High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

LCM-MVSNet		99.86 1	99.86 1	99.87 1	99.99 1	99.77 1	99.77 1	99.80 1	99.97 1	99.97 1	99.95 1	99.74 1	99.98 1	99.56 1	100.00 1	99.85 4

Anonymous20231211		99.29 2	99.41 2	98.91 22	99.94 2	97.08 37	99.47 3	99.51 5	99.56 2	99.83 3	99.80 2	99.13 3	99.90 13	97.55 49	99.93 21	99.75 13

LTVRE_ROB	96.88 1	99.18 3	99.34 3	98.72 35	99.71 7	96.99 40	99.69 2	99.57 3	99.02 14	99.62 10	99.36 16	98.53 8	99.52 163	98.58 24	99.95 13	99.66 23
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
pmmvs6		99.07 4	99.24 4	98.56 45	99.81 3	96.38 57	98.87 9	99.30 9	99.01 15	99.63 9	99.66 4	99.27 2	99.68 103	97.75 41	99.89 33	99.62 31

mvs_tets		98.90 5	98.94 8	98.75 30	99.69 8	96.48 55	98.54 20	99.22 10	96.23 110	99.71 5	99.48 7	98.77 7	99.93 2	98.89 10	99.95 13	99.84 6

TDRefinement		98.90 5	98.86 11	99.02 8	99.54 23	98.06 6	99.34 5	99.44 7	98.85 19	99.00 40	99.20 31	97.42 31	99.59 144	97.21 62	99.76 50	99.40 91

UA-Net		98.88 7	98.76 16	99.22 2	99.11 77	97.89 10	99.47 3	99.32 8	99.08 9	97.87 137	99.67 3	96.47 74	99.92 4	97.88 34	99.98 3	99.85 4

v52		98.85 8	99.01 5	98.37 56	99.61 15	95.53 83	99.01 7	99.04 45	98.48 26	99.31 22	99.41 11	96.82 56	99.87 21	99.44 2	99.95 13	99.70 19

V4		98.85 8	99.01 5	98.37 56	99.61 15	95.53 83	99.01 7	99.04 45	98.48 26	99.31 22	99.41 11	96.81 57	99.87 21	99.44 2	99.95 13	99.70 19

DTE-MVSNet		98.79 10	98.86 11	98.59 43	99.55 21	96.12 64	98.48 24	99.10 25	99.36 3	99.29 25	99.06 47	97.27 37	99.93 2	97.71 43	99.91 27	99.70 19

jajsoiax		98.77 11	98.79 15	98.74 32	99.66 10	96.48 55	98.45 25	99.12 22	95.83 125	99.67 7	99.37 14	98.25 11	99.92 4	98.77 14	99.94 19	99.82 7

PEN-MVS		98.75 12	98.85 13	98.44 50	99.58 18	95.67 77	98.45 25	99.15 19	99.33 4	99.30 24	99.00 48	97.27 37	99.92 4	97.64 44	99.92 24	99.75 13

v7n		98.73 13	98.99 7	97.95 82	99.64 12	94.20 126	98.67 12	99.14 20	99.08 9	99.42 16	99.23 29	96.53 69	99.91 12	99.27 4	99.93 21	99.73 16

PS-CasMVS		98.73 13	98.85 13	98.39 55	99.55 21	95.47 85	98.49 22	99.13 21	99.22 7	99.22 28	98.96 52	97.35 33	99.92 4	97.79 39	99.93 21	99.79 8

test_djsdf		98.73 13	98.74 18	98.69 37	99.63 13	96.30 60	98.67 12	99.02 51	96.50 99	99.32 21	99.44 10	97.43 30	99.92 4	98.73 17	99.95 13	99.86 3

anonymousdsp		98.72 16	98.63 21	98.99 10	99.62 14	97.29 34	98.65 15	99.19 14	95.62 131	99.35 20	99.37 14	97.38 32	99.90 13	98.59 23	99.91 27	99.77 9

wuykxyi23d		98.68 17	98.53 26	99.13 3	99.44 34	97.97 7	96.85 117	99.02 51	95.81 126	99.88 2	99.38 13	98.14 14	99.69 97	98.32 28	99.95 13	99.73 16

WR-MVS_H		98.65 18	98.62 23	98.75 30	99.51 26	96.61 51	98.55 19	99.17 15	99.05 12	99.17 31	98.79 60	95.47 105	99.89 17	97.95 32	99.91 27	99.75 13

OurMVSNet-221017-0		98.61 19	98.61 25	98.63 41	99.77 4	96.35 58	99.17 6	99.05 38	98.05 41	99.61 11	99.52 5	93.72 164	99.88 19	98.72 20	99.88 34	99.65 24

v748		98.58 20	98.89 10	97.67 99	99.61 15	93.53 149	98.59 16	98.90 75	98.97 17	99.43 15	99.15 40	96.53 69	99.85 24	98.88 11	99.91 27	99.64 27

nrg030		98.54 21	98.62 23	98.32 61	99.22 56	95.66 78	97.90 56	99.08 30	98.31 32	99.02 37	98.74 65	97.68 24	99.61 134	97.77 40	99.85 39	99.70 19

PS-MVSNAJss		98.53 22	98.63 21	98.21 69	99.68 9	94.82 105	98.10 44	99.21 11	96.91 87	99.75 4	99.45 9	95.82 91	99.92 4	98.80 13	99.96 11	99.89 1

MIMVSNet1		98.51 23	98.45 31	98.67 38	99.72 6	96.71 46	98.76 10	98.89 77	98.49 25	99.38 18	99.14 41	95.44 107	99.84 28	96.47 81	99.80 46	99.47 64

pm-mvs1		98.47 24	98.67 19	97.86 86	99.52 25	94.58 113	98.28 31	99.00 62	97.57 63	99.27 26	99.22 30	98.32 10	99.50 175	97.09 68	99.75 54	99.50 50

ACMH	93.61 9	98.44 25	98.76 16	97.51 109	99.43 37	93.54 148	98.23 34	99.05 38	97.40 79	99.37 19	99.08 46	98.79 6	99.47 182	97.74 42	99.71 63	99.50 50
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CP-MVSNet		98.42 26	98.46 29	98.30 64	99.46 32	95.22 93	98.27 33	98.84 87	99.05 12	99.01 38	98.65 73	95.37 108	99.90 13	97.57 48	99.91 27	99.77 9

abl_6		98.42 26	98.19 41	99.09 4	99.16 64	98.10 5	97.73 69	99.11 23	97.76 50	98.62 57	98.27 104	97.88 21	99.80 37	95.67 105	99.50 112	99.38 96

TransMVSNet (Re)		98.38 28	98.67 19	97.51 109	99.51 26	93.39 153	98.20 39	98.87 81	98.23 35	99.48 12	99.27 25	98.47 9	99.55 156	96.52 78	99.53 105	99.60 34

TranMVSNet+NR-MVSNet		98.33 29	98.30 39	98.43 51	99.07 81	95.87 70	96.73 122	99.05 38	98.67 21	98.84 45	98.45 86	97.58 27	99.88 19	96.45 82	99.86 38	99.54 45

HPM-MVS_fast		98.32 30	98.13 44	98.88 23	99.54 23	97.48 27	98.35 28	99.03 50	95.88 122	97.88 132	98.22 109	98.15 13	99.74 59	96.50 80	99.62 79	99.42 86

ANet_high		98.31 31	98.94 8	96.41 177	99.33 47	89.64 214	97.92 55	99.56 4	99.27 5	99.66 8	99.50 6	97.67 25	99.83 30	97.55 49	99.98 3	99.77 9

VPA-MVSNet		98.27 32	98.46 29	97.70 95	99.06 82	93.80 138	97.76 64	99.00 62	98.40 29	99.07 35	98.98 50	96.89 50	99.75 54	97.19 65	99.79 47	99.55 44

Vis-MVSNet		98.27 32	98.34 35	98.07 74	99.33 47	95.21 95	98.04 48	99.46 6	97.32 82	97.82 141	99.11 43	96.75 59	99.86 23	97.84 36	99.36 155	99.15 134
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
COLMAP_ROB	94.48 6	98.25 34	98.11 45	98.64 40	99.21 59	97.35 32	97.96 52	99.16 16	98.34 31	98.78 48	98.52 81	97.32 34	99.45 191	94.08 168	99.67 73	99.13 137
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
ACMH+	93.58 10	98.23 35	98.31 37	97.98 81	99.39 42	95.22 93	97.55 81	99.20 13	98.21 36	99.25 27	98.51 82	98.21 12	99.40 210	94.79 145	99.72 59	99.32 107

FC-MVSNet-test		98.16 36	98.37 33	97.56 104	99.49 30	93.10 157	98.35 28	99.21 11	98.43 28	98.89 44	98.83 59	94.30 143	99.81 33	97.87 35	99.91 27	99.77 9

MTAPA		98.14 37	97.84 57	99.06 5	99.44 34	97.90 8	97.25 92	98.73 113	97.69 57	97.90 128	97.96 138	95.81 95	99.82 31	96.13 88	99.61 84	99.45 71

APDe-MVS		98.14 37	98.03 50	98.47 49	98.72 111	96.04 67	98.07 46	99.10 25	95.96 119	98.59 61	98.69 69	96.94 48	99.81 33	96.64 74	99.58 92	99.57 40

APD-MVS_3200maxsize		98.13 39	97.90 54	98.79 28	98.79 104	97.31 33	97.55 81	98.92 73	97.72 55	98.25 89	98.13 121	97.10 43	99.75 54	95.44 117	99.24 176	99.32 107

HPM-MVS		98.11 40	97.83 58	98.92 19	99.42 39	97.46 28	98.57 17	99.05 38	95.43 140	97.41 156	97.50 179	97.98 17	99.79 38	95.58 114	99.57 95	99.50 50
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
Gipuma		98.07 41	98.31 37	97.36 126	99.76 5	96.28 61	98.51 21	99.10 25	98.76 20	96.79 183	99.34 20	96.61 66	98.82 289	96.38 83	99.50 112	96.98 288
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ACMMP		98.05 42	97.75 63	98.93 18	99.23 55	97.60 19	98.09 45	98.96 70	95.75 128	97.91 127	98.06 130	96.89 50	99.76 48	95.32 122	99.57 95	99.43 84
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
ACMM	93.33 11	98.05 42	97.79 59	98.85 24	99.15 67	97.55 23	96.68 124	98.83 95	95.21 148	98.36 77	98.13 121	98.13 16	99.62 128	96.04 92	99.54 103	99.39 94
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
v13		98.02 44	98.52 27	96.51 170	99.02 88	90.14 205	98.07 46	99.09 29	98.10 40	99.13 32	99.35 18	94.84 122	99.74 59	99.12 5	99.98 3	99.65 24

