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	95.06 1	97.73 1	98.39 2	96.95 1	96.33 47	96.94 31	98.30 22	94.90 15	98.61 2	97.73 3	97.97 32	98.57 28	95.74 7	99.24 1	98.70 4	98.72 7	98.70 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
TDRefinement		97.59 2	98.32 3	96.73 4	95.90 60	98.10 2	99.08 2	93.92 32	98.24 4	96.44 15	98.12 27	97.86 68	96.06 2	99.24 1	98.93 1	99.00 2	97.77 5

WR-MVS		97.53 3	98.20 4	96.76 3	96.93 26	98.17 1	98.60 11	96.67 6	96.39 13	94.46 44	99.14 1	98.92 13	94.57 18	99.06 3	98.80 2	99.32 1	96.92 26

SixPastTwentyTwo		97.36 4	97.73 10	96.92 2	97.36 12	96.15 50	98.29 23	94.43 23	96.50 11	96.96 8	98.74 8	98.74 20	96.04 3	99.03 5	97.74 17	98.44 23	97.22 12

PS-CasMVS		97.22 5	97.84 7	96.50 5	97.08 22	97.92 6	98.17 28	97.02 2	94.71 27	95.32 24	98.52 15	98.97 12	92.91 42	99.04 4	98.47 6	98.49 19	97.24 11

PEN-MVS		97.16 6	97.87 6	96.33 12	97.20 19	97.97 4	98.25 25	96.86 5	95.09 25	94.93 36	98.66 11	99.16 8	92.27 52	98.98 6	98.39 8	98.49 19	96.83 30

DTE-MVSNet		97.16 6	97.75 9	96.47 6	97.40 11	97.95 5	98.20 27	96.89 4	95.30 20	95.15 28	98.66 11	98.80 18	92.77 46	98.97 7	98.27 10	98.44 23	96.28 40

COLMAP_ROB	93.74 2	97.09 8	97.98 5	96.05 18	95.97 57	97.78 9	98.56 12	91.72 72	97.53 7	96.01 17	98.14 26	98.76 19	95.28 8	98.76 11	98.23 11	98.77 5	96.67 35
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
WR-MVS_H		97.06 9	97.78 8	96.23 14	96.74 35	98.04 3	98.25 25	97.32 1	94.40 34	93.71 64	98.55 14	98.89 14	92.97 39	98.91 9	98.45 7	98.38 28	97.19 13

CP-MVSNet		96.97 10	97.42 13	96.44 7	97.06 23	97.82 8	98.12 30	96.98 3	93.50 45	95.21 26	97.98 31	98.44 32	92.83 45	98.93 8	98.37 9	98.46 22	96.91 27

ACMH	90.17 8	96.61 11	97.69 11	95.35 30	95.29 74	96.94 31	98.43 16	92.05 64	98.04 5	95.38 22	98.07 29	99.25 7	93.23 36	98.35 16	97.16 35	97.72 45	96.00 45
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20231211		96.59 12	98.43 1	94.44 50	95.89 62	96.12 51	95.23 115	95.91 8	99.42 1	92.75 84	98.87 5	99.94 1	88.19 121	98.64 13	98.50 5	98.66 10	97.49 8

UA-Net		96.56 13	96.73 23	96.36 10	98.99 1	97.90 7	97.79 41	95.64 10	92.78 60	92.54 89	96.23 78	95.02 134	94.31 21	98.43 15	98.12 12	98.89 3	98.58 2

ACMMPR		96.54 14	96.71 24	96.35 11	97.55 9	97.63 11	98.62 10	94.54 18	94.45 31	94.19 50	95.04 103	97.35 75	94.92 13	97.85 32	97.50 23	98.26 29	97.17 14

v7n		96.49 15	97.20 18	95.65 23	95.57 70	96.04 53	97.93 35	92.49 50	96.40 12	97.13 7	98.99 4	99.41 4	93.79 28	97.84 34	96.15 53	97.00 68	95.60 53

DeepC-MVS	92.47 4	96.44 16	96.75 22	96.08 17	97.57 7	97.19 27	97.96 34	94.28 24	95.29 21	94.92 37	98.31 22	96.92 85	93.69 29	96.81 58	96.50 45	98.06 38	96.27 41
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
v52		96.35 17	97.40 14	95.12 39	93.83 118	95.54 67	97.82 39	88.95 138	96.27 14	97.22 5	99.11 2	99.40 5	95.80 5	98.16 19	96.37 48	97.10 63	96.96 22

V4		96.35 17	97.40 14	95.12 39	93.83 118	95.54 67	97.82 39	88.95 138	96.27 14	97.21 6	99.10 3	99.40 5	95.79 6	98.17 18	96.37 48	97.10 63	96.96 22

ACMM	90.06 9	96.31 19	96.42 30	96.19 15	97.21 18	97.16 29	98.71 5	93.79 36	94.35 35	93.81 60	92.80 132	98.23 44	95.11 9	98.07 23	97.45 25	98.51 18	96.86 29
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	89.90 10	96.27 20	97.52 12	94.81 46	95.19 76	97.18 28	97.97 33	92.52 48	96.72 9	90.50 130	97.31 59	99.11 9	94.10 23	98.67 12	97.90 15	98.56 16	95.79 49

APDe-MVS		96.23 21	97.22 17	95.08 41	96.66 39	97.56 14	98.63 9	93.69 38	94.62 28	89.80 139	97.73 43	98.13 52	93.84 27	97.79 36	97.63 19	97.87 43	97.08 18

CP-MVS		96.21 22	96.16 41	96.27 13	97.56 8	97.13 30	98.43 16	94.70 17	92.62 62	94.13 52	92.71 133	98.03 58	94.54 19	98.00 27	97.60 20	98.23 30	97.05 19

MPTG		96.18 23	96.01 43	96.38 8	98.30 2	96.18 49	98.51 14	94.48 22	94.56 29	94.81 42	91.73 142	96.96 83	94.30 22	98.09 21	97.83 16	97.91 42	96.73 32

HFP-MVS		96.18 23	96.53 28	95.77 21	97.34 15	97.26 24	98.16 29	94.54 18	94.45 31	92.52 90	95.05 101	96.95 84	93.89 26	97.28 43	97.46 24	98.19 31	97.25 9

MP-MVS		96.13 25	95.93 46	96.37 9	98.19 4	97.31 22	98.49 15	94.53 21	91.39 96	94.38 47	94.32 115	96.43 100	94.59 17	97.75 38	97.44 26	98.04 39	96.88 28

ACMMP		96.12 26	96.27 37	95.93 19	97.20 19	97.60 12	98.64 8	93.74 37	92.47 64	93.13 79	93.23 127	98.06 55	94.51 20	97.99 28	97.57 22	98.39 27	96.99 20
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
LGP-MVS_train		96.10 27	96.29 35	95.87 20	96.72 36	97.35 21	98.43 16	93.83 35	90.81 111	92.67 88	95.05 101	98.86 16	95.01 10	98.11 20	97.37 31	98.52 17	96.50 37

CSCG		96.07 28	97.15 19	94.81 46	96.06 55	97.58 13	96.52 76	90.98 88	96.51 10	93.60 67	97.13 64	98.55 30	93.01 38	97.17 46	95.36 71	98.68 9	97.78 4

v748		96.05 29	97.00 20	94.95 44	94.41 92	94.77 96	96.72 65	91.03 87	96.12 16	96.71 11	98.74 8	99.59 2	93.55 31	97.97 29	95.96 57	97.28 56	95.84 48

TSAR-MVS + MP.		95.99 30	96.57 27	95.31 32	96.87 27	96.50 42	98.71 5	91.58 75	93.25 51	92.71 85	96.86 68	96.57 96	93.92 24	98.09 21	97.91 14	98.08 36	96.81 31

