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		99.93 1	99.92 1	99.94 1	99.99 1	99.97 1	99.90 1	99.89 2	99.98 1	99.99 1	99.96 1	99.77 1	100.00 1	99.81 3	100.00 1	99.85 9

Anonymous20231211		99.71 2	99.70 3	99.74 2	99.97 2	99.52 2	99.74 4	99.82 4	99.73 6	99.91 4	99.89 2	99.27 9	99.94 20	99.02 49	99.94 33	99.75 21

pmmvs6		99.67 3	99.70 3	99.60 12	99.90 5	99.27 16	99.53 9	99.76 7	99.64 10	99.84 9	99.83 3	99.50 5	99.87 72	99.36 28	99.92 49	99.64 40

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 18	99.85 18	99.11 41	99.90 1	99.78 5	99.63 12	99.78 10	99.67 21	99.48 6	99.81 139	99.30 31	99.97 23	99.77 16
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
mvs_tets		99.63 5	99.67 5	99.49 42	99.88 8	98.61 69	99.34 15	99.71 12	99.27 44	99.90 5	99.74 8	99.68 3	99.97 3	99.55 20	99.99 11	99.88 5

v52		99.59 6	99.60 8	99.55 20	99.87 12	99.00 45	99.59 7	99.56 49	99.56 22	99.68 20	99.72 11	98.57 34	99.93 26	99.85 1	99.99 11	99.72 24

V4		99.59 6	99.60 8	99.55 20	99.87 12	99.00 45	99.59 7	99.56 49	99.56 22	99.68 20	99.72 11	98.57 34	99.93 26	99.85 1	99.99 11	99.72 24

jajsoiax		99.58 8	99.61 7	99.48 43	99.87 12	98.61 69	99.28 29	99.66 19	99.09 67	99.89 8	99.68 19	99.53 4	99.97 3	99.50 22	99.99 11	99.87 6

ANet_high		99.57 9	99.67 5	99.28 69	99.89 7	98.09 102	99.14 44	99.93 1	99.82 2	99.93 2	99.81 4	99.17 14	99.94 20	99.31 30	100.00 1	99.82 10

v7n		99.53 10	99.57 10	99.41 51	99.88 8	98.54 77	99.45 10	99.61 30	99.66 9	99.68 20	99.66 22	98.44 42	99.95 13	99.73 8	99.96 28	99.75 21

test_djsdf		99.52 11	99.51 11	99.53 32	99.86 16	98.74 58	99.39 13	99.56 49	99.11 60	99.70 15	99.73 10	99.00 17	99.97 3	99.26 32	99.98 19	99.89 3

anonymousdsp		99.51 12	99.47 15	99.62 6	99.88 8	99.08 44	99.34 15	99.69 15	98.93 82	99.65 23	99.72 11	98.93 20	99.95 13	99.11 44	100.00 1	99.82 10

UA-Net		99.47 13	99.40 17	99.70 3	99.49 91	99.29 13	99.80 3	99.72 11	99.82 2	99.04 113	99.81 4	98.05 63	99.96 8	98.85 56	99.99 11	99.86 8

PS-MVSNAJss		99.46 14	99.49 12	99.35 60	99.90 5	98.15 98	99.20 35	99.65 20	99.48 25	99.92 3	99.71 14	98.07 60	99.96 8	99.53 21	100.00 1	99.93 1

v748		99.44 15	99.48 13	99.33 65	99.88 8	98.43 84	99.42 11	99.53 59	99.63 12	99.69 17	99.60 34	97.99 68	99.91 43	99.60 14	99.96 28	99.66 33

pm-mvs1		99.44 15	99.48 13	99.33 65	99.80 22	98.63 66	99.29 25	99.63 25	99.30 41	99.65 23	99.60 34	99.16 16	99.82 126	99.07 46	99.83 79	99.56 75

TransMVSNet (Re)		99.44 15	99.47 15	99.36 55	99.80 22	98.58 72	99.27 31	99.57 43	99.39 32	99.75 12	99.62 28	99.17 14	99.83 114	99.06 47	99.62 154	99.66 33

DTE-MVSNet		99.43 18	99.35 22	99.66 4	99.71 34	99.30 12	99.31 20	99.51 64	99.64 10	99.56 33	99.46 52	98.23 50	99.97 3	98.78 59	99.93 39	99.72 24

