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.

Anonymous20231211		99.36 1	99.64 1	99.03 9	99.22 33	99.53 6	99.38 15	99.55 1	99.70 1	98.74 19	99.74 6	99.96 1	97.48 71	99.75 1	99.63 1	99.80 2	99.19 3

LTVRE_ROB	97.71 1	99.33 2	99.47 2	99.16 7	99.16 39	99.11 10	99.39 14	99.16 11	99.26 3	99.22 4	99.51 32	99.75 4	98.54 19	99.71 2	99.47 4	99.52 12	99.46 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
SixPastTwentyTwo		99.25 3	99.20 4	99.32 1	99.53 14	99.32 8	99.64 2	99.19 10	98.05 13	99.19 5	99.74 6	98.96 54	99.03 5	99.69 3	99.58 2	99.32 23	99.06 6

WR-MVS		99.22 4	99.15 5	99.30 2	99.54 11	99.62 1	99.63 4	99.45 2	97.75 17	98.47 25	99.71 8	99.05 42	98.88 7	99.54 6	99.49 3	99.81 1	98.87 10

PS-CasMVS		99.08 5	98.90 13	99.28 3	99.65 3	99.56 4	99.59 6	99.39 4	96.36 35	98.83 16	99.46 38	99.09 34	98.62 14	99.51 7	99.36 8	99.63 3	98.97 7

PEN-MVS		99.08 5	98.95 10	99.23 5	99.65 3	99.59 2	99.64 2	99.34 6	96.68 28	98.65 20	99.43 41	99.33 16	98.47 21	99.50 8	99.32 9	99.60 5	98.79 12

v7n		99.03 7	99.03 9	99.02 10	99.09 50	99.11 10	99.57 9	98.82 18	98.21 9	99.25 2	99.84 3	99.59 8	98.76 9	99.23 19	98.83 28	98.63 67	98.40 34

DTE-MVSNet		99.03 7	98.88 14	99.21 6	99.66 2	99.59 2	99.62 5	99.34 6	96.92 25	98.52 22	99.36 48	98.98 49	98.57 17	99.49 9	99.23 12	99.56 9	98.55 23

TDRefinement		99.00 9	99.13 6	98.86 12	98.99 56	99.05 15	99.58 7	98.29 48	98.96 5	97.96 47	99.40 45	98.67 85	98.87 8	99.60 4	99.46 5	99.46 18	98.74 17

v52		98.98 10	99.10 7	98.85 13	98.91 59	99.03 16	99.41 12	97.77 92	98.12 10	99.07 8	99.84 3	99.60 6	99.15 2	99.29 15	98.99 19	98.79 59	98.79 12

V4		98.98 10	99.10 7	98.85 13	98.91 59	99.03 16	99.41 12	97.77 92	98.12 10	99.06 9	99.85 2	99.60 6	99.15 2	99.30 14	98.99 19	98.80 57	98.79 12

WR-MVS_H		98.97 12	98.82 16	99.14 8	99.56 9	99.56 4	99.54 11	99.42 3	96.07 42	98.37 27	99.34 49	99.09 34	98.43 22	99.45 10	99.41 6	99.53 10	98.86 11

v748		98.92 13	98.95 10	98.87 11	98.54 79	98.69 48	99.33 17	98.64 22	98.07 12	99.06 9	99.66 12	99.76 3	98.68 11	99.25 18	98.72 32	99.01 35	98.54 24

CP-MVSNet		98.91 14	98.61 21	99.25 4	99.63 5	99.50 7	99.55 10	99.36 5	95.53 68	98.77 18	99.11 58	98.64 88	98.57 17	99.42 11	99.28 11	99.61 4	98.78 15

anonymousdsp		98.85 15	98.88 14	98.83 15	98.69 75	98.20 78	99.68 1	97.35 134	97.09 24	98.98 12	99.86 1	99.43 11	98.94 6	99.28 16	99.19 13	99.33 21	99.08 5

pmmvs6		98.77 16	99.35 3	98.09 48	98.32 94	98.92 20	98.57 80	99.03 12	99.36 2	96.86 94	99.77 5	99.86 2	96.20 109	99.56 5	99.39 7	99.59 6	98.61 21

ACMH	95.26 7	98.75 17	98.93 12	98.54 27	98.86 63	99.01 18	99.58 7	98.10 67	98.67 6	97.30 73	99.18 56	99.42 12	98.40 23	99.19 21	98.86 26	98.99 39	98.19 41
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
COLMAP_ROB	96.84 2	98.75 17	98.82 16	98.66 23	99.14 43	98.79 31	99.30 19	97.67 96	98.33 8	97.82 50	99.20 55	99.18 31	98.76 9	99.27 17	98.96 21	99.29 25	98.03 45
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
UA-Net		98.66 19	98.60 23	98.73 19	99.83 1	99.28 9	98.56 82	99.24 8	96.04 43	97.12 81	98.44 84	98.95 55	98.17 30	99.15 23	99.00 18	99.48 17	99.33 2

DeepC-MVS	96.08 5	98.58 20	98.49 25	98.68 21	99.37 25	98.52 62	99.01 37	98.17 62	97.17 23	98.25 31	99.56 25	99.62 5	98.29 26	98.40 53	98.09 62	98.97 42	98.08 44
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TranMVSNet+NR-MVSNet		98.45 21	98.22 31	98.72 20	99.32 29	99.06 13	98.99 39	98.89 14	95.52 69	97.53 61	99.42 43	98.83 68	98.01 36	98.55 47	98.34 48	99.57 8	97.80 54

CSCG		98.45 21	98.61 21	98.26 38	99.11 47	99.06 13	98.17 99	97.49 111	97.93 15	97.37 70	98.88 64	99.29 17	98.10 31	98.40 53	97.51 82	99.32 23	99.16 4

Gipuma		98.43 23	98.15 33	98.76 18	99.00 55	98.29 75	97.91 114	98.06 70	99.02 4	99.50 1	96.33 133	98.67 85	99.22 1	99.02 26	98.02 72	98.88 54	97.66 59
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ACMH+	94.90 8	98.40 24	98.71 19	98.04 59	98.93 58	98.84 25	99.30 19	97.86 84	97.78 16	94.19 173	98.77 72	99.39 14	98.61 15	99.33 13	99.07 14	99.33 21	97.81 53

ACMMPR		98.31 25	98.07 36	98.60 24	99.58 6	98.83 26	99.09 29	98.48 26	96.25 38	97.03 85	96.81 123	99.09 34	98.39 24	98.55 47	98.45 41	99.01 35	98.53 27

APDe-MVS		98.29 26	98.42 26	98.14 44	99.45 21	98.90 21	99.18 26	98.30 44	95.96 48	95.13 152	98.79 70	99.25 24	97.92 43	98.80 33	98.71 33	98.85 55	98.54 24

TransMVSNet (Re)		98.23 27	98.72 18	97.66 85	98.22 106	98.73 44	98.66 77	98.03 73	98.60 7	96.40 111	99.60 21	98.24 108	95.26 125	99.19 21	99.05 17	99.36 19	97.64 60

DU-MVS		98.23 27	97.74 54	98.81 16	99.23 31	98.77 33	98.76 63	98.88 15	94.10 120	98.50 23	98.87 66	98.32 105	97.99 38	98.40 53	98.08 69	99.49 16	97.64 60

UniMVSNet (Re)		98.23 27	97.85 44	98.67 22	99.15 40	98.87 23	98.74 72	98.84 17	94.27 119	97.94 48	99.01 60	98.39 102	97.82 48	98.35 58	98.29 52	99.51 15	97.78 55

MIMVSNet1		98.22 30	98.51 24	97.87 72	99.40 24	98.82 28	99.31 18	98.53 24	97.39 20	96.59 102	99.31 51	99.23 27	94.76 135	98.93 29	98.67 34	98.63 67	97.25 83