OPM-MVS		95.96 31	96.59 26	95.23 35	96.67 38	96.52 41	97.86 37	93.28 42	95.27 23	93.46 69	96.26 75	98.85 17	92.89 43	97.09 47	96.37 48	97.22 60	95.78 50

SteuartSystems-ACMMP		95.96 31	96.13 42	95.76 22	97.06 23	97.36 20	98.40 20	94.24 26	91.49 88	91.91 104	94.50 111	96.89 86	94.99 11	98.01 26	97.44 26	97.97 41	97.25 9
Skip Steuart: Steuart Systems R&D Blog.
ACMP	89.62 11	95.96 31	96.28 36	95.59 24	96.58 41	97.23 26	98.26 24	93.22 43	92.33 69	92.31 96	94.29 116	98.73 21	94.68 15	98.04 24	97.14 36	98.47 21	96.17 43
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PGM-MVS		95.90 34	95.72 49	96.10 16	97.53 10	97.45 19	98.55 13	94.12 29	90.25 114	93.71 64	93.20 128	97.18 79	94.63 16	97.68 39	97.34 32	98.08 36	96.97 21

PMVS	87.16 16	95.88 35	96.47 29	95.19 37	97.00 25	96.02 54	96.70 66	91.57 76	94.43 33	95.33 23	97.16 63	95.37 123	92.39 49	98.89 10	98.72 3	98.17 33	94.71 68
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
ACMMP_Plus		95.86 36	96.18 38	95.47 29	97.11 21	97.26 24	98.37 21	93.48 41	93.49 46	93.99 55	95.61 85	94.11 143	92.49 47	97.87 31	97.44 26	97.40 52	97.52 7

Gipuma		95.86 36	96.17 39	95.50 28	95.92 59	94.59 103	94.77 122	92.50 49	97.82 6	97.90 2	95.56 87	97.88 66	94.71 14	98.02 25	94.81 85	97.23 59	94.48 74
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LS3D		95.83 38	96.35 32	95.22 36	96.47 44	97.49 15	97.99 31	92.35 53	94.92 26	94.58 43	94.88 106	95.11 132	91.52 66	98.48 14	98.05 13	98.42 25	95.49 54

SD-MVS		95.77 39	96.17 39	95.30 33	96.72 36	96.19 48	97.01 51	93.04 44	94.03 40	92.71 85	96.45 73	96.78 93	93.91 25	96.79 59	95.89 60	98.42 25	97.09 17

TranMVSNet+NR-MVSNet		95.72 40	96.42 30	94.91 45	96.21 50	96.77 35	96.90 58	94.99 13	92.62 62	91.92 103	98.51 16	98.63 25	90.82 92	97.27 44	96.83 39	98.63 13	94.31 75

ESAPD		95.63 41	96.35 32	94.80 48	96.76 34	97.29 23	97.74 42	94.15 28	91.69 83	90.01 136	96.65 70	97.29 76	92.45 48	97.41 41	97.18 33	97.67 49	96.95 24

DU-MVS		95.51 42	95.68 50	95.33 31	96.45 45	96.44 44	96.61 73	95.32 11	89.97 120	93.78 61	97.46 56	98.07 54	91.19 76	97.03 48	96.53 43	98.61 14	94.22 76

UniMVSNet (Re)		95.46 43	95.86 47	95.00 43	96.09 52	96.60 36	96.68 70	94.99 13	90.36 113	92.13 99	97.64 51	98.13 52	91.38 69	96.90 53	96.74 40	98.73 6	94.63 71

RPSCF		95.46 43	96.95 21	93.73 79	95.72 67	95.94 57	95.58 110	88.08 152	95.31 19	91.34 114	96.26 75	98.04 57	93.63 30	98.28 17	97.67 18	98.01 40	97.13 15

anonymousdsp		95.45 45	96.70 25	93.99 65	88.43 207	92.05 160	99.18 1	85.42 188	94.29 36	96.10 16	98.63 13	99.08 11	96.11 1	97.77 37	97.41 29	98.70 8	97.69 6

APD-MVS		95.38 46	95.68 50	95.03 42	97.30 16	96.90 33	97.83 38	93.92 32	89.40 130	90.35 131	95.41 91	97.69 70	92.97 39	97.24 45	97.17 34	97.83 44	95.96 46
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
UniMVSNet_NR-MVSNet		95.34 47	95.51 54	95.14 38	95.80 65	96.55 37	96.61 73	94.79 16	90.04 119	93.78 61	97.51 54	97.25 77	91.19 76	96.68 61	96.31 51	98.65 12	94.22 76

X-MVS		95.33 48	95.13 61	95.57 26	97.35 13	97.48 16	98.43 16	94.28 24	92.30 70	93.28 72	86.89 188	96.82 89	91.87 57	97.85 32	97.59 21	98.19 31	96.95 24

3Dnovator+	92.82 3	95.22 49	95.16 60	95.29 34	96.17 51	96.55 37	97.64 44	94.02 31	94.16 39	94.29 49	92.09 139	93.71 148	91.90 55	96.68 61	96.51 44	97.70 47	96.40 38

HPM-MVS++		95.21 50	94.89 65	95.59 24	97.79 6	95.39 75	97.68 43	94.05 30	91.91 80	94.35 48	93.38 126	95.07 133	92.94 41	96.01 72	95.88 61	96.73 71	96.61 36

TSAR-MVS + ACMM		95.17 51	95.95 44	94.26 55	96.07 54	96.46 43	95.67 107	94.21 27	93.84 42	90.99 122	97.18 62	95.24 131	93.55 31	96.60 64	95.61 67	95.06 133	96.69 34

HSP-MVS		95.04 52	95.45 56	94.57 49	96.87 27	97.77 10	98.71 5	93.88 34	91.21 101	91.48 112	95.36 92	98.37 38	90.73 93	94.37 106	92.98 120	95.77 115	98.08 3

CPTT-MVS		95.00 53	94.52 76	95.57 26	96.84 31	96.78 34	97.88 36	93.67 39	92.20 72	92.35 95	85.87 195	97.56 72	94.98 12	96.96 51	96.07 56	97.70 47	96.18 42

Baseline_NR-MVSNet		94.85 54	95.35 58	94.26 55	96.45 45	93.86 125	96.70 66	94.54 18	90.07 118	90.17 135	98.77 7	97.89 63	90.64 97	97.03 48	96.16 52	97.04 67	93.67 84

EG-PatchMatch MVS		94.81 55	95.53 53	93.97 66	95.89 62	94.62 100	95.55 111	88.18 148	92.77 61	94.88 39	97.04 66	98.61 26	93.31 33	96.89 54	95.19 76	95.99 107	93.56 88

OMC-MVS		94.74 56	95.46 55	93.91 71	94.62 87	96.26 47	96.64 72	89.36 128	94.20 37	94.15 51	94.02 121	97.73 69	91.34 71	96.15 70	95.04 79	97.37 53	94.80 65

DeepC-MVS_fast	91.38 6	94.73 57	94.98 62	94.44 50	96.83 33	96.12 51	96.69 68	92.17 59	92.98 56	93.72 63	94.14 117	95.45 121	90.49 102	95.73 78	95.30 72	96.71 72	95.13 62
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PHI-MVS		94.65 58	94.84 67	94.44 50	94.95 81	96.55 37	96.46 79	91.10 85	88.96 134	96.00 18	94.55 110	95.32 126	90.67 95	96.97 50	96.69 42	97.44 51	94.84 64

pmmvs6		94.58 59	97.30 16	91.40 123	94.84 83	94.61 101	93.40 147	92.43 52	98.51 3	85.61 165	98.73 10	99.53 3	84.40 142	97.88 30	97.03 37	97.72 45	94.79 66