SteuartSystems-ACMMP		98.02 44	97.76 62	98.79 28	99.43 37	97.21 36	97.15 96	98.90 75	96.58 98	98.08 107	97.87 149	97.02 47	99.76 48	95.25 124	99.59 89	99.40 91
Skip Steuart: Steuart Systems R&D Blog.
zzz-MVS		98.01 46	97.66 69	99.06 5	99.44 34	97.90 8	95.66 177	98.73 113	97.69 57	97.90 128	97.96 138	95.81 95	99.82 31	96.13 88	99.61 84	99.45 71

v12		97.97 47	98.47 28	96.46 174	98.98 92	90.01 209	97.97 51	99.08 30	98.00 43	99.11 34	99.34 20	94.70 125	99.73 64	99.07 6	99.98 3	99.64 27

XVS		97.96 48	97.63 74	98.94 15	99.15 67	97.66 16	97.77 62	98.83 95	97.42 71	96.32 204	97.64 167	96.49 72	99.72 70	95.66 107	99.37 152	99.45 71

NR-MVSNet		97.96 48	97.86 56	98.26 66	98.73 109	95.54 81	98.14 42	98.73 113	97.79 48	99.42 16	97.83 150	94.40 140	99.78 39	95.91 100	99.76 50	99.46 66

ACMMPR		97.95 50	97.62 76	98.94 15	99.20 60	97.56 22	97.59 78	98.83 95	96.05 113	97.46 154	97.63 168	96.77 58	99.76 48	95.61 111	99.46 126	99.49 58

FMVSNet1		97.95 50	98.08 46	97.56 104	99.14 75	93.67 142	98.23 34	98.66 130	97.41 78	99.00 40	99.19 32	95.47 105	99.73 64	95.83 101	99.76 50	99.30 111

HFP-MVS		97.94 52	97.64 72	98.83 25	99.15 67	97.50 25	97.59 78	98.84 87	96.05 113	97.49 149	97.54 174	97.07 45	99.70 88	95.61 111	99.46 126	99.30 111

LPG-MVS_test		97.94 52	97.67 68	98.74 32	99.15 67	97.02 38	97.09 105	99.02 51	95.15 153	98.34 79	98.23 106	97.91 19	99.70 88	94.41 156	99.73 56	99.50 50

FIs		97.93 54	98.07 47	97.48 116	99.38 43	92.95 159	98.03 50	99.11 23	98.04 42	98.62 57	98.66 71	93.75 163	99.78 39	97.23 61	99.84 40	99.73 16

region2R		97.92 55	97.59 78	98.92 19	99.22 56	97.55 23	97.60 77	98.84 87	96.00 117	97.22 161	97.62 169	96.87 53	99.76 48	95.48 115	99.43 140	99.46 66

CP-MVS		97.92 55	97.56 81	98.99 10	98.99 90	97.82 12	97.93 54	98.96 70	96.11 112	96.89 181	97.45 182	96.85 54	99.78 39	95.19 127	99.63 78	99.38 96

mPP-MVS		97.91 57	97.53 82	99.04 7	99.22 56	97.87 11	97.74 67	98.78 105	96.04 115	97.10 167	97.73 162	96.53 69	99.78 39	95.16 131	99.50 112	99.46 66

V9		97.90 58	98.40 32	96.40 178	98.93 94	89.86 211	97.86 58	99.07 34	97.88 47	99.05 36	99.30 23	94.53 136	99.72 70	99.01 8	99.98 3	99.63 29

ACMMP_Plus		97.89 59	97.63 74	98.67 38	99.35 46	96.84 43	96.36 135	98.79 102	95.07 160	97.88 132	98.35 93	97.24 40	99.72 70	96.05 91	99.58 92	99.45 71

PGM-MVS		97.88 60	97.52 83	98.96 13	99.20 60	97.62 18	97.09 105	99.06 36	95.45 138	97.55 145	97.94 142	97.11 42	99.78 39	94.77 147	99.46 126	99.48 61

DP-MVS		97.87 61	97.89 55	97.81 89	98.62 127	94.82 105	97.13 99	98.79 102	98.98 16	98.74 52	98.49 83	95.80 97	99.49 177	95.04 138	99.44 131	99.11 145

RPSCF		97.87 61	97.51 84	98.95 14	99.15 67	98.43 3	97.56 80	99.06 36	96.19 111	98.48 69	98.70 68	94.72 124	99.24 243	94.37 159	99.33 165	99.17 130

test_0402		97.84 63	97.97 51	97.47 117	99.19 62	94.07 129	96.71 123	98.73 113	98.66 22	98.56 63	98.41 88	96.84 55	99.69 97	94.82 142	99.81 43	98.64 199

V14		97.83 64	98.33 36	96.35 179	98.88 100	89.72 212	97.75 65	99.05 38	97.74 51	99.01 38	99.27 25	94.35 141	99.71 80	98.95 9	99.97 8	99.62 31

UniMVSNet_NR-MVSNet		97.83 64	97.65 70	98.37 56	98.72 111	95.78 72	95.66 177	99.02 51	98.11 39	98.31 84	97.69 166	94.65 130	99.85 24	97.02 70	99.71 63	99.48 61

UniMVSNet (Re)		97.83 64	97.65 70	98.35 60	98.80 103	95.86 71	95.92 165	99.04 45	97.51 68	98.22 91	97.81 154	94.68 128	99.78 39	97.14 67	99.75 54	99.41 88

v11		97.82 67	98.36 34	96.17 195	98.93 94	89.16 231	97.79 61	99.08 30	97.64 60	99.19 29	99.32 22	94.28 144	99.72 70	99.07 6	99.97 8	99.63 29

DeepC-MVS	95.41 4	97.82 67	97.70 65	98.16 70	98.78 105	95.72 74	96.23 144	99.02 51	93.92 197	98.62 57	98.99 49	97.69 23	99.62 128	96.18 87	99.87 36	99.15 134
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DU-MVS		97.79 69	97.60 77	98.36 59	98.73 109	95.78 72	95.65 179	98.87 81	97.57 63	98.31 84	97.83 150	94.69 126	99.85 24	97.02 70	99.71 63	99.46 66

v15		97.77 70	98.26 40	96.30 184	98.81 102	89.59 219	97.62 74	99.04 45	97.59 62	98.97 42	99.24 27	94.19 148	99.70 88	98.88 11	99.97 8	99.61 33

LS3D		97.77 70	97.50 85	98.57 44	96.24 299	97.58 21	98.45 25	98.85 84	98.58 24	97.51 147	97.94 142	95.74 98	99.63 122	95.19 127	98.97 200	98.51 210

3Dnovator+	96.13 3	97.73 72	97.59 78	98.15 71	98.11 196	95.60 79	98.04 48	98.70 122	98.13 38	96.93 179	98.45 86	95.30 112	99.62 128	95.64 109	98.96 201	99.24 123

tfpnnormal		97.72 73	97.97 51	96.94 147	99.26 51	92.23 170	97.83 60	98.45 152	98.25 34	99.13 32	98.66 71	96.65 63	99.69 97	93.92 173	99.62 79	98.91 172

Baseline_NR-MVSNet		97.72 73	97.79 59	97.50 112	99.56 19	93.29 154	95.44 188	98.86 83	98.20 37	98.37 76	99.24 27	94.69 126	99.55 156	95.98 97	99.79 47	99.65 24

v17		97.70 75	98.17 42	96.28 187	98.77 106	89.59 219	97.62 74	99.01 60	97.54 65	98.72 54	99.18 35	94.06 152	99.68 103	98.74 16	99.92 24	99.58 36

MP-MVS-pluss		97.69 76	97.36 90	98.70 36	99.50 29	96.84 43	95.38 197	98.99 65	92.45 237	98.11 101	98.31 97	97.25 39	99.77 47	96.60 75	99.62 79	99.48 61
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
v16		97.69 76	98.16 43	96.29 186	98.75 107	89.60 217	97.62 74	99.01 60	97.53 67	98.69 56	99.18 35	94.05 153	99.68 103	98.73 17	99.88 34	99.58 36

EG-PatchMatch MVS		97.69 76	97.79 59	97.40 124	99.06 82	93.52 150	95.96 161	98.97 69	94.55 177	98.82 46	98.76 63	97.31 35	99.29 237	97.20 64	99.44 131	99.38 96

MP-MVS		97.64 79	97.18 106	99.00 9	99.32 49	97.77 14	97.49 84	98.73 113	96.27 107	95.59 232	97.75 159	96.30 79	99.78 39	93.70 179	99.48 122	99.45 71

#test#		97.62 80	97.22 103	98.83 25	99.15 67	97.50 25	96.81 119	98.84 87	94.25 188	97.49 149	97.54 174	97.07 45	99.70 88	94.37 159	99.46 126	99.30 111

3Dnovator	96.53 2	97.61 81	97.64 72	97.50 112	97.74 238	93.65 146	98.49 22	98.88 79	96.86 91	97.11 166	98.55 79	95.82 91	99.73 64	95.94 98	99.42 143	99.13 137

v18		97.60 82	98.06 48	96.23 188	98.68 121	89.46 222	97.48 85	98.98 67	97.33 81	98.60 60	99.13 42	93.86 156	99.67 110	98.62 21	99.87 36	99.56 41

v8		97.60 82	98.06 48	96.23 188	98.71 114	89.44 223	97.43 87	98.82 99	97.29 83	98.74 52	99.10 44	93.86 156	99.68 103	98.61 22	99.94 19	99.56 41

XVG-ACMP-BASELINE		97.58 84	97.28 95	98.49 47	99.16 64	96.90 42	96.39 130	98.98 67	95.05 161	98.06 110	98.02 133	95.86 87	99.56 152	94.37 159	99.64 77	99.00 158

SMA-MVS		97.55 85	97.19 105	98.61 42	98.83 101	96.71 46	96.74 121	98.81 101	91.81 249	98.78 48	98.36 92	96.63 65	99.68 103	95.17 129	99.59 89	99.45 71

v10		97.55 85	97.97 51	96.31 183	98.60 129	89.64 214	97.44 86	99.02 51	96.60 96	98.72 54	99.16 39	93.48 168	99.72 70	98.76 15	99.92 24	99.58 36

OPM-MVS		97.54 87	97.25 96	98.41 52	99.11 77	96.61 51	95.24 209	98.46 151	94.58 176	98.10 104	98.07 127	97.09 44	99.39 216	95.16 131	99.44 131	99.21 125

XXY-MVS		97.54 87	97.70 65	97.07 140	99.46 32	92.21 171	97.22 95	99.00 62	94.93 164	98.58 62	98.92 56	97.31 35	99.41 207	94.44 154	99.43 140	99.59 35

Regformer-4		97.53 89	97.47 87	97.71 94	97.35 266	93.91 134	95.26 207	98.14 198	97.97 44	98.34 79	97.89 147	95.49 103	99.71 80	97.41 57	99.42 143	99.51 49

SixPastTwentyTwo		97.49 90	97.57 80	97.26 132	99.56 19	92.33 167	98.28 31	96.97 258	98.30 33	99.45 14	99.35 18	88.43 254	99.89 17	98.01 31	99.76 50	99.54 45