HFP-MVS		98.17 31	98.02 37	98.35 36	99.36 26	98.62 53	98.79 60	98.46 31	96.24 39	96.53 104	97.13 120	98.98 49	98.02 35	98.20 61	98.42 43	98.95 46	98.54 24

Baseline_NR-MVSNet		98.17 31	97.90 41	98.48 30	99.23 31	98.59 55	98.83 58	98.73 21	93.97 127	96.95 88	99.66 12	98.23 110	97.90 44	98.40 53	99.06 16	99.25 26	97.42 75

TSAR-MVS + MP.		98.15 33	98.23 30	98.06 57	98.47 82	98.16 84	99.23 22	96.87 149	95.58 63	96.72 96	98.41 85	99.06 39	98.05 34	98.99 27	98.90 24	99.00 37	98.51 28

MPTG		98.14 34	97.78 50	98.55 26	99.58 6	98.58 56	98.98 41	98.48 26	95.98 46	97.39 68	94.73 162	99.27 21	97.98 40	98.81 32	98.64 36	98.90 49	98.46 30

pm-mvs1		98.14 34	98.66 20	97.53 93	97.93 138	98.49 65	98.14 100	98.19 58	97.95 14	96.17 123	99.63 18	98.85 66	95.41 123	98.91 30	98.89 25	99.34 20	97.86 52

ACMMP_Plus		98.12 36	98.08 35	98.18 42	99.34 27	98.74 42	98.97 43	98.00 74	95.13 82	96.90 89	97.54 109	99.27 21	97.18 82	98.72 37	98.45 41	98.68 65	98.69 18

UniMVSNet_NR-MVSNet		98.12 36	97.56 63	98.78 17	99.13 45	98.89 22	98.76 63	98.78 19	93.81 130	98.50 23	98.81 69	97.64 127	97.99 38	98.18 64	97.92 74	99.53 10	97.64 60

ACMM	94.29 11	98.12 36	97.71 56	98.59 25	99.51 16	98.58 56	99.24 21	98.25 50	96.22 40	96.90 89	95.01 158	98.89 60	98.52 20	98.66 42	98.32 51	99.13 29	98.28 39
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SteuartSystems-ACMMP		98.06 39	97.78 50	98.39 34	99.54 11	98.79 31	98.94 48	98.42 34	93.98 126	95.85 132	96.66 128	99.25 24	98.61 15	98.71 39	98.38 45	98.97 42	98.67 20
Skip Steuart: Steuart Systems R&D Blog.
v13		98.04 40	97.86 43	98.24 39	98.36 89	98.77 33	99.04 31	98.47 28	95.93 49	98.20 35	99.67 11	99.11 33	98.00 37	97.11 98	96.93 101	97.40 134	97.53 67

OPM-MVS		98.01 41	98.01 38	98.00 62	99.11 47	98.12 89	98.68 76	97.72 94	96.65 29	96.68 100	98.40 86	99.28 20	97.44 73	98.20 61	97.82 80	98.40 88	97.58 65

Vis-MVSNet		98.01 41	98.42 26	97.54 92	96.89 188	98.82 28	99.14 27	97.59 100	96.30 36	97.04 84	99.26 53	98.83 68	96.01 114	98.73 35	98.21 55	98.58 69	98.75 16
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
NR-MVSNet		98.00 43	97.88 42	98.13 45	98.33 91	98.77 33	98.83 58	98.88 15	94.10 120	97.46 66	98.87 66	98.58 94	95.78 116	99.13 24	98.16 60	99.52 12	97.53 67

CP-MVS		98.00 43	97.57 61	98.50 28	99.47 20	98.56 59	98.91 51	98.38 37	94.71 94	97.01 86	95.20 154	99.06 39	98.20 28	98.61 45	98.46 40	99.02 33	98.40 34

ACMMP		97.99 45	97.60 59	98.45 32	99.53 14	98.83 26	99.13 28	98.30 44	94.57 100	96.39 115	95.32 152	98.95 55	98.37 25	98.61 45	98.47 39	99.00 37	98.45 31
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
v12		97.98 46	97.78 50	98.21 40	98.33 91	98.74 42	99.01 37	98.44 33	95.82 56	98.13 36	99.64 15	99.08 37	97.95 41	96.97 110	96.82 104	97.39 136	97.38 79

MP-MVS		97.98 46	97.53 64	98.50 28	99.56 9	98.58 56	98.97 43	98.39 36	93.49 135	97.14 78	96.08 139	99.23 27	98.06 33	98.50 50	98.38 45	98.90 49	98.44 32

EG-PatchMatch MVS		97.98 46	97.92 40	98.04 59	98.84 65	98.04 97	97.90 115	96.83 153	95.07 84	98.79 17	99.07 59	99.37 15	97.88 46	98.74 34	98.16 60	98.01 108	96.96 94

ACMP	94.03 12	97.97 49	97.61 58	98.39 34	99.43 23	98.51 63	98.97 43	98.06 70	94.63 98	96.10 125	96.12 138	99.20 29	98.63 13	98.68 40	98.20 58	99.14 28	97.93 49
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LGP-MVS_train		97.96 50	97.53 64	98.45 32	99.45 21	98.64 52	99.09 29	98.27 49	92.99 148	96.04 127	96.57 129	99.29 17	98.66 12	98.73 35	98.42 43	99.19 27	98.09 43

v11		97.94 51	97.72 55	98.20 41	98.37 88	98.69 48	98.96 46	98.30 44	95.68 59	98.35 28	99.70 9	99.19 30	97.93 42	96.76 117	96.82 104	97.28 148	97.23 86

LS3D		97.93 52	97.80 46	98.08 53	99.20 36	98.77 33	98.89 54	97.92 78	96.59 30	96.99 87	96.71 126	97.14 138	96.39 105	99.04 25	98.96 21	99.10 32	97.39 76

V9		97.91 53	97.70 57	98.17 43	98.30 98	98.70 47	98.98 41	98.40 35	95.72 58	98.07 40	99.64 15	99.04 43	97.90 44	96.82 114	96.71 111	97.37 139	97.23 86

V14		97.85 54	97.60 59	98.13 45	98.27 100	98.66 51	98.94 48	98.36 39	95.62 60	98.04 43	99.62 19	98.99 47	97.84 47	96.65 122	96.59 117	97.34 142	97.07 91

SD-MVS		97.84 55	97.78 50	97.90 66	98.33 91	98.06 94	97.95 111	97.80 89	96.03 45	96.72 96	97.57 107	99.18 31	97.50 70	97.88 67	97.08 96	99.11 31	98.68 19

RPSCF		97.83 56	98.27 28	97.31 103	98.23 103	98.06 94	97.44 145	95.79 181	96.90 26	95.81 134	98.76 73	98.61 92	97.70 55	98.90 31	98.36 47	98.90 49	98.29 36

PGM-MVS		97.82 57	97.25 70	98.48 30	99.54 11	98.75 41	99.02 33	98.35 41	92.41 153	96.84 95	95.39 151	98.99 47	98.24 27	98.43 51	98.34 48	98.90 49	98.41 33

v15		97.77 58	97.50 66	98.09 48	98.23 103	98.62 53	98.90 52	98.32 43	95.51 71	98.01 45	99.60 21	98.95 55	97.78 49	96.47 128	96.45 122	97.32 143	96.90 96

PMVS	90.51 17	97.77 58	97.98 39	97.53 93	98.68 76	98.14 88	97.67 124	97.03 144	96.43 31	98.38 26	98.72 75	97.03 141	94.44 141	99.37 12	99.30 10	98.98 41	96.86 101
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
ESAPD		97.71 60	97.79 47	97.62 86	99.21 34	98.80 30	98.31 94	98.30 44	93.60 133	94.74 161	97.94 98	99.24 26	96.58 97	98.42 52	98.27 53	98.56 70	98.28 39

tfpnnormal		97.66 61	97.79 47	97.52 95	98.32 94	98.53 61	98.45 87	97.69 95	97.59 19	96.12 124	97.79 103	96.70 143	95.69 119	98.35 58	98.34 48	98.85 55	97.22 88