TDRefinement		99.42 19	99.38 19	99.55 20	99.76 26	99.33 11	99.68 5	99.71 12	99.38 34	99.53 37	99.61 30	98.64 29	99.80 151	98.24 85	99.84 73	99.52 94

PEN-MVS		99.41 20	99.34 24	99.62 6	99.73 28	99.14 34	99.29 25	99.54 58	99.62 16	99.56 33	99.42 59	98.16 56	99.96 8	98.78 59	99.93 39	99.77 16

nrg030		99.40 21	99.35 22	99.54 25	99.58 56	99.13 37	98.98 61	99.48 74	99.68 7	99.46 49	99.26 79	98.62 30	99.73 207	99.17 43	99.92 49	99.76 19

PS-CasMVS		99.40 21	99.33 26	99.62 6	99.71 34	99.10 42	99.29 25	99.53 59	99.53 24	99.46 49	99.41 61	98.23 50	99.95 13	98.89 55	99.95 30	99.81 12

MIMVSNet1		99.38 23	99.32 27	99.55 20	99.86 16	99.19 24	99.41 12	99.59 34	99.59 19	99.71 14	99.57 39	97.12 121	99.90 47	99.21 38	99.87 68	99.54 86

OurMVSNet-221017-0		99.37 24	99.31 28	99.53 32	99.91 4	98.98 47	99.63 6	99.58 36	99.44 29	99.78 10	99.76 6	96.39 169	99.92 34	99.44 26	99.92 49	99.68 30

wuykxyi23d		99.36 25	99.31 28	99.50 41	99.81 21	98.67 65	98.08 125	99.75 8	98.03 122	99.90 5	99.60 34	99.18 12	99.94 20	99.46 25	99.98 19	99.89 3

Vis-MVSNet		99.34 26	99.36 21	99.27 72	99.73 28	98.26 91	99.17 41	99.78 5	99.11 60	99.27 81	99.48 50	98.82 22	99.95 13	98.94 52	99.93 39	99.59 58
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
WR-MVS_H		99.33 27	99.22 36	99.65 5	99.71 34	99.24 19	99.32 17	99.55 54	99.46 28	99.50 43	99.34 70	97.30 106	99.93 26	98.90 53	99.93 39	99.77 16

VPA-MVSNet		99.30 28	99.30 31	99.28 69	99.49 91	98.36 89	99.00 59	99.45 85	99.63 12	99.52 39	99.44 57	98.25 48	99.88 63	99.09 45	99.84 73	99.62 45

FC-MVSNet-test		99.27 29	99.25 34	99.34 63	99.77 25	98.37 88	99.30 24	99.57 43	99.61 18	99.40 59	99.50 46	97.12 121	99.85 85	99.02 49	99.94 33	99.80 13

ACMH	96.65 7	99.25 30	99.24 35	99.26 74	99.72 33	98.38 87	99.07 52	99.55 54	98.30 111	99.65 23	99.45 56	99.22 10	99.76 187	98.44 76	99.77 104	99.64 40
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
v13		99.24 31	99.39 18	98.77 138	99.63 51	96.79 181	99.24 33	99.65 20	99.39 32	99.62 27	99.70 16	97.50 92	99.84 100	99.78 5	100.00 1	99.67 31

v12		99.21 32	99.37 20	98.74 146	99.60 54	96.72 186	99.19 39	99.65 20	99.35 38	99.62 27	99.69 17	97.43 99	99.83 114	99.76 6	100.00 1	99.66 33

CP-MVSNet		99.21 32	99.09 45	99.56 18	99.65 46	98.96 51	99.13 46	99.34 120	99.42 30	99.33 71	99.26 79	97.01 129	99.94 20	98.74 63	99.93 39	99.79 14

V9		99.18 34	99.34 24	98.70 147	99.58 56	96.63 189	99.14 44	99.64 24	99.30 41	99.61 29	99.68 19	97.33 104	99.83 114	99.75 7	100.00 1	99.65 37

TranMVSNet+NR-MVSNet		99.17 35	99.07 47	99.46 48	99.37 119	98.87 53	98.39 106	99.42 95	99.42 30	99.36 65	99.06 116	98.38 44	99.95 13	98.34 81	99.90 57	99.57 70