DeepPCF-MVS	90.68 7	94.56 60	94.92 64	94.15 57	94.11 102	95.71 63	97.03 50	90.65 94	93.39 50	94.08 53	95.29 95	94.15 142	93.21 37	95.22 90	94.92 83	95.82 114	95.75 51

NR-MVSNet		94.55 61	95.66 52	93.25 95	94.26 97	96.44 44	96.69 68	95.32 11	89.97 120	91.79 108	97.46 56	98.39 37	82.85 151	96.87 56	96.48 46	98.57 15	93.98 81

v13		94.54 62	94.93 63	94.09 58	93.81 120	95.44 71	96.99 54	91.67 73	92.43 66	95.20 27	98.33 19	98.73 21	91.87 57	93.67 124	92.26 129	95.00 135	93.63 86

v12		94.44 63	94.79 69	94.02 62	93.75 123	95.37 76	96.92 55	91.61 74	92.21 71	95.10 29	98.27 23	98.69 23	91.73 61	93.49 126	92.15 134	94.97 139	93.37 91

Vis-MVSNet		94.39 64	95.85 48	92.68 107	90.91 189	95.88 58	97.62 46	91.41 79	91.95 78	89.20 141	97.29 60	96.26 103	90.60 101	96.95 52	95.91 58	96.32 90	96.71 33
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
V9		94.33 65	94.66 72	93.94 69	93.69 127	95.31 77	96.84 60	91.53 77	92.04 77	95.00 33	98.22 24	98.64 24	91.62 63	93.29 128	92.05 136	94.93 140	93.10 96

v11		94.32 66	94.62 73	93.97 66	93.95 110	95.31 77	96.83 61	91.30 81	91.95 78	95.51 20	98.32 21	98.61 26	91.44 68	92.83 135	92.23 131	94.77 144	93.08 97

TSAR-MVS + GP.		94.25 67	94.81 68	93.60 80	96.52 43	95.80 61	94.37 129	92.47 51	90.89 108	88.92 142	95.34 93	94.38 140	92.85 44	96.36 68	95.62 66	96.47 77	95.28 59

CNVR-MVS		94.24 68	94.47 78	93.96 68	96.56 42	95.67 64	96.43 81	91.95 66	92.08 75	91.28 116	90.51 154	95.35 124	91.20 75	96.34 69	95.50 69	96.34 87	95.88 47

V14		94.21 69	94.52 76	93.85 72	93.62 128	95.25 80	96.76 64	91.42 78	91.83 81	94.91 38	98.15 25	98.57 28	91.49 67	93.06 133	91.93 140	94.90 141	92.82 101

v15		94.09 70	94.37 80	93.77 77	93.56 130	95.18 81	96.68 70	91.34 80	91.64 85	94.83 41	98.09 28	98.51 31	91.37 70	92.84 134	91.80 142	94.85 142	92.53 112

v1192		93.98 71	93.94 89	94.01 63	93.91 114	94.63 99	97.00 52	89.75 112	91.01 105	96.50 12	97.93 33	98.26 42	91.74 60	92.06 154	92.05 136	95.18 128	91.66 130

v10		93.96 72	94.12 87	93.77 77	93.37 137	95.45 70	96.83 61	91.13 84	89.70 126	95.02 31	97.88 37	98.23 44	91.27 72	92.39 144	92.18 132	94.99 136	93.00 99

CDPH-MVS		93.96 72	93.86 91	94.08 60	96.31 48	95.84 59	96.92 55	91.85 69	87.21 159	91.25 118	92.83 130	96.06 111	91.05 85	95.57 79	94.81 85	97.12 61	94.72 67

MVS_0304		93.92 74	93.81 96	94.05 61	96.06 55	96.00 55	96.43 81	92.76 46	85.99 168	94.43 46	94.04 120	97.08 80	88.12 123	94.65 103	94.20 103	96.47 77	94.71 68

MSLP-MVS++		93.91 75	94.30 84	93.45 83	95.51 71	95.83 60	93.12 157	91.93 68	91.45 93	91.40 113	87.42 183	96.12 110	93.27 34	96.57 65	96.40 47	95.49 119	96.29 39

v1921920		93.90 76	93.82 94	94.00 64	93.74 124	94.31 107	97.12 47	89.33 129	91.13 102	96.77 10	97.90 34	98.06 55	91.95 54	91.93 161	91.54 149	95.10 131	91.85 125

train_agg		93.89 77	93.46 111	94.40 53	97.35 13	93.78 126	97.63 45	92.19 58	88.12 144	90.52 129	93.57 125	95.78 115	92.31 51	94.78 100	93.46 113	96.36 82	94.70 70

v144192		93.89 77	93.85 92	93.94 69	93.50 131	94.33 106	97.12 47	89.49 123	90.89 108	96.49 13	97.78 42	98.27 41	91.89 56	92.17 153	91.70 144	95.19 127	91.78 128

v1240		93.89 77	93.72 99	94.09 58	93.98 107	94.31 107	97.12 47	89.37 127	90.74 112	96.92 9	98.05 30	97.89 63	92.15 53	91.53 165	91.60 147	94.99 136	91.93 124

NCCC		93.87 80	93.42 112	94.40 53	96.84 31	95.42 72	96.47 78	92.62 47	92.36 68	92.05 100	83.83 204	95.55 117	91.84 59	95.89 74	95.23 75	96.56 75	95.63 52

v1144		93.83 81	93.87 90	93.78 76	93.72 125	94.57 104	96.85 59	89.98 105	91.31 98	95.90 19	97.89 35	98.40 36	91.13 80	92.01 157	92.01 138	95.10 131	90.94 134

MVS_111021_HR		93.82 82	94.26 86	93.31 89	95.01 79	93.97 122	95.73 104	89.75 112	92.06 76	92.49 91	94.01 122	96.05 112	90.61 100	95.95 73	94.78 88	96.28 92	93.04 98

TAPA-MVS	88.94 13	93.78 83	94.31 83	93.18 98	94.14 100	95.99 56	95.74 103	86.98 170	93.43 48	93.88 59	90.16 158	96.88 87	91.05 85	94.33 107	93.95 104	97.28 56	95.40 55
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
v7		93.65 84	93.73 98	93.57 81	93.38 136	94.60 102	96.83 61	89.92 108	89.69 127	95.02 31	97.89 35	98.24 43	91.27 72	92.38 145	92.18 132	94.99 136	91.12 132

EPP-MVSNet		93.63 85	93.95 88	93.26 93	95.15 77	96.54 40	96.18 96	91.97 65	91.74 82	85.76 162	94.95 105	84.27 186	91.60 65	97.61 40	97.38 30	98.87 4	95.18 61

v17		93.60 86	93.85 92	93.30 91	93.15 142	94.99 90	96.46 79	90.81 90	89.58 129	93.61 66	97.66 50	98.15 51	91.19 76	92.60 141	91.61 146	94.61 155	92.37 114

v8		93.60 86	93.82 94	93.34 87	93.13 143	95.06 85	96.39 87	90.75 92	89.90 122	94.03 54	97.70 48	98.21 47	91.08 84	92.36 146	91.47 154	94.63 151	92.07 120

MCST-MVS		93.60 86	93.40 115	93.83 73	95.30 73	95.40 74	96.49 77	90.87 89	90.08 117	91.72 109	90.28 156	95.99 113	91.69 62	93.94 120	92.99 119	96.93 70	95.13 62

PVSNet_Blended_VisFu		93.60 86	93.41 113	93.83 73	96.31 48	95.65 65	95.71 105	90.58 97	88.08 147	93.17 77	95.29 95	92.20 157	90.72 94	94.69 102	93.41 116	96.51 76	94.54 72