FC-MVSNet-train		97.65 62	98.16 32	97.05 115	98.85 64	98.85 24	99.34 16	98.08 68	94.50 108	94.41 167	99.21 54	98.80 72	92.66 163	98.98 28	98.85 27	98.96 44	97.94 48

v10		97.64 63	97.26 69	98.08 53	98.07 123	98.56 59	98.86 56	98.18 61	94.48 110	98.24 32	99.56 25	98.98 49	97.72 53	96.05 146	96.26 129	97.42 132	96.93 95

X-MVS		97.60 64	97.00 90	98.29 37	99.50 17	98.76 37	98.90 52	98.37 38	94.67 97	96.40 111	91.47 196	98.78 74	97.60 65	98.55 47	98.50 38	98.96 44	98.29 36

3Dnovator+	96.20 4	97.58 65	97.14 79	98.10 47	98.98 57	97.85 122	98.60 79	98.33 42	96.41 33	97.23 77	94.66 164	97.26 134	96.91 88	97.91 66	97.87 76	98.53 74	98.03 45

HPM-MVS++		97.56 66	97.11 84	98.09 48	99.18 38	97.95 106	98.57 80	98.20 56	94.08 122	97.25 76	95.96 143	98.81 71	97.13 83	97.51 82	97.30 93	98.21 99	98.15 42

FC-MVSNet-test		97.54 67	98.26 29	96.70 130	98.87 62	97.79 128	98.49 84	98.56 23	96.04 43	90.39 208	99.65 14	98.67 85	95.15 128	99.23 19	99.07 14	98.73 61	97.39 76

v17		97.54 67	97.21 72	97.92 64	98.02 126	98.50 64	98.79 60	98.24 51	94.39 114	97.60 59	99.45 40	98.72 83	97.68 57	96.29 135	96.28 127	97.19 157	96.86 101

TSAR-MVS + ACMM		97.54 67	97.79 47	97.26 104	98.23 103	98.10 92	97.71 123	97.88 83	95.97 47	95.57 145	98.71 76	98.57 95	97.36 76	97.74 72	96.81 107	96.83 171	98.59 22

DeepC-MVS_fast	95.38 6	97.53 70	97.30 68	97.79 77	98.83 68	97.64 131	98.18 97	97.14 140	95.57 64	97.83 49	97.10 121	98.80 72	96.53 101	97.41 87	97.32 90	98.24 97	97.26 82
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
v1192		97.52 71	97.03 88	98.09 48	98.31 97	98.01 100	98.96 46	97.25 137	95.22 79	98.89 14	99.64 15	98.83 68	97.68 57	95.63 158	95.91 147	97.47 129	95.97 126

v1144		97.51 72	97.05 86	98.04 59	98.26 101	97.98 103	98.88 55	97.42 124	95.38 74	98.56 21	99.59 24	99.01 46	97.65 59	95.77 156	96.06 141	97.47 129	95.56 137

v16		97.51 72	97.19 74	97.89 68	97.99 130	98.49 65	98.77 62	98.23 54	94.29 116	97.48 63	99.42 43	98.68 84	97.69 56	96.28 136	96.29 126	97.18 158	96.85 103

v8		97.51 72	97.16 77	97.91 65	97.99 130	98.48 67	98.76 63	98.17 62	94.54 104	97.69 53	99.48 34	98.76 78	97.63 64	96.10 142	96.14 135	97.20 153	96.64 110

v1921920		97.50 75	97.00 90	98.07 55	98.20 108	97.94 109	99.03 32	97.06 142	95.29 78	99.01 11	99.62 19	98.73 82	97.74 52	95.52 161	95.78 152	97.39 136	96.12 123

v144192		97.49 76	96.99 92	98.07 55	98.11 121	97.95 106	99.02 33	97.21 138	94.90 90	98.88 15	99.53 31	98.89 60	97.75 51	95.59 159	95.90 148	97.43 131	96.16 121

APD-MVS		97.47 77	97.16 77	97.84 74	99.32 29	98.39 71	98.47 86	98.21 55	92.08 158	95.23 149	96.68 127	98.90 59	96.99 86	98.20 61	98.21 55	98.80 57	97.67 58
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
v7		97.45 78	97.01 89	97.97 63	98.07 123	97.96 104	98.86 56	97.50 108	94.46 111	98.24 32	99.56 25	98.98 49	97.72 53	96.05 146	96.26 129	97.42 132	95.79 130

HSP-MVS		97.44 79	97.13 82	97.79 77	99.34 27	98.99 19	99.23 22	98.12 65	93.43 137	95.95 128	97.45 110	99.50 9	96.44 104	96.35 131	95.33 161	97.65 124	98.89 9

PVSNet_Blended_VisFu		97.44 79	97.14 79	97.79 77	99.15 40	98.44 68	98.32 93	97.66 97	93.74 132	97.73 52	98.79 70	96.93 142	95.64 122	97.69 74	96.91 102	98.25 96	97.50 71

PHI-MVS		97.44 79	97.17 76	97.74 84	98.14 116	98.41 70	98.03 105	97.50 108	92.07 159	98.01 45	97.33 114	98.62 91	96.02 113	98.34 60	98.21 55	98.76 60	97.24 85

v1240		97.43 82	96.87 103	98.09 48	98.25 102	97.92 112	99.02 33	97.06 142	94.77 93	99.09 7	99.68 10	98.51 98	97.78 49	95.25 166	95.81 150	97.32 143	96.13 122

v18		97.40 83	97.04 87	97.81 76	97.90 141	98.42 69	98.71 75	98.17 62	94.06 124	97.34 72	99.40 45	98.59 93	97.60 65	96.05 146	96.12 138	97.14 161	96.67 108

FMVSNet1		97.40 83	98.09 34	96.60 135	97.80 152	98.76 37	98.26 96	98.50 25	96.79 27	93.13 195	99.28 52	98.64 88	92.90 161	97.67 76	97.86 77	99.02 33	97.64 60

divwei89l23v2f112		97.37 85	96.92 94	97.89 68	98.18 111	97.90 116	98.76 63	97.42 124	95.38 74	98.09 38	99.56 25	98.87 63	97.59 67	95.78 153	95.98 142	97.29 145	94.97 150

v1		97.37 85	96.92 94	97.89 68	98.18 111	97.91 115	98.76 63	97.42 124	95.38 74	98.09 38	99.55 30	98.88 62	97.59 67	95.78 153	95.98 142	97.29 145	94.98 149

v1141		97.36 87	96.92 94	97.88 71	98.18 111	97.90 116	98.76 63	97.42 124	95.38 74	98.07 40	99.56 25	98.87 63	97.59 67	95.78 153	95.98 142	97.29 145	94.97 150

v2v482		97.33 88	96.84 104	97.90 66	98.19 109	97.83 123	98.74 72	97.44 123	95.42 73	98.23 34	99.46 38	98.84 67	97.46 72	95.51 162	96.10 139	97.36 140	94.72 155

v1neww		97.30 89	96.88 98	97.78 80	97.99 130	97.87 119	98.75 69	97.46 116	94.54 104	97.62 56	99.48 34	98.76 78	97.65 59	96.09 143	96.15 131	97.20 153	95.28 145

v7new		97.30 89	96.88 98	97.78 80	97.99 130	97.87 119	98.75 69	97.46 116	94.54 104	97.62 56	99.48 34	98.76 78	97.65 59	96.09 143	96.15 131	97.20 153	95.28 145

v6		97.30 89	96.88 98	97.78 80	97.99 130	97.87 119	98.75 69	97.46 116	94.54 104	97.61 58	99.48 34	98.77 77	97.65 59	96.09 143	96.15 131	97.21 152	95.28 145

