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	99.52 160	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 44	99.81 3	96.38 56	98.87 9	99.30 9	99.01 15	99.63 9	99.66 4	99.27 2	99.68 101	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 54	98.54 20	99.22 10	96.23 109	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	99.59 141	97.21 62	99.76 50	99.40 90

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	97.87 135	99.67 3	96.47 72	99.92 4	97.88 34	99.98 3	99.85 4

v52		98.85 8	99.01 5	98.37 54	99.61 15	95.53 81	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 54	99.61 15	95.53 81	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 42	99.55 21	96.12 63	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 54	98.45 25	99.12 22	95.83 124	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 49	99.58 18	95.67 75	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 80	99.64 12	94.20 124	98.67 12	99.14 20	99.08 9	99.42 16	99.23 29	96.53 67	99.91 12	99.27 4	99.93 21	99.73 16

PS-CasMVS		98.73 13	98.85 13	98.39 53	99.55 21	95.47 83	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 59	98.67 12	99.02 51	96.50 98	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	95.62 130	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	96.85 115	99.02 51	95.81 125	99.88 2	99.38 13	98.14 14	99.69 95	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 50	98.55 19	99.17 15	99.05 12	99.17 31	98.79 60	95.47 103	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 57	99.17 6	99.05 38	98.05 41	99.61 11	99.52 5	93.72 162	99.88 19	98.72 20	99.88 34	99.65 24

v748		98.58 20	98.89 10	97.67 97	99.61 15	93.53 147	98.59 16	98.90 75	98.97 17	99.43 15	99.15 40	96.53 67	99.85 24	98.88 11	99.91 27	99.64 27

nrg030		98.54 21	98.62 23	98.32 59	99.22 56	95.66 76	97.90 56	99.08 30	98.31 32	99.02 37	98.74 65	97.68 24	99.61 131	97.77 40	99.85 39	99.70 19

PS-MVSNAJss		98.53 22	98.63 21	98.21 67	99.68 9	94.82 103	98.10 44	99.21 11	96.91 87	99.75 4	99.45 9	95.82 89	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	95.44 105	99.84 28	96.47 81	99.80 46	99.47 64

pm-mvs1		98.47 24	98.67 19	97.86 84	99.52 25	94.58 111	98.28 31	99.00 62	97.57 63	99.27 26	99.22 30	98.32 10	99.50 169	97.09 68	99.75 54	99.50 50

ACMH	93.61 9	98.44 25	98.76 16	97.51 107	99.43 37	93.54 146	98.23 34	99.05 38	97.40 79	99.37 19	99.08 46	98.79 6	99.47 176	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 62	99.46 32	95.22 91	98.27 33	98.84 87	99.05 12	99.01 38	98.65 73	95.37 106	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 56	98.27 103	97.88 21	99.80 37	95.67 105	99.50 111	99.38 95

TransMVSNet (Re)		98.38 28	98.67 19	97.51 107	99.51 26	93.39 151	98.20 39	98.87 81	98.23 35	99.48 12	99.27 25	98.47 9	99.55 153	96.52 78	99.53 104	99.60 34

TranMVSNet+NR-MVSNet		98.33 29	98.30 39	98.43 50	99.07 81	95.87 68	96.73 119	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	95.88 121	97.88 130	98.22 108	98.15 13	99.74 57	96.50 80	99.62 79	99.42 85

ANet_high		98.31 31	98.94 8	96.41 175	99.33 47	89.64 212	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 93	99.06 82	93.80 136	97.76 64	99.00 62	98.40 29	99.07 35	98.98 50	96.89 50	99.75 52	97.19 65	99.79 47	99.55 44

Vis-MVSNet		98.27 32	98.34 35	98.07 72	99.33 47	95.21 93	98.04 48	99.46 6	97.32 82	97.82 139	99.11 43	96.75 59	99.86 23	97.84 36	99.36 153	99.15 132
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	99.45 185	94.08 167	99.67 73	99.13 135
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 79	99.39 42	95.22 91	97.55 81	99.20 13	98.21 36	99.25 27	98.51 82	98.21 12	99.40 204	94.79 144	99.72 59	99.32 105

FC-MVSNet-test		98.16 36	98.37 33	97.56 102	99.49 30	93.10 155	98.35 28	99.21 11	98.43 28	98.89 44	98.83 59	94.30 141	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	98.73 112	97.69 57	97.90 126	97.96 137	95.81 93	99.82 31	96.13 88	99.61 84	99.45 71

APDe-MVS		98.14 37	98.03 50	98.47 48	98.72 109	96.04 65	98.07 46	99.10 25	95.96 118	98.59 60	98.69 69	96.94 48	99.81 33	96.64 74	99.58 91	99.57 40

APD-MVS_3200maxsize		98.13 39	97.90 54	98.79 28	98.79 102	97.31 33	97.55 81	98.92 73	97.72 55	98.25 88	98.13 120	97.10 43	99.75 52	95.44 117	99.24 174	99.32 105

HPM-MVS		98.11 40	97.83 58	98.92 19	99.42 39	97.46 28	98.57 17	99.05 38	95.43 139	97.41 154	97.50 176	97.98 17	99.79 38	95.58 114	99.57 94	99.50 50

Gipuma		98.07 41	98.31 37	97.36 124	99.76 5	96.28 60	98.51 21	99.10 25	98.76 20	96.79 181	99.34 20	96.61 64	98.82 283	96.38 83	99.50 111	96.98 284
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	95.75 127	97.91 125	98.06 129	96.89 50	99.76 48	95.32 122	99.57 94	99.43 83
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	96.68 121	98.83 94	95.21 147	98.36 76	98.13 120	98.13 16	99.62 125	96.04 92	99.54 102	99.39 93
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
v13		98.02 44	98.52 27	96.51 168	99.02 87	90.14 203	98.07 46	99.09 29	98.10 40	99.13 32	99.35 18	94.84 120	99.74 57	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 97	98.08 106	97.87 148	97.02 47	99.76 48	95.25 124	99.59 89	99.40 90
Skip Steuart: Steuart Systems R&D Blog.
MPTG		98.01 46	97.66 69	99.06 5	99.44 34	97.90 8	95.66 173	98.73 112	97.69 57	97.90 126	97.96 137	95.81 93	99.82 31	96.13 88	99.61 84	99.45 71

v12		97.97 47	98.47 28	96.46 172	98.98 91	90.01 207	97.97 51	99.08 30	98.00 43	99.11 34	99.34 20	94.70 123	99.73 62	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 94	97.42 71	96.32 201	97.64 166	96.49 70	99.72 68	95.66 107	99.37 150	99.45 71

NR-MVSNet		97.96 48	97.86 56	98.26 64	98.73 107	95.54 79	98.14 42	98.73 112	97.79 48	99.42 16	97.83 149	94.40 138	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 94	96.05 112	97.46 152	97.63 167	96.77 58	99.76 48	95.61 111	99.46 125	99.49 58

FMVSNet1		97.95 50	98.08 46	97.56 102	99.14 75	93.67 140	98.23 34	98.66 129	97.41 78	99.00 40	99.19 32	95.47 103	99.73 62	95.83 101	99.76 50	99.30 109

HFP-MVS		97.94 52	97.64 72	98.83 25	99.15 67	97.50 25	97.59 78	98.84 87	96.05 112	97.49 147	97.54 171	97.07 45	99.70 86	95.61 111	99.46 125	99.30 109

LPG-MVS_test		97.94 52	97.67 68	98.74 32	99.15 67	97.02 38	97.09 105	99.02 51	95.15 152	98.34 78	98.23 105	97.91 19	99.70 86	94.41 155	99.73 56	99.50 50

FIs		97.93 54	98.07 47	97.48 114	99.38 43	92.95 157	98.03 50	99.11 23	98.04 42	98.62 56	98.66 71	93.75 161	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	96.00 116	97.22 159	97.62 168	96.87 53	99.76 48	95.48 115	99.43 138	99.46 66

CP-MVS		97.92 55	97.56 81	98.99 10	98.99 89	97.82 12	97.93 54	98.96 70	96.11 111	96.89 179	97.45 179	96.85 54	99.78 39	95.19 127	99.63 78	99.38 95

mPP-MVS		97.91 57	97.53 82	99.04 7	99.22 56	97.87 11	97.74 67	98.78 104	96.04 114	97.10 165	97.73 161	96.53 67	99.78 39	95.16 130	99.50 111	99.46 66

V9		97.90 58	98.40 32	96.40 176	98.93 93	89.86 209	97.86 58	99.07 34	97.88 47	99.05 36	99.30 23	94.53 134	99.72 68	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	96.36 131	98.79 101	95.07 159	97.88 130	98.35 92	97.24 40	99.72 68	96.05 91	99.58 91	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	95.45 137	97.55 143	97.94 141	97.11 42	99.78 39	94.77 146	99.46 125	99.48 61

DP-MVS		97.87 61	97.89 55	97.81 87	98.62 125	94.82 103	97.13 99	98.79 101	98.98 16	98.74 51	98.49 83	95.80 95	99.49 171	95.04 137	99.44 130	99.11 143

RPSCF		97.87 61	97.51 84	98.95 14	99.15 67	98.43 3	97.56 80	99.06 36	96.19 110	98.48 68	98.70 68	94.72 122	99.24 237	94.37 158	99.33 163	99.17 128

test_0402		97.84 63	97.97 51	97.47 115	99.19 62	94.07 127	96.71 120	98.73 112	98.66 22	98.56 62	98.41 88	96.84 55	99.69 95	94.82 141	99.81 43	98.64 197

V14		97.83 64	98.33 36	96.35 177	98.88 99	89.72 210	97.75 65	99.05 38	97.74 51	99.01 38	99.27 25	94.35 139	99.71 78	98.95 9	99.97 8	99.62 31

UniMVSNet_NR-MVSNet		97.83 64	97.65 70	98.37 54	98.72 109	95.78 70	95.66 173	99.02 51	98.11 39	98.31 83	97.69 165	94.65 128	99.85 24	97.02 70	99.71 63	99.48 61