FMVSNet1		99.17 35	99.17 39	99.17 80	99.55 72	98.24 92	99.20 35	99.44 88	99.21 46	99.43 54	99.55 41	97.82 78	99.86 77	98.42 78	99.89 63	99.41 142

FIs		99.14 37	99.09 45	99.29 68	99.70 40	98.28 90	99.13 46	99.52 63	99.48 25	99.24 89	99.41 61	96.79 146	99.82 126	98.69 65	99.88 64	99.76 19

V14		99.14 37	99.30 31	98.66 150	99.56 68	96.53 190	99.08 49	99.63 25	99.24 45	99.60 30	99.66 22	97.23 116	99.82 126	99.73 8	100.00 1	99.65 37

XXY-MVS		99.14 37	99.15 43	99.10 91	99.76 26	97.74 140	98.85 71	99.62 28	98.48 105	99.37 63	99.49 49	98.75 25	99.86 77	98.20 88	99.80 92	99.71 27

v11		99.12 40	99.31 28	98.53 175	99.59 55	96.11 209	99.08 49	99.65 20	99.15 55	99.60 30	99.69 17	97.26 112	99.83 114	99.81 3	100.00 1	99.66 33

v15		99.11 41	99.27 33	98.62 156	99.52 80	96.43 194	99.01 55	99.63 25	99.18 54	99.59 32	99.64 26	97.13 120	99.81 139	99.71 10	100.00 1	99.64 40

ACMH+	96.62 9	99.08 42	99.00 49	99.33 65	99.71 34	98.83 54	98.60 82	99.58 36	99.11 60	99.53 37	99.18 91	98.81 23	99.67 232	96.71 162	99.77 104	99.50 101

v17		99.07 43	99.22 36	98.61 159	99.50 85	96.42 195	99.01 55	99.60 32	99.15 55	99.48 45	99.61 30	97.05 124	99.81 139	99.64 12	99.98 19	99.61 49

v16		99.07 43	99.22 36	98.61 159	99.50 85	96.42 195	99.01 55	99.60 32	99.15 55	99.46 49	99.61 30	97.04 125	99.81 139	99.64 12	99.97 23	99.61 49

Gipuma		99.03 45	99.16 41	98.64 152	99.94 3	98.51 79	99.32 17	99.75 8	99.58 21	98.60 169	99.62 28	98.22 52	99.51 284	97.70 112	99.73 118	97.89 285
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
v18		99.02 46	99.17 39	98.57 166	99.45 105	96.31 201	98.94 63	99.58 36	99.06 69	99.43 54	99.58 38	96.91 134	99.80 151	99.60 14	99.97 23	99.59 58

v8		99.01 47	99.16 41	98.57 166	99.47 98	96.31 201	98.90 66	99.47 80	99.03 71	99.52 39	99.57 39	96.93 133	99.81 139	99.60 14	99.98 19	99.60 52

HPM-MVS_fast		99.01 47	98.82 55	99.57 16	99.71 34	99.35 9	99.00 59	99.50 65	97.33 179	98.94 130	98.86 158	98.75 25	99.82 126	97.53 119	99.71 127	99.56 75

APDe-MVS		98.99 49	98.79 58	99.60 12	99.21 147	99.15 33	98.87 68	99.48 74	97.57 156	99.35 67	99.24 82	97.83 75	99.89 56	97.88 102	99.70 130	99.75 21

abl_6		98.99 49	98.78 59	99.61 9	99.45 105	99.46 4	98.60 82	99.50 65	98.59 98	99.24 89	99.04 123	98.54 37	99.89 56	96.45 182	99.62 154	99.50 101

EG-PatchMatch MVS		98.99 49	99.01 48	98.94 116	99.50 85	97.47 153	98.04 131	99.59 34	98.15 121	99.40 59	99.36 67	98.58 33	99.76 187	98.78 59	99.68 141	99.59 58

COLMAP_ROB	96.50 10	98.99 49	98.85 53	99.41 51	99.58 56	99.10 42	98.74 74	99.56 49	99.09 67	99.33 71	99.19 89	98.40 43	99.72 215	95.98 202	99.76 113	99.42 140
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Baseline_NR-MVSNet		98.98 53	98.86 52	99.36 55	99.82 20	98.55 74	97.47 194	99.57 43	99.37 35	99.21 93	99.61 30	96.76 149	99.83 114	98.06 93	99.83 79	99.71 27

v10		98.97 54	99.11 44	98.55 171	99.44 108	96.21 207	98.90 66	99.55 54	98.73 92	99.48 45	99.60 34	96.63 155	99.83 114	99.70 11	99.99 11	99.61 49