TransMVSNet (Re)		93.55 90	96.32 34	90.32 135	94.38 93	94.05 117	93.30 154	89.53 121	97.15 8	85.12 167	98.83 6	97.89 63	82.21 157	96.75 60	96.14 54	97.35 54	93.46 89

v16		93.53 91	93.80 97	93.20 96	93.10 148	94.98 91	96.43 81	90.81 90	89.39 132	93.12 80	97.63 52	98.01 59	91.19 76	92.60 141	91.65 145	94.58 157	92.36 115

v1		93.48 92	93.57 105	93.37 84	93.48 132	94.18 114	96.41 86	89.61 117	91.46 91	95.03 30	97.82 39	98.43 33	90.95 89	92.00 158	91.37 158	94.75 145	89.70 146

v1141		93.47 93	93.56 106	93.36 86	93.48 132	94.17 115	96.42 84	89.62 115	91.44 94	94.99 35	97.81 40	98.42 34	90.94 90	92.00 158	91.38 156	94.74 147	89.69 148

divwei89l23v2f112		93.47 93	93.56 106	93.37 84	93.48 132	94.17 115	96.42 84	89.62 115	91.46 91	95.00 33	97.81 40	98.42 34	90.94 90	92.00 158	91.38 156	94.75 145	89.70 146

v2v482		93.42 95	93.49 110	93.32 88	93.44 135	94.05 117	96.36 93	89.76 111	91.41 95	95.24 25	97.63 52	98.34 39	90.44 103	91.65 163	91.76 143	94.69 148	89.62 149

canonicalmvs		93.38 96	94.36 81	92.24 113	93.94 112	96.41 46	94.18 135	90.47 98	93.07 55	88.47 148	88.66 169	93.78 147	88.80 114	95.74 77	95.75 63	97.57 50	97.13 15

3Dnovator	91.81 5	93.36 97	94.27 85	92.29 112	92.99 150	95.03 86	95.76 102	87.79 157	93.82 43	92.38 94	92.19 138	93.37 152	88.14 122	95.26 89	94.85 84	96.69 73	95.40 55

v18		93.33 98	93.59 104	93.04 104	92.94 151	94.87 93	96.31 94	90.59 96	88.96 134	92.89 83	97.51 54	97.90 62	91.01 88	92.33 150	91.48 153	94.50 158	92.05 121

v1neww		93.27 99	93.40 115	93.12 99	93.13 143	94.20 111	96.39 87	89.56 118	89.87 124	93.95 56	97.71 46	98.21 47	91.09 82	92.36 146	91.49 150	94.62 153	89.96 141

v7new		93.27 99	93.40 115	93.12 99	93.13 143	94.20 111	96.39 87	89.56 118	89.87 124	93.95 56	97.71 46	98.21 47	91.09 82	92.36 146	91.49 150	94.62 153	89.96 141

pm-mvs1		93.27 99	95.94 45	90.16 136	94.13 101	93.66 128	92.61 167	89.91 109	95.73 18	84.28 173	98.51 16	98.29 40	82.80 152	96.44 66	95.76 62	97.25 58	93.21 94

v6		93.27 99	93.41 113	93.12 99	93.13 143	94.20 111	96.39 87	89.55 120	89.89 123	93.93 58	97.72 44	98.22 46	91.10 81	92.36 146	91.49 150	94.63 151	89.95 143

TinyColmap		93.17 103	93.33 118	93.00 105	93.84 117	92.76 145	94.75 124	88.90 140	93.97 41	97.48 4	95.28 97	95.29 127	88.37 119	95.31 88	91.58 148	94.65 150	89.10 154

MVS_111021_LR		93.15 104	93.65 101	92.56 108	93.89 116	92.28 156	95.09 116	86.92 172	91.26 100	92.99 82	94.46 113	96.22 106	90.64 97	95.11 93	93.45 114	95.85 112	92.74 105

CNLPA		93.14 105	93.67 100	92.53 109	94.62 87	94.73 97	95.00 118	86.57 176	92.85 59	92.43 92	90.94 147	94.67 137	90.35 104	95.41 81	93.70 108	96.23 97	93.37 91

PLC	87.27 15	93.08 106	92.92 122	93.26 93	94.67 84	95.03 86	94.38 128	90.10 100	91.69 83	92.14 98	87.24 184	93.91 145	91.61 64	95.05 94	94.73 94	96.67 74	92.80 102
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CANet		93.07 107	93.05 121	93.10 102	95.90 60	95.41 73	95.88 99	91.94 67	84.77 175	93.36 70	94.05 119	95.25 130	86.25 133	94.33 107	93.94 105	95.30 122	93.58 87

TSAR-MVS + COLMAP		93.06 108	93.65 101	92.36 110	94.62 87	94.28 109	95.36 114	89.46 125	92.18 73	91.64 110	95.55 88	95.27 129	88.60 117	93.24 129	92.50 126	94.46 159	92.55 111

Effi-MVS+		92.93 109	92.16 132	93.83 73	94.29 95	93.53 136	95.04 117	92.98 45	85.27 172	94.46 44	90.24 157	95.34 125	89.99 106	93.72 122	94.23 102	96.22 98	92.79 103

Fast-Effi-MVS+		92.93 109	92.64 126	93.27 92	93.81 120	93.88 124	95.90 98	90.61 95	83.98 180	92.71 85	92.81 131	96.22 106	90.67 95	94.90 99	93.92 106	95.92 109	92.77 104

HQP-MVS		92.87 111	92.49 127	93.31 89	95.75 66	95.01 89	95.64 108	91.06 86	88.54 141	91.62 111	88.16 174	96.25 104	89.47 109	92.26 152	91.81 141	96.34 87	95.40 55

FMVSNet1		92.86 112	95.26 59	90.06 138	92.40 162	95.16 82	94.37 129	92.22 55	93.18 54	82.16 187	96.76 69	97.48 73	81.85 162	95.32 85	94.98 80	97.34 55	93.93 82

CLD-MVS		92.81 113	94.32 82	91.05 125	95.39 72	95.31 77	95.82 101	81.44 210	89.40 130	91.94 102	95.86 82	97.36 74	85.83 135	95.35 83	94.59 97	95.85 112	92.34 117
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
IS_MVSNet		92.76 114	93.25 119	92.19 114	94.91 82	95.56 66	95.86 100	92.12 61	88.10 145	82.71 182	93.15 129	88.30 175	88.86 113	97.29 42	96.95 38	98.66 10	93.38 90

FC-MVSNet-train		92.75 115	95.40 57	89.66 148	95.21 75	94.82 94	97.00 52	89.40 126	91.13 102	81.71 188	97.72 44	96.43 100	77.57 195	96.89 54	96.72 41	97.05 66	94.09 79

V42		92.67 116	93.50 109	91.71 120	91.41 180	92.96 143	95.71 105	85.00 189	89.67 128	93.22 75	97.67 49	98.01 59	91.02 87	92.65 138	92.12 135	93.86 167	91.42 131

PM-MVS		92.65 117	93.20 120	92.00 116	92.11 173	90.16 176	95.99 97	84.81 192	91.31 98	92.41 93	95.87 81	96.64 95	92.35 50	93.65 125	92.91 121	94.34 162	91.85 125

QAPM		92.57 118	93.51 108	91.47 121	92.91 153	94.82 94	93.01 159	87.51 161	91.49 88	91.21 119	92.24 136	91.70 159	88.74 115	94.54 104	94.39 101	95.41 120	95.37 58