UniMVSNet (Re)		97.83 64	97.65 70	98.35 58	98.80 101	95.86 69	95.92 161	99.04 45	97.51 68	98.22 90	97.81 153	94.68 126	99.78 39	97.14 67	99.75 54	99.41 87

v11		97.82 67	98.36 34	96.17 193	98.93 93	89.16 229	97.79 61	99.08 30	97.64 60	99.19 29	99.32 22	94.28 142	99.72 68	99.07 6	99.97 8	99.63 29

DeepC-MVS	95.41 4	97.82 67	97.70 65	98.16 68	98.78 103	95.72 72	96.23 140	99.02 51	93.92 194	98.62 56	98.99 49	97.69 23	99.62 125	96.18 87	99.87 36	99.15 132
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 57	98.73 107	95.78 70	95.65 175	98.87 81	97.57 63	98.31 83	97.83 149	94.69 124	99.85 24	97.02 70	99.71 63	99.46 66

v15		97.77 70	98.26 40	96.30 182	98.81 100	89.59 217	97.62 74	99.04 45	97.59 62	98.97 42	99.24 27	94.19 146	99.70 86	98.88 11	99.97 8	99.61 33

LS3D		97.77 70	97.50 85	98.57 43	96.24 294	97.58 21	98.45 25	98.85 84	98.58 24	97.51 145	97.94 141	95.74 96	99.63 119	95.19 127	98.97 198	98.51 208

3Dnovator+	96.13 3	97.73 72	97.59 78	98.15 69	98.11 191	95.60 77	98.04 48	98.70 121	98.13 38	96.93 177	98.45 86	95.30 110	99.62 125	95.64 109	98.96 199	99.24 121

tfpnnormal		97.72 73	97.97 51	96.94 145	99.26 51	92.23 168	97.83 60	98.45 151	98.25 34	99.13 32	98.66 71	96.65 62	99.69 95	93.92 172	99.62 79	98.91 170

Baseline_NR-MVSNet		97.72 73	97.79 59	97.50 110	99.56 19	93.29 152	95.44 182	98.86 83	98.20 37	98.37 75	99.24 27	94.69 124	99.55 153	95.98 97	99.79 47	99.65 24

v17		97.70 75	98.17 42	96.28 185	98.77 104	89.59 217	97.62 74	99.01 60	97.54 65	98.72 53	99.18 35	94.06 150	99.68 101	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	95.38 191	98.99 65	92.45 232	98.11 100	98.31 96	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	96.29 184	98.75 105	89.60 215	97.62 74	99.01 60	97.53 67	98.69 55	99.18 35	94.05 151	99.68 101	98.73 17	99.88 34	99.58 36

EG-PatchMatch MVS		97.69 76	97.79 59	97.40 122	99.06 82	93.52 148	95.96 157	98.97 69	94.55 174	98.82 46	98.76 63	97.31 35	99.29 231	97.20 64	99.44 130	99.38 95

MP-MVS		97.64 79	97.18 105	99.00 9	99.32 49	97.77 14	97.49 84	98.73 112	96.27 106	95.59 229	97.75 158	96.30 77	99.78 39	93.70 178	99.48 121	99.45 71

#test#		97.62 80	97.22 103	98.83 25	99.15 67	97.50 25	96.81 117	98.84 87	94.25 185	97.49 147	97.54 171	97.07 45	99.70 86	94.37 158	99.46 125	99.30 109

3Dnovator	96.53 2	97.61 81	97.64 72	97.50 110	97.74 233	93.65 144	98.49 22	98.88 79	96.86 90	97.11 164	98.55 79	95.82 89	99.73 62	95.94 98	99.42 141	99.13 135

v18		97.60 82	98.06 48	96.23 186	98.68 119	89.46 220	97.48 85	98.98 67	97.33 81	98.60 59	99.13 42	93.86 154	99.67 107	98.62 21	99.87 36	99.56 41

v8		97.60 82	98.06 48	96.23 186	98.71 112	89.44 221	97.43 87	98.82 98	97.29 83	98.74 51	99.10 44	93.86 154	99.68 101	98.61 22	99.94 19	99.56 41

XVG-ACMP-BASELINE		97.58 84	97.28 95	98.49 46	99.16 64	96.90 42	96.39 127	98.98 67	95.05 160	98.06 108	98.02 132	95.86 85	99.56 149	94.37 158	99.64 77	99.00 156

v10		97.55 85	97.97 51	96.31 181	98.60 127	89.64 212	97.44 86	99.02 51	96.60 95	98.72 53	99.16 39	93.48 166	99.72 68	98.76 15	99.92 24	99.58 36

OPM-MVS		97.54 86	97.25 96	98.41 51	99.11 77	96.61 50	95.24 203	98.46 150	94.58 173	98.10 103	98.07 126	97.09 44	99.39 210	95.16 130	99.44 130	99.21 123

XXY-MVS		97.54 86	97.70 65	97.07 138	99.46 32	92.21 169	97.22 95	99.00 62	94.93 163	98.58 61	98.92 56	97.31 35	99.41 201	94.44 153	99.43 138	99.59 35

Regformer-4		97.53 88	97.47 87	97.71 92	97.35 261	93.91 132	95.26 201	98.14 197	97.97 44	98.34 78	97.89 146	95.49 101	99.71 78	97.41 57	99.42 141	99.51 49

SixPastTwentyTwo		97.49 89	97.57 80	97.26 130	99.56 19	92.33 165	98.28 31	96.97 257	98.30 33	99.45 14	99.35 18	88.43 252	99.89 17	98.01 31	99.76 50	99.54 45

ACMP	92.54 13	97.47 90	97.10 112	98.55 45	99.04 85	96.70 47	96.24 139	98.89 77	93.71 202	97.97 117	97.75 158	97.44 29	99.63 119	93.22 186	99.70 66	99.32 105
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
testing_2		97.43 91	97.71 64	96.60 161	98.91 96	90.85 193	96.01 150	98.54 143	94.78 166	98.78 48	98.96 52	96.35 76	99.54 155	97.25 60	99.82 42	99.40 90

TSAR-MVS + MP.		97.42 92	97.23 102	98.00 78	99.38 43	95.00 97	97.63 73	98.20 188	93.00 218	98.16 95	98.06 129	95.89 84	99.72 68	95.67 105	99.10 187	99.28 116

Regformer-2		97.41 93	97.24 98	97.93 81	97.21 270	94.72 106	94.85 224	98.27 180	97.74 51	98.11 100	97.50 176	95.58 99	99.69 95	96.57 77	99.31 165	99.37 100

CSCG		97.40 94	97.30 92	97.69 95	98.95 92	94.83 102	97.28 91	98.99 65	96.35 105	98.13 99	95.95 261	95.99 82	99.66 112	94.36 161	99.73 56	98.59 202

XVG-OURS-SEG-HR		97.38 95	97.07 115	98.30 62	99.01 88	97.41 31	94.66 229	99.02 51	95.20 148	98.15 97	97.52 174	98.83 5	98.43 311	94.87 139	96.41 306	99.07 150

HSP-MVS		97.37 96	96.85 125	98.92 19	99.26 51	97.70 15	97.66 70	98.23 184	95.65 128	98.51 65	96.46 237	92.15 202	99.81 33	95.14 132	98.58 234	99.26 120

VDD-MVS		97.37 96	97.25 96	97.74 91	98.69 118	94.50 114	97.04 107	95.61 282	98.59 23	98.51 65	98.72 66	92.54 194	99.58 143	96.02 94	99.49 118	99.12 140

SD-MVS		97.37 96	97.70 65	96.35 177	98.14 187	95.13 94	96.54 122	98.92 73	95.94 119	99.19 29	98.08 125	97.74 22	95.06 343	95.24 125	99.54 102	98.87 179

PM-MVS		97.36 99	97.10 112	98.14 70	98.91 96	96.77 45	96.20 141	98.63 136	93.82 199	98.54 63	98.33 94	93.98 152	99.05 255	95.99 96	99.45 129	98.61 201

LCM-MVSNet-Re		97.33 100	97.33 91	97.32 126	98.13 190	93.79 137	96.99 109	99.65 2	96.74 93	99.47 13	98.93 55	96.91 49	99.84 28	90.11 244	99.06 193	98.32 225

EI-MVSNet-UG-set		97.32 101	97.40 88	97.09 137	97.34 264	92.01 177	95.33 195	97.65 230	97.74 51	98.30 85	98.14 119	95.04 116	99.69 95	97.55 49	99.52 108	99.58 36

EI-MVSNet-Vis-set		97.32 101	97.39 89	97.11 135	97.36 260	92.08 175	95.34 194	97.65 230	97.74 51	98.29 86	98.11 123	95.05 114	99.68 101	97.50 53	99.50 111	99.56 41

Regformer-1		97.27 103	97.16 107	97.61 100	97.21 270	93.86 134	94.85 224	98.04 208	97.62 61	98.03 111	97.50 176	95.34 107	99.63 119	96.52 78	99.31 165	99.35 103

VPNet		97.26 104	97.49 86	96.59 163	99.47 31	90.58 199	96.27 135	98.53 144	97.77 49	98.46 70	98.41 88	94.59 130	99.68 101	94.61 149	99.29 169	99.52 48

Regformer-3		97.25 105	97.29 93	97.11 135	97.35 261	92.32 166	95.26 201	97.62 235	97.67 59	98.17 94	97.89 146	95.05 114	99.56 149	97.16 66	99.42 141	99.46 66

canonicalmvs		97.23 106	97.21 104	97.30 127	97.65 242	94.39 116	97.84 59	99.05 38	97.42 71	96.68 184	93.85 301	97.63 26	99.33 224	96.29 85	98.47 239	98.18 240

AllTest		97.20 107	96.92 123	98.06 73	99.08 79	96.16 61	97.14 98	99.16 16	94.35 182	97.78 140	98.07 126	95.84 86	99.12 246	91.41 212	99.42 141	98.91 170

XVG-OURS		97.12 108	96.74 132	98.26 64	98.99 89	97.45 29	93.82 265	99.05 38	95.19 149	98.32 81	97.70 164	95.22 112	98.41 312	94.27 163	98.13 250	98.93 167