DeepC-MVS	97.60 4	98.97 54	98.93 51	99.10 91	99.35 122	97.98 116	98.01 137	99.46 82	97.56 158	99.54 35	99.50 46	98.97 18	99.84 100	98.06 93	99.92 49	99.49 108
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
NR-MVSNet		98.95 56	98.82 55	99.36 55	99.16 158	98.72 63	99.22 34	99.20 161	99.10 64	99.72 13	98.76 174	96.38 170	99.86 77	98.00 98	99.82 82	99.50 101

testing_2		98.93 57	98.99 50	98.76 140	99.57 61	97.03 173	97.85 153	99.13 184	98.46 106	99.44 53	99.44 57	98.22 52	99.74 202	98.85 56	99.94 33	99.51 96

DP-MVS		98.93 57	98.81 57	99.28 69	99.21 147	98.45 83	98.46 101	99.33 125	99.63 12	99.48 45	99.15 101	97.23 116	99.75 193	97.17 133	99.66 150	99.63 44

ACMM	96.08 12	98.91 59	98.73 66	99.48 43	99.55 72	99.14 34	98.07 127	99.37 106	97.62 150	99.04 113	98.96 140	98.84 21	99.79 165	97.43 125	99.65 151	99.49 108
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MTAPA		98.88 60	98.64 83	99.61 9	99.67 44	99.36 7	98.43 103	99.20 161	98.83 86	98.89 135	98.90 149	96.98 131	99.92 34	97.16 134	99.70 130	99.56 75

VPNet		98.87 61	98.83 54	99.01 108	99.70 40	97.62 148	98.43 103	99.35 116	99.47 27	99.28 79	99.05 121	96.72 151	99.82 126	98.09 91	99.36 201	99.59 58

UniMVSNet (Re)		98.87 61	98.71 70	99.35 60	99.24 135	98.73 61	97.73 164	99.38 102	98.93 82	99.12 101	98.73 176	96.77 147	99.86 77	98.63 67	99.80 92	99.46 126

UniMVSNet_NR-MVSNet		98.86 63	98.68 78	99.40 53	99.17 156	98.74 58	97.68 168	99.40 97	99.14 58	99.06 107	98.59 200	96.71 152	99.93 26	98.57 70	99.77 104	99.53 91

APD-MVS_3200maxsize		98.84 64	98.61 88	99.53 32	99.19 151	99.27 16	98.49 95	99.33 125	98.64 94	99.03 115	98.98 135	97.89 73	99.85 85	96.54 176	99.42 196	99.46 126

PM-MVS		98.82 65	98.72 69	99.12 88	99.64 49	98.54 77	97.98 140	99.68 16	97.62 150	99.34 70	99.18 91	97.54 90	99.77 183	97.79 105	99.74 115	99.04 220

DU-MVS		98.82 65	98.63 84	99.39 54	99.16 158	98.74 58	97.54 188	99.25 149	98.84 85	99.06 107	98.76 174	96.76 149	99.93 26	98.57 70	99.77 104	99.50 101

3Dnovator	98.27 2	98.81 67	98.73 66	99.05 101	98.76 228	97.81 134	99.25 32	99.30 137	98.57 102	98.55 175	99.33 72	97.95 72	99.90 47	97.16 134	99.67 146	99.44 132

MPTG		98.79 68	98.52 95	99.61 9	99.67 44	99.36 7	97.33 199	99.20 161	98.83 86	98.89 135	98.90 149	96.98 131	99.92 34	97.16 134	99.70 130	99.56 75

HPM-MVS		98.79 68	98.53 94	99.59 15	99.65 46	99.29 13	99.16 42	99.43 92	96.74 210	98.61 167	98.38 220	98.62 30	99.87 72	96.47 180	99.67 146	99.59 58