ACMP	92.54 13	97.47 91	97.10 113	98.55 46	99.04 85	96.70 48	96.24 143	98.89 77	93.71 207	97.97 119	97.75 159	97.44 29	99.63 122	93.22 187	99.70 66	99.32 107
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
testing_2		97.43 92	97.71 64	96.60 163	98.91 97	90.85 195	96.01 154	98.54 144	94.78 169	98.78 48	98.96 52	96.35 78	99.54 158	97.25 60	99.82 42	99.40 91

TSAR-MVS + MP.		97.42 93	97.23 102	98.00 80	99.38 43	95.00 99	97.63 73	98.20 189	93.00 223	98.16 96	98.06 130	95.89 86	99.72 70	95.67 105	99.10 189	99.28 118

Regformer-2		97.41 94	97.24 98	97.93 83	97.21 275	94.72 108	94.85 230	98.27 181	97.74 51	98.11 101	97.50 179	95.58 101	99.69 97	96.57 77	99.31 167	99.37 101

CSCG		97.40 95	97.30 92	97.69 97	98.95 93	94.83 104	97.28 91	98.99 65	96.35 106	98.13 100	95.95 264	95.99 84	99.66 115	94.36 162	99.73 56	98.59 204

XVG-OURS-SEG-HR		97.38 96	97.07 116	98.30 64	99.01 89	97.41 31	94.66 235	99.02 51	95.20 149	98.15 98	97.52 177	98.83 5	98.43 317	94.87 140	96.41 311	99.07 152

HSP-MVS		97.37 97	96.85 126	98.92 19	99.26 51	97.70 15	97.66 70	98.23 185	95.65 129	98.51 66	96.46 240	92.15 204	99.81 33	95.14 133	98.58 236	99.26 122

VDD-MVS		97.37 97	97.25 96	97.74 93	98.69 120	94.50 116	97.04 107	95.61 283	98.59 23	98.51 66	98.72 66	92.54 196	99.58 146	96.02 94	99.49 119	99.12 142

SD-MVS		97.37 97	97.70 65	96.35 179	98.14 192	95.13 96	96.54 125	98.92 73	95.94 120	99.19 29	98.08 126	97.74 22	95.06 349	95.24 125	99.54 103	98.87 181

PM-MVS		97.36 100	97.10 113	98.14 72	98.91 97	96.77 45	96.20 145	98.63 137	93.82 204	98.54 64	98.33 95	93.98 154	99.05 261	95.99 96	99.45 130	98.61 203

LCM-MVSNet-Re		97.33 101	97.33 91	97.32 128	98.13 195	93.79 139	96.99 109	99.65 2	96.74 94	99.47 13	98.93 55	96.91 49	99.84 28	90.11 247	99.06 195	98.32 227

EI-MVSNet-UG-set		97.32 102	97.40 88	97.09 139	97.34 269	92.01 179	95.33 201	97.65 231	97.74 51	98.30 86	98.14 120	95.04 118	99.69 97	97.55 49	99.52 109	99.58 36

EI-MVSNet-Vis-set		97.32 102	97.39 89	97.11 137	97.36 265	92.08 177	95.34 200	97.65 231	97.74 51	98.29 87	98.11 124	95.05 116	99.68 103	97.50 53	99.50 112	99.56 41

Regformer-1		97.27 104	97.16 108	97.61 102	97.21 275	93.86 136	94.85 230	98.04 209	97.62 61	98.03 113	97.50 179	95.34 109	99.63 122	96.52 78	99.31 167	99.35 105

VPNet		97.26 105	97.49 86	96.59 165	99.47 31	90.58 201	96.27 139	98.53 145	97.77 49	98.46 71	98.41 88	94.59 132	99.68 103	94.61 150	99.29 171	99.52 48

Regformer-3		97.25 106	97.29 93	97.11 137	97.35 266	92.32 168	95.26 207	97.62 236	97.67 59	98.17 95	97.89 147	95.05 116	99.56 152	97.16 66	99.42 143	99.46 66

canonicalmvs		97.23 107	97.21 104	97.30 129	97.65 247	94.39 118	97.84 59	99.05 38	97.42 71	96.68 186	93.85 304	97.63 26	99.33 230	96.29 85	98.47 241	98.18 242

ESAPD		97.22 108	96.82 129	98.40 54	99.03 86	96.07 65	95.64 181	98.84 87	94.84 165	98.08 107	97.60 171	96.69 61	99.76 48	91.22 219	99.44 131	99.37 101

AllTest		97.20 109	96.92 124	98.06 75	99.08 79	96.16 62	97.14 98	99.16 16	94.35 185	97.78 142	98.07 127	95.84 88	99.12 252	91.41 213	99.42 143	98.91 172

XVG-OURS		97.12 110	96.74 134	98.26 66	98.99 90	97.45 29	93.82 271	99.05 38	95.19 150	98.32 82	97.70 165	95.22 114	98.41 318	94.27 164	98.13 252	98.93 169

V42		97.04 111	97.16 108	96.68 161	98.59 131	91.05 192	96.33 137	98.36 166	94.60 173	97.99 115	98.30 100	93.32 174	99.62 128	97.40 58	99.53 105	99.38 96

APD-MVS		97.00 112	96.53 146	98.41 52	98.55 136	96.31 59	96.32 138	98.77 106	92.96 229	97.44 155	97.58 173	95.84 88	99.74 59	91.96 201	99.35 158	99.19 127
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
HPM-MVS++		96.99 113	96.38 151	98.81 27	98.64 122	97.59 20	95.97 157	98.20 189	95.51 136	95.06 240	96.53 236	94.10 151	99.70 88	94.29 163	99.15 182	99.13 137

GBi-Net		96.99 113	96.80 131	97.56 104	97.96 209	93.67 142	98.23 34	98.66 130	95.59 133	97.99 115	99.19 32	89.51 245	99.73 64	94.60 151	99.44 131	99.30 111

test1		96.99 113	96.80 131	97.56 104	97.96 209	93.67 142	98.23 34	98.66 130	95.59 133	97.99 115	99.19 32	89.51 245	99.73 64	94.60 151	99.44 131	99.30 111

VDDNet		96.98 116	96.84 127	97.41 123	99.40 41	93.26 155	97.94 53	95.31 285	99.26 6	98.39 75	99.18 35	87.85 261	99.62 128	95.13 134	99.09 190	99.35 105

v1neww		96.97 117	97.24 98	96.15 196	98.70 116	89.44 223	95.97 157	98.33 171	95.25 145	97.88 132	98.15 117	93.83 159	99.61 134	97.50 53	99.50 112	99.41 88

v7new		96.97 117	97.24 98	96.15 196	98.70 116	89.44 223	95.97 157	98.33 171	95.25 145	97.88 132	98.15 117	93.83 159	99.61 134	97.50 53	99.50 112	99.41 88

v6		96.97 117	97.24 98	96.15 196	98.71 114	89.44 223	95.97 157	98.33 171	95.25 145	97.89 130	98.15 117	93.86 156	99.61 134	97.51 52	99.50 112	99.42 86

PHI-MVS		96.96 120	96.53 146	98.25 68	97.48 256	96.50 54	96.76 120	98.85 84	93.52 210	96.19 213	96.85 215	95.94 85	99.42 196	93.79 177	99.43 140	98.83 185

v7		96.93 121	97.17 107	96.23 188	98.59 131	89.64 214	95.96 161	98.66 130	94.41 181	97.87 137	98.38 91	93.47 169	99.64 119	97.93 33	99.24 176	99.43 84

IS-MVSNet		96.93 121	96.68 136	97.70 95	99.25 54	94.00 132	98.57 17	96.74 265	98.36 30	98.14 99	97.98 137	88.23 255	99.71 80	93.10 190	99.72 59	99.38 96

CNVR-MVS		96.92 123	96.55 143	98.03 79	98.00 206	95.54 81	94.87 228	98.17 194	94.60 173	96.38 198	97.05 203	95.67 99	99.36 225	95.12 135	99.08 191	99.19 127

IterMVS-LS		96.92 123	97.29 93	95.79 218	98.51 143	88.13 254	95.10 213	98.66 130	96.99 84	98.46 71	98.68 70	92.55 194	99.74 59	96.91 72	99.79 47	99.50 50
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
WR-MVS		96.90 125	96.81 130	97.16 134	98.56 135	92.20 173	94.33 243	98.12 200	97.34 80	98.20 93	97.33 192	92.81 185	99.75 54	94.79 145	99.81 43	99.54 45

DeepPCF-MVS	94.58 5	96.90 125	96.43 150	98.31 63	97.48 256	97.23 35	92.56 304	98.60 140	92.84 231	98.54 64	97.40 185	96.64 64	98.78 293	94.40 158	99.41 149	98.93 169

v1141		96.86 127	97.14 110	96.04 203	98.55 136	89.06 234	95.44 188	98.33 171	95.14 155	97.93 125	98.19 111	93.36 172	99.62 128	97.61 45	99.69 67	99.44 80

divwei89l23v2f112		96.86 127	97.14 110	96.04 203	98.54 139	89.06 234	95.44 188	98.33 171	95.14 155	97.93 125	98.19 111	93.36 172	99.61 134	97.61 45	99.68 71	99.44 80

v1		96.86 127	97.14 110	96.04 203	98.55 136	89.06 234	95.44 188	98.33 171	95.14 155	97.94 122	98.18 115	93.39 171	99.61 134	97.61 45	99.69 67	99.44 80

v1144		96.84 130	97.08 115	96.13 200	98.42 153	89.28 229	95.41 195	98.67 128	94.21 190	97.97 119	98.31 97	93.06 179	99.65 116	98.06 30	99.62 79	99.45 71

VNet		96.84 130	96.83 128	96.88 151	98.06 198	92.02 178	96.35 136	97.57 238	97.70 56	97.88 132	97.80 155	92.40 201	99.54 158	94.73 149	98.96 201	99.08 150

EPP-MVSNet		96.84 130	96.58 140	97.65 100	99.18 63	93.78 140	98.68 11	96.34 268	97.91 46	97.30 159	98.06 130	88.46 253	99.85 24	93.85 175	99.40 150	99.32 107

v1192		96.83 133	97.06 117	96.15 196	98.28 163	89.29 228	95.36 198	98.77 106	93.73 206	98.11 101	98.34 94	93.02 183	99.67 110	98.35 26	99.58 92	99.50 50

MVS_111021_LR		96.82 134	96.55 143	97.62 101	98.27 165	95.34 88	93.81 272	98.33 171	94.59 175	96.56 190	96.63 231	96.61 66	98.73 297	94.80 144	99.34 160	98.78 190

Effi-MVS+-dtu		96.81 135	96.09 160	98.99 10	96.90 287	98.69 2	96.42 129	98.09 202	95.86 123	95.15 239	95.54 274	94.26 145	99.81 33	94.06 169	98.51 239	98.47 212