V42		97.04 109	97.16 107	96.68 159	98.59 129	91.05 190	96.33 133	98.36 165	94.60 170	97.99 113	98.30 99	93.32 172	99.62 125	97.40 58	99.53 104	99.38 95

APD-MVS		97.00 110	96.53 144	98.41 51	98.55 134	96.31 58	96.32 134	98.77 105	92.96 224	97.44 153	97.58 170	95.84 86	99.74 57	91.96 200	99.35 156	99.19 125
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
HPM-MVS++		96.99 111	96.38 149	98.81 27	98.64 120	97.59 20	95.97 153	98.20 188	95.51 135	95.06 237	96.53 233	94.10 149	99.70 86	94.29 162	99.15 180	99.13 135

GBi-Net		96.99 111	96.80 129	97.56 102	97.96 204	93.67 140	98.23 34	98.66 129	95.59 132	97.99 113	99.19 32	89.51 243	99.73 62	94.60 150	99.44 130	99.30 109

test1		96.99 111	96.80 129	97.56 102	97.96 204	93.67 140	98.23 34	98.66 129	95.59 132	97.99 113	99.19 32	89.51 243	99.73 62	94.60 150	99.44 130	99.30 109

VDDNet		96.98 114	96.84 126	97.41 121	99.40 41	93.26 153	97.94 53	95.31 284	99.26 6	98.39 74	99.18 35	87.85 259	99.62 125	95.13 133	99.09 188	99.35 103

v1neww		96.97 115	97.24 98	96.15 194	98.70 114	89.44 221	95.97 153	98.33 170	95.25 144	97.88 130	98.15 116	93.83 157	99.61 131	97.50 53	99.50 111	99.41 87

v7new		96.97 115	97.24 98	96.15 194	98.70 114	89.44 221	95.97 153	98.33 170	95.25 144	97.88 130	98.15 116	93.83 157	99.61 131	97.50 53	99.50 111	99.41 87

v6		96.97 115	97.24 98	96.15 194	98.71 112	89.44 221	95.97 153	98.33 170	95.25 144	97.89 128	98.15 116	93.86 154	99.61 131	97.51 52	99.50 111	99.42 85

PHI-MVS		96.96 118	96.53 144	98.25 66	97.48 251	96.50 53	96.76 118	98.85 84	93.52 205	96.19 210	96.85 212	95.94 83	99.42 190	93.79 176	99.43 138	98.83 183

v7		96.93 119	97.17 106	96.23 186	98.59 129	89.64 212	95.96 157	98.66 129	94.41 178	97.87 135	98.38 91	93.47 167	99.64 116	97.93 33	99.24 174	99.43 83

IS-MVSNet		96.93 119	96.68 134	97.70 93	99.25 54	94.00 130	98.57 17	96.74 264	98.36 30	98.14 98	97.98 136	88.23 253	99.71 78	93.10 189	99.72 59	99.38 95

CNVR-MVS		96.92 121	96.55 141	98.03 77	98.00 201	95.54 79	94.87 222	98.17 193	94.60 170	96.38 196	97.05 200	95.67 97	99.36 219	95.12 134	99.08 189	99.19 125

IterMVS-LS		96.92 121	97.29 93	95.79 216	98.51 141	88.13 252	95.10 207	98.66 129	96.99 84	98.46 70	98.68 70	92.55 192	99.74 57	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		96.90 123	96.81 128	97.16 132	98.56 133	92.20 171	94.33 237	98.12 199	97.34 80	98.20 92	97.33 189	92.81 183	99.75 52	94.79 144	99.81 43	99.54 45

DeepPCF-MVS	94.58 5	96.90 123	96.43 148	98.31 61	97.48 251	97.23 35	92.56 298	98.60 139	92.84 226	98.54 63	97.40 182	96.64 63	98.78 287	94.40 157	99.41 147	98.93 167

v1141		96.86 125	97.14 109	96.04 201	98.55 134	89.06 232	95.44 182	98.33 170	95.14 154	97.93 123	98.19 110	93.36 170	99.62 125	97.61 45	99.69 67	99.44 79

divwei89l23v2f112		96.86 125	97.14 109	96.04 201	98.54 137	89.06 232	95.44 182	98.33 170	95.14 154	97.93 123	98.19 110	93.36 170	99.61 131	97.61 45	99.68 71	99.44 79

v1		96.86 125	97.14 109	96.04 201	98.55 134	89.06 232	95.44 182	98.33 170	95.14 154	97.94 120	98.18 114	93.39 169	99.61 131	97.61 45	99.69 67	99.44 79

v1144		96.84 128	97.08 114	96.13 198	98.42 151	89.28 227	95.41 189	98.67 127	94.21 187	97.97 117	98.31 96	93.06 177	99.65 113	98.06 30	99.62 79	99.45 71

VNet		96.84 128	96.83 127	96.88 149	98.06 193	92.02 176	96.35 132	97.57 237	97.70 56	97.88 130	97.80 154	92.40 199	99.54 155	94.73 148	98.96 199	99.08 148

EPP-MVSNet		96.84 128	96.58 138	97.65 98	99.18 63	93.78 138	98.68 11	96.34 267	97.91 46	97.30 157	98.06 129	88.46 251	99.85 24	93.85 174	99.40 148	99.32 105

v1192		96.83 131	97.06 116	96.15 194	98.28 161	89.29 226	95.36 192	98.77 105	93.73 201	98.11 100	98.34 93	93.02 181	99.67 107	98.35 26	99.58 91	99.50 50

MVS_111021_LR		96.82 132	96.55 141	97.62 99	98.27 163	95.34 86	93.81 266	98.33 170	94.59 172	96.56 188	96.63 228	96.61 64	98.73 291	94.80 143	99.34 158	98.78 188

Effi-MVS+-dtu		96.81 133	96.09 158	98.99 10	96.90 282	98.69 2	96.42 126	98.09 201	95.86 122	95.15 236	95.54 271	94.26 143	99.81 33	94.06 168	98.51 237	98.47 210

UGNet		96.81 133	96.56 140	97.58 101	96.64 285	93.84 135	97.75 65	97.12 252	96.47 101	93.62 283	98.88 58	93.22 175	99.53 157	95.61 111	99.69 67	99.36 102
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		96.78 135	97.06 116	95.95 209	98.57 132	88.77 242	95.36 192	98.26 182	95.18 150	97.85 137	98.23 105	92.58 191	99.63 119	97.80 38	99.69 67	99.45 71

v1240		96.74 136	97.02 118	95.91 212	98.18 180	88.52 244	95.39 190	98.88 79	93.15 215	98.46 70	98.40 90	92.80 184	99.71 78	98.45 25	99.49 118	99.49 58

DeepC-MVS_fast	94.34 7	96.74 136	96.51 146	97.44 119	97.69 237	94.15 125	96.02 149	98.43 155	93.17 214	97.30 157	97.38 187	95.48 102	99.28 232	93.74 177	99.34 158	98.88 177
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		96.73 138	96.54 143	97.27 128	98.35 155	93.66 143	93.42 279	98.36 165	94.74 167	96.58 186	96.76 221	96.54 66	98.99 263	94.87 139	99.27 172	99.15 132

v1921920		96.72 139	96.96 121	95.99 205	98.21 174	88.79 241	95.42 187	98.79 101	93.22 209	98.19 93	98.26 104	92.68 187	99.70 86	98.34 27	99.55 100	99.49 58

FMVSNet2		96.72 139	96.67 135	96.87 150	97.96 204	91.88 179	97.15 96	98.06 206	95.59 132	98.50 67	98.62 74	89.51 243	99.65 113	94.99 138	99.60 87	99.07 150

PMVS	89.60 17	96.71 141	96.97 119	95.95 209	99.51 26	97.81 13	97.42 88	97.49 238	97.93 45	95.95 216	98.58 75	96.88 52	96.91 337	89.59 251	99.36 153	93.12 335
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
v144192		96.69 142	96.90 124	96.03 204	98.25 170	88.92 235	95.49 180	98.77 105	93.05 217	98.09 104	98.29 100	92.51 196	99.70 86	98.11 29	99.56 96	99.47 64

CPTT-MVS		96.69 142	96.08 159	98.49 46	98.89 98	96.64 49	97.25 92	98.77 105	92.89 225	96.01 215	97.13 196	92.23 201	99.67 107	92.24 198	99.34 158	99.17 128

HQP_MVS		96.66 144	96.33 152	97.68 96	98.70 114	94.29 119	96.50 124	98.75 109	96.36 103	96.16 211	96.77 219	91.91 214	99.46 181	92.59 194	99.20 177	99.28 116

EI-MVSNet		96.63 145	96.93 122	95.74 217	97.26 268	88.13 252	95.29 199	97.65 230	96.99 84	97.94 120	98.19 110	92.55 192	99.58 143	96.91 72	99.56 96	99.50 50

ab-mvs		96.59 146	96.59 137	96.60 161	98.64 120	92.21 169	98.35 28	97.67 226	94.45 175	96.99 169	98.79 60	94.96 118	99.49 171	90.39 241	99.07 191	98.08 243

v148		96.58 147	96.97 119	95.42 227	98.63 124	87.57 265	95.09 209	97.90 211	95.91 120	98.24 89	97.96 137	93.42 168	99.39 210	96.04 92	99.52 108	99.29 115

test20.03		96.58 147	96.61 136	96.48 171	98.49 143	91.72 183	95.68 172	97.69 225	96.81 91	98.27 87	97.92 144	94.18 147	98.71 293	90.78 228	99.66 75	99.00 156

NCCC		96.52 149	95.99 163	98.10 71	97.81 218	95.68 74	95.00 218	98.20 188	95.39 140	95.40 232	96.36 244	93.81 159	99.45 185	93.55 181	98.42 240	99.17 128

pmmvs-eth3d		96.49 150	96.18 155	97.42 120	98.25 170	94.29 119	94.77 228	98.07 205	89.81 260	97.97 117	98.33 94	93.11 176	99.08 252	95.46 116	99.84 40	98.89 173

