14 152	92.17 214	97.44 192	97.29 157	77.88 230	91.63 230	97.45 170	96.18 194	98.41 176	97.99 147

EPMVS		93.67 221	90.82 224	96.99 206	98.62 211	96.39 214	98.40 174	99.11 157	95.54 157	97.87 177	97.14 162	81.27 228	94.97 201	88.54 233	86.80 226	92.95 227	90.06 230

TAMVS		96.95 174	96.94 159	96.97 207	99.07 190	97.67 200	97.98 196	97.12 224	95.04 166	95.41 226	99.27 79	95.57 184	94.09 213	97.32 178	97.11 173	98.16 186	96.59 188

EPNet		96.44 185	96.08 180	96.86 208	99.32 154	97.15 206	97.69 210	99.32 126	93.67 199	98.11 165	95.64 193	93.44 191	89.07 234	96.86 189	96.83 180	97.67 193	98.97 55
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test2356		92.46 224	88.72 232	96.82 209	98.48 217	95.34 231	96.22 234	98.09 209	87.46 239	96.01 218	92.82 217	64.42 238	95.10 199	94.08 222	94.05 214	97.02 204	92.87 217

new_pmnet		96.59 181	96.40 171	96.81 210	98.24 227	95.46 229	97.71 209	94.75 233	96.92 103	96.80 214	99.23 84	97.81 159	96.69 174	96.58 194	95.16 205	96.69 206	93.64 215

pmmvs3		96.30 189	95.87 185	96.80 211	97.66 233	96.48 211	97.93 197	93.80 234	93.40 203	98.54 135	98.27 126	97.50 163	97.37 165	97.49 168	93.11 216	95.52 215	94.85 207

EPNet_dtu		96.31 188	95.96 183	96.72 212	99.18 176	95.39 230	97.03 227	99.13 156	93.02 207	99.35 40	97.23 159	97.07 171	90.70 231	95.74 206	95.08 207	94.94 217	98.16 138
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FPMVS		96.97 173	97.20 150	96.70 213	97.75 231	96.11 219	97.72 207	95.47 229	97.13 98	98.02 169	97.57 150	96.67 175	92.97 221	99.00 57	98.34 99	98.28 180	95.58 199

FMVSNet5		94.57 212	92.77 212	96.67 214	97.88 229	98.72 139	97.54 216	98.70 185	88.64 238	95.11 229	86.90 229	81.77 226	93.27 219	97.92 133	98.07 111	97.50 198	97.34 170

tpmp4_e23		92.43 226	88.82 230	96.64 215	98.46 219	95.17 232	97.61 214	98.85 175	92.42 209	98.18 160	93.03 215	74.92 233	93.80 216	88.91 230	84.60 231	92.95 227	92.66 220

CostFormer		92.75 223	89.49 227	96.55 216	98.78 201	95.83 227	97.55 215	98.59 191	91.83 225	97.34 199	96.31 184	78.53 229	94.50 207	86.14 234	84.92 230	92.54 230	92.84 218

dps		92.35 227	88.78 231	96.52 217	98.21 228	95.94 224	97.78 203	98.38 200	89.88 236	96.81 213	95.07 198	75.31 232	94.70 205	88.62 232	86.21 228	93.21 226	90.41 227

1111		94.22 217	92.26 215	96.51 218	99.71 61	98.75 136	99.03 108	99.83 12	95.01 167	93.39 236	99.54 63	60.23 242	89.58 232	97.90 134	97.62 151	97.50 198	96.75 185

DWT-MVSNet_training		91.07 231	86.55 234	96.35 219	98.28 225	95.82 228	98.00 194	95.03 232	91.24 230	97.99 173	90.35 223	63.43 239	95.25 196	86.06 235	86.62 227	93.55 223	92.30 221

CMPMVS	74.71 19	96.17 193	96.06 181	96.30 220	97.41 235	94.52 235	94.83 237	95.46 230	91.57 226	97.26 205	94.45 207	98.33 142	94.98 200	98.28 107	97.59 154	97.86 192	97.68 158
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MVS-HIRNet		94.86 207	93.83 205	96.07 221	97.07 237	94.00 236	94.31 238	99.17 147	91.23 231	98.17 161	98.69 111	97.43 165	95.66 192	94.05 223	91.92 218	92.04 232	89.46 232

test-LLR		94.79 208	93.71 206	96.06 222	99.20 172	96.16 216	96.31 231	98.50 195	89.98 234	94.08 232	97.01 166	86.43 208	92.20 227	96.76 192	95.31 202	96.05 211	94.31 210

tpm cat1		91.52 230	87.70 233	95.97 223	98.33 223	94.98 234	97.06 226	98.03 211	92.11 216	98.03 168	94.77 201	77.19 231	92.71 223	83.56 237	82.24 234	91.67 234	89.04 234

tpmrst		92.45 225	89.48 228	95.92 224	98.43 221	95.03 233	97.14 224	97.92 215	94.16 191	97.56 189	97.86 143	81.63 227	93.56 218	85.89 236	82.86 232	90.91 237	88.95 235

test12356		95.71 200	95.55 190	95.89 225	98.27 226	96.48 211	96.90 228	97.35 222	92.13 215	95.64 222	99.13 89	97.97 154	92.34 225	96.94 186	96.55 187	94.87 218	89.61 231

test0.0.03 1		95.81 198	95.77 188	95.85 226	99.20 172	98.15 177	97.49 220	98.50 195	92.24 212	92.74 239	96.82 173	92.70 193	88.60 235	97.31 180	97.01 179	98.57 168	96.19 194