UGNet		96.81 135	96.56 142	97.58 103	96.64 290	93.84 137	97.75 65	97.12 253	96.47 102	93.62 288	98.88 58	93.22 177	99.53 160	95.61 111	99.69 67	99.36 104
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
v2v482		96.78 137	97.06 117	95.95 211	98.57 134	88.77 244	95.36 198	98.26 183	95.18 151	97.85 139	98.23 106	92.58 193	99.63 122	97.80 38	99.69 67	99.45 71

v1240		96.74 138	97.02 119	95.91 214	98.18 185	88.52 246	95.39 196	98.88 79	93.15 220	98.46 71	98.40 90	92.80 186	99.71 80	98.45 25	99.49 119	99.49 58

DeepC-MVS_fast	94.34 7	96.74 138	96.51 148	97.44 121	97.69 242	94.15 127	96.02 153	98.43 156	93.17 219	97.30 159	97.38 190	95.48 104	99.28 238	93.74 178	99.34 160	98.88 179
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MVS_111021_HR		96.73 140	96.54 145	97.27 130	98.35 157	93.66 145	93.42 285	98.36 166	94.74 170	96.58 188	96.76 224	96.54 68	98.99 269	94.87 140	99.27 174	99.15 134

v1921920		96.72 141	96.96 122	95.99 207	98.21 178	88.79 243	95.42 193	98.79 102	93.22 214	98.19 94	98.26 105	92.68 189	99.70 88	98.34 27	99.55 101	99.49 58

FMVSNet2		96.72 141	96.67 137	96.87 152	97.96 209	91.88 181	97.15 96	98.06 207	95.59 133	98.50 68	98.62 74	89.51 245	99.65 116	94.99 139	99.60 87	99.07 152

PMVS	89.60 17	96.71 143	96.97 120	95.95 211	99.51 26	97.81 13	97.42 88	97.49 239	97.93 45	95.95 219	98.58 75	96.88 52	96.91 343	89.59 254	99.36 155	93.12 342
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
v144192		96.69 144	96.90 125	96.03 206	98.25 174	88.92 237	95.49 186	98.77 106	93.05 222	98.09 105	98.29 101	92.51 198	99.70 88	98.11 29	99.56 97	99.47 64

CPTT-MVS		96.69 144	96.08 161	98.49 47	98.89 99	96.64 50	97.25 92	98.77 106	92.89 230	96.01 218	97.13 199	92.23 203	99.67 110	92.24 199	99.34 160	99.17 130

HQP_MVS		96.66 146	96.33 154	97.68 98	98.70 116	94.29 121	96.50 127	98.75 110	96.36 104	96.16 214	96.77 222	91.91 216	99.46 187	92.59 195	99.20 179	99.28 118

EI-MVSNet		96.63 147	96.93 123	95.74 219	97.26 273	88.13 254	95.29 205	97.65 231	96.99 84	97.94 122	98.19 111	92.55 194	99.58 146	96.91 72	99.56 97	99.50 50

ab-mvs		96.59 148	96.59 139	96.60 163	98.64 122	92.21 171	98.35 28	97.67 227	94.45 178	96.99 171	98.79 60	94.96 120	99.49 177	90.39 244	99.07 193	98.08 245

v148		96.58 149	96.97 120	95.42 229	98.63 126	87.57 269	95.09 215	97.90 212	95.91 121	98.24 90	97.96 138	93.42 170	99.39 216	96.04 92	99.52 109	99.29 117

test20.03		96.58 149	96.61 138	96.48 173	98.49 145	91.72 185	95.68 176	97.69 226	96.81 92	98.27 88	97.92 145	94.18 149	98.71 299	90.78 231	99.66 75	99.00 158

NCCC		96.52 151	95.99 165	98.10 73	97.81 223	95.68 76	95.00 224	98.20 189	95.39 141	95.40 235	96.36 247	93.81 161	99.45 191	93.55 182	98.42 242	99.17 130

pmmvs-eth3d		96.49 152	96.18 157	97.42 122	98.25 174	94.29 121	94.77 234	98.07 206	89.81 266	97.97 119	98.33 95	93.11 178	99.08 258	95.46 116	99.84 40	98.89 175

OMC-MVS		96.48 153	96.00 164	97.91 84	98.30 159	96.01 69	94.86 229	98.60 140	91.88 247	97.18 163	97.21 196	96.11 82	99.04 262	90.49 242	99.34 160	98.69 197

TSAR-MVS + GP.		96.47 154	96.12 158	97.49 115	97.74 238	95.23 90	94.15 256	96.90 260	93.26 213	98.04 112	96.70 227	94.41 139	98.89 281	94.77 147	99.14 183	98.37 220

Fast-Effi-MVS+-dtu		96.44 155	96.12 158	97.39 125	97.18 277	94.39 118	95.46 187	98.73 113	96.03 116	94.72 248	94.92 286	96.28 81	99.69 97	93.81 176	97.98 256	98.09 244

K. test v3		96.44 155	96.28 155	96.95 146	99.41 40	91.53 187	97.65 71	90.31 332	98.89 18	98.93 43	99.36 16	84.57 279	99.92 4	97.81 37	99.56 97	99.39 94

MSLP-MVS++		96.42 157	96.71 135	95.57 224	97.82 222	90.56 203	95.71 172	98.84 87	94.72 171	96.71 185	97.39 188	94.91 121	98.10 333	95.28 123	99.02 197	98.05 250

MVS_Test		96.27 158	96.79 133	94.73 252	96.94 285	86.63 285	96.18 146	98.33 171	94.94 162	96.07 216	98.28 102	95.25 113	99.26 241	97.21 62	97.90 263	98.30 230

MCST-MVS		96.24 159	95.80 171	97.56 104	98.75 107	94.13 128	94.66 235	98.17 194	90.17 263	96.21 212	96.10 258	95.14 115	99.43 195	94.13 167	98.85 216	99.13 137

MVS_0304		96.22 160	95.94 169	97.04 142	97.07 281	92.54 163	94.19 252	99.04 45	95.17 152	93.74 283	96.92 212	91.77 218	99.73 64	95.76 103	99.81 43	98.85 184

mvs-test1		96.20 161	95.50 179	98.32 61	96.90 287	98.16 4	95.07 218	98.09 202	95.86 123	93.63 287	94.32 300	94.26 145	99.71 80	94.06 169	97.27 298	97.07 285

Effi-MVS+		96.19 162	96.01 163	96.71 158	97.43 262	92.19 174	96.12 149	99.10 25	95.45 138	93.33 301	94.71 288	97.23 41	99.56 152	93.21 188	97.54 286	98.37 220

DELS-MVS		96.17 163	96.23 156	95.99 207	97.55 254	90.04 207	92.38 308	98.52 146	94.13 193	96.55 193	97.06 202	94.99 119	99.58 146	95.62 110	99.28 172	98.37 220
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
MVSFormer		96.14 164	96.36 152	95.49 228	97.68 243	87.81 266	98.67 12	99.02 51	96.50 99	94.48 262	96.15 255	86.90 266	99.92 4	98.73 17	99.13 185	98.74 193

testgi		96.07 165	96.50 149	94.80 249	99.26 51	87.69 268	95.96 161	98.58 143	95.08 159	98.02 114	96.25 251	97.92 18	97.60 339	88.68 269	98.74 222	99.11 145

LF4IMVS		96.07 165	95.63 176	97.36 126	98.19 182	95.55 80	95.44 188	98.82 99	92.29 239	95.70 230	96.55 234	92.63 192	98.69 301	91.75 210	99.33 165	97.85 260

alignmvs		96.01 167	95.52 178	97.50 112	97.77 237	94.71 109	96.07 150	96.84 261	97.48 69	96.78 184	94.28 301	85.50 272	99.40 210	96.22 86	98.73 225	98.40 217

TinyColmap		96.00 168	96.34 153	94.96 243	97.90 214	87.91 263	94.13 258	98.49 149	94.41 181	98.16 96	97.76 156	96.29 80	98.68 304	90.52 239	99.42 143	98.30 230

PVSNet_Blended_VisFu		95.95 169	95.80 171	96.42 176	99.28 50	90.62 200	95.31 203	99.08 30	88.40 277	96.97 177	98.17 116	92.11 206	99.78 39	93.64 180	99.21 178	98.86 182

test_prior3		95.91 170	95.39 182	97.46 118	97.79 232	94.26 124	93.33 289	98.42 159	94.21 190	94.02 274	96.25 251	93.64 165	99.34 227	91.90 202	98.96 201	98.79 188

UnsupCasMVSNet_eth		95.91 170	95.73 173	96.44 175	98.48 147	91.52 188	95.31 203	98.45 152	95.76 127	97.48 152	97.54 174	89.53 244	98.69 301	94.43 155	94.61 328	99.13 137

QAPM		95.88 172	95.57 177	96.80 153	97.90 214	91.84 183	98.18 41	98.73 113	88.41 276	96.42 196	98.13 121	94.73 123	99.75 54	88.72 267	98.94 205	98.81 186

CANet		95.86 173	95.65 175	96.49 172	96.41 297	90.82 197	94.36 242	98.41 161	94.94 162	92.62 313	96.73 225	92.68 189	99.71 80	95.12 135	99.60 87	98.94 166

MVP-Stereo		95.69 174	95.28 184	96.92 148	98.15 191	93.03 158	95.64 181	98.20 189	90.39 260	96.63 187	97.73 162	91.63 219	99.10 256	91.84 206	97.31 296	98.63 201
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MDA-MVSNet-bldmvs		95.69 174	95.67 174	95.74 219	98.48 147	88.76 245	92.84 296	97.25 246	96.00 117	97.59 144	97.95 141	91.38 224	99.46 187	93.16 189	96.35 312	98.99 161

new-patchmatchnet		95.67 176	96.58 140	92.94 300	97.48 256	80.21 327	92.96 295	98.19 193	94.83 167	98.82 46	98.79 60	93.31 175	99.51 173	95.83 101	99.04 196	99.12 142

xiu_mvs_v1_base_debu		95.62 177	95.96 166	94.60 257	98.01 203	88.42 247	93.99 263	98.21 186	92.98 224	95.91 220	94.53 290	96.39 75	99.72 70	95.43 119	98.19 249	95.64 321

xiu_mvs_v1_base		95.62 177	95.96 166	94.60 257	98.01 203	88.42 247	93.99 263	98.21 186	92.98 224	95.91 220	94.53 290	96.39 75	99.72 70	95.43 119	98.19 249	95.64 321

xiu_mvs_v1_base_debi		95.62 177	95.96 166	94.60 257	98.01 203	88.42 247	93.99 263	98.21 186	92.98 224	95.91 220	94.53 290	96.39 75	99.72 70	95.43 119	98.19 249	95.64 321

DP-MVS Recon		95.55 180	95.13 188	96.80 153	98.51 143	93.99 133	94.60 237	98.69 123	90.20 262	95.78 226	96.21 254	92.73 188	98.98 271	90.58 238	98.86 214	97.42 275

test_normal		95.51 181	95.46 180	95.68 223	97.97 208	89.12 233	93.73 274	95.86 277	91.98 243	97.17 164	96.94 209	91.55 220	99.42 196	95.21 126	98.73 225	98.51 210

testmv		95.51 181	95.33 183	96.05 202	98.23 176	89.51 221	93.50 283	98.63 137	94.25 188	98.22 91	97.73 162	92.51 198	99.47 182	85.22 308	99.72 59	99.17 130