EPP-MVSNet		97.29 92	96.88 98	97.76 83	98.70 72	99.10 12	98.92 50	98.36 39	95.12 83	93.36 191	97.39 112	91.00 185	97.65 59	98.72 37	98.91 23	99.58 7	97.92 50

MVS_111021_HR		97.27 93	97.11 84	97.46 97	98.46 83	97.82 125	97.50 136	96.86 150	94.97 87	97.13 80	96.99 122	98.39 102	96.82 90	97.65 80	97.38 87	98.02 107	96.56 113

TSAR-MVS + GP.		97.26 94	97.33 67	97.18 109	98.21 107	98.06 94	96.38 182	97.66 97	93.92 129	95.23 149	98.48 82	98.33 104	97.41 74	97.63 81	97.35 88	98.18 101	97.57 66

OMC-MVS		97.23 95	97.21 72	97.25 107	97.85 143	97.52 140	97.92 113	95.77 182	95.83 55	97.09 83	97.86 101	98.52 97	96.62 94	97.51 82	96.65 113	98.26 94	96.57 111

3Dnovator	96.31 3	97.22 96	97.19 74	97.25 107	98.14 116	97.95 106	98.03 105	96.77 155	96.42 32	97.14 78	95.11 155	97.59 128	95.14 130	97.79 70	97.72 81	98.26 94	97.76 57

MVS_0304		97.18 97	96.84 104	97.58 89	99.15 40	98.19 79	98.11 101	97.81 88	92.36 154	98.06 42	97.43 111	99.06 39	94.24 145	96.80 116	96.54 119	98.12 103	97.52 69

no-one		97.16 98	97.57 61	96.68 132	96.30 199	95.74 183	98.40 91	94.04 211	96.28 37	96.30 117	97.95 97	99.45 10	99.06 4	96.93 112	98.19 59	95.99 186	98.48 29

canonicalmvs		97.11 99	96.88 98	97.38 98	98.34 90	98.72 46	97.52 135	97.94 77	95.60 61	95.01 157	94.58 165	94.50 167	96.59 96	97.84 68	98.03 71	98.90 49	98.91 8

V42		97.10 100	96.97 93	97.26 104	97.64 157	97.60 133	98.45 87	95.99 171	94.44 112	97.35 71	99.40 45	98.63 90	97.34 78	96.33 134	96.38 125	96.82 173	96.00 125

CPTT-MVS		97.08 101	96.25 117	98.05 58	99.21 34	98.30 74	98.54 83	97.98 75	94.28 117	95.89 131	89.57 208	98.54 96	98.18 29	97.82 69	97.32 90	98.54 72	97.91 51

DeepPCF-MVS	94.55 10	97.05 102	97.13 82	96.95 118	96.06 201	97.12 155	98.01 108	95.44 188	95.18 80	97.50 62	97.86 101	98.08 114	97.31 80	97.23 93	97.00 98	97.36 140	97.45 73

QAPM		97.04 103	97.14 79	96.93 120	97.78 155	98.02 99	97.36 150	96.72 156	94.68 96	96.23 118	97.21 118	97.68 125	95.70 118	97.37 89	97.24 95	97.78 117	97.77 56

CNVR-MVS		97.03 104	96.77 108	97.34 100	98.89 61	97.67 130	97.64 127	97.17 139	94.40 113	95.70 140	94.02 173	98.76 78	96.49 103	97.78 71	97.29 94	98.12 103	97.47 72

v148		96.99 105	96.70 110	97.34 100	97.89 142	97.23 147	98.33 92	96.96 145	95.57 64	97.12 81	98.99 61	99.40 13	97.23 81	96.22 139	95.45 157	96.50 178	94.02 171

DELS-MVS		96.90 106	97.24 71	96.50 141	97.85 143	98.18 80	97.88 117	95.92 174	93.48 136	95.34 147	98.86 68	98.94 58	94.03 151	97.33 91	97.04 97	98.00 109	96.85 103
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
MVS_111021_LR		96.86 107	96.72 109	97.03 116	97.80 152	97.06 158	97.04 166	95.51 187	94.55 101	97.47 64	97.35 113	97.68 125	96.66 92	97.11 98	96.73 109	97.69 121	96.57 111

PM-MVS		96.85 108	96.62 112	97.11 111	97.13 182	96.51 167	98.29 95	94.65 204	94.84 91	98.12 37	98.59 78	97.20 135	97.41 74	96.24 138	96.41 124	97.09 162	96.56 113

pmmvs-eth3d		96.84 109	96.22 119	97.56 90	97.63 159	96.38 174	98.74 72	96.91 148	94.63 98	98.26 30	99.43 41	98.28 106	96.58 97	94.52 179	95.54 155	97.24 150	94.75 154

CANet		96.81 110	96.50 113	97.17 110	99.10 49	97.96 104	97.86 119	97.51 106	91.30 166	97.75 51	97.64 105	97.89 120	93.39 157	96.98 109	96.73 109	97.40 134	96.99 93

Fast-Effi-MVS+		96.80 111	95.92 129	97.84 74	98.57 78	97.46 142	98.06 103	98.24 51	89.64 186	97.57 60	96.45 131	97.35 132	96.73 91	97.22 94	96.64 114	97.86 114	96.65 109

MCST-MVS		96.79 112	96.08 122	97.62 86	98.78 70	97.52 140	98.01 108	97.32 135	93.20 141	95.84 133	93.97 175	98.12 112	97.34 78	96.34 132	95.88 149	98.45 84	97.51 70

UGNet		96.79 112	97.82 45	95.58 168	97.57 161	98.39 71	98.48 85	97.84 87	95.85 54	94.68 162	97.91 100	99.07 38	87.12 209	97.71 73	97.51 82	97.80 115	98.29 36
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
TAPA-MVS	93.96 13	96.79 112	96.70 110	96.90 123	97.64 157	97.58 134	97.54 134	94.50 208	95.14 81	96.64 101	96.76 125	97.90 119	96.63 93	95.98 149	96.14 135	98.45 84	97.39 76
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CLD-MVS		96.73 115	96.92 94	96.51 140	98.70 72	97.57 136	97.64 127	92.07 215	93.10 146	96.31 116	98.29 88	99.02 45	95.99 115	97.20 95	96.47 121	98.37 90	96.81 105
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
train_agg		96.68 116	95.93 128	97.56 90	99.08 51	97.16 150	98.44 89	97.37 132	91.12 169	95.18 151	95.43 150	98.48 100	97.36 76	96.48 127	95.52 156	97.95 112	97.34 81

CDPH-MVS		96.68 116	95.99 125	97.48 96	99.13 45	97.64 131	98.08 102	97.46 116	90.56 176	95.13 152	94.87 160	98.27 107	96.56 99	97.09 100	96.45 122	98.54 72	97.08 90

MSLP-MVS++		96.66 118	96.46 116	96.89 124	98.02 126	97.71 129	95.57 200	96.96 145	94.36 115	96.19 122	91.37 198	98.24 108	97.07 84	97.69 74	97.89 75	97.52 127	97.95 47

TinyColmap		96.64 119	96.07 123	97.32 102	97.84 148	96.40 171	97.63 129	96.25 165	95.86 53	98.98 12	97.94 98	96.34 149	96.17 110	97.30 92	95.38 160	97.04 164	93.24 178

IS_MVSNet		96.62 120	96.48 115	96.78 127	98.46 83	98.68 50	98.61 78	98.24 51	92.23 155	89.63 214	95.90 144	94.40 168	96.23 107	98.65 43	98.77 29	99.52 12	96.76 106