OMC-MVS		96.48 151	96.00 162	97.91 82	98.30 157	96.01 67	94.86 223	98.60 139	91.88 242	97.18 161	97.21 193	96.11 80	99.04 256	90.49 239	99.34 158	98.69 195

TSAR-MVS + GP.		96.47 152	96.12 156	97.49 113	97.74 233	95.23 88	94.15 250	96.90 259	93.26 208	98.04 110	96.70 224	94.41 137	98.89 275	94.77 146	99.14 181	98.37 218

Fast-Effi-MVS+-dtu		96.44 153	96.12 156	97.39 123	97.18 272	94.39 116	95.46 181	98.73 112	96.03 115	94.72 245	94.92 283	96.28 79	99.69 95	93.81 175	97.98 254	98.09 242

K. test v3		96.44 153	96.28 153	96.95 144	99.41 40	91.53 185	97.65 71	90.31 330	98.89 18	98.93 43	99.36 16	84.57 277	99.92 4	97.81 37	99.56 96	99.39 93

MSLP-MVS++		96.42 155	96.71 133	95.57 222	97.82 217	90.56 201	95.71 168	98.84 87	94.72 168	96.71 183	97.39 185	94.91 119	98.10 327	95.28 123	99.02 195	98.05 246

MVS_Test		96.27 156	96.79 131	94.73 250	96.94 280	86.63 281	96.18 142	98.33 170	94.94 161	96.07 213	98.28 101	95.25 111	99.26 235	97.21 62	97.90 260	98.30 228

MCST-MVS		96.24 157	95.80 169	97.56 102	98.75 105	94.13 126	94.66 229	98.17 193	90.17 257	96.21 209	96.10 255	95.14 113	99.43 189	94.13 166	98.85 214	99.13 135

MVS_0304		96.22 158	95.94 167	97.04 140	97.07 276	92.54 161	94.19 246	99.04 45	95.17 151	93.74 278	96.92 209	91.77 216	99.73 62	95.76 103	99.81 43	98.85 182

mvs-test1		96.20 159	95.50 177	98.32 59	96.90 282	98.16 4	95.07 212	98.09 201	95.86 122	93.63 282	94.32 297	94.26 143	99.71 78	94.06 168	97.27 293	97.07 281

Effi-MVS+		96.19 160	96.01 161	96.71 156	97.43 257	92.19 172	96.12 145	99.10 25	95.45 137	93.33 296	94.71 285	97.23 41	99.56 149	93.21 187	97.54 281	98.37 218

DELS-MVS		96.17 161	96.23 154	95.99 205	97.55 249	90.04 205	92.38 302	98.52 145	94.13 190	96.55 191	97.06 199	94.99 117	99.58 143	95.62 110	99.28 170	98.37 218
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		96.14 162	96.36 150	95.49 226	97.68 238	87.81 262	98.67 12	99.02 51	96.50 98	94.48 257	96.15 252	86.90 264	99.92 4	98.73 17	99.13 183	98.74 191

testgi		96.07 163	96.50 147	94.80 247	99.26 51	87.69 264	95.96 157	98.58 142	95.08 158	98.02 112	96.25 248	97.92 18	97.60 333	88.68 266	98.74 220	99.11 143

LF4IMVS		96.07 163	95.63 174	97.36 124	98.19 177	95.55 78	95.44 182	98.82 98	92.29 234	95.70 227	96.55 231	92.63 190	98.69 295	91.75 209	99.33 163	97.85 256

alignmvs		96.01 165	95.52 176	97.50 110	97.77 232	94.71 107	96.07 146	96.84 260	97.48 69	96.78 182	94.28 298	85.50 270	99.40 204	96.22 86	98.73 223	98.40 215

TinyColmap		96.00 166	96.34 151	94.96 241	97.90 209	87.91 259	94.13 252	98.49 148	94.41 178	98.16 95	97.76 155	96.29 78	98.68 298	90.52 236	99.42 141	98.30 228

PVSNet_Blended_VisFu		95.95 167	95.80 169	96.42 174	99.28 50	90.62 198	95.31 197	99.08 30	88.40 271	96.97 175	98.17 115	92.11 204	99.78 39	93.64 179	99.21 176	98.86 180

test_prior3		95.91 168	95.39 180	97.46 116	97.79 227	94.26 122	93.33 283	98.42 158	94.21 187	94.02 269	96.25 248	93.64 163	99.34 221	91.90 201	98.96 199	98.79 186

UnsupCasMVSNet_eth		95.91 168	95.73 171	96.44 173	98.48 145	91.52 186	95.31 197	98.45 151	95.76 126	97.48 150	97.54 171	89.53 242	98.69 295	94.43 154	94.61 323	99.13 135

QAPM		95.88 170	95.57 175	96.80 151	97.90 209	91.84 181	98.18 41	98.73 112	88.41 270	96.42 194	98.13 120	94.73 121	99.75 52	88.72 264	98.94 203	98.81 184

CANet		95.86 171	95.65 173	96.49 170	96.41 292	90.82 195	94.36 236	98.41 160	94.94 161	92.62 308	96.73 222	92.68 187	99.71 78	95.12 134	99.60 87	98.94 164

MVP-Stereo		95.69 172	95.28 182	96.92 146	98.15 186	93.03 156	95.64 177	98.20 188	90.39 254	96.63 185	97.73 161	91.63 217	99.10 250	91.84 205	97.31 291	98.63 199
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MDA-MVSNet-bldmvs		95.69 172	95.67 172	95.74 217	98.48 145	88.76 243	92.84 290	97.25 245	96.00 116	97.59 142	97.95 140	91.38 222	99.46 181	93.16 188	96.35 307	98.99 159

new-patchmatchnet		95.67 174	96.58 138	92.94 295	97.48 251	80.21 322	92.96 289	98.19 192	94.83 164	98.82 46	98.79 60	93.31 173	99.51 168	95.83 101	99.04 194	99.12 140

xiu_mvs_v1_base_debu		95.62 175	95.96 164	94.60 253	98.01 198	88.42 245	93.99 257	98.21 185	92.98 219	95.91 217	94.53 287	96.39 73	99.72 68	95.43 119	98.19 247	95.64 314

xiu_mvs_v1_base		95.62 175	95.96 164	94.60 253	98.01 198	88.42 245	93.99 257	98.21 185	92.98 219	95.91 217	94.53 287	96.39 73	99.72 68	95.43 119	98.19 247	95.64 314

xiu_mvs_v1_base_debi		95.62 175	95.96 164	94.60 253	98.01 198	88.42 245	93.99 257	98.21 185	92.98 219	95.91 217	94.53 287	96.39 73	99.72 68	95.43 119	98.19 247	95.64 314

DP-MVS Recon		95.55 178	95.13 186	96.80 151	98.51 141	93.99 131	94.60 231	98.69 122	90.20 256	95.78 223	96.21 251	92.73 186	98.98 265	90.58 235	98.86 212	97.42 271

test_normal		95.51 179	95.46 178	95.68 221	97.97 203	89.12 231	93.73 268	95.86 276	91.98 238	97.17 162	96.94 206	91.55 218	99.42 190	95.21 126	98.73 223	98.51 208

testmv		95.51 179	95.33 181	96.05 200	98.23 172	89.51 219	93.50 277	98.63 136	94.25 185	98.22 90	97.73 161	92.51 196	99.47 176	85.22 303	99.72 59	99.17 128

Fast-Effi-MVS+		95.49 181	95.07 188	96.75 154	97.67 241	92.82 158	94.22 244	98.60 139	91.61 244	93.42 293	92.90 311	96.73 60	99.70 86	92.60 193	97.89 261	97.74 261

TAMVS		95.49 181	94.94 193	97.16 132	98.31 156	93.41 150	95.07 212	96.82 261	91.09 249	97.51 145	97.82 152	89.96 237	99.42 190	88.42 269	99.44 130	98.64 197

OpenMVS	94.22 8	95.48 183	95.20 184	96.32 180	97.16 273	91.96 178	97.74 67	98.84 87	87.26 282	94.36 259	98.01 133	93.95 153	99.67 107	90.70 232	98.75 219	97.35 278

CLD-MVS		95.47 184	95.07 188	96.69 158	98.27 163	92.53 162	91.36 316	98.67 127	91.22 248	95.78 223	94.12 299	95.65 98	98.98 265	90.81 226	99.72 59	98.57 203
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
train_agg		95.46 185	94.66 203	97.88 83	97.84 215	95.23 88	93.62 272	98.39 161	87.04 286	93.78 275	95.99 256	94.58 131	99.52 160	91.76 207	98.90 205	98.89 173

DI_MVS_plusplus_test		95.46 185	95.43 179	95.55 223	98.05 194	88.84 239	94.18 247	95.75 278	91.92 241	97.32 156	96.94 206	91.44 220	99.39 210	94.81 142	98.48 238	98.43 214

CDPH-MVS		95.45 187	94.65 204	97.84 86	98.28 161	94.96 99	93.73 268	98.33 170	85.03 307	95.44 230	96.60 229	95.31 109	99.44 188	90.01 246	99.13 183	99.11 143

IterMVS		95.42 188	95.83 168	94.20 265	97.52 250	83.78 312	92.41 301	97.47 242	95.49 136	98.06 108	98.49 83	87.94 255	99.58 143	96.02 94	99.02 195	99.23 122
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
agg_prior1		95.39 189	94.60 207	97.75 90	97.80 222	94.96 99	93.39 280	98.36 165	87.20 284	93.49 288	95.97 259	94.65 128	99.53 157	91.69 210	98.86 212	98.77 189

Test4		95.39 189	95.24 183	95.82 215	98.07 192	89.60 215	94.40 235	98.49 148	91.39 247	97.40 155	96.32 246	87.32 263	99.41 201	95.09 136	98.71 225	98.44 213

mvs_anonymous		95.36 191	96.07 160	93.21 288	96.29 293	81.56 317	94.60 231	97.66 228	93.30 207	96.95 176	98.91 57	93.03 180	99.38 215	96.60 75	97.30 292	98.69 195

MSDG		95.33 192	95.13 186	95.94 211	97.40 259	91.85 180	91.02 319	98.37 164	95.30 142	96.31 203	95.99 256	94.51 135	98.38 316	89.59 251	97.65 277	97.60 266