Fast-Effi-MVS+		95.49 183	95.07 190	96.75 156	97.67 246	92.82 160	94.22 250	98.60 140	91.61 250	93.42 298	92.90 315	96.73 60	99.70 88	92.60 194	97.89 264	97.74 265

TAMVS		95.49 183	94.94 195	97.16 134	98.31 158	93.41 152	95.07 218	96.82 262	91.09 255	97.51 147	97.82 153	89.96 239	99.42 196	88.42 272	99.44 131	98.64 199

OpenMVS	94.22 8	95.48 185	95.20 186	96.32 182	97.16 278	91.96 180	97.74 67	98.84 87	87.26 288	94.36 264	98.01 134	93.95 155	99.67 110	90.70 235	98.75 221	97.35 282

CLD-MVS		95.47 186	95.07 190	96.69 160	98.27 165	92.53 164	91.36 322	98.67 128	91.22 254	95.78 226	94.12 302	95.65 100	98.98 271	90.81 229	99.72 59	98.57 205
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
train_agg		95.46 187	94.66 205	97.88 85	97.84 220	95.23 90	93.62 278	98.39 162	87.04 292	93.78 280	95.99 259	94.58 133	99.52 163	91.76 208	98.90 207	98.89 175

DI_MVS_plusplus_test		95.46 187	95.43 181	95.55 225	98.05 199	88.84 241	94.18 253	95.75 279	91.92 246	97.32 158	96.94 209	91.44 222	99.39 216	94.81 143	98.48 240	98.43 216

CDPH-MVS		95.45 189	94.65 206	97.84 88	98.28 163	94.96 101	93.73 274	98.33 171	85.03 313	95.44 233	96.60 232	95.31 111	99.44 194	90.01 249	99.13 185	99.11 145

IterMVS		95.42 190	95.83 170	94.20 269	97.52 255	83.78 317	92.41 307	97.47 243	95.49 137	98.06 110	98.49 83	87.94 257	99.58 146	96.02 94	99.02 197	99.23 124
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
agg_prior1		95.39 191	94.60 209	97.75 92	97.80 227	94.96 101	93.39 286	98.36 166	87.20 290	93.49 293	95.97 262	94.65 130	99.53 160	91.69 211	98.86 214	98.77 191

Test4		95.39 191	95.24 185	95.82 217	98.07 197	89.60 217	94.40 241	98.49 149	91.39 253	97.40 157	96.32 249	87.32 265	99.41 207	95.09 137	98.71 227	98.44 215

mvs_anonymous		95.36 193	96.07 162	93.21 293	96.29 298	81.56 322	94.60 237	97.66 229	93.30 212	96.95 178	98.91 57	93.03 182	99.38 221	96.60 75	97.30 297	98.69 197

MSDG		95.33 194	95.13 188	95.94 213	97.40 264	91.85 182	91.02 325	98.37 165	95.30 143	96.31 206	95.99 259	94.51 137	98.38 322	89.59 254	97.65 282	97.60 270

LFMVS		95.32 195	94.88 199	96.62 162	98.03 200	91.47 189	97.65 71	90.72 327	99.11 8	97.89 130	98.31 97	79.20 292	99.48 180	93.91 174	99.12 188	98.93 169

agg_prior3		95.30 196	94.46 217	97.80 90	97.80 227	95.00 99	93.63 277	98.34 170	86.33 298	93.40 300	95.84 266	94.15 150	99.50 175	91.76 208	98.90 207	98.89 175

F-COLMAP		95.30 196	94.38 219	98.05 78	98.64 122	96.04 67	95.61 185	98.66 130	89.00 271	93.22 302	96.40 246	92.90 184	99.35 226	87.45 291	97.53 287	98.77 191

Anonymous20231206		95.27 198	95.06 192	95.88 215	98.72 111	89.37 227	95.70 173	97.85 215	88.00 284	96.98 172	97.62 169	91.95 212	99.34 227	89.21 259	99.53 105	98.94 166

FMVSNet3		95.26 199	94.94 195	96.22 192	96.53 293	90.06 206	95.99 155	97.66 229	94.11 194	97.99 115	97.91 146	80.22 290	99.63 122	94.60 151	99.44 131	98.96 163

N_pmnet		95.18 200	94.23 222	98.06 75	97.85 216	96.55 53	92.49 305	91.63 319	89.34 268	98.09 105	97.41 184	90.33 233	99.06 260	91.58 212	99.31 167	98.56 206

HQP-MVS		95.17 201	94.58 211	96.92 148	97.85 216	92.47 165	94.26 244	98.43 156	93.18 216	92.86 306	95.08 280	90.33 233	99.23 245	90.51 240	98.74 222	99.05 155

Vis-MVSNet (Re-imp)		95.11 202	94.85 200	95.87 216	99.12 76	89.17 230	97.54 83	94.92 287	96.50 99	96.58 188	97.27 194	83.64 280	99.48 180	88.42 272	99.67 73	98.97 162

AdaColmap		95.11 202	94.62 208	96.58 166	97.33 270	94.45 117	94.92 226	98.08 204	93.15 220	93.98 277	95.53 275	94.34 142	99.10 256	85.69 303	98.61 233	96.20 314

API-MVS		95.09 204	95.01 193	95.31 232	96.61 291	94.02 131	96.83 118	97.18 250	95.60 132	95.79 225	94.33 299	94.54 135	98.37 324	85.70 302	98.52 237	93.52 339

CNLPA		95.04 205	94.47 214	96.75 156	97.81 223	95.25 89	94.12 259	97.89 213	94.41 181	94.57 257	95.69 268	90.30 236	98.35 325	86.72 297	98.76 220	96.64 302

Patchmtry		95.03 206	94.59 210	96.33 181	94.83 324	90.82 197	96.38 134	97.20 248	96.59 97	97.49 149	98.57 76	77.67 298	99.38 221	92.95 193	99.62 79	98.80 187

PVSNet_BlendedMVS		95.02 207	94.93 197	95.27 233	97.79 232	87.40 274	94.14 257	98.68 125	88.94 272	94.51 260	98.01 134	93.04 180	99.30 234	89.77 252	99.49 119	99.11 145

diffmvs		95.00 208	95.00 194	95.01 242	96.53 293	87.96 262	95.73 170	98.32 180	90.67 259	91.89 320	97.43 183	92.07 209	98.90 278	95.44 117	96.88 301	98.16 243

TAPA-MVS	93.32 12	94.93 209	94.23 222	97.04 142	98.18 185	94.51 114	95.22 210	98.73 113	81.22 330	96.25 210	95.95 264	93.80 162	98.98 271	89.89 250	98.87 212	97.62 268
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CDS-MVSNet		94.88 210	94.12 227	97.14 136	97.64 248	93.57 147	93.96 266	97.06 255	90.05 264	96.30 207	96.55 234	86.10 269	99.47 182	90.10 248	99.31 167	98.40 217
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
no-one		94.84 211	94.76 203	95.09 239	98.29 160	87.49 271	91.82 316	97.49 239	88.21 280	97.84 140	98.75 64	91.51 221	99.27 239	88.96 264	99.99 2	98.52 209

MS-PatchMatch		94.83 212	94.91 198	94.57 260	96.81 289	87.10 280	94.23 249	97.34 244	88.74 274	97.14 165	97.11 200	91.94 213	98.23 329	92.99 192	97.92 261	98.37 220

pmmvs4		94.82 213	94.19 225	96.70 159	97.42 263	92.75 162	92.09 313	96.76 263	86.80 295	95.73 229	97.22 195	89.28 248	98.89 281	93.28 185	99.14 183	98.46 214

YYNet1		94.73 214	94.84 201	94.41 264	97.47 260	85.09 299	90.29 330	95.85 278	92.52 234	97.53 146	97.76 156	91.97 211	99.18 248	93.31 184	96.86 302	98.95 164

MDA-MVSNet_test_wron		94.73 214	94.83 202	94.42 263	97.48 256	85.15 297	90.28 331	95.87 276	92.52 234	97.48 152	97.76 156	91.92 215	99.17 250	93.32 183	96.80 305	98.94 166

UnsupCasMVSNet_bld		94.72 216	94.26 221	96.08 201	98.62 127	90.54 204	93.38 287	98.05 208	90.30 261	97.02 170	96.80 220	89.54 242	99.16 251	88.44 271	96.18 314	98.56 206

BH-untuned		94.69 217	94.75 204	94.52 262	97.95 213	87.53 270	94.07 260	97.01 256	93.99 195	97.10 167	95.65 270	92.65 191	98.95 276	87.60 288	96.74 306	97.09 284

Patchmatch-RL test		94.66 218	94.49 213	95.19 235	98.54 139	88.91 238	92.57 303	98.74 112	91.46 252	98.32 82	97.75 159	77.31 303	98.81 291	96.06 90	99.61 84	97.85 260

CANet_DTU		94.65 219	94.21 224	95.96 209	95.90 308	89.68 213	93.92 267	97.83 218	93.19 215	90.12 334	95.64 271	88.52 252	99.57 151	93.27 186	99.47 124	98.62 202

pmmvs5		94.63 220	94.34 220	95.50 227	97.63 249	88.34 250	94.02 261	97.13 252	87.15 291	95.22 238	97.15 198	87.50 262	99.27 239	93.99 172	99.26 175	98.88 179

PAPM_NR		94.61 221	94.17 226	95.96 209	98.36 156	91.23 190	95.93 164	97.95 210	92.98 224	93.42 298	94.43 298	90.53 231	98.38 322	87.60 288	96.29 313	98.27 233

PatchMatch-RL		94.61 221	93.81 233	97.02 145	98.19 182	95.72 74	93.66 276	97.23 247	88.17 281	94.94 244	95.62 272	91.43 223	98.57 309	87.36 292	97.68 279	96.76 298

BH-RMVSNet		94.56 223	94.44 218	94.91 244	97.57 251	87.44 273	93.78 273	96.26 269	93.69 208	96.41 197	96.50 239	92.10 207	99.00 268	85.96 300	97.71 276	98.31 228

USDC		94.56 223	94.57 212	94.55 261	97.78 236	86.43 287	92.75 299	98.65 136	85.96 301	96.91 180	97.93 144	90.82 229	98.74 296	90.71 234	99.59 89	98.47 212

jason		94.39 225	94.04 229	95.41 231	98.29 160	87.85 265	92.74 301	96.75 264	85.38 311	95.29 236	96.15 255	88.21 256	99.65 116	94.24 165	99.34 160	98.74 193
jason: jason.
1121		94.26 226	93.26 241	97.27 130	98.26 173	94.73 107	95.86 166	97.71 225	77.96 343	94.53 259	96.71 226	91.93 214	99.40 210	87.71 278	98.64 231	97.69 266