NCCC		96.56 121	95.68 131	97.59 88	99.04 53	97.54 139	97.67 124	97.56 104	94.84 91	96.10 125	87.91 211	98.09 113	96.98 87	97.20 95	96.80 108	98.21 99	97.38 79

Effi-MVS+		96.46 122	95.28 137	97.85 73	98.64 77	97.16 150	97.15 163	98.75 20	90.27 179	98.03 44	93.93 176	96.21 150	96.55 100	96.34 132	96.69 112	97.97 111	96.33 118

IterMVS-LS		96.35 123	95.85 130	96.93 120	97.53 162	98.00 101	97.37 148	97.97 76	95.49 72	96.71 99	98.94 63	93.23 174	94.82 133	93.15 197	95.05 165	97.17 159	97.12 89
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
USDC		96.30 124	95.64 133	97.07 113	97.62 160	96.35 176	97.17 161	95.71 183	95.52 69	99.17 6	98.11 95	97.46 129	95.67 120	95.44 164	93.60 183	97.09 162	92.99 183

Vis-MVSNet (Re-imp)		96.29 125	96.50 113	96.05 155	97.96 137	97.83 123	97.30 152	97.86 84	93.14 143	88.90 218	96.80 124	95.28 159	95.15 128	98.37 57	98.25 54	99.12 30	95.84 127

MSDG		96.27 126	96.17 121	96.38 147	97.85 143	96.27 177	96.55 178	94.41 209	94.55 101	95.62 142	97.56 108	97.80 121	96.22 108	97.17 97	96.27 128	97.67 123	93.60 174

CNLPA		96.24 127	95.97 126	96.57 137	97.48 169	97.10 157	96.75 172	94.95 198	94.92 89	96.20 121	94.81 161	96.61 145	96.25 106	96.94 111	95.64 153	97.79 116	95.74 133

PLC	92.55 15	96.10 128	95.36 134	96.96 117	98.13 119	96.88 161	96.49 179	96.67 160	94.07 123	95.71 139	91.14 199	96.09 153	96.84 89	96.70 120	96.58 118	97.92 113	96.03 124
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test20.03		96.08 129	96.80 106	95.25 177	99.19 37	97.58 134	97.24 158	97.56 104	94.95 88	91.91 204	98.58 79	98.03 116	87.88 205	97.43 86	96.94 100	97.69 121	94.05 170

TSAR-MVS + COLMAP		96.05 130	95.94 127	96.18 150	97.46 170	96.41 170	97.26 157	95.83 178	94.69 95	95.30 148	98.31 87	96.52 146	94.71 136	95.48 163	94.87 167	96.54 177	95.33 140

EU-MVSNet		96.03 131	96.23 118	95.80 162	95.48 215	94.18 193	98.99 39	91.51 217	97.22 22	97.66 54	99.15 57	98.51 98	98.08 32	95.92 150	92.88 191	93.09 202	95.72 134

PCF-MVS	92.69 14	95.98 132	95.05 144	97.06 114	98.43 85	97.56 137	97.76 121	96.65 161	89.95 184	95.70 140	96.18 137	98.48 100	95.74 117	93.64 191	93.35 187	98.09 106	96.18 120
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
HQP-MVS		95.97 133	95.01 146	97.08 112	98.72 71	97.19 149	97.07 165	96.69 159	91.49 164	95.77 136	92.19 191	97.93 118	96.15 111	94.66 175	94.16 174	98.10 105	97.45 73

Effi-MVS+-dtu		95.94 134	95.08 143	96.94 119	98.54 79	97.38 143	96.66 175	97.89 82	88.68 189	95.92 129	92.90 185	97.28 133	94.18 150	96.68 121	96.13 137	98.45 84	96.51 115

conf0.05thres1000		95.91 135	94.67 151	97.37 99	98.54 79	98.73 44	98.41 90	98.07 69	96.10 41	94.93 159	92.83 186	80.67 211	95.26 125	98.68 40	98.65 35	98.99 39	97.02 92

AdaColmap		95.85 136	94.65 152	97.26 104	98.70 72	97.20 148	97.33 151	97.30 136	91.28 167	95.90 130	88.16 210	96.17 152	96.60 95	97.34 90	96.82 104	97.71 118	95.60 136

FMVSNet2		95.77 137	96.20 120	95.27 175	96.77 191	98.18 80	97.28 153	97.90 79	93.12 144	91.37 205	98.25 90	96.05 154	90.04 189	94.96 173	95.94 146	98.28 91	96.90 96

OpenMVS	94.63 9	95.75 138	95.04 145	96.58 136	97.85 143	97.55 138	96.71 174	96.07 169	90.15 182	96.47 106	90.77 204	95.95 155	94.41 142	97.01 108	96.95 99	98.00 109	96.90 96

pmmvs5		95.70 139	95.22 138	96.26 148	96.55 196	97.24 146	97.50 136	94.99 197	90.95 171	96.87 91	98.47 83	97.40 130	94.45 140	92.86 199	94.98 166	97.23 151	94.64 157

Anonymous20231206		95.69 140	95.68 131	95.70 164	98.32 94	96.95 159	97.37 148	96.65 161	93.33 138	93.61 183	98.70 77	98.03 116	91.04 179	95.07 169	94.59 173	97.20 153	93.09 181

MAR-MVS		95.51 141	94.49 155	96.71 129	97.92 139	96.40 171	96.72 173	98.04 72	86.74 211	96.72 96	92.52 189	95.14 161	94.02 152	96.81 115	96.54 119	96.85 169	97.25 83
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
DI_MVS_plusplus_trai		95.48 142	94.51 154	96.61 134	97.13 182	97.30 144	98.05 104	96.79 154	93.75 131	95.08 155	96.38 132	89.76 188	94.95 131	93.97 190	94.82 170	97.64 125	95.63 135

MDA-MVSNet-bldmvs		95.45 143	95.20 139	95.74 163	94.24 223	96.38 174	97.93 112	94.80 199	95.56 67	96.87 91	98.29 88	95.24 160	96.50 102	98.65 43	90.38 204	94.09 195	91.93 188

PVSNet_BlendedMVS		95.44 144	95.09 141	95.86 160	97.31 176	97.13 153	96.31 186	95.01 195	88.55 192	96.23 118	94.55 168	97.75 122	92.56 169	96.42 129	95.44 158	97.71 118	95.81 128

PVSNet_Blended		95.44 144	95.09 141	95.86 160	97.31 176	97.13 153	96.31 186	95.01 195	88.55 192	96.23 118	94.55 168	97.75 122	92.56 169	96.42 129	95.44 158	97.71 118	95.81 128

pmmvs4		95.37 146	94.25 156	96.67 133	97.01 185	95.28 187	97.60 130	96.07 169	93.11 145	97.29 74	98.09 96	94.23 170	95.21 127	91.56 208	93.91 180	96.82 173	93.59 175

MVS_Test		95.34 147	94.88 148	95.89 158	96.93 187	96.84 164	96.66 175	97.08 141	90.06 183	94.02 175	97.61 106	96.64 144	93.59 156	92.73 201	94.02 178	97.03 165	96.24 119

GBi-Net		95.21 148	95.35 135	95.04 178	96.77 191	98.18 80	97.28 153	97.58 101	88.43 194	90.28 210	96.01 140	92.43 177	90.04 189	97.67 76	97.86 77	98.28 91	96.90 96

test1		95.21 148	95.35 135	95.04 178	96.77 191	98.18 80	97.28 153	97.58 101	88.43 194	90.28 210	96.01 140	92.43 177	90.04 189	97.67 76	97.86 77	98.28 91	96.90 96

tfpn_n400		95.11 150	93.86 161	96.57 137	98.16 114	97.92 112	97.59 131	97.90 79	95.90 51	92.83 200	89.94 205	83.01 202	94.23 147	97.50 84	97.43 85	98.73 61	95.30 143

tfpnconf		95.11 150	93.86 161	96.57 137	98.16 114	97.92 112	97.59 131	97.90 79	95.90 51	92.83 200	89.94 205	83.01 202	94.23 147	97.50 84	97.43 85	98.73 61	95.30 143