MIMVSNet1		92.52 119	94.88 66	89.77 144	96.09 52	91.99 161	96.92 55	89.68 114	95.92 17	84.55 170	96.64 71	98.21 47	78.44 188	96.08 71	95.10 77	92.91 179	90.22 139

tfpnnormal		92.45 120	94.77 70	89.74 145	93.95 110	93.44 138	93.25 155	88.49 146	95.27 23	83.20 177	96.51 72	96.23 105	83.17 149	95.47 80	94.52 99	96.38 81	91.97 123

PCF-MVS	87.46 14	92.44 121	91.80 135	93.19 97	94.66 85	95.80 61	96.37 91	90.19 99	87.57 152	92.23 97	89.26 165	93.97 144	89.24 110	91.32 167	90.82 163	96.46 79	93.86 83
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
AdaColmap		92.41 122	91.49 139	93.48 82	95.96 58	95.02 88	95.37 113	91.73 71	87.97 150	91.28 116	82.82 209	91.04 163	90.62 99	95.82 76	95.07 78	95.95 108	92.67 106

v148		92.38 123	92.78 124	91.91 117	92.86 154	92.13 159	94.84 120	87.03 169	91.47 90	93.07 81	96.92 67	98.89 14	90.10 105	92.05 155	89.69 171	93.56 170	88.27 167

pmmvs-eth3d		92.34 124	92.33 128	92.34 111	92.67 157	90.67 172	96.37 91	89.06 132	90.98 106	93.60 67	97.13 64	97.02 82	88.29 120	90.20 174	91.42 155	94.07 165	88.89 157

DELS-MVS		92.33 125	93.61 103	90.83 128	92.84 155	95.13 84	94.76 123	87.22 168	87.78 151	88.42 150	95.78 84	95.28 128	85.71 136	94.44 105	93.91 107	96.01 106	92.97 100
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
Effi-MVS+-dtu		92.32 126	91.66 137	93.09 103	95.13 78	94.73 97	94.57 127	92.14 60	81.74 188	90.33 132	88.13 175	95.91 114	89.24 110	94.23 116	93.65 112	97.12 61	93.23 93

UGNet		92.31 127	94.70 71	89.53 150	90.99 188	95.53 69	96.19 95	92.10 63	91.35 97	85.76 162	95.31 94	95.48 120	76.84 199	95.22 90	94.79 87	95.32 121	95.19 60
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
USDC		92.17 128	92.17 131	92.18 115	92.93 152	92.22 157	93.66 142	87.41 163	93.49 46	97.99 1	94.10 118	96.68 94	86.46 131	92.04 156	89.18 177	94.61 155	87.47 170

IterMVS-LS		92.10 129	92.33 128	91.82 119	93.18 140	93.66 128	92.80 165	92.27 54	90.82 110	90.59 128	97.19 61	90.97 164	87.76 124	89.60 180	90.94 162	94.34 162	93.16 95
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MSDG		92.09 130	92.84 123	91.22 124	92.55 158	92.97 142	93.42 146	85.43 187	90.24 115	91.83 106	94.70 107	94.59 138	88.48 118	94.91 98	93.31 118	95.59 118	89.15 153

no-one		92.05 131	94.57 75	89.12 154	85.55 219	87.65 189	94.21 134	77.34 216	93.43 48	89.64 140	95.11 100	99.11 9	95.86 4	95.38 82	95.24 74	92.08 183	96.11 44

MAR-MVS		91.86 132	91.14 142	92.71 106	94.29 95	94.24 110	94.91 119	91.82 70	81.66 189	93.32 71	84.51 202	93.42 151	86.86 129	95.16 92	94.44 100	95.05 134	94.53 73
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
EU-MVSNet		91.63 133	92.73 125	90.35 134	88.36 208	87.89 186	96.53 75	81.51 209	92.45 65	91.82 107	96.44 74	97.05 81	93.26 35	94.10 118	88.94 181	90.61 186	92.24 118

FC-MVSNet-test		91.49 134	94.43 79	88.07 173	94.97 80	90.53 175	95.42 112	91.18 83	93.24 52	72.94 218	98.37 18	93.86 146	78.78 182	97.82 35	96.13 55	95.13 129	91.05 133

conf0.05thres1000		91.24 135	91.85 134	90.53 131	94.59 90	94.56 105	94.33 132	89.52 122	93.67 44	83.77 175	91.04 145	79.10 203	83.98 143	96.66 63	95.56 68	96.98 69	92.36 115

OpenMVS	89.22 12	91.09 136	91.42 140	90.71 129	92.79 156	93.61 133	92.74 166	85.47 186	86.10 167	90.73 123	85.71 196	93.07 155	86.69 130	94.07 119	93.34 117	95.86 110	94.02 80

FPMVS		90.81 137	91.60 138	89.88 142	92.52 159	88.18 181	93.31 153	83.62 198	91.59 87	88.45 149	88.96 167	89.73 170	86.96 127	96.42 67	95.69 65	94.43 160	90.65 135

DI_MVS_plusplus_trai		90.68 138	90.40 146	91.00 126	92.43 161	92.61 150	94.17 136	88.98 134	88.32 143	88.76 146	93.67 124	87.58 177	86.44 132	89.74 178	90.33 165	95.24 126	90.56 138

Vis-MVSNet (Re-imp)		90.68 138	92.18 130	88.92 157	94.63 86	92.75 146	92.91 161	91.20 82	89.21 133	75.01 213	93.96 123	89.07 173	82.72 154	95.88 75	95.30 72	97.08 65	89.08 155

FMVSNet2		90.28 140	92.04 133	88.23 171	91.22 184	94.05 117	92.88 162	90.69 93	86.53 163	79.89 198	94.38 114	92.73 156	78.54 185	91.64 164	92.26 129	96.17 101	92.67 106

MVS_Test		90.19 141	90.58 143	89.74 145	92.12 172	91.74 163	92.51 168	88.54 145	82.80 185	87.50 154	94.62 108	95.02 134	83.97 144	88.69 187	89.32 175	93.79 168	91.85 125

EPNet		90.17 142	89.07 159	91.45 122	97.25 17	90.62 174	94.84 120	93.54 40	80.96 191	91.85 105	86.98 187	85.88 182	77.79 192	92.30 151	92.58 125	93.41 172	94.20 78
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_BlendedMVS		90.09 143	90.12 148	90.05 139	92.40 162	92.74 147	91.74 178	85.89 181	80.54 198	90.30 133	88.54 170	95.51 118	84.69 140	92.64 139	90.25 167	95.28 124	90.61 136

PVSNet_Blended		90.09 143	90.12 148	90.05 139	92.40 162	92.74 147	91.74 178	85.89 181	80.54 198	90.30 133	88.54 170	95.51 118	84.69 140	92.64 139	90.25 167	95.28 124	90.61 136

pmmvs4		89.95 145	89.32 157	90.69 130	91.60 179	89.17 180	94.37 129	87.63 160	88.07 148	91.02 121	94.50 111	90.50 167	86.13 134	86.33 202	89.40 174	93.39 173	87.29 172

MDA-MVSNet-bldmvs		89.75 146	91.67 136	87.50 178	74.25 233	90.88 170	94.68 125	85.89 181	91.64 85	91.03 120	95.86 82	94.35 141	89.10 112	96.87 56	86.37 191	90.04 187	85.72 181

PatchMatch-RL		89.59 147	88.80 164	90.51 132	92.20 171	88.00 185	91.72 180	86.64 173	84.75 176	88.25 151	87.10 186	90.66 166	89.85 108	93.23 130	92.28 128	94.41 161	85.60 183

Fast-Effi-MVS+-dtu		89.57 148	88.42 170	90.92 127	93.35 138	91.57 164	93.01 159	95.71 9	78.94 212	87.65 153	84.68 201	93.14 154	82.00 159	90.84 170	91.01 161	93.78 169	88.77 158

view800		89.42 149	89.11 158	89.78 143	94.00 103	93.71 127	93.96 138	88.47 147	88.10 145	82.91 178	82.61 210	79.85 201	83.10 150	94.92 97	95.38 70	96.26 96	89.19 152