EU-MVSNet		94.25 227	94.47 214	93.60 284	98.14 192	82.60 320	97.24 94	92.72 311	85.08 312	98.48 69	98.94 54	82.59 283	98.76 295	97.47 56	99.53 105	99.44 80

xiu_mvs_v2_base		94.22 228	94.63 207	92.99 299	97.32 271	84.84 302	92.12 311	97.84 216	91.96 244	94.17 267	93.43 305	96.07 83	99.71 80	91.27 216	97.48 289	94.42 331

RPMNet		94.22 228	94.03 230	94.78 250	95.44 317	88.15 252	96.18 146	93.73 295	97.43 70	94.10 270	98.49 83	79.40 291	99.39 216	95.69 104	95.81 316	96.81 296

sss		94.22 228	93.72 234	95.74 219	97.71 241	89.95 210	93.84 270	96.98 257	88.38 279	93.75 282	95.74 267	87.94 257	98.89 281	91.02 222	98.10 253	98.37 220

MVSTER		94.21 231	93.93 232	95.05 241	95.83 310	86.46 286	95.18 211	97.65 231	92.41 238	97.94 122	98.00 136	72.39 329	99.58 146	96.36 84	99.56 97	99.12 142

MAR-MVS		94.21 231	93.03 245	97.76 91	96.94 285	97.44 30	96.97 116	97.15 251	87.89 286	92.00 318	92.73 320	92.14 205	99.12 252	83.92 316	97.51 288	96.73 299
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
1112_ss		94.12 233	93.42 238	96.23 188	98.59 131	90.85 195	94.24 248	98.85 84	85.49 306	92.97 304	94.94 284	86.01 270	99.64 119	91.78 207	97.92 261	98.20 239

PS-MVSNAJ		94.10 234	94.47 214	93.00 298	97.35 266	84.88 301	91.86 315	97.84 216	91.96 244	94.17 267	92.50 322	95.82 91	99.71 80	91.27 216	97.48 289	94.40 332

CHOSEN 1792x2688		94.10 234	93.41 239	96.18 194	99.16 64	90.04 207	92.15 310	98.68 125	79.90 335	96.22 211	97.83 150	87.92 260	99.42 196	89.18 260	99.65 76	99.08 150

MG-MVS		94.08 236	94.00 231	94.32 266	97.09 280	85.89 288	93.19 293	95.96 274	92.52 234	94.93 245	97.51 178	89.54 242	98.77 294	87.52 290	97.71 276	98.31 228

PLC	91.02 16	94.05 237	92.90 247	97.51 109	98.00 206	95.12 97	94.25 247	98.25 184	86.17 299	91.48 323	95.25 278	91.01 227	99.19 247	85.02 310	96.69 307	98.22 237
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
114514_t		93.96 238	93.22 243	96.19 193	99.06 82	90.97 194	95.99 155	98.94 72	73.88 349	93.43 297	96.93 211	92.38 202	99.37 224	89.09 261	99.28 172	98.25 235

PVSNet_Blended		93.96 238	93.65 235	94.91 244	97.79 232	87.40 274	91.43 321	98.68 125	84.50 317	94.51 260	94.48 293	93.04 180	99.30 234	89.77 252	98.61 233	98.02 255

lupinMVS		93.77 240	93.28 240	95.24 234	97.68 243	87.81 266	92.12 311	96.05 271	84.52 316	94.48 262	95.06 282	86.90 266	99.63 122	93.62 181	99.13 185	98.27 233

PatchT		93.75 241	93.57 237	94.29 268	95.05 322	87.32 276	96.05 151	92.98 306	97.54 65	94.25 265	98.72 66	75.79 311	99.24 243	95.92 99	95.81 316	96.32 312

EPNet		93.72 242	92.62 254	97.03 144	87.61 356	92.25 169	96.27 139	91.28 321	96.74 94	87.65 344	97.39 188	85.00 276	99.64 119	92.14 200	99.48 122	99.20 126
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HyFIR lowres test		93.72 242	92.65 253	96.91 150	98.93 94	91.81 184	91.23 324	98.52 146	82.69 323	96.46 195	96.52 238	80.38 289	99.90 13	90.36 245	98.79 217	99.03 156

PMMVS2		93.66 244	94.07 228	92.45 307	97.57 251	80.67 326	86.46 343	96.00 272	93.99 195	97.10 167	97.38 190	89.90 240	97.82 336	88.76 266	99.47 124	98.86 182

OpenMVS_ROB	91.80 14	93.64 245	93.05 244	95.42 229	97.31 272	91.21 191	95.08 217	96.68 267	81.56 327	96.88 182	96.41 244	90.44 232	99.25 242	85.39 307	97.67 280	95.80 319

Patchmatch-test		93.60 246	93.25 242	94.63 255	96.14 304	87.47 272	96.04 152	94.50 291	93.57 209	96.47 194	96.97 207	76.50 306	98.61 307	90.67 236	98.41 243	97.81 263

WTY-MVS		93.55 247	93.00 246	95.19 235	97.81 223	87.86 264	93.89 268	96.00 272	89.02 270	94.07 272	95.44 276	86.27 268	99.33 230	87.69 280	96.82 303	98.39 219

Test_1112_low_res		93.53 248	92.86 248	95.54 226	98.60 129	88.86 240	92.75 299	98.69 123	82.66 324	92.65 311	96.92 212	84.75 277	99.56 152	90.94 225	97.76 265	98.19 240

MIMVSNet		93.42 249	92.86 248	95.10 238	98.17 187	88.19 251	98.13 43	93.69 296	92.07 240	95.04 242	98.21 110	80.95 287	99.03 265	81.42 328	98.06 254	98.07 247

FMVSNet5		93.39 250	92.35 256	96.50 171	95.83 310	90.81 199	97.31 89	98.27 181	92.74 232	96.27 208	98.28 102	62.23 350	99.67 110	90.86 227	99.36 155	99.03 156

Patchmatch-test1		93.38 251	93.59 236	92.73 303	96.24 299	81.40 323	93.24 291	94.00 294	91.58 251	94.57 257	96.67 229	87.94 257	99.03 265	90.42 243	97.66 281	97.77 264

CR-MVSNet		93.29 252	92.79 250	94.78 250	95.44 317	88.15 252	96.18 146	97.20 248	84.94 314	94.10 270	98.57 76	77.67 298	99.39 216	95.17 129	95.81 316	96.81 296

wuyk23d		93.25 253	95.20 186	87.40 334	96.07 305	95.38 86	97.04 107	94.97 286	95.33 142	99.70 6	98.11 124	98.14 14	91.94 351	77.76 340	99.68 71	74.89 351

LP		93.12 254	92.78 252	94.14 270	94.50 329	85.48 292	95.73 170	95.68 281	92.97 228	95.05 241	97.17 197	81.93 284	99.40 210	93.06 191	88.96 343	97.55 271

test1235678		92.95 255	92.40 255	94.61 256	96.95 284	86.87 282	90.75 327	97.75 221	91.00 257	96.33 200	95.38 277	85.21 274	98.92 277	79.00 334	99.20 179	98.03 253

X-MVStestdata		92.86 256	90.83 290	98.94 15	99.15 67	97.66 16	97.77 62	98.83 95	97.42 71	96.32 204	36.50 353	96.49 72	99.72 70	95.66 107	99.37 152	99.45 71

GA-MVS		92.83 257	92.15 259	94.87 247	96.97 283	87.27 277	90.03 332	96.12 270	91.83 248	94.05 273	94.57 289	76.01 310	98.97 275	92.46 197	97.34 295	98.36 225

CMPMVS	73.10 23	92.74 258	91.39 270	96.77 155	93.57 341	94.67 111	94.21 251	97.67 227	80.36 334	93.61 289	96.60 232	82.85 282	97.35 340	84.86 311	98.78 218	98.29 232
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
HY-MVS	91.43 15	92.58 259	91.81 267	94.90 246	96.49 295	88.87 239	97.31 89	94.62 289	85.92 302	90.50 331	96.84 216	85.05 275	99.40 210	83.77 319	95.78 319	96.43 311

view600		92.56 260	92.11 260	93.91 275	98.45 149	84.76 304	97.10 101	90.23 333	97.42 71	96.98 172	94.48 293	73.62 319	99.60 140	82.49 323	98.28 245	97.36 276

view800		92.56 260	92.11 260	93.91 275	98.45 149	84.76 304	97.10 101	90.23 333	97.42 71	96.98 172	94.48 293	73.62 319	99.60 140	82.49 323	98.28 245	97.36 276

conf0.05thres1000		92.56 260	92.11 260	93.91 275	98.45 149	84.76 304	97.10 101	90.23 333	97.42 71	96.98 172	94.48 293	73.62 319	99.60 140	82.49 323	98.28 245	97.36 276

tfpn		92.56 260	92.11 260	93.91 275	98.45 149	84.76 304	97.10 101	90.23 333	97.42 71	96.98 172	94.48 293	73.62 319	99.60 140	82.49 323	98.28 245	97.36 276

TR-MVS		92.54 264	92.20 258	93.57 285	96.49 295	86.66 284	93.51 282	94.73 288	89.96 265	94.95 243	93.87 303	90.24 238	98.61 307	81.18 329	94.88 325	95.45 325

PMMVS		92.39 265	91.08 278	96.30 184	93.12 344	92.81 161	90.58 329	95.96 274	79.17 338	91.85 321	92.27 323	90.29 237	98.66 306	89.85 251	96.68 308	97.43 274

1314		92.38 266	92.30 257	92.64 305	95.42 319	85.15 297	95.86 166	96.97 258	85.40 310	90.62 327	93.06 313	91.12 226	97.80 337	86.74 296	95.49 324	94.97 329

new_pmnet		92.34 267	91.69 268	94.32 266	96.23 301	89.16 231	92.27 309	92.88 308	84.39 319	95.29 236	96.35 248	85.66 271	96.74 346	84.53 313	97.56 285	97.05 286

CVMVSNet		92.33 268	92.79 250	90.95 320	97.26 273	75.84 342	95.29 205	92.33 314	81.86 325	96.27 208	98.19 111	81.44 285	98.46 316	94.23 166	98.29 244	98.55 208

PAPR		92.22 269	91.27 274	95.07 240	95.73 313	88.81 242	91.97 314	97.87 214	85.80 304	90.91 325	92.73 320	91.16 225	98.33 326	79.48 332	95.76 320	98.08 245

DSMNet-mixed		92.19 270	91.83 266	93.25 292	96.18 303	83.68 318	96.27 139	93.68 298	76.97 346	92.54 314	99.18 35	89.20 250	98.55 312	83.88 317	98.60 235	97.51 273

BH-w/o		92.14 271	91.94 264	92.73 303	97.13 279	85.30 294	92.46 306	95.64 282	89.33 269	94.21 266	92.74 319	89.60 241	98.24 328	81.68 327	94.66 327	94.66 330

PCF-MVS	89.43 18	92.12 272	90.64 293	96.57 168	97.80 227	93.48 151	89.88 336	98.45 152	74.46 348	96.04 217	95.68 269	90.71 230	99.31 232	73.73 344	99.01 199	96.91 292
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
thres600view7		92.03 273	91.43 269	93.82 280	98.19 182	84.61 308	96.27 139	90.39 328	96.81 92	96.37 199	93.11 308	73.44 325	99.49 177	80.32 330	97.95 257	97.36 276