HyFIR lowres test		95.05 152	93.54 167	96.81 126	97.81 151	96.88 161	98.18 97	97.46 116	94.28 117	94.98 158	96.57 129	92.89 176	96.15 111	90.90 213	91.87 198	96.28 183	91.35 189

CHOSEN 1792x2688		94.98 153	94.69 150	95.31 173	97.27 178	95.58 184	97.90 115	95.56 186	95.03 85	93.77 182	95.65 147	99.29 17	95.30 124	91.51 209	91.28 201	92.05 211	94.50 160

CANet_DTU		94.96 154	94.62 153	95.35 172	98.03 125	96.11 179	96.92 167	95.60 185	88.59 191	97.27 75	95.27 153	96.50 147	88.77 200	95.53 160	95.59 154	95.54 189	94.78 153

tfpnview11		94.92 155	93.56 166	96.50 141	98.12 120	97.99 102	97.48 138	97.86 84	94.50 108	92.83 200	89.94 205	83.01 202	94.19 149	96.91 113	98.07 70	98.50 78	94.53 158

CDS-MVSNet		94.91 156	95.17 140	94.60 186	97.85 143	96.21 178	96.90 168	96.39 164	90.81 173	93.40 189	97.24 117	94.54 166	85.78 215	96.25 137	96.15 131	97.26 149	95.01 148
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MS-PatchMatch		94.84 157	94.76 149	94.94 181	96.38 198	94.69 192	95.90 192	94.03 212	92.49 152	93.81 179	95.79 145	96.38 148	94.54 138	94.70 174	94.85 168	94.97 192	94.43 162

testgi		94.81 158	96.05 124	93.35 198	99.06 52	96.87 163	97.57 133	96.70 158	95.77 57	88.60 220	93.19 183	98.87 63	81.21 225	97.03 107	96.64 114	96.97 168	93.99 172

PatchMatch-RL		94.79 159	93.75 165	96.00 156	96.80 190	95.00 188	95.47 204	95.25 192	90.68 175	95.80 135	92.97 184	93.64 172	95.67 120	96.13 141	95.81 150	96.99 167	92.01 187

FPMVS		94.70 160	94.99 147	94.37 188	95.84 208	93.20 199	96.00 191	91.93 216	95.03 85	94.64 164	94.68 163	93.29 173	90.95 180	98.07 65	97.34 89	96.85 169	93.29 176

view800		94.54 161	92.55 177	96.86 125	98.28 99	98.22 77	97.97 110	97.62 99	92.10 157	94.19 173	85.52 217	81.33 210	94.61 137	97.41 87	98.51 37	98.50 78	94.72 155

new-patchmatchnet		94.48 162	94.02 158	95.02 180	97.51 168	95.00 188	95.68 199	94.26 210	97.32 21	95.73 137	99.60 21	98.22 111	91.30 175	94.13 187	84.41 216	95.65 188	89.45 200

IterMVS		94.48 162	93.46 169	95.66 165	97.52 163	96.43 168	97.20 159	94.73 202	92.91 150	96.44 107	98.75 74	91.10 184	94.53 139	92.10 205	90.10 206	93.51 197	92.84 184
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MDTV_nov1_ep13_2view		94.39 164	93.34 170	95.63 166	97.23 179	95.33 186	97.76 121	96.84 152	94.55 101	97.47 64	98.96 62	97.70 124	93.88 153	92.27 203	86.81 214	90.56 214	87.73 210

tfpn1000		94.36 165	93.33 172	95.56 170	98.09 122	98.07 93	97.08 164	97.78 91	94.02 125	89.16 217	91.38 197	80.56 212	92.54 171	96.76 117	98.09 62	98.69 64	94.40 165

view600		94.36 165	92.33 182	96.73 128	98.14 116	98.03 98	97.88 117	97.36 133	91.61 161	94.29 170	84.38 219	82.08 207	94.31 144	97.05 101	98.75 31	98.42 87	94.41 163

Fast-Effi-MVS+-dtu		94.34 167	93.26 173	95.62 167	97.82 149	95.97 181	95.86 193	99.01 13	86.88 209	93.39 190	90.83 202	95.46 158	90.61 184	94.46 182	94.68 171	97.01 166	94.51 159

thres600view7		94.34 167	92.31 183	96.70 130	98.19 109	98.12 89	97.85 120	97.45 121	91.49 164	93.98 177	84.27 220	82.02 208	94.24 145	97.04 102	98.76 30	98.49 80	94.47 161

diffmvs		94.34 167	93.83 164	94.93 182	96.41 197	94.88 190	96.41 180	96.09 168	93.24 140	93.79 181	98.12 94	92.20 180	91.98 172	90.79 214	92.20 195	94.91 194	95.35 139

EPNet		94.33 170	93.52 168	95.27 175	98.81 69	94.71 191	96.77 171	98.20 56	88.12 197	96.53 104	92.53 188	91.19 183	85.25 219	95.22 167	95.26 162	96.09 185	97.63 64
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
GA-MVS		94.18 171	92.98 174	95.58 168	97.36 174	96.42 169	96.21 189	95.86 175	90.29 178	95.08 155	96.19 136	85.37 192	92.82 162	94.01 189	94.14 175	96.16 184	94.41 163

gg-mvs-nofinetune		94.13 172	93.93 160	94.37 188	97.99 130	95.86 182	95.45 207	99.22 9	97.61 18	95.10 154	99.50 33	84.50 193	81.73 224	95.31 165	94.12 176	96.71 176	90.59 193

FMVSNet3		94.06 173	93.85 163	94.31 191	95.46 216	97.80 127	96.34 183	97.58 101	88.43 194	90.28 210	96.01 140	92.43 177	88.67 201	91.82 206	93.96 179	97.53 126	96.50 116

thres400		94.04 174	91.94 187	96.50 141	97.98 136	97.82 125	97.66 126	96.96 145	90.96 170	94.20 171	83.24 222	82.82 205	93.80 154	96.50 126	98.09 62	98.38 89	94.15 169

CVMVSNet		94.01 175	94.25 156	93.73 195	94.36 222	92.44 204	97.45 144	88.56 222	95.59 62	93.06 198	98.88 64	90.03 187	94.84 132	94.08 188	93.45 184	94.09 195	95.31 141

thres200		93.98 176	91.90 188	96.40 146	97.66 156	98.12 89	97.20 159	97.45 121	90.16 181	93.82 178	83.08 223	83.74 198	93.80 154	97.04 102	97.48 84	98.49 80	93.70 173

tfpn200view9		93.80 177	91.75 189	96.20 149	97.52 163	98.15 85	97.48 138	97.47 115	87.65 200	93.56 185	83.03 224	84.12 194	92.62 164	97.04 102	98.09 62	98.52 75	94.17 166

conf200view11		93.79 178	91.75 189	96.17 151	97.52 163	98.15 85	97.48 138	97.48 113	87.65 200	93.42 187	83.03 224	84.12 194	92.62 164	97.04 102	98.09 62	98.52 75	94.17 166

tfpn111		93.73 179	91.63 191	96.17 151	97.52 163	98.15 85	97.48 138	97.48 113	87.65 200	93.42 187	82.19 227	84.12 194	92.62 164	97.04 102	98.09 62	98.52 75	94.17 166

MIMVSNet		93.68 180	93.96 159	93.35 198	97.82 149	96.08 180	96.34 183	98.46 31	91.28 167	86.67 229	94.95 159	94.87 163	84.39 220	94.53 177	94.65 172	96.45 180	91.34 190