GBi-Net		89.35 150	90.58 143	87.91 174	91.22 184	94.05 117	92.88 162	90.05 102	79.40 204	78.60 204	90.58 151	87.05 178	78.54 185	95.32 85	94.98 80	96.17 101	92.67 106

test1		89.35 150	90.58 143	87.91 174	91.22 184	94.05 117	92.88 162	90.05 102	79.40 204	78.60 204	90.58 151	87.05 178	78.54 185	95.32 85	94.98 80	96.17 101	92.67 106

thres600view7		89.14 152	88.83 162	89.51 151	93.71 126	93.55 134	93.93 139	88.02 153	87.30 156	82.40 183	81.18 213	80.63 199	82.69 155	94.27 111	95.90 59	96.27 94	88.94 156

view600		89.09 153	88.78 165	89.46 152	93.59 129	93.33 140	93.92 140	87.76 158	87.40 153	82.79 179	81.29 212	80.71 198	82.59 156	94.28 110	95.72 64	96.12 104	88.70 159

tfpn_n400		89.03 154	89.39 155	88.61 161	93.98 107	92.33 153	91.83 176	88.97 135	92.97 57	78.90 200	84.93 198	78.24 205	81.77 165	95.00 95	93.67 109	96.22 98	88.59 160

tfpnconf		89.03 154	89.39 155	88.61 161	93.98 107	92.33 153	91.83 176	88.97 135	92.97 57	78.90 200	84.93 198	78.24 205	81.77 165	95.00 95	93.67 109	96.22 98	88.59 160

CVMVSNet		88.97 156	89.73 151	88.10 172	87.33 215	85.22 195	94.68 125	78.68 212	88.94 136	86.98 158	95.55 88	85.71 183	89.87 107	91.19 168	89.69 171	91.05 184	91.78 128

CANet_DTU		88.95 157	89.51 154	88.29 170	93.12 147	91.22 167	93.61 143	83.47 201	80.07 203	90.71 127	89.19 166	93.68 149	76.27 203	91.44 166	91.17 160	92.59 180	89.83 144

GA-MVS		88.76 158	88.04 173	89.59 149	92.32 165	91.46 165	92.28 172	86.62 174	83.82 182	89.84 138	92.51 135	81.94 193	83.53 147	89.41 182	89.27 176	92.95 178	87.90 168

tfpnview11		88.74 159	88.95 160	88.50 163	93.91 114	92.43 152	91.70 182	88.90 140	90.93 107	78.90 200	84.93 198	78.24 205	81.71 167	94.32 109	94.60 96	95.86 110	87.23 173

pmmvs5		88.63 160	89.70 152	87.39 180	89.24 201	90.64 173	91.87 175	82.13 205	83.34 183	87.86 152	94.58 109	96.15 109	79.87 174	87.33 198	89.07 180	93.39 173	86.76 176

thres400		88.54 161	88.15 172	88.98 155	93.17 141	92.84 144	93.56 144	86.93 171	86.45 164	82.37 184	79.96 215	81.46 196	81.83 163	93.21 131	94.76 89	96.04 105	88.39 165

CDS-MVSNet		88.41 162	89.79 150	86.79 185	94.55 91	90.82 171	92.50 169	89.85 110	83.26 184	80.52 194	91.05 144	89.93 168	69.11 213	93.17 132	92.71 124	94.21 164	87.63 169
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
gg-mvs-nofinetune		88.32 163	88.81 163	87.75 176	93.07 149	89.37 179	89.06 206	95.94 7	95.29 21	87.15 155	97.38 58	76.38 209	68.05 216	91.04 169	89.10 179	93.24 175	83.10 191

IterMVS		88.32 163	88.25 171	88.41 165	90.83 190	91.24 166	93.07 158	81.69 207	86.77 161	88.55 147	95.61 85	86.91 181	87.01 126	87.38 197	83.77 198	89.29 190	86.06 180
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
thres200		88.29 165	87.88 174	88.76 158	92.50 160	93.55 134	92.47 170	88.02 153	84.80 173	81.44 189	79.28 217	82.20 192	81.83 163	94.27 111	93.67 109	96.27 94	87.40 171

diffmvs		88.28 166	88.88 161	87.58 177	89.51 199	88.07 184	91.88 174	85.83 184	87.31 154	86.34 160	96.01 80	88.90 174	81.90 160	85.49 209	86.61 190	90.04 187	89.77 145

IB-MVS	86.01 17	88.24 167	87.63 176	88.94 156	92.03 176	91.77 162	92.40 171	85.58 185	78.24 214	84.85 168	71.99 230	93.45 150	83.96 145	93.48 127	92.33 127	94.84 143	92.15 119
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
MDTV_nov1_ep13_2view		88.22 168	87.85 175	88.65 160	91.40 181	86.75 191	94.07 137	84.97 190	88.86 138	93.20 76	96.11 79	96.21 108	83.70 146	87.29 199	80.29 209	84.56 208	79.46 206

test20.03		88.20 169	91.26 141	84.63 199	96.64 40	89.39 178	90.73 193	89.97 106	91.07 104	72.02 220	94.98 104	95.45 121	69.35 212	92.70 137	91.19 159	89.06 192	84.02 184

HyFIR lowres test		88.19 170	86.56 183	90.09 137	91.24 183	92.17 158	94.30 133	88.79 142	84.06 178	85.45 166	89.52 163	85.64 184	88.64 116	85.40 210	87.28 186	92.14 182	81.87 194

tfpn1000		88.13 171	88.68 167	87.49 179	93.94 112	92.64 149	91.50 184	88.70 144	90.12 116	74.35 215	86.74 190	75.27 211	80.14 173	94.16 117	94.66 95	96.33 89	87.16 174

tfpn200view9		87.94 172	87.51 177	88.44 164	92.28 166	93.63 132	93.35 152	88.11 151	80.90 192	80.89 190	78.25 218	82.25 188	79.65 177	94.27 111	94.76 89	96.36 82	88.48 162

conf200view11		87.93 173	87.51 177	88.41 165	92.28 166	93.64 130	93.36 148	88.12 149	80.90 192	80.71 192	78.25 218	82.25 188	79.65 177	94.27 111	94.76 89	96.36 82	88.48 162

FMVSNet3		87.90 174	88.63 168	87.04 182	89.78 198	93.46 137	91.62 183	90.05 102	79.40 204	78.60 204	90.58 151	87.05 178	77.07 198	88.03 194	89.86 170	95.12 130	92.04 122

MS-PatchMatch		87.72 175	88.62 169	86.66 187	90.81 191	88.18 181	90.92 189	82.25 204	85.86 169	80.40 197	90.14 159	89.29 172	84.93 137	89.39 183	89.12 178	90.67 185	88.34 166

tfpn		87.65 176	85.66 188	89.96 141	94.36 94	93.94 123	93.85 141	89.02 133	88.71 140	82.78 180	83.79 205	53.79 232	83.43 148	95.35 83	94.54 98	96.35 86	89.51 150

tfpn111		87.59 177	86.89 180	88.41 165	92.28 166	93.64 130	93.36 148	88.12 149	80.90 192	80.71 192	73.93 227	82.25 188	79.65 177	94.27 111	94.76 89	96.36 82	88.48 162

Anonymous20231206		87.45 178	89.66 153	84.87 196	94.00 103	87.73 188	91.36 185	86.41 179	88.89 137	75.03 212	92.59 134	96.82 89	72.48 210	89.72 179	88.06 183	89.93 189	83.81 186