PatchmatchNet		91.98 274	91.87 265	92.30 309	94.60 327	79.71 328	95.12 212	93.59 301	89.52 267	93.61 289	97.02 205	77.94 296	99.18 248	90.84 228	94.57 329	98.01 256
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tfpn111		91.92 275	91.39 270	93.49 287	98.21 178	84.50 309	96.39 130	90.39 328	96.87 88	96.33 200	93.08 310	73.44 325	99.51 173	79.87 331	97.94 260	96.46 307

conf0.01		91.90 276	90.98 281	94.67 253	98.27 165	88.03 256	96.98 110	88.58 341	93.90 198	94.64 251	91.45 329	69.62 338	99.52 163	87.62 282	97.74 266	96.46 307

conf0.002		91.90 276	90.98 281	94.67 253	98.27 165	88.03 256	96.98 110	88.58 341	93.90 198	94.64 251	91.45 329	69.62 338	99.52 163	87.62 282	97.74 266	96.46 307

cascas		91.89 278	91.35 272	93.51 286	94.27 332	85.60 290	88.86 339	98.61 139	79.32 337	92.16 317	91.44 335	89.22 249	98.12 332	90.80 230	97.47 291	96.82 295

tfpn1000		91.88 279	91.20 277	93.89 279	97.96 209	87.13 279	97.13 99	88.16 348	94.41 181	94.87 246	92.77 317	68.34 345	99.47 182	89.24 258	97.95 257	95.06 327

conf200view11		91.81 280	91.26 275	93.46 288	98.21 178	84.50 309	96.39 130	90.39 328	96.87 88	96.33 200	93.08 310	73.44 325	99.42 196	78.85 336	97.74 266	96.46 307

JIA-IIPM		91.79 281	90.69 292	95.11 237	93.80 338	90.98 193	94.16 255	91.78 318	96.38 103	90.30 333	99.30 23	72.02 331	98.90 278	88.28 274	90.17 340	95.45 325

thres100view900		91.76 282	91.26 275	93.26 291	98.21 178	84.50 309	96.39 130	90.39 328	96.87 88	96.33 200	93.08 310	73.44 325	99.42 196	78.85 336	97.74 266	95.85 317

thresconf0.02		91.72 283	90.98 281	93.97 271	98.27 165	88.03 256	96.98 110	88.58 341	93.90 198	94.64 251	91.45 329	69.62 338	99.52 163	87.62 282	97.74 266	94.35 333

tfpn_n400		91.72 283	90.98 281	93.97 271	98.27 165	88.03 256	96.98 110	88.58 341	93.90 198	94.64 251	91.45 329	69.62 338	99.52 163	87.62 282	97.74 266	94.35 333

tfpnconf		91.72 283	90.98 281	93.97 271	98.27 165	88.03 256	96.98 110	88.58 341	93.90 198	94.64 251	91.45 329	69.62 338	99.52 163	87.62 282	97.74 266	94.35 333

tfpnview11		91.72 283	90.98 281	93.97 271	98.27 165	88.03 256	96.98 110	88.58 341	93.90 198	94.64 251	91.45 329	69.62 338	99.52 163	87.62 282	97.74 266	94.35 333

thres400		91.68 287	91.00 279	93.71 282	98.02 201	84.35 313	95.70 173	90.79 325	96.26 108	95.90 223	92.13 325	73.62 319	99.42 196	78.85 336	97.74 266	97.36 276

tfpn200view9		91.55 288	91.00 279	93.21 293	98.02 201	84.35 313	95.70 173	90.79 325	96.26 108	95.90 223	92.13 325	73.62 319	99.42 196	78.85 336	97.74 266	95.85 317

ADS-MVSNet2		91.47 289	90.51 295	94.36 265	95.51 315	85.63 289	95.05 221	95.70 280	83.46 321	92.69 309	96.84 216	79.15 293	99.41 207	85.66 304	90.52 338	98.04 251

EPNet_dtu		91.39 290	90.75 291	93.31 290	90.48 354	82.61 319	94.80 232	92.88 308	93.39 211	81.74 352	94.90 287	81.36 286	99.11 255	88.28 274	98.87 212	98.21 238
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet	86.72 19	91.10 291	90.97 287	91.49 314	97.56 253	78.04 335	87.17 341	94.60 290	84.65 315	92.34 315	92.20 324	87.37 264	98.47 315	85.17 309	97.69 278	97.96 257

tpm		91.08 292	90.85 289	91.75 313	95.33 320	78.09 333	95.03 223	91.27 322	88.75 273	93.53 292	97.40 185	71.24 332	99.30 234	91.25 218	93.87 330	97.87 259

thres200		91.00 293	90.42 297	92.77 302	97.47 260	83.98 316	94.01 262	91.18 323	95.12 158	95.44 233	91.21 337	73.93 315	99.31 232	77.76 340	97.63 284	95.01 328

tfpn_ndepth		90.98 294	90.24 299	93.20 295	97.72 240	87.18 278	96.52 126	88.20 347	92.63 233	93.69 286	90.70 342	68.22 346	99.42 196	86.98 294	97.47 291	93.00 343

ADS-MVSNet		90.95 295	90.26 298	93.04 296	95.51 315	82.37 321	95.05 221	93.41 302	83.46 321	92.69 309	96.84 216	79.15 293	98.70 300	85.66 304	90.52 338	98.04 251

testus		90.90 296	90.51 295	92.06 311	96.07 305	79.45 329	88.99 337	98.44 155	85.46 308	94.15 269	90.77 339	89.12 251	98.01 335	73.66 345	97.95 257	98.71 196

tpmvs		90.79 297	90.87 288	90.57 323	92.75 348	76.30 340	95.79 169	93.64 299	91.04 256	91.91 319	96.26 250	77.19 304	98.86 287	89.38 257	89.85 341	96.56 305

tpmrst		90.31 298	90.61 294	89.41 327	94.06 336	72.37 349	95.06 220	93.69 296	88.01 283	92.32 316	96.86 214	77.45 300	98.82 289	91.04 221	87.01 346	97.04 287

test0.0.03 1		90.11 299	89.21 306	92.83 301	93.89 337	86.87 282	91.74 317	88.74 340	92.02 241	94.71 249	91.14 338	73.92 316	94.48 350	83.75 320	92.94 332	97.16 283

MVS		90.02 300	89.20 307	92.47 306	94.71 325	86.90 281	95.86 166	96.74 265	64.72 351	90.62 327	92.77 317	92.54 196	98.39 320	79.30 333	95.56 323	92.12 344

pmmvs3		90.00 301	88.90 310	93.32 289	94.20 335	85.34 293	91.25 323	92.56 313	78.59 340	93.82 279	95.17 279	67.36 348	98.69 301	89.08 262	98.03 255	95.92 315

CHOSEN 280x420		89.98 302	89.19 308	92.37 308	95.60 314	81.13 324	86.22 344	97.09 254	81.44 329	87.44 345	93.15 307	73.99 314	99.47 182	88.69 268	99.07 193	96.52 306

test-LLR		89.97 303	89.90 301	90.16 324	94.24 333	74.98 343	89.89 333	89.06 338	92.02 241	89.97 335	90.77 339	73.92 316	98.57 309	91.88 204	97.36 293	96.92 290

FPMVS		89.92 304	88.63 311	93.82 280	98.37 155	96.94 41	91.58 318	93.34 303	88.00 284	90.32 332	97.10 201	70.87 334	91.13 352	71.91 348	96.16 315	93.39 341

CostFormer		89.75 305	89.25 304	91.26 317	94.69 326	78.00 336	95.32 202	91.98 316	81.50 328	90.55 329	96.96 208	71.06 333	98.89 281	88.59 270	92.63 335	96.87 293

PatchFormer-LS_test		89.62 306	89.12 309	91.11 319	93.62 339	78.42 332	94.57 239	93.62 300	88.39 278	90.54 330	88.40 347	72.33 330	99.03 265	92.41 198	88.20 344	95.89 316

E-PMN		89.52 307	89.78 302	88.73 329	93.14 343	77.61 337	83.26 348	92.02 315	94.82 168	93.71 284	93.11 308	75.31 312	96.81 344	85.81 301	96.81 304	91.77 346

EPMVS		89.26 308	88.55 312	91.39 315	92.36 349	79.11 330	95.65 179	79.86 353	88.60 275	93.12 303	96.53 236	70.73 335	98.10 333	90.75 232	89.32 342	96.98 288

EMVS		89.06 309	89.22 305	88.61 330	93.00 345	77.34 338	82.91 349	90.92 324	94.64 172	92.63 312	91.81 328	76.30 308	97.02 342	83.83 318	96.90 300	91.48 347

1111		88.78 310	89.39 303	86.96 335	98.53 141	62.84 354	91.49 319	97.48 241	94.45 178	96.56 190	96.45 241	43.83 360	98.87 285	86.33 298	99.40 150	99.18 129

IB-MVS	85.98 20	88.63 311	86.95 320	93.68 283	95.12 321	84.82 303	90.85 326	90.17 337	87.55 287	88.48 341	91.34 336	58.01 352	99.59 144	87.24 293	93.80 331	96.63 304
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
tpm2		88.47 312	87.69 315	90.79 321	94.98 323	77.34 338	95.09 215	91.83 317	77.51 345	89.40 337	96.41 244	67.83 347	98.73 297	83.58 321	92.60 336	96.29 313

tpmp4_e23		88.46 313	87.54 316	91.22 318	94.56 328	78.08 334	95.63 184	93.17 304	79.08 339	85.85 347	96.80 220	65.86 349	98.85 288	84.10 315	92.85 333	96.72 300

MVS-HIRNet		88.40 314	90.20 300	82.99 338	97.01 282	60.04 356	93.11 294	85.61 350	84.45 318	88.72 340	99.09 45	84.72 278	98.23 329	82.52 322	96.59 309	90.69 349

gg-mvs-nofinetune		88.28 315	86.96 319	92.23 310	92.84 347	84.44 312	98.19 40	74.60 355	99.08 9	87.01 346	99.47 8	56.93 353	98.23 329	78.91 335	95.61 322	94.01 337

dp		88.08 316	88.05 314	88.16 333	92.85 346	68.81 351	94.17 254	92.88 308	85.47 307	91.38 324	96.14 257	68.87 344	98.81 291	86.88 295	83.80 350	96.87 293

tpm cat1		88.01 317	87.33 317	90.05 326	94.48 330	76.28 341	94.47 240	94.35 293	73.84 350	89.26 338	95.61 273	73.64 318	98.30 327	84.13 314	86.20 347	95.57 324

test12356		87.98 318	88.41 313	86.69 336	95.84 309	63.49 353	87.15 342	97.32 245	87.21 289	91.78 322	93.36 306	70.66 336	98.39 320	74.70 343	97.64 283	98.19 240

test-mter		87.92 319	87.17 318	90.16 324	94.24 333	74.98 343	89.89 333	89.06 338	86.44 297	89.97 335	90.77 339	54.96 356	98.57 309	91.88 204	97.36 293	96.92 290