EPNet_dtu		93.45 181	92.51 180	94.55 187	98.39 87	91.67 214	95.46 205	97.50 108	86.56 214	97.38 69	93.52 178	94.20 171	85.82 214	93.31 194	92.53 192	92.72 205	95.76 132
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
IB-MVS	92.44 16	93.33 182	92.15 185	94.70 184	97.42 171	96.39 173	95.57 200	94.67 203	86.40 217	93.59 184	78.28 233	95.76 157	89.59 195	95.88 152	95.98 142	97.39 136	96.34 117
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
tfpn_ndepth		93.27 183	92.11 186	94.61 185	96.96 186	97.93 111	96.87 169	97.49 111	90.91 172	87.89 225	85.98 215	83.53 199	89.77 193	95.91 151	97.31 92	98.67 66	93.25 177

thres100view900		92.93 184	90.89 195	95.31 173	97.52 163	96.82 165	96.41 180	95.08 193	87.65 200	93.56 185	83.03 224	84.12 194	91.12 178	94.53 177	96.91 102	98.17 102	93.21 179

tfpn		92.86 185	89.37 202	96.93 120	98.40 86	98.34 73	98.02 107	97.80 89	92.54 151	93.99 176	86.54 214	57.58 235	94.82 133	97.66 79	97.99 73	98.56 70	94.95 152

N_pmnet		92.46 186	92.38 181	92.55 205	97.91 140	93.47 198	97.42 146	94.01 213	96.40 34	88.48 221	98.50 81	98.07 115	88.14 204	91.04 212	84.30 217	89.35 220	84.85 219

TAMVS		92.46 186	93.34 170	91.44 215	97.03 184	93.84 197	94.68 217	90.60 219	90.44 177	85.31 230	97.14 119	93.03 175	85.78 215	94.34 184	93.67 182	95.22 191	90.93 192

test1235678		92.36 188	92.55 177	92.13 209	97.16 180	92.69 202	96.32 185	94.62 205	86.69 212	88.16 223	97.28 115	97.13 139	83.28 222	94.54 176	93.40 185	93.26 198	86.11 216

testmv		92.35 189	92.53 179	92.13 209	97.16 180	92.68 203	96.31 186	94.61 207	86.68 213	88.16 223	97.27 116	97.09 140	83.28 222	94.52 179	93.39 186	93.26 198	86.10 217

CMPMVS	71.81 19	92.34 190	92.85 175	91.75 213	92.70 228	90.43 221	88.84 233	88.56 222	85.87 218	94.35 169	90.98 200	95.89 156	91.14 177	96.14 140	94.83 169	94.93 193	95.78 131
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
LP		92.03 191	90.19 198	94.17 192	94.52 221	93.87 196	96.79 170	95.05 194	93.58 134	95.62 142	95.68 146	83.37 201	91.78 173	90.73 215	86.99 213	91.27 212	87.09 213

MVSTER		91.97 192	90.31 196	93.91 193	96.81 189	96.91 160	94.22 218	95.64 184	84.98 220	92.98 199	93.42 179	72.56 224	86.64 213	95.11 168	93.89 181	97.16 160	95.31 141

CR-MVSNet		91.94 193	88.50 204	95.94 157	96.14 200	92.08 208	95.23 211	98.47 28	84.30 224	96.44 107	94.58 165	75.57 218	92.92 159	90.22 216	92.22 193	96.43 181	90.56 194

conf0.01		91.86 194	88.22 205	96.10 153	97.40 172	97.94 109	97.48 138	97.41 128	87.65 200	93.22 193	80.39 229	63.83 231	92.62 164	96.63 123	98.09 62	98.47 82	93.03 182

gm-plane-assit		91.85 195	87.91 208	96.44 145	99.14 43	98.25 76	99.02 33	97.38 130	95.57 64	98.31 29	99.34 49	51.00 240	88.93 198	93.16 196	91.57 199	95.85 187	86.50 215

thresconf0.02		91.75 196	88.21 206	95.87 159	97.38 173	97.14 152	97.27 156	96.85 151	93.04 147	92.39 203	82.19 227	63.31 232	93.10 158	94.43 183	95.06 164	98.23 98	92.32 186

PMMVS		91.67 197	91.47 193	91.91 212	89.43 234	88.61 229	94.99 214	85.67 228	87.50 206	93.80 180	94.42 171	94.88 162	90.71 183	92.26 204	92.96 190	96.83 171	89.65 198

CHOSEN 280x420		91.55 198	90.27 197	93.05 201	94.61 220	88.01 230	96.56 177	94.62 205	88.04 198	94.20 171	92.66 187	86.60 190	90.82 181	95.06 170	91.89 197	87.49 227	89.61 199

PatchT		91.40 199	88.54 203	94.74 183	91.48 233	92.18 207	97.42 146	97.51 106	84.96 221	96.44 107	94.16 172	75.47 219	92.92 159	90.22 216	92.22 193	92.66 208	90.56 194

pmmvs3		91.20 200	91.40 194	90.96 217	91.71 232	91.08 217	95.41 208	81.34 232	87.36 207	94.57 165	95.02 157	94.30 169	90.42 185	94.28 185	89.26 208	92.30 210	88.49 206

test0.0.03 1		91.17 201	91.50 192	90.80 218	98.01 128	95.46 185	94.22 218	95.80 179	86.55 215	81.75 235	90.83 202	87.93 189	78.48 228	94.51 181	94.11 177	96.50 178	91.08 191

conf0.002		91.12 202	86.87 216	96.08 154	97.35 175	97.89 118	97.48 138	97.38 130	87.65 200	93.19 194	79.38 231	57.48 236	92.62 164	96.56 125	96.64 114	98.46 83	92.50 185

new_pmnet		90.85 203	92.26 184	89.21 224	93.68 226	89.05 227	93.20 227	84.16 231	92.99 148	84.25 231	97.72 104	94.60 165	86.80 212	93.20 195	91.30 200	93.21 200	86.94 214

RPMNet		90.52 204	86.27 220	95.48 171	95.95 205	92.08 208	95.55 203	98.12 65	84.30 224	95.60 144	87.49 213	72.78 223	91.24 176	87.93 220	89.34 207	96.41 182	89.98 197

MDTV_nov1_ep13		90.30 205	87.32 214	93.78 194	96.00 203	92.97 200	95.46 205	95.39 189	88.61 190	95.41 146	94.45 170	80.39 213	89.87 192	86.58 223	83.54 220	90.56 214	84.71 220

testus		90.01 206	90.03 199	89.98 220	95.89 206	91.43 216	93.88 221	89.30 221	83.54 226	89.68 213	87.81 212	94.62 164	78.31 229	92.87 198	92.01 196	92.85 204	87.91 209

PatchmatchNet		89.98 207	86.23 221	94.36 190	96.56 195	91.90 213	96.07 190	96.72 156	90.18 180	96.87 91	93.36 182	78.06 217	91.46 174	84.71 229	81.40 225	88.45 223	83.97 224
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ADS-MVSNet		89.89 208	87.70 209	92.43 207	95.52 213	90.91 219	95.57 200	95.33 190	93.19 142	91.21 206	93.41 180	82.12 206	89.05 196	86.21 224	83.77 219	87.92 224	84.31 221

tpm		89.84 209	86.81 217	93.36 197	96.60 194	91.92 212	95.02 213	97.39 129	86.79 210	96.54 103	95.03 156	69.70 227	87.66 206	88.79 219	86.19 215	86.95 229	89.27 201

test-LLR		89.77 210	87.47 212	92.45 206	98.01 128	89.77 223	93.25 225	95.80 179	81.56 230	89.19 215	92.08 192	79.59 214	85.77 217	91.47 210	89.04 211	92.69 206	88.75 203