PMMVS2		96.29 190	97.05 155	95.40 227	98.32 224	96.16 216	98.18 189	97.46 219	97.20 96	84.51 241	99.60 53	98.68 131	96.37 181	98.59 80	97.38 163	97.58 196	91.76 224

test-mter		94.62 210	94.02 203	95.32 228	97.72 232	96.75 208	96.23 233	95.67 228	89.83 237	93.23 238	96.99 168	85.94 214	92.66 224	97.32 178	96.11 196	96.44 207	95.22 204

TESTMET0.1,1		94.44 215	93.71 206	95.30 229	97.84 230	96.16 216	96.31 231	95.32 231	89.98 234	94.08 232	97.01 166	86.43 208	92.20 227	96.76 192	95.31 202	96.05 211	94.31 210

E-PMN		92.28 228	90.12 225	94.79 230	98.56 214	90.90 238	95.16 236	93.68 235	95.36 159	95.10 230	96.56 178	89.05 198	95.24 197	95.21 213	81.84 235	90.98 235	81.94 236

EMVS		91.84 229	89.39 229	94.70 231	98.44 220	90.84 239	95.27 235	93.53 236	95.18 162	95.26 228	95.62 194	87.59 205	94.77 204	94.87 216	80.72 236	90.95 236	80.88 237

testpf		87.81 232	83.90 235	92.37 232	96.76 239	88.65 240	93.04 240	98.24 204	85.20 240	95.28 227	86.82 230	72.43 236	82.35 237	82.62 238	82.30 233	88.55 238	89.29 233

MVE	82.47 18	93.12 222	94.09 199	91.99 233	90.79 240	82.50 242	93.93 239	96.30 227	96.06 147	88.81 240	98.19 129	96.38 178	97.56 154	97.24 182	95.18 204	84.58 239	93.07 216
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
.test1245		74.10 233	68.09 236	81.11 234	99.71 61	98.75 136	99.03 108	99.83 12	95.01 167	93.39 236	99.54 63	60.23 242	89.58 232	97.90 134	10.38 238	5.14 242	14.81 238

tmp_tt				65.28 235	82.24 241	71.50 243	70.81 243	23.21 238	96.14 144	81.70 242	85.98 236	92.44 194	49.84 238	95.81 204	94.36 212	83.86 240

GG-mvs-BLEND		65.66 234	92.62 214	34.20 236	1.45 244	93.75 237	85.40 242	1.64 241	91.37 227	17.21 243	87.25 227	94.78 187	3.25 241	95.64 208	93.80 215	96.27 208	91.74 225

test123		9.37 236	12.26 238	6.00 237	3.32 243	4.06 245	6.39 246	3.41 239	13.20 242	10.48 244	16.43 241	16.22 245	6.76 240	11.37 240	10.40 237	5.62 241	14.10 240

testmvs		9.73 235	13.38 237	5.48 238	3.62 242	4.12 244	6.40 245	3.19 240	14.92 241	7.68 245	22.10 240	13.89 246	6.83 239	13.47 239	10.38 238	5.14 242	14.81 238

sosnet-low-res		0.00 237	0.00 239	0.00 239	0.00 245	0.00 246	0.00 247	0.00 242	0.00 243	0.00 246	0.00 242	0.00 247	0.00 242	0.00 241	0.00 240	0.00 244	0.00 241

sosnet		0.00 237	0.00 239	0.00 239	0.00 245	0.00 246	0.00 247	0.00 242	0.00 243	0.00 246	0.00 242	0.00 247	0.00 242	0.00 241	0.00 240	0.00 244	0.00 241

Anonymous202405211			98.44 83		99.79 33	99.32 52	99.05 106	99.34 120	96.59 122		97.95 141	97.68 161	97.16 167	99.36 30	99.28 33	99.61 34	98.90 67

our_test_3					99.29 160	97.72 197	98.98 114

ambc			97.89 124		99.45 133	97.88 189	97.78 203		97.27 88	99.80 2	98.99 102	98.48 139	98.55 110	97.80 146	96.68 183	98.54 169	98.10 141

MTAPA										99.19 65		99.68 22

MTMP										99.20 63		99.54 42

Patchmatch-RL test							32.47 244

XVS					99.77 38	99.07 86	99.46 60			98.95 102		99.37 57				99.33 79

X-MVStestdata					99.77 38	99.07 86	99.46 60			98.95 102		99.37 57				99.33 79

mPP-MVS					99.75 47							99.49 50

NP-MVS									93.07 206

Patchmtry						96.05 221	97.64 212	99.78 19		98.50 139

DeepMVS_CX						87.86 241	92.27 241	61.98 237	93.64 200	93.62 235	91.17 219	91.67 195	94.90 203	95.99 203		92.48 231	94.18 212

High-resolution multi-view benchmark