DWT-MVSNet_test		87.92 319	86.77 321	91.39 315	93.18 342	78.62 331	95.10 213	91.42 320	85.58 305	88.00 342	88.73 346	60.60 351	98.90 278	90.60 237	87.70 345	96.65 301

PAPM		87.64 321	85.84 324	93.04 296	96.54 292	84.99 300	88.42 340	95.57 284	79.52 336	83.82 349	93.05 314	80.57 288	98.41 318	62.29 352	92.79 334	95.71 320

TESTMET0.1,1		87.20 322	86.57 322	89.07 328	93.62 339	72.84 348	89.89 333	87.01 349	85.46 308	89.12 339	90.20 344	56.00 355	97.72 338	90.91 226	96.92 299	96.64 302

MVE	73.61 22	86.48 323	85.92 323	88.18 332	96.23 301	85.28 295	81.78 351	75.79 354	86.01 300	82.53 351	91.88 327	92.74 187	87.47 354	71.42 349	94.86 326	91.78 345
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test2356		85.45 324	83.26 327	92.01 312	91.12 351	80.76 325	85.16 345	92.90 307	83.90 320	90.63 326	87.71 349	53.10 357	97.24 341	69.20 350	95.65 321	98.03 253

PVSNet_0	81.89 21	84.49 325	83.21 328	88.34 331	95.76 312	74.97 345	83.49 347	92.70 312	78.47 341	87.94 343	86.90 350	83.38 281	96.63 347	73.44 346	66.86 353	93.40 340

PNet_i23d		83.82 326	83.39 326	85.10 337	96.07 305	65.16 352	81.87 350	94.37 292	90.87 258	93.92 278	92.89 316	52.80 358	96.44 348	77.52 342	70.22 352	93.70 338

testpf		82.70 327	84.35 325	77.74 339	88.97 355	73.23 347	93.85 269	84.33 351	88.10 282	85.06 348	90.42 343	52.62 359	91.05 353	91.00 223	84.82 349	68.93 352

.test1245		73.49 328	79.27 329	56.15 341	98.53 141	62.84 354	91.49 319	97.48 241	94.45 178	96.56 190	96.45 241	43.83 360	98.87 285	86.33 298	8.32 355	6.75 355

tmp_tt		57.23 329	62.50 330	41.44 342	34.77 357	49.21 358	83.93 346	60.22 359	15.31 353	71.11 354	79.37 352	70.09 337	44.86 356	64.76 351	82.93 351	30.25 353

pcd1.5k->3k		41.47 330	44.19 331	33.29 343	99.65 11	0.00 361	0.00 352	99.07 34	0.00 356	0.00 357	0.00 358	99.04 4	0.00 359	0.00 356	99.96 11	99.87 2

cdsmvs_eth3d_5k		24.22 331	32.30 332	0.00 346	0.00 360	0.00 361	0.00 352	98.10 201	0.00 356	0.00 357	95.06 282	97.54 28	0.00 359	0.00 356	0.00 357	0.00 357

test123		12.59 332	15.49 333	3.87 344	6.07 358	2.55 359	90.75 327	2.59 361	2.52 354	5.20 356	13.02 355	4.96 362	1.85 358	5.20 354	9.09 354	7.23 354

testmvs		12.33 333	15.23 334	3.64 345	5.77 359	2.23 360	88.99 337	3.62 360	2.30 355	5.29 355	13.09 354	4.52 363	1.95 357	5.16 355	8.32 355	6.75 355

pcd_1.5k_mvsjas		7.98 334	10.65 335	0.00 346	0.00 360	0.00 361	0.00 352	0.00 362	0.00 356	0.00 357	0.00 358	95.82 91	0.00 359	0.00 356	0.00 357	0.00 357

ab-mvs-re		7.91 335	10.55 336	0.00 346	0.00 360	0.00 361	0.00 352	0.00 362	0.00 356	0.00 357	94.94 284	0.00 364	0.00 359	0.00 356	0.00 357	0.00 357

sosnet-low-res		0.00 336	0.00 337	0.00 346	0.00 360	0.00 361	0.00 352	0.00 362	0.00 356	0.00 357	0.00 358	0.00 364	0.00 359	0.00 356	0.00 357	0.00 357

sosnet		0.00 336	0.00 337	0.00 346	0.00 360	0.00 361	0.00 352	0.00 362	0.00 356	0.00 357	0.00 358	0.00 364	0.00 359	0.00 356	0.00 357	0.00 357

uncertanet		0.00 336	0.00 337	0.00 346	0.00 360	0.00 361	0.00 352	0.00 362	0.00 356	0.00 357	0.00 358	0.00 364	0.00 359	0.00 356	0.00 357	0.00 357

Regformer		0.00 336	0.00 337	0.00 346	0.00 360	0.00 361	0.00 352	0.00 362	0.00 356	0.00 357	0.00 358	0.00 364	0.00 359	0.00 356	0.00 357	0.00 357

uanet		0.00 336	0.00 337	0.00 346	0.00 360	0.00 361	0.00 352	0.00 362	0.00 356	0.00 357	0.00 358	0.00 364	0.00 359	0.00 356	0.00 357	0.00 357

GSMVS																98.06 248

test_part3							95.64 181		94.84 165		97.60 171		99.76 48	91.22 219

test_part2					99.03 86	96.07 65				98.08 107

test_part1								98.84 87				96.69 61			99.44 131	99.37 101

sam_mvs1												77.80 297				98.06 248

sam_mvs												77.38 301

semantic-postprocess				94.85 248	97.68 243	85.53 291		97.63 235	96.99 84	98.36 77	98.54 80	87.44 263	99.75 54	97.07 69	99.08 191	99.27 121

ambc				96.56 169	98.23 176	91.68 186	97.88 57	98.13 199		98.42 74	98.56 78	94.22 147	99.04 262	94.05 171	99.35 158	98.95 164

MTGPA								98.73 113

test_post1							94.98 225				10.37 357	76.21 309	99.04 262	89.47 256

test_post											10.87 356	76.83 305	99.07 259

patchmatchnet-post											96.84 216	77.36 302	99.42 196

GG-mvs-BLEND				90.60 322	91.00 352	84.21 315	98.23 34	72.63 358		82.76 350	84.11 351	56.14 354	96.79 345	72.20 347	92.09 337	90.78 348

MTMP								74.60 355

gm-plane-assit					91.79 350	71.40 350			81.67 326		90.11 345		98.99 269	84.86 311

test9_res														91.29 215	98.89 211	99.00 158

TEST9					97.84 220	95.23 90	93.62 278	98.39 162	86.81 294	93.78 280	95.99 259	94.68 128	99.52 163

test_8					97.81 223	95.07 98	93.54 281	98.38 164	87.04 292	93.71 284	95.96 263	94.58 133	99.52 163

agg_prior2														90.34 246	98.90 207	99.10 149

agg_prior					97.80 227	94.96 101		98.36 166		93.49 293			99.53 160

TestCases				98.06 75	99.08 79	96.16 62		99.16 16	94.35 185	97.78 142	98.07 127	95.84 88	99.12 252	91.41 213	99.42 143	98.91 172

test_prior4						95.38 86	93.61 280

test_prior2							93.33 289		94.21 190	94.02 274	96.25 251	93.64 165		91.90 202	98.96 201

test_prior				97.46 118	97.79 232	94.26 124		98.42 159					99.34 227			98.79 188

旧先验2							93.35 288		77.95 344	95.77 228			98.67 305	90.74 233

新几何2							93.43 284

新几何1				97.25 133	98.29 160	94.70 110		97.73 223	77.98 342	94.83 247	96.67 229	92.08 208	99.45 191	88.17 276	98.65 230	97.61 269

旧先验1					97.80 227	93.87 135		97.75 221			97.04 204	93.57 167			98.68 228	98.72 195

无先验							93.20 292	97.91 211	80.78 331				99.40 210	87.71 278		97.94 258

原ACMM2							92.82 297

原ACMM1				96.58 166	98.16 189	92.12 175		98.15 197	85.90 303	93.49 293	96.43 243	92.47 200	99.38 221	87.66 281	98.62 232	98.23 236

test222					98.17 187	93.24 156	92.74 301	97.61 237	75.17 347	94.65 250	96.69 228	90.96 228			98.66 229	97.66 267

testdata2													99.46 187	87.84 277

segment_acmp												95.34 109

testdata				95.70 222	98.16 189	90.58 201		97.72 224	80.38 333	95.62 231	97.02 205	92.06 210	98.98 271	89.06 263	98.52 237	97.54 272

testdata1							92.77 298		93.78 205

test12				97.46 118	97.61 250	94.07 129		97.78 220		93.57 291		93.31 175	99.42 196		98.78 218	98.89 175

plane_prior7					98.70 116	94.67 111

plane_prior6					98.38 154	94.37 120						91.91 216

plane_prior5								98.75 110					99.46 187	92.59 195	99.20 179	99.28 118

plane_prior4											96.77 222

plane_prior3						94.51 114			95.29 144	96.16 214

plane_prior2							96.50 127		96.36 104

plane_prior1					98.49 145

plane_prior						94.29 121	95.42 193		94.31 187						98.93 206

n2								0.00 362

nn								0.00 362

door-mid								98.17 194

lessismore_v0				97.05 141	99.36 45	92.12 175		84.07 352		98.77 51	98.98 50	85.36 273	99.74 59	97.34 59	99.37 152	99.30 111

LGP-MVS_train				98.74 32	99.15 67	97.02 38		99.02 51	95.15 153	98.34 79	98.23 106	97.91 19	99.70 88	94.41 156	99.73 56	99.50 50

test11								98.08 204

door								97.81 219

HQP5-MVS						92.47 165

HQP-NCC					97.85 216		94.26 244		93.18 216	92.86 306

ACMP_Plane					97.85 216		94.26 244		93.18 216	92.86 306

BP-MVS														90.51 240

HQP4-MVS										92.87 305			99.23 245			99.06 154

HQP3-MVS								98.43 156							98.74 222

HQP2-MVS												90.33 233

NP-MVS					98.14 192	93.72 141					95.08 280

MDTV_nov1_ep13_2view						57.28 357	94.89 227		80.59 332	94.02 274		78.66 295		85.50 306		97.82 262

MDTV_nov1_ep13			91.28 273		94.31 331	73.51 346	94.80 232	93.16 305	86.75 296	93.45 296	97.40 185	76.37 307	98.55 312	88.85 265	96.43 310

ACMMP++_ref															99.52 109

ACMMP++															99.55 101

Test By Simon												94.51 137

ITE_SJBPF				97.85 87	98.64 122	96.66 49		98.51 148	95.63 130	97.22 161	97.30 193	95.52 102	98.55 312	90.97 224	98.90 207	98.34 226

DeepMVS_CX				77.17 340	90.94 353	85.28 295		74.08 357	52.51 352	80.87 353	88.03 348	75.25 313	70.63 355	59.23 353	84.94 348	75.62 350

High-resolution multi-view benchmark