LFMVS		95.32 193	94.88 197	96.62 160	98.03 195	91.47 187	97.65 71	90.72 326	99.11 8	97.89 128	98.31 96	79.20 290	99.48 174	93.91 173	99.12 186	98.93 167

agg_prior3		95.30 194	94.46 215	97.80 88	97.80 222	95.00 97	93.63 271	98.34 169	86.33 292	93.40 295	95.84 263	94.15 148	99.50 169	91.76 207	98.90 205	98.89 173

F-COLMAP		95.30 194	94.38 217	98.05 76	98.64 120	96.04 65	95.61 179	98.66 129	89.00 265	93.22 297	96.40 243	92.90 182	99.35 220	87.45 286	97.53 282	98.77 189

Anonymous20231206		95.27 196	95.06 190	95.88 213	98.72 109	89.37 225	95.70 169	97.85 214	88.00 278	96.98 170	97.62 168	91.95 210	99.34 221	89.21 256	99.53 104	98.94 164

FMVSNet3		95.26 197	94.94 193	96.22 190	96.53 288	90.06 204	95.99 151	97.66 228	94.11 191	97.99 113	97.91 145	80.22 288	99.63 119	94.60 150	99.44 130	98.96 161

N_pmnet		95.18 198	94.23 220	98.06 73	97.85 211	96.55 52	92.49 299	91.63 318	89.34 262	98.09 104	97.41 181	90.33 231	99.06 254	91.58 211	99.31 165	98.56 204

HQP-MVS		95.17 199	94.58 209	96.92 146	97.85 211	92.47 163	94.26 238	98.43 155	93.18 211	92.86 301	95.08 277	90.33 231	99.23 239	90.51 237	98.74 220	99.05 153

Vis-MVSNet (Re-imp)		95.11 200	94.85 198	95.87 214	99.12 76	89.17 228	97.54 83	94.92 286	96.50 98	96.58 186	97.27 191	83.64 278	99.48 174	88.42 269	99.67 73	98.97 160

AdaColmap		95.11 200	94.62 206	96.58 164	97.33 265	94.45 115	94.92 220	98.08 203	93.15 215	93.98 272	95.53 272	94.34 140	99.10 250	85.69 298	98.61 231	96.20 307

API-MVS		95.09 202	95.01 191	95.31 230	96.61 286	94.02 129	96.83 116	97.18 249	95.60 131	95.79 222	94.33 296	94.54 133	98.37 318	85.70 297	98.52 235	93.52 332

CNLPA		95.04 203	94.47 212	96.75 154	97.81 218	95.25 87	94.12 253	97.89 212	94.41 178	94.57 252	95.69 265	90.30 234	98.35 319	86.72 292	98.76 218	96.64 298

Patchmtry		95.03 204	94.59 208	96.33 179	94.83 319	90.82 195	96.38 130	97.20 247	96.59 96	97.49 147	98.57 76	77.67 296	99.38 215	92.95 192	99.62 79	98.80 185

PVSNet_BlendedMVS		95.02 205	94.93 195	95.27 231	97.79 227	87.40 270	94.14 251	98.68 124	88.94 266	94.51 255	98.01 133	93.04 178	99.30 228	89.77 249	99.49 118	99.11 143

diffmvs		95.00 206	95.00 192	95.01 240	96.53 288	87.96 258	95.73 166	98.32 179	90.67 253	91.89 315	97.43 180	92.07 207	98.90 272	95.44 117	96.88 296	98.16 241

TAPA-MVS	93.32 12	94.93 207	94.23 220	97.04 140	98.18 180	94.51 112	95.22 204	98.73 112	81.22 324	96.25 207	95.95 261	93.80 160	98.98 265	89.89 247	98.87 210	97.62 264
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CDS-MVSNet		94.88 208	94.12 225	97.14 134	97.64 243	93.57 145	93.96 260	97.06 254	90.05 258	96.30 204	96.55 231	86.10 267	99.47 176	90.10 245	99.31 165	98.40 215
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
no-one		94.84 209	94.76 201	95.09 237	98.29 158	87.49 267	91.82 310	97.49 238	88.21 274	97.84 138	98.75 64	91.51 219	99.27 233	88.96 261	99.99 2	98.52 207

MS-PatchMatch		94.83 210	94.91 196	94.57 256	96.81 284	87.10 276	94.23 243	97.34 243	88.74 268	97.14 163	97.11 197	91.94 211	98.23 323	92.99 191	97.92 258	98.37 218

pmmvs4		94.82 211	94.19 223	96.70 157	97.42 258	92.75 160	92.09 307	96.76 262	86.80 289	95.73 226	97.22 192	89.28 246	98.89 275	93.28 184	99.14 181	98.46 212

YYNet1		94.73 212	94.84 199	94.41 260	97.47 255	85.09 295	90.29 324	95.85 277	92.52 229	97.53 144	97.76 155	91.97 209	99.18 242	93.31 183	96.86 297	98.95 162

MDA-MVSNet_test_wron		94.73 212	94.83 200	94.42 259	97.48 251	85.15 293	90.28 325	95.87 275	92.52 229	97.48 150	97.76 155	91.92 213	99.17 244	93.32 182	96.80 300	98.94 164

UnsupCasMVSNet_bld		94.72 214	94.26 219	96.08 199	98.62 125	90.54 202	93.38 281	98.05 207	90.30 255	97.02 168	96.80 217	89.54 240	99.16 245	88.44 268	96.18 309	98.56 204

BH-untuned		94.69 215	94.75 202	94.52 258	97.95 208	87.53 266	94.07 254	97.01 255	93.99 192	97.10 165	95.65 267	92.65 189	98.95 270	87.60 283	96.74 301	97.09 280

Patchmatch-RL test		94.66 216	94.49 211	95.19 233	98.54 137	88.91 236	92.57 297	98.74 111	91.46 246	98.32 81	97.75 158	77.31 301	98.81 285	96.06 90	99.61 84	97.85 256

CANet_DTU		94.65 217	94.21 222	95.96 207	95.90 303	89.68 211	93.92 261	97.83 217	93.19 210	90.12 329	95.64 268	88.52 250	99.57 148	93.27 185	99.47 123	98.62 200

pmmvs5		94.63 218	94.34 218	95.50 225	97.63 244	88.34 248	94.02 255	97.13 251	87.15 285	95.22 235	97.15 195	87.50 260	99.27 233	93.99 171	99.26 173	98.88 177

PAPM_NR		94.61 219	94.17 224	95.96 207	98.36 154	91.23 188	95.93 160	97.95 209	92.98 219	93.42 293	94.43 295	90.53 229	98.38 316	87.60 283	96.29 308	98.27 231

PatchMatch-RL		94.61 219	93.81 231	97.02 143	98.19 177	95.72 72	93.66 270	97.23 246	88.17 275	94.94 241	95.62 269	91.43 221	98.57 303	87.36 287	97.68 274	96.76 294

BH-RMVSNet		94.56 221	94.44 216	94.91 242	97.57 246	87.44 269	93.78 267	96.26 268	93.69 203	96.41 195	96.50 236	92.10 205	99.00 262	85.96 295	97.71 271	98.31 226

USDC		94.56 221	94.57 210	94.55 257	97.78 231	86.43 283	92.75 293	98.65 135	85.96 295	96.91 178	97.93 143	90.82 227	98.74 290	90.71 231	99.59 89	98.47 210

jason		94.39 223	94.04 227	95.41 229	98.29 158	87.85 261	92.74 295	96.75 263	85.38 305	95.29 233	96.15 252	88.21 254	99.65 113	94.24 164	99.34 158	98.74 191
jason: jason.
1121		94.26 224	93.26 239	97.27 128	98.26 169	94.73 105	95.86 162	97.71 224	77.96 337	94.53 254	96.71 223	91.93 212	99.40 204	87.71 275	98.64 229	97.69 262

EU-MVSNet		94.25 225	94.47 212	93.60 280	98.14 187	82.60 315	97.24 94	92.72 310	85.08 306	98.48 68	98.94 54	82.59 281	98.76 289	97.47 56	99.53 104	99.44 79

xiu_mvs_v2_base		94.22 226	94.63 205	92.99 294	97.32 266	84.84 298	92.12 305	97.84 215	91.96 239	94.17 262	93.43 302	96.07 81	99.71 78	91.27 215	97.48 284	94.42 324

RPMNet		94.22 226	94.03 228	94.78 248	95.44 312	88.15 250	96.18 142	93.73 294	97.43 70	94.10 265	98.49 83	79.40 289	99.39 210	95.69 104	95.81 311	96.81 292

sss		94.22 226	93.72 232	95.74 217	97.71 236	89.95 208	93.84 264	96.98 256	88.38 273	93.75 277	95.74 264	87.94 255	98.89 275	91.02 219	98.10 251	98.37 218

MVSTER		94.21 229	93.93 230	95.05 239	95.83 305	86.46 282	95.18 205	97.65 230	92.41 233	97.94 120	98.00 135	72.39 326	99.58 143	96.36 84	99.56 96	99.12 140

MAR-MVS		94.21 229	93.03 243	97.76 89	96.94 280	97.44 30	96.97 114	97.15 250	87.89 280	92.00 313	92.73 316	92.14 203	99.12 246	83.92 311	97.51 283	96.73 295
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		94.12 231	93.42 236	96.23 186	98.59 129	90.85 193	94.24 242	98.85 84	85.49 300	92.97 299	94.94 281	86.01 268	99.64 116	91.78 206	97.92 258	98.20 237

PS-MVSNAJ		94.10 232	94.47 212	93.00 293	97.35 261	84.88 297	91.86 309	97.84 215	91.96 239	94.17 262	92.50 318	95.82 89	99.71 78	91.27 215	97.48 284	94.40 325

CHOSEN 1792x2688		94.10 232	93.41 237	96.18 192	99.16 64	90.04 205	92.15 304	98.68 124	79.90 329	96.22 208	97.83 149	87.92 258	99.42 190	89.18 257	99.65 76	99.08 148