FMVSNet5		89.65 211	87.60 211	92.04 211	95.63 212	96.61 166	94.82 216	94.75 200	80.11 233	87.72 226	77.73 234	73.81 222	83.81 221	95.64 157	96.08 140	95.49 190	93.21 179

EPMVS		89.28 212	86.28 219	92.79 204	96.01 202	92.00 211	95.83 194	95.85 177	90.78 174	91.00 207	94.58 165	74.65 220	88.93 198	85.00 227	82.88 223	89.09 221	84.09 223

test-mter		89.16 213	88.14 207	90.37 219	94.79 219	91.05 218	93.60 224	85.26 229	81.65 229	88.32 222	92.22 190	79.35 216	87.03 210	92.28 202	90.12 205	93.19 201	90.29 196

CostFormer		89.06 214	85.65 222	93.03 203	95.88 207	92.40 205	95.30 210	95.86 175	86.49 216	93.12 197	93.40 181	74.18 221	88.25 203	82.99 230	81.46 224	89.77 218	88.66 205

MVS-HIRNet		88.72 215	86.49 218	91.33 216	91.81 231	85.66 231	87.02 235	96.25 165	81.48 232	94.82 160	96.31 135	92.14 181	90.32 187	87.60 221	83.82 218	87.74 225	78.42 230

tpmp4_e23		88.68 216	84.61 224	93.43 196	96.00 203	91.46 215	95.40 209	96.60 163	87.71 199	94.67 163	88.54 209	69.81 226	88.41 202	85.50 226	81.08 226	89.52 219	88.18 208

1111		88.65 217	87.69 210	89.78 223	98.84 65	94.02 194	95.79 195	98.19 58	91.57 162	82.27 232	98.19 91	53.19 238	74.80 230	94.98 171	93.04 189	88.80 222	88.82 202

TESTMET0.1,1		88.60 218	87.47 212	89.93 222	94.23 224	89.77 223	93.25 225	84.47 230	81.56 230	89.19 215	92.08 192	79.59 214	85.77 217	91.47 210	89.04 211	92.69 206	88.75 203

dps		88.36 219	84.32 226	93.07 200	93.86 225	92.29 206	94.89 215	95.93 173	83.50 227	93.13 195	91.87 194	67.79 229	90.32 187	85.99 225	83.22 221	90.28 217	85.56 218

test12356		88.21 220	89.73 200	86.43 228	91.94 230	89.52 226	91.79 228	86.07 227	85.51 219	81.97 234	95.56 149	96.20 151	79.11 227	94.14 186	90.94 202	87.70 226	76.23 231

tpmrst		87.60 221	84.13 227	91.66 214	95.65 211	89.73 225	93.77 222	94.74 201	88.85 188	93.35 192	95.60 148	72.37 225	87.40 207	81.24 232	78.19 228	85.02 232	82.90 228

tpm cat1		87.19 222	82.78 228	92.33 208	95.66 210	90.61 220	94.19 220	95.27 191	86.97 208	94.38 168	90.91 201	69.40 228	87.21 208	79.57 233	77.82 229	87.25 228	84.18 222

E-PMN		86.94 223	85.10 223	89.09 226	95.77 209	83.54 234	89.89 231	86.55 224	92.18 156	87.34 227	94.02 173	83.42 200	89.63 194	93.32 193	77.11 230	85.33 230	72.09 232

DWT-MVSNet_training		86.69 224	81.24 230	93.05 201	95.31 218	92.06 210	95.75 197	91.51 217	84.32 223	94.49 166	83.46 221	55.37 237	90.81 182	82.76 231	83.19 222	90.45 216	87.52 211

EMVS		86.63 225	84.48 225	89.15 225	95.51 214	83.66 233	90.19 230	86.14 226	91.78 160	88.68 219	93.83 177	81.97 209	89.05 196	92.76 200	76.09 231	85.31 231	71.28 233

PMMVS2		86.47 226	92.62 176	79.29 230	92.01 229	85.63 232	93.74 223	86.37 225	93.95 128	54.18 239	98.19 91	97.39 131	58.46 233	96.57 124	93.07 188	90.99 213	83.55 226

test2356		85.48 227	81.66 229	89.94 221	95.36 217	88.71 228	91.69 229	92.78 214	78.28 235	86.79 228	85.80 216	58.29 234	80.44 226	89.39 218	89.17 209	92.60 209	81.98 229

MVE	72.99 18	85.37 228	89.43 201	80.63 229	74.43 235	71.94 237	88.25 234	89.81 220	93.27 139	67.32 237	96.32 134	91.83 182	90.40 186	93.36 192	90.79 203	73.55 235	88.49 206
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testpf		81.59 229	76.31 231	87.75 227	93.50 227	83.16 235	89.19 232	95.94 172	73.85 236	90.39 208	80.32 230	61.17 233	73.99 232	76.52 234	75.82 232	83.50 233	83.33 227

.test1245		69.06 230	63.57 232	75.47 231	98.84 65	94.02 194	95.79 195	98.19 58	91.57 162	82.27 232	98.19 91	53.19 238	74.80 230	94.98 171	5.51 234	2.94 237	7.51 234

GG-mvs-BLEND		61.03 231	87.02 215	30.71 233	0.74 239	90.01 222	78.90 237	0.74 237	84.56 222	9.46 240	79.17 232	90.69 186	1.37 237	91.74 207	89.13 210	93.04 203	83.83 225

testmvs		4.99 232	6.88 233	2.78 235	1.73 237	2.04 240	3.10 240	1.71 235	7.27 237	3.92 242	12.18 236	6.71 241	3.31 236	6.94 235	5.51 234	2.94 237	7.51 234

test123		4.41 233	5.71 234	2.88 234	1.28 238	2.21 239	3.09 241	1.65 236	6.35 238	4.98 241	8.53 237	3.88 242	3.46 235	5.79 236	5.71 233	2.85 239	7.50 236

sosnet-low-res		0.00 234	0.00 235	0.00 236	0.00 240	0.00 241	0.00 242	0.00 238	0.00 239	0.00 243	0.00 238	0.00 243	0.00 238	0.00 237	0.00 236	0.00 240	0.00 237

sosnet		0.00 234	0.00 235	0.00 236	0.00 240	0.00 241	0.00 242	0.00 238	0.00 239	0.00 243	0.00 238	0.00 243	0.00 238	0.00 237	0.00 236	0.00 240	0.00 237

ambc			96.78 107		99.01 54	97.11 156	95.73 198		95.91 50	99.25 2	98.56 80	97.17 136	97.04 85	96.76 117	95.22 163	96.72 175	96.73 107

MTAPA										97.43 67		99.27 21

MTMP										97.63 55		99.03 44

Patchmatch-RL test							17.42 239

tmp_tt				45.72 232	60.00 236	38.74 238	45.50 238	12.18 234	79.58 234	68.42 236	67.62 235	65.04 230	22.12 234	84.83 228	78.72 227	66.08 236

XVS					99.48 18	98.76 37	99.22 24			96.40 111		98.78 74				98.94 47

X-MVStestdata					99.48 18	98.76 37	99.22 24			96.40 111		98.78 74				98.94 47

abl_6				96.45 144	97.79 154	97.28 145	97.16 162	96.16 167	89.92 185	95.72 138	91.59 195	97.16 137	94.37 143			97.51 128	95.49 138

mPP-MVS					99.58 6							98.98 49

NP-MVS									89.27 187

Patchmtry						92.70 201	95.23 211	98.47 28		96.44 107

DeepMVS_CX						72.99 236	80.14 236	37.34 233	83.46 228	60.13 238	84.40 218	85.48 191	86.93 211	87.22 222		79.61 234	87.32 212

High-resolution multi-view benchmark