EPNet_dtu		87.40 179	86.27 185	88.72 159	95.68 68	83.37 204	92.09 173	90.08 101	78.11 217	91.29 115	86.33 191	89.74 169	75.39 204	89.07 184	87.89 184	87.81 197	89.38 151
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CHOSEN 1792x2688		86.64 180	86.62 182	86.65 188	90.33 194	87.86 187	93.19 156	83.30 202	83.95 181	82.32 185	87.93 177	89.34 171	86.92 128	85.64 208	84.95 195	83.85 214	86.68 177

testgi		86.49 181	90.31 147	82.03 204	95.63 69	88.18 181	93.47 145	84.89 191	93.23 53	69.54 227	87.16 185	97.96 61	60.66 221	91.90 162	89.90 169	87.99 195	83.84 185

thres100view900		86.46 182	86.00 187	86.99 183	92.28 166	91.03 168	91.09 187	84.49 194	80.90 192	80.89 190	78.25 218	82.25 188	77.57 195	90.17 175	92.84 122	95.63 116	86.57 178

gm-plane-assit		86.15 183	82.51 199	90.40 133	95.81 64	92.29 155	97.99 31	84.66 193	92.15 74	93.15 78	97.84 38	44.65 237	78.60 184	88.02 195	85.95 192	92.20 181	76.69 213

tfpn_ndepth		85.89 184	86.40 184	85.30 194	91.31 182	92.47 151	90.78 191	87.75 159	84.79 174	71.04 222	76.95 222	78.80 204	74.52 207	92.72 136	93.43 115	96.39 80	85.65 182

conf0.01		85.72 185	83.49 196	88.32 168	92.11 173	93.35 139	93.36 148	88.02 153	80.90 192	80.51 195	74.83 225	59.86 230	79.65 177	93.80 121	94.76 89	96.29 91	86.94 175

CMPMVS	66.55 18	85.55 186	87.46 179	83.32 202	84.99 220	81.97 209	79.19 231	75.93 218	79.32 207	88.82 144	85.09 197	91.07 162	82.12 158	92.56 143	89.63 173	88.84 193	92.56 110
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
CR-MVSNet		85.32 187	81.58 203	89.69 147	90.36 193	84.79 198	86.72 217	92.22 55	75.38 222	90.73 123	90.41 155	67.88 220	84.86 138	83.76 212	85.74 193	93.24 175	83.14 189

conf0.002		84.82 188	81.84 202	88.30 169	92.05 175	93.28 141	93.36 148	88.00 156	80.90 192	80.48 196	73.43 229	52.48 235	79.65 177	93.72 122	92.82 123	96.28 92	86.22 179

MVSTER		84.79 189	83.79 194	85.96 190	89.14 202	89.80 177	89.39 204	82.99 203	74.16 226	82.78 180	85.97 194	66.81 222	76.84 199	90.77 171	88.83 182	94.66 149	90.19 140

MIMVSNet		84.76 190	86.75 181	82.44 203	91.71 178	85.95 193	89.74 202	89.49 123	85.28 171	69.69 226	87.93 177	90.88 165	64.85 218	88.26 192	87.74 185	89.18 191	81.24 195

new-patchmatchnet		84.45 191	88.75 166	79.43 211	93.28 139	81.87 210	81.68 228	83.48 200	94.47 30	71.53 221	98.33 19	97.88 66	58.61 224	90.35 173	77.33 216	87.99 195	81.05 197

thresconf0.02		84.34 192	82.02 201	87.06 181	92.23 170	90.93 169	91.05 188	86.43 178	88.83 139	77.65 210	73.93 227	55.81 231	79.68 176	90.62 172	90.28 166	95.30 122	83.73 187

LP		84.09 193	84.31 191	83.85 201	79.40 228	84.34 201	90.26 196	84.02 195	87.99 149	84.66 169	91.61 143	79.13 202	80.58 171	85.90 207	81.59 204	84.16 213	79.59 205

PatchT		83.44 194	81.10 205	86.18 189	77.92 230	82.58 208	89.87 200	87.39 164	75.88 221	90.73 123	89.86 160	66.71 223	84.86 138	83.76 212	85.74 193	86.33 204	83.14 189

RPMNet		83.42 195	78.40 214	89.28 153	89.79 197	84.79 198	90.64 194	92.11 62	75.38 222	87.10 156	79.80 216	61.99 229	82.79 153	81.88 218	82.07 203	93.23 177	82.87 192

TAMVS		82.96 196	86.15 186	79.24 214	90.57 192	83.12 207	87.29 212	75.12 221	84.06 178	65.81 229	92.22 137	88.27 176	69.11 213	88.72 185	87.26 188	87.56 200	79.38 207

PatchmatchNet		82.44 197	78.69 213	86.83 184	89.81 196	81.55 211	90.78 191	87.27 167	82.39 187	88.85 143	88.31 173	70.96 216	81.90 160	78.58 225	74.33 225	82.35 220	74.69 217
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MDTV_nov1_ep13		82.33 198	79.66 208	85.45 192	88.83 204	83.88 202	90.09 199	81.98 206	79.07 211	88.82 144	88.70 168	73.77 212	78.41 189	80.29 222	76.08 219	84.56 208	75.83 214

tpmp4_e23		82.16 199	78.26 216	86.70 186	89.92 195	84.82 197	91.17 186	89.95 107	81.21 190	87.10 156	81.91 211	64.01 226	77.88 191	79.89 223	74.99 223	84.18 212	81.00 198

CostFormer		82.15 200	79.54 209	85.20 195	88.92 203	85.70 194	90.87 190	86.26 180	79.19 210	83.87 174	87.89 179	69.20 218	76.62 201	77.50 228	75.28 221	84.69 207	82.02 193

PMMVS		81.93 201	83.48 197	80.12 209	72.35 234	75.05 227	88.54 208	64.01 227	77.02 219	82.22 186	87.51 182	91.12 161	79.70 175	86.59 200	86.64 189	93.88 166	80.41 199

pmmvs3		81.69 202	83.83 193	79.19 215	78.33 229	78.57 217	89.53 203	58.71 231	78.88 213	84.34 172	88.36 172	91.96 158	77.69 194	87.48 196	82.42 202	86.54 203	79.18 208

tpm		81.58 203	78.84 211	84.79 198	91.11 187	79.50 214	89.79 201	83.75 196	79.30 208	92.05 100	90.98 146	64.78 225	74.54 205	80.50 221	76.67 218	77.49 225	80.15 202

test0.0.03 1		81.51 204	83.30 198	79.42 212	93.99 105	86.50 192	85.93 223	87.32 165	78.16 215	61.62 230	80.78 214	81.78 194	59.87 222	88.40 191	87.27 187	87.78 199	80.19 201

test1235678		81.50 205	84.78 189	77.67 221	87.67 211	80.27 212	90.12 197	77.62 214	80.36 200	69.71 224	90.93 148	96.51 97	56.57 226	88.60 189	84.93 196	84.34 210	71.87 226

testmv		81.49 206	84.76 190	77.67 221	87.67 211	80.25 213	90.12 197	77.62 214	80.34 201	69.71 224	90.92 149	96.47 98	56.57 226	88.58 190	84.92 197	84.33 211	71.86 227

dps		81.42 207	77.88 221	85.56 191	87.67 211	85.17 196	88.37 210	87.46 162	74.37 225	84.55 170	86.80 189	62.18 228	80.20 172	81.13 220	77.52 215	85.10 205	77.98 211

test-LLR		80.62 208	77.20 224	84.62 200	93.99 105	75.11 225	87.04 213	87.32 165	70.11 230	78.59 207	83.17 207	71.60 214	73.88 208	82.32 216	79.20 212	86.91 201	78.87 209

tpm cat1		80.03 209	75.93 227	84.81 197	89.31 200	83.26 206	88.86 207	86.55 177	79.24 209	86.10 161	84.22 203	63.62 227	77.37 197	73.43 230	70.88 228	80.67 221	76.87 212