MG-MVS		94.08 234	94.00 229	94.32 262	97.09 275	85.89 284	93.19 287	95.96 273	92.52 229	94.93 242	97.51 175	89.54 240	98.77 288	87.52 285	97.71 271	98.31 226

PLC	91.02 16	94.05 235	92.90 245	97.51 107	98.00 201	95.12 95	94.25 241	98.25 183	86.17 293	91.48 318	95.25 275	91.01 225	99.19 241	85.02 305	96.69 302	98.22 235
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
114514_t		93.96 236	93.22 241	96.19 191	99.06 82	90.97 192	95.99 151	98.94 72	73.88 343	93.43 292	96.93 208	92.38 200	99.37 218	89.09 258	99.28 170	98.25 233

PVSNet_Blended		93.96 236	93.65 233	94.91 242	97.79 227	87.40 270	91.43 315	98.68 124	84.50 311	94.51 255	94.48 290	93.04 178	99.30 228	89.77 249	98.61 231	98.02 251

lupinMVS		93.77 238	93.28 238	95.24 232	97.68 238	87.81 262	92.12 305	96.05 270	84.52 310	94.48 257	95.06 279	86.90 264	99.63 119	93.62 180	99.13 183	98.27 231

PatchT		93.75 239	93.57 235	94.29 264	95.05 317	87.32 272	96.05 147	92.98 305	97.54 65	94.25 260	98.72 66	75.79 309	99.24 237	95.92 99	95.81 311	96.32 305

EPNet		93.72 240	92.62 252	97.03 142	87.61 351	92.25 167	96.27 135	91.28 320	96.74 93	87.65 339	97.39 185	85.00 274	99.64 116	92.14 199	99.48 121	99.20 124
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HyFIR lowres test		93.72 240	92.65 251	96.91 148	98.93 93	91.81 182	91.23 318	98.52 145	82.69 317	96.46 193	96.52 235	80.38 287	99.90 13	90.36 242	98.79 215	99.03 154

PMMVS2		93.66 242	94.07 226	92.45 302	97.57 246	80.67 321	86.46 337	96.00 271	93.99 192	97.10 165	97.38 187	89.90 238	97.82 330	88.76 263	99.47 123	98.86 180

OpenMVS_ROB	91.80 14	93.64 243	93.05 242	95.42 227	97.31 267	91.21 189	95.08 211	96.68 266	81.56 321	96.88 180	96.41 241	90.44 230	99.25 236	85.39 302	97.67 275	95.80 312

Patchmatch-test		93.60 244	93.25 240	94.63 251	96.14 299	87.47 268	96.04 148	94.50 290	93.57 204	96.47 192	96.97 204	76.50 304	98.61 301	90.67 233	98.41 241	97.81 259

WTY-MVS		93.55 245	93.00 244	95.19 233	97.81 218	87.86 260	93.89 262	96.00 271	89.02 264	94.07 267	95.44 273	86.27 266	99.33 224	87.69 277	96.82 298	98.39 217

Test_1112_low_res		93.53 246	92.86 246	95.54 224	98.60 127	88.86 238	92.75 293	98.69 122	82.66 318	92.65 306	96.92 209	84.75 275	99.56 149	90.94 222	97.76 262	98.19 238

MIMVSNet		93.42 247	92.86 246	95.10 236	98.17 182	88.19 249	98.13 43	93.69 295	92.07 235	95.04 239	98.21 109	80.95 285	99.03 259	81.42 323	98.06 252	98.07 245

FMVSNet5		93.39 248	92.35 254	96.50 169	95.83 305	90.81 197	97.31 89	98.27 180	92.74 227	96.27 205	98.28 101	62.23 345	99.67 107	90.86 224	99.36 153	99.03 154

Patchmatch-test1		93.38 249	93.59 234	92.73 298	96.24 294	81.40 318	93.24 285	94.00 293	91.58 245	94.57 252	96.67 226	87.94 255	99.03 259	90.42 240	97.66 276	97.77 260

CR-MVSNet		93.29 250	92.79 248	94.78 248	95.44 312	88.15 250	96.18 142	97.20 247	84.94 308	94.10 265	98.57 76	77.67 296	99.39 210	95.17 129	95.81 311	96.81 292

wuyk23d		93.25 251	95.20 184	87.40 329	96.07 300	95.38 84	97.04 107	94.97 285	95.33 141	99.70 6	98.11 123	98.14 14	91.94 345	77.76 334	99.68 71	74.89 344

LP		93.12 252	92.78 250	94.14 266	94.50 324	85.48 288	95.73 166	95.68 280	92.97 223	95.05 238	97.17 194	81.93 282	99.40 204	93.06 190	88.96 338	97.55 267

test1235678		92.95 253	92.40 253	94.61 252	96.95 279	86.87 278	90.75 321	97.75 220	91.00 251	96.33 198	95.38 274	85.21 272	98.92 271	79.00 328	99.20 177	98.03 249

X-MVStestdata		92.86 254	90.83 285	98.94 15	99.15 67	97.66 16	97.77 62	98.83 94	97.42 71	96.32 201	36.50 347	96.49 70	99.72 68	95.66 107	99.37 150	99.45 71

GA-MVS		92.83 255	92.15 257	94.87 245	96.97 278	87.27 273	90.03 326	96.12 269	91.83 243	94.05 268	94.57 286	76.01 308	98.97 269	92.46 196	97.34 290	98.36 223

CMPMVS	73.10 23	92.74 256	91.39 268	96.77 153	93.57 336	94.67 109	94.21 245	97.67 226	80.36 328	93.61 284	96.60 229	82.85 280	97.35 334	84.86 306	98.78 216	98.29 230
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
HY-MVS	91.43 15	92.58 257	91.81 265	94.90 244	96.49 290	88.87 237	97.31 89	94.62 288	85.92 296	90.50 326	96.84 213	85.05 273	99.40 204	83.77 314	95.78 314	96.43 304

view600		92.56 258	92.11 258	93.91 271	98.45 147	84.76 300	97.10 101	90.23 331	97.42 71	96.98 170	94.48 290	73.62 317	99.60 137	82.49 318	98.28 243	97.36 272

view800		92.56 258	92.11 258	93.91 271	98.45 147	84.76 300	97.10 101	90.23 331	97.42 71	96.98 170	94.48 290	73.62 317	99.60 137	82.49 318	98.28 243	97.36 272

conf0.05thres1000		92.56 258	92.11 258	93.91 271	98.45 147	84.76 300	97.10 101	90.23 331	97.42 71	96.98 170	94.48 290	73.62 317	99.60 137	82.49 318	98.28 243	97.36 272

tfpn		92.56 258	92.11 258	93.91 271	98.45 147	84.76 300	97.10 101	90.23 331	97.42 71	96.98 170	94.48 290	73.62 317	99.60 137	82.49 318	98.28 243	97.36 272

TR-MVS		92.54 262	92.20 256	93.57 281	96.49 290	86.66 280	93.51 276	94.73 287	89.96 259	94.95 240	93.87 300	90.24 236	98.61 301	81.18 324	94.88 320	95.45 318

PMMVS		92.39 263	91.08 275	96.30 182	93.12 339	92.81 159	90.58 323	95.96 273	79.17 332	91.85 316	92.27 319	90.29 235	98.66 300	89.85 248	96.68 303	97.43 270

1314		92.38 264	92.30 255	92.64 300	95.42 314	85.15 293	95.86 162	96.97 257	85.40 304	90.62 322	93.06 309	91.12 224	97.80 331	86.74 291	95.49 319	94.97 322

new_pmnet		92.34 265	91.69 266	94.32 262	96.23 296	89.16 229	92.27 303	92.88 307	84.39 313	95.29 233	96.35 245	85.66 269	96.74 340	84.53 308	97.56 280	97.05 282

CVMVSNet		92.33 266	92.79 248	90.95 315	97.26 268	75.84 337	95.29 199	92.33 313	81.86 319	96.27 205	98.19 110	81.44 283	98.46 310	94.23 165	98.29 242	98.55 206

PAPR		92.22 267	91.27 271	95.07 238	95.73 308	88.81 240	91.97 308	97.87 213	85.80 298	90.91 320	92.73 316	91.16 223	98.33 320	79.48 326	95.76 315	98.08 243

DSMNet-mixed		92.19 268	91.83 264	93.25 287	96.18 298	83.68 313	96.27 135	93.68 297	76.97 340	92.54 309	99.18 35	89.20 248	98.55 306	83.88 312	98.60 233	97.51 269

BH-w/o		92.14 269	91.94 262	92.73 298	97.13 274	85.30 290	92.46 300	95.64 281	89.33 263	94.21 261	92.74 315	89.60 239	98.24 322	81.68 322	94.66 322	94.66 323

PCF-MVS	89.43 18	92.12 270	90.64 288	96.57 166	97.80 222	93.48 149	89.88 330	98.45 151	74.46 342	96.04 214	95.68 266	90.71 228	99.31 226	73.73 338	99.01 197	96.91 288
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
thres600view7		92.03 271	91.43 267	93.82 276	98.19 177	84.61 304	96.27 135	90.39 327	96.81 91	96.37 197	93.11 305	73.44 323	99.49 171	80.32 325	97.95 255	97.36 272

PatchmatchNet		91.98 272	91.87 263	92.30 304	94.60 322	79.71 323	95.12 206	93.59 300	89.52 261	93.61 284	97.02 202	77.94 294	99.18 242	90.84 225	94.57 324	98.01 252
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
cascas		91.89 273	91.35 269	93.51 282	94.27 327	85.60 286	88.86 333	98.61 138	79.32 331	92.16 312	91.44 329	89.22 247	98.12 326	90.80 227	97.47 286	96.82 291

tfpn1000		91.88 274	91.20 274	93.89 275	97.96 204	87.13 275	97.13 99	88.16 344	94.41 178	94.87 243	92.77 313	68.34 340	99.47 176	89.24 255	97.95 255	95.06 320

conf200view11		91.81 275	91.26 272	93.46 283	98.21 174	84.50 305	96.39 127	90.39 327	96.87 88	96.33 198	93.08 307	73.44 323	99.42 190	78.85 330	97.74 263	96.46 303

JIA-IIPM		91.79 276	90.69 287	95.11 235	93.80 333	90.98 191	94.16 249	91.78 317	96.38 102	90.30 328	99.30 23	72.02 328	98.90 272	88.28 271	90.17 335	95.45 318

thres100view900		91.76 277	91.26 272	93.26 286	98.21 174	84.50 305	96.39 127	90.39 327	96.87 88	96.33 198	93.08 307	73.44 323	99.42 190	78.85 330	97.74 263	95.85 310

thresconf0.02		91.72 278	90.98 278	93.97 267	98.27 163	88.03 254	96.98 110	88.58 339	93.90 195	94.64 248	91.45 325	69.62 335	99.52 160	87.62 279	97.74 263	94.35 326

tfpn_n400		91.72 278	90.98 278	93.97 267	98.27 163	88.03 254	96.98 110	88.58 339	93.90 195	94.64 248	91.45 325	69.62 335	99.52 160	87.62 279	97.74 263	94.35 326

tfpnconf		91.72 278	90.98 278	93.97 267	98.27 163	88.03 254	96.98 110	88.58 339	93.90 195	94.64 248	91.45 325	69.62 335	99.52 160	87.62 279	97.74 263	94.35 326

tfpnview11		91.72 278	90.98 278	93.97 267	98.27 163	88.03 254	96.98 110	88.58 339	93.90 195	94.64 248	91.45 325	69.62 335	99.52 160	87.62 279	97.74 263	94.35 326

thres400		91.68 282	91.00 276	93.71 278	98.02 196	84.35 308	95.70 169	90.79 324	96.26 107	95.90 220	92.13 321	73.62 317	99.42 190	78.85 330	97.74 263	97.36 272

tfpn200view9		91.55 283	91.00 276	93.21 288	98.02 196	84.35 308	95.70 169	90.79 324	96.26 107	95.90 220	92.13 321	73.62 317	99.42 190	78.85 330	97.74 263	95.85 310

ADS-MVSNet2		91.47 284	90.51 290	94.36 261	95.51 310	85.63 285	95.05 215	95.70 279	83.46 315	92.69 304	96.84 213	79.15 291	99.41 201	85.66 299	90.52 333	98.04 247

EPNet_dtu		91.39 285	90.75 286	93.31 285	90.48 349	82.61 314	94.80 226	92.88 307	93.39 206	81.74 347	94.90 284	81.36 284	99.11 249	88.28 271	98.87 210	98.21 236
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet	86.72 19	91.10 286	90.97 282	91.49 309	97.56 248	78.04 330	87.17 335	94.60 289	84.65 309	92.34 310	92.20 320	87.37 262	98.47 309	85.17 304	97.69 273	97.96 253

tpm		91.08 287	90.85 284	91.75 308	95.33 315	78.09 328	95.03 217	91.27 321	88.75 267	93.53 287	97.40 182	71.24 329	99.30 228	91.25 217	93.87 325	97.87 255

thres200		91.00 288	90.42 292	92.77 297	97.47 255	83.98 311	94.01 256	91.18 322	95.12 157	95.44 230	91.21 331	73.93 313	99.31 226	77.76 334	97.63 279	95.01 321

tfpn_ndepth		90.98 289	90.24 294	93.20 290	97.72 235	87.18 274	96.52 123	88.20 343	92.63 228	93.69 281	90.70 336	68.22 341	99.42 190	86.98 289	97.47 286	93.00 336

ADS-MVSNet		90.95 290	90.26 293	93.04 291	95.51 310	82.37 316	95.05 215	93.41 301	83.46 315	92.69 304	96.84 213	79.15 291	98.70 294	85.66 299	90.52 333	98.04 247

testus		90.90 291	90.51 290	92.06 306	96.07 300	79.45 324	88.99 331	98.44 154	85.46 302	94.15 264	90.77 333	89.12 249	98.01 329	73.66 339	97.95 255	98.71 194

tpmvs		90.79 292	90.87 283	90.57 318	92.75 343	76.30 335	95.79 165	93.64 298	91.04 250	91.91 314	96.26 247	77.19 302	98.86 281	89.38 254	89.85 336	96.56 301

tpmrst		90.31 293	90.61 289	89.41 322	94.06 331	72.37 344	95.06 214	93.69 295	88.01 277	92.32 311	96.86 211	77.45 298	98.82 283	91.04 218	87.01 341	97.04 283

test0.0.03 1		90.11 294	89.21 301	92.83 296	93.89 332	86.87 278	91.74 311	88.74 338	92.02 236	94.71 246	91.14 332	73.92 314	94.48 344	83.75 315	92.94 327	97.16 279

MVS		90.02 295	89.20 302	92.47 301	94.71 320	86.90 277	95.86 162	96.74 264	64.72 345	90.62 322	92.77 313	92.54 194	98.39 314	79.30 327	95.56 318	92.12 337

pmmvs3		90.00 296	88.90 305	93.32 284	94.20 330	85.34 289	91.25 317	92.56 312	78.59 334	93.82 274	95.17 276	67.36 343	98.69 295	89.08 259	98.03 253	95.92 308

CHOSEN 280x420		89.98 297	89.19 303	92.37 303	95.60 309	81.13 319	86.22 338	97.09 253	81.44 323	87.44 340	93.15 304	73.99 312	99.47 176	88.69 265	99.07 191	96.52 302

test-LLR		89.97 298	89.90 296	90.16 319	94.24 328	74.98 338	89.89 327	89.06 336	92.02 236	89.97 330	90.77 333	73.92 314	98.57 303	91.88 203	97.36 288	96.92 286

FPMVS		89.92 299	88.63 306	93.82 276	98.37 153	96.94 41	91.58 312	93.34 302	88.00 278	90.32 327	97.10 198	70.87 331	91.13 346	71.91 342	96.16 310	93.39 334

CostFormer		89.75 300	89.25 299	91.26 312	94.69 321	78.00 331	95.32 196	91.98 315	81.50 322	90.55 324	96.96 205	71.06 330	98.89 275	88.59 267	92.63 330	96.87 289

PatchFormer-LS_test		89.62 301	89.12 304	91.11 314	93.62 334	78.42 327	94.57 233	93.62 299	88.39 272	90.54 325	88.40 341	72.33 327	99.03 259	92.41 197	88.20 339	95.89 309

E-PMN		89.52 302	89.78 297	88.73 324	93.14 338	77.61 332	83.26 342	92.02 314	94.82 165	93.71 279	93.11 305	75.31 310	96.81 338	85.81 296	96.81 299	91.77 339

EPMVS		89.26 303	88.55 307	91.39 310	92.36 344	79.11 325	95.65 175	79.86 349	88.60 269	93.12 298	96.53 233	70.73 332	98.10 327	90.75 229	89.32 337	96.98 284

EMVS		89.06 304	89.22 300	88.61 325	93.00 340	77.34 333	82.91 343	90.92 323	94.64 169	92.63 307	91.81 324	76.30 306	97.02 336	83.83 313	96.90 295	91.48 340

1111		88.78 305	89.39 298	86.96 330	98.53 139	62.84 349	91.49 313	97.48 240	94.45 175	96.56 188	96.45 238	43.83 355	98.87 279	86.33 293	99.40 148	99.18 127

IB-MVS	85.98 20	88.63 306	86.95 315	93.68 279	95.12 316	84.82 299	90.85 320	90.17 335	87.55 281	88.48 336	91.34 330	58.01 347	99.59 141	87.24 288	93.80 326	96.63 300
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		88.47 307	87.69 310	90.79 316	94.98 318	77.34 333	95.09 209	91.83 316	77.51 339	89.40 332	96.41 241	67.83 342	98.73 291	83.58 316	92.60 331	96.29 306

tpmp4_e23		88.46 308	87.54 311	91.22 313	94.56 323	78.08 329	95.63 178	93.17 303	79.08 333	85.85 342	96.80 217	65.86 344	98.85 282	84.10 310	92.85 328	96.72 296

MVS-HIRNet		88.40 309	90.20 295	82.99 333	97.01 277	60.04 351	93.11 288	85.61 346	84.45 312	88.72 335	99.09 45	84.72 276	98.23 323	82.52 317	96.59 304	90.69 342

gg-mvs-nofinetune		88.28 310	86.96 314	92.23 305	92.84 342	84.44 307	98.19 40	74.60 351	99.08 9	87.01 341	99.47 8	56.93 348	98.23 323	78.91 329	95.61 317	94.01 330

dp		88.08 311	88.05 309	88.16 328	92.85 341	68.81 346	94.17 248	92.88 307	85.47 301	91.38 319	96.14 254	68.87 339	98.81 285	86.88 290	83.80 345	96.87 289

tpm cat1		88.01 312	87.33 312	90.05 321	94.48 325	76.28 336	94.47 234	94.35 292	73.84 344	89.26 333	95.61 270	73.64 316	98.30 321	84.13 309	86.20 342	95.57 317

test12356		87.98 313	88.41 308	86.69 331	95.84 304	63.49 348	87.15 336	97.32 244	87.21 283	91.78 317	93.36 303	70.66 333	98.39 314	74.70 337	97.64 278	98.19 238

test-mter		87.92 314	87.17 313	90.16 319	94.24 328	74.98 338	89.89 327	89.06 336	86.44 291	89.97 330	90.77 333	54.96 351	98.57 303	91.88 203	97.36 288	96.92 286

DWT-MVSNet_test		87.92 314	86.77 316	91.39 310	93.18 337	78.62 326	95.10 207	91.42 319	85.58 299	88.00 337	88.73 340	60.60 346	98.90 272	90.60 234	87.70 340	96.65 297

PAPM		87.64 316	85.84 319	93.04 291	96.54 287	84.99 296	88.42 334	95.57 283	79.52 330	83.82 344	93.05 310	80.57 286	98.41 312	62.29 346	92.79 329	95.71 313

TESTMET0.1,1		87.20 317	86.57 317	89.07 323	93.62 334	72.84 343	89.89 327	87.01 345	85.46 302	89.12 334	90.20 338	56.00 350	97.72 332	90.91 223	96.92 294	96.64 298