N_pmnet		79.33 210	84.22 192	73.62 226	91.72 177	73.72 229	86.11 221	76.36 217	92.38 67	53.38 234	95.54 90	95.62 116	59.14 223	84.23 211	74.84 224	75.03 230	73.25 223

EPMVS		79.26 211	78.20 218	80.49 207	87.04 216	78.86 216	86.08 222	83.51 199	82.63 186	73.94 216	89.59 161	68.67 219	72.03 211	78.17 226	75.08 222	80.37 222	74.37 219

CHOSEN 280x420		79.24 212	78.26 216	80.38 208	79.60 227	68.80 234	89.32 205	75.38 219	77.25 218	78.02 209	75.57 224	76.17 210	81.19 169	88.61 188	81.39 205	78.79 223	80.03 203

DWT-MVSNet_training		79.22 213	73.99 229	85.33 193	88.57 205	84.41 200	90.56 195	80.96 211	73.90 227	85.72 164	75.62 223	50.09 236	81.30 168	76.91 229	77.02 217	84.88 206	79.97 204

ADS-MVSNet		79.11 214	79.38 210	78.80 217	81.90 225	75.59 223	84.36 224	83.69 197	87.31 154	76.76 211	87.58 181	76.90 208	68.55 215	78.70 224	75.56 220	77.53 224	74.07 221

FMVSNet5		79.08 215	78.83 212	79.38 213	87.52 214	86.78 190	87.64 211	78.15 213	69.54 232	70.64 223	65.97 234	65.44 224	63.87 219	90.17 175	90.46 164	88.48 194	83.45 188

tpmrst		78.81 216	76.18 226	81.87 205	88.56 206	77.45 220	86.74 216	81.52 208	80.08 202	83.48 176	90.84 150	66.88 221	74.54 205	73.04 231	71.02 227	76.38 227	73.95 222

test-mter		78.71 217	78.35 215	79.12 216	84.03 222	76.58 221	88.51 209	59.06 230	71.06 228	78.87 203	83.73 206	71.83 213	76.44 202	83.41 215	80.61 207	87.79 198	81.24 195

MVS-HIRNet		78.28 218	75.28 228	81.79 206	80.33 226	69.38 233	76.83 232	86.59 175	70.76 229	86.66 159	89.57 162	81.04 197	77.74 193	77.81 227	71.65 226	82.62 217	66.73 229

testus		78.20 219	81.50 204	74.36 225	85.59 218	79.36 215	86.99 215	65.76 225	76.01 220	73.00 217	77.98 221	93.35 153	51.30 232	86.33 202	82.79 201	83.50 216	74.68 218

E-PMN		77.81 220	77.88 221	77.73 220	88.26 209	70.48 232	80.19 230	71.20 223	86.66 162	72.89 219	88.09 176	81.74 195	78.75 183	90.02 177	68.30 229	75.10 229	59.85 232

EMVS		77.65 221	77.49 223	77.83 218	87.75 210	71.02 231	81.13 229	70.54 224	86.38 165	74.52 214	89.38 164	80.19 200	78.22 190	89.48 181	67.13 230	74.83 231	58.84 233

TESTMET0.1,1		77.47 222	77.20 224	77.78 219	81.94 224	75.11 225	87.04 213	58.33 232	70.11 230	78.59 207	83.17 207	71.60 214	73.88 208	82.32 216	79.20 212	86.91 201	78.87 209

1111		76.85 223	78.03 219	75.46 223	94.16 98	78.29 218	86.40 219	89.12 130	87.23 157	61.26 231	95.15 98	44.14 238	51.46 230	86.04 205	81.00 206	70.40 233	74.37 219

new_pmnet		76.65 224	83.52 195	68.63 228	82.60 223	72.08 230	76.76 233	64.17 226	84.41 177	49.73 236	91.77 140	91.53 160	56.16 228	86.59 200	83.26 200	82.37 219	75.02 215

test12356		75.40 225	80.89 206	69.01 227	77.43 231	75.75 222	83.03 226	61.48 228	78.13 216	59.08 233	87.69 180	94.95 136	57.37 225	88.18 193	80.59 208	75.65 228	60.93 231

MVE	60.41 19	73.21 226	80.84 207	64.30 229	56.34 235	57.24 236	75.28 235	72.76 222	87.14 160	41.39 237	86.31 192	85.30 185	80.66 170	86.17 204	83.36 199	59.35 234	80.38 200
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test2356		72.95 227	71.24 230	74.95 224	84.89 221	75.49 224	82.67 227	75.38 219	68.02 233	68.65 228	74.40 226	52.81 234	55.61 229	81.50 219	79.80 210	82.50 218	66.70 230

testpf		72.68 228	66.81 231	79.53 210	86.52 217	73.89 228	83.56 225	88.74 143	58.70 235	79.68 199	71.31 231	53.64 233	62.23 220	68.68 232	66.64 231	76.46 226	74.82 216

PMMVS2		69.86 229	82.14 200	55.52 231	75.19 232	63.08 235	75.52 234	60.97 229	88.50 142	25.11 239	91.77 140	96.44 99	25.43 233	88.70 186	79.34 211	70.93 232	67.17 228

.test1245		60.07 230	56.75 232	63.93 230	94.16 98	78.29 218	86.40 219	89.12 130	87.23 157	61.26 231	95.15 98	44.14 238	51.46 230	86.04 205	2.51 234	1.21 238	3.92 235

GG-mvs-BLEND		54.28 231	77.89 220	26.72 233	0.37 239	83.31 205	70.04 236	0.39 237	74.71 224	5.36 240	68.78 232	83.06 187	0.62 237	83.73 214	78.99 214	83.55 215	72.68 225

testmvs		2.38 232	3.35 233	1.26 235	0.83 237	0.96 240	1.53 240	0.83 235	3.59 237	1.63 242	6.03 236	2.93 241	1.55 236	3.49 235	2.51 234	1.21 238	3.92 235

test123		2.16 233	2.82 234	1.41 234	0.62 238	1.18 239	1.53 240	0.82 236	2.78 238	2.27 241	4.18 237	1.98 242	1.64 235	2.58 236	3.01 233	1.56 237	4.00 234

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			94.61 74		98.09 5	95.14 83	91.71 181		94.18 38	96.46 14	96.26 75	96.30 102	91.26 74	94.70 101	92.00 139	93.45 171	93.67 84

MTAPA										94.88 39		96.88 87

MTMP										95.43 21		97.25 77

Patchmatch-RL test							8.96 239

tmp_tt				28.44 232	36.05 236	15.86 238	21.29 238	6.40 234	54.52 236	51.96 235	50.37 235	38.68 240	9.55 234	61.75 234	59.66 232	45.36 236

XVS					96.86 29	97.48 16	98.73 3			93.28 72		96.82 89				98.17 33

X-MVStestdata					96.86 29	97.48 16	98.73 3			93.28 72		96.82 89				98.17 33

abl_6				91.88 118	93.76 122	94.98 91	95.64 108	88.97 135	86.20 166	90.00 137	86.31 192	94.50 139	87.31 125			95.60 117	92.48 113

mPP-MVS					98.24 3							97.65 71

NP-MVS									85.48 170

Patchmtry						83.74 203	86.72 217	92.22 55		90.73 123

DeepMVS_CX						47.68 237	53.20 237	19.21 233	63.24 234	26.96 238	66.50 233	69.82 217	66.91 217	64.27 233		54.91 235	72.72 224

High-resolution multi-view benchmark