MVE	73.61 22	86.48 318	85.92 318	88.18 327	96.23 296	85.28 291	81.78 345	75.79 350	86.01 294	82.53 346	91.88 323	92.74 185	87.47 348	71.42 343	94.86 321	91.78 338
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test2356		85.45 319	83.26 322	92.01 307	91.12 346	80.76 320	85.16 339	92.90 306	83.90 314	90.63 321	87.71 343	53.10 352	97.24 335	69.20 344	95.65 316	98.03 249

PVSNet_0	81.89 21	84.49 320	83.21 323	88.34 326	95.76 307	74.97 340	83.49 341	92.70 311	78.47 335	87.94 338	86.90 344	83.38 279	96.63 341	73.44 340	66.86 348	93.40 333

PNet_i23d		83.82 321	83.39 321	85.10 332	96.07 300	65.16 347	81.87 344	94.37 291	90.87 252	93.92 273	92.89 312	52.80 353	96.44 342	77.52 336	70.22 347	93.70 331

testpf		82.70 322	84.35 320	77.74 334	88.97 350	73.23 342	93.85 263	84.33 347	88.10 276	85.06 343	90.42 337	52.62 354	91.05 347	91.00 220	84.82 344	68.93 345

.test1245		73.49 323	79.27 324	56.15 336	98.53 139	62.84 349	91.49 313	97.48 240	94.45 175	96.56 188	96.45 238	43.83 355	98.87 279	86.33 293	8.32 350	6.75 348

tmp_tt		57.23 324	62.50 325	41.44 337	34.77 352	49.21 353	83.93 340	60.22 355	15.31 347	71.11 349	79.37 346	70.09 334	44.86 350	64.76 345	82.93 346	30.25 346

pcd1.5k->3k		41.47 325	44.19 326	33.29 338	99.65 11	0.00 356	0.00 346	99.07 34	0.00 350	0.00 352	0.00 352	99.04 4	0.00 353	0.00 350	99.96 11	99.87 2

cdsmvs_eth3d_5k		24.22 326	32.30 327	0.00 341	0.00 355	0.00 356	0.00 346	98.10 200	0.00 350	0.00 352	95.06 279	97.54 28	0.00 353	0.00 350	0.00 352	0.00 350

test123		12.59 327	15.49 328	3.87 339	6.07 353	2.55 354	90.75 321	2.59 357	2.52 348	5.20 351	13.02 349	4.96 357	1.85 352	5.20 348	9.09 349	7.23 347

testmvs		12.33 328	15.23 329	3.64 340	5.77 354	2.23 355	88.99 331	3.62 356	2.30 349	5.29 350	13.09 348	4.52 358	1.95 351	5.16 349	8.32 350	6.75 348

pcd_1.5k_mvsjas		7.98 329	10.65 330	0.00 341	0.00 355	0.00 356	0.00 346	0.00 358	0.00 350	0.00 352	0.00 352	95.82 89	0.00 353	0.00 350	0.00 352	0.00 350

ab-mvs-re		7.91 330	10.55 331	0.00 341	0.00 355	0.00 356	0.00 346	0.00 358	0.00 350	0.00 352	94.94 281	0.00 359	0.00 353	0.00 350	0.00 352	0.00 350

sosnet-low-res		0.00 331	0.00 332	0.00 341	0.00 355	0.00 356	0.00 346	0.00 358	0.00 350	0.00 352	0.00 352	0.00 359	0.00 353	0.00 350	0.00 352	0.00 350

sosnet		0.00 331	0.00 332	0.00 341	0.00 355	0.00 356	0.00 346	0.00 358	0.00 350	0.00 352	0.00 352	0.00 359	0.00 353	0.00 350	0.00 352	0.00 350

uncertanet		0.00 331	0.00 332	0.00 341	0.00 355	0.00 356	0.00 346	0.00 358	0.00 350	0.00 352	0.00 352	0.00 359	0.00 353	0.00 350	0.00 352	0.00 350

Regformer		0.00 331	0.00 332	0.00 341	0.00 355	0.00 356	0.00 346	0.00 358	0.00 350	0.00 352	0.00 352	0.00 359	0.00 353	0.00 350	0.00 352	0.00 350

uanet		0.00 331	0.00 332	0.00 341	0.00 355	0.00 356	0.00 346	0.00 358	0.00 350	0.00 352	0.00 352	0.00 359	0.00 353	0.00 350	0.00 352	0.00 350

test_part2					99.03 86	96.07 64				98.08 106

test_part1								98.84 87				96.69 61			99.44 130	99.37 100

test_all								98.80 100

sam_mvs1												77.80 295

sam_mvs												77.38 299

semantic-postprocess				94.85 246	97.68 238	85.53 287		97.63 234	96.99 84	98.36 76	98.54 80	87.44 261	99.75 52	97.07 69	99.08 189	99.27 119

ambc				96.56 167	98.23 172	91.68 184	97.88 57	98.13 198		98.42 73	98.56 78	94.22 145	99.04 256	94.05 170	99.35 156	98.95 162

MTGPA								98.73 112

test_post1							94.98 219				10.37 351	76.21 307	99.04 256	89.47 253

test_post											10.87 350	76.83 303	99.07 253

patchmatchnet-post											96.84 213	77.36 300	99.42 190

GG-mvs-BLEND				90.60 317	91.00 347	84.21 310	98.23 34	72.63 354		82.76 345	84.11 345	56.14 349	96.79 339	72.20 341	92.09 332	90.78 341

MTMP								74.60 351

gm-plane-assit					91.79 345	71.40 345			81.67 320		90.11 339		98.99 263	84.86 306

test9_res														91.29 214	98.89 209	99.00 156

TEST9					97.84 215	95.23 88	93.62 272	98.39 161	86.81 288	93.78 275	95.99 256	94.68 126	99.52 160

test_8					97.81 218	95.07 96	93.54 275	98.38 163	87.04 286	93.71 279	95.96 260	94.58 131	99.52 160

agg_prior2														90.34 243	98.90 205	99.10 147

agg_prior					97.80 222	94.96 99		98.36 165		93.49 288			99.53 157

TestCases				98.06 73	99.08 79	96.16 61		99.16 16	94.35 182	97.78 140	98.07 126	95.84 86	99.12 246	91.41 212	99.42 141	98.91 170

test_prior4						95.38 84	93.61 274

test_prior2							93.33 283		94.21 187	94.02 269	96.25 248	93.64 163		91.90 201	98.96 199

test_prior				97.46 116	97.79 227	94.26 122		98.42 158					99.34 221			98.79 186

旧先验2							93.35 282		77.95 338	95.77 225			98.67 299	90.74 230

新几何2							93.43 278

新几何1				97.25 131	98.29 158	94.70 108		97.73 222	77.98 336	94.83 244	96.67 226	92.08 206	99.45 185	88.17 273	98.65 228	97.61 265

旧先验1					97.80 222	93.87 133		97.75 220			97.04 201	93.57 165			98.68 226	98.72 193

无先验							93.20 286	97.91 210	80.78 325				99.40 204	87.71 275		97.94 254

原ACMM2							92.82 291

原ACMM1				96.58 164	98.16 184	92.12 173		98.15 196	85.90 297	93.49 288	96.43 240	92.47 198	99.38 215	87.66 278	98.62 230	98.23 234

test222					98.17 182	93.24 154	92.74 295	97.61 236	75.17 341	94.65 247	96.69 225	90.96 226			98.66 227	97.66 263

testdata2													99.46 181	87.84 274

segment_acmp												95.34 107

testdata				95.70 220	98.16 184	90.58 199		97.72 223	80.38 327	95.62 228	97.02 202	92.06 208	98.98 265	89.06 260	98.52 235	97.54 268

testdata1							92.77 292		93.78 200

test12				97.46 116	97.61 245	94.07 127		97.78 219		93.57 286		93.31 173	99.42 190		98.78 216	98.89 173

plane_prior7					98.70 114	94.67 109

plane_prior6					98.38 152	94.37 118						91.91 214

plane_prior5								98.75 109					99.46 181	92.59 194	99.20 177	99.28 116

plane_prior4											96.77 219

plane_prior3						94.51 112			95.29 143	96.16 211

plane_prior2							96.50 124		96.36 103

plane_prior1					98.49 143

plane_prior						94.29 119	95.42 187		94.31 184						98.93 204

n2								0.00 358

nn								0.00 358

door-mid								98.17 193

lessismore_v0				97.05 139	99.36 45	92.12 173		84.07 348		98.77 50	98.98 50	85.36 271	99.74 57	97.34 59	99.37 150	99.30 109

LGP-MVS_train				98.74 32	99.15 67	97.02 38		99.02 51	95.15 152	98.34 78	98.23 105	97.91 19	99.70 86	94.41 155	99.73 56	99.50 50

test11								98.08 203

door								97.81 218

HQP5-MVS						92.47 163

HQP-NCC					97.85 211		94.26 238		93.18 211	92.86 301

ACMP_Plane					97.85 211		94.26 238		93.18 211	92.86 301

BP-MVS														90.51 237

HQP4-MVS										92.87 300			99.23 239			99.06 152

HQP3-MVS								98.43 155							98.74 220

HQP2-MVS												90.33 231

NP-MVS					98.14 187	93.72 139					95.08 277

MDTV_nov1_ep13_2view						57.28 352	94.89 221		80.59 326	94.02 269		78.66 293		85.50 301		97.82 258

MDTV_nov1_ep13			91.28 270		94.31 326	73.51 341	94.80 226	93.16 304	86.75 290	93.45 291	97.40 182	76.37 305	98.55 306	88.85 262	96.43 305

ACMMP++_ref															99.52 108

ACMMP++															99.55 100

Test By Simon												94.51 135

ITE_SJBPF				97.85 85	98.64 120	96.66 48		98.51 147	95.63 129	97.22 159	97.30 190	95.52 100	98.55 306	90.97 221	98.90 205	98.34 224

DeepMVS_CX				77.17 335	90.94 348	85.28 291		74.08 353	52.51 346	80.87 348	88.03 342	75.25 311	70.63 349	59.23 347	84.94 343	75.62 343

High-resolution multi-view benchmark