SteuartSystems-ACMMP		98.79 68	98.54 93	99.54 25	99.73 28	99.16 28	98.23 112	99.31 130	97.92 126	98.90 133	98.90 149	98.00 66	99.88 63	96.15 196	99.72 123	99.58 65
Skip Steuart: Steuart Systems R&D Blog.
V42		98.78 71	98.78 59	98.76 140	99.44 108	97.04 172	98.27 110	99.19 167	97.87 138	99.25 88	99.16 97	96.84 141	99.78 174	99.21 38	99.84 73	99.46 126

test20.03		98.78 71	98.77 61	98.78 136	99.46 102	97.20 165	97.78 157	99.24 154	99.04 70	99.41 57	98.90 149	97.65 83	99.76 187	97.70 112	99.79 96	99.39 148

test_0402		98.76 73	98.71 70	98.93 117	99.56 68	98.14 100	98.45 102	99.34 120	99.28 43	98.95 126	98.91 146	98.34 46	99.79 165	95.63 218	99.91 54	98.86 241

ACMMP_Plus		98.75 74	98.48 102	99.57 16	99.58 56	99.29 13	97.82 156	99.25 149	96.94 202	98.78 150	99.12 105	98.02 64	99.84 100	97.13 138	99.67 146	99.59 58

SixPastTwentyTwo		98.75 74	98.62 85	99.16 83	99.83 19	97.96 119	99.28 29	98.20 270	99.37 35	99.70 15	99.65 25	92.65 260	99.93 26	99.04 48	99.84 73	99.60 52

ACMMP		98.75 74	98.50 98	99.52 37	99.56 68	99.16 28	98.87 68	99.37 106	97.16 196	98.82 147	99.01 129	97.71 81	99.87 72	96.29 188	99.69 137	99.54 86
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
Regformer-4		98.73 77	98.68 78	98.89 122	99.02 184	97.22 164	97.17 212	99.06 193	99.21 46	99.17 98	98.85 160	97.45 97	99.86 77	98.48 75	99.70 130	99.60 52

XVS		98.72 78	98.45 109	99.53 32	99.46 102	99.21 21	98.65 77	99.34 120	98.62 96	97.54 236	98.63 194	97.50 92	99.83 114	96.79 154	99.53 183	99.56 75

HFP-MVS		98.71 79	98.44 111	99.51 39	99.49 91	99.16 28	98.52 89	99.31 130	97.47 165	98.58 172	98.50 213	97.97 70	99.85 85	96.57 171	99.59 161	99.53 91

LPG-MVS_test		98.71 79	98.46 107	99.47 46	99.57 61	98.97 48	98.23 112	99.48 74	96.60 217	99.10 104	99.06 116	98.71 27	99.83 114	95.58 221	99.78 100	99.62 45

v1neww		98.70 81	98.76 62	98.52 176	99.47 98	96.30 203	98.03 132	99.18 171	97.92 126	99.26 86	99.08 110	96.91 134	99.78 174	99.19 40	99.82 82	99.47 122

v7new		98.70 81	98.76 62	98.52 176	99.47 98	96.30 203	98.03 132	99.18 171	97.92 126	99.26 86	99.08 110	96.91 134	99.78 174	99.19 40	99.82 82	99.47 122

v6		98.70 81	98.76 62	98.52 176	99.47 98	96.30 203	98.03 132	99.18 171	97.92 126	99.27 81	99.08 110	96.91 134	99.78 174	99.19 40	99.82 82	99.48 114

ACMMPR		98.70 81	98.42 114	99.54 25	99.52 80	99.14 34	98.52 89	99.31 130	97.47 165	98.56 174	98.54 208	97.75 80	99.88 63	96.57 171	99.59 161	99.58 65

CP-MVS		98.70 81	98.42 114	99.52 37	99.36 120	99.12 39	98.72 76	99.36 110	97.54 160	98.30 189	98.40 219	97.86 74	99.89 56	96.53 177	99.72 123	99.56 75

region2R		98.69 86	98.40 116	99.54 25	99.53 78	99.17 26	98.52 89	99.31 130	97.46 170	98.44 181	98.51 210	97.83 75	99.88 63	96.46 181	99.58 167	99.58 65

EI-MVSNet-UG-set		98.69 86	98.71 70	98.62 156	99.10 165	96.37 199	97.23 204	98.87 226	99.20 49	99.19 94	98.99 132	97.30 106	99.85 85	98.77 62	99.79 96	99.65 37

3Dnovator+	97.89 3	98.69 86	98.51 96	99.24 76	98.81 224	98.40 85	99.02 54	99.19 167	98.99 74	98.07 198	99.28 75	97.11 123	99.84 100	96.84 152	99.32 208	99.47 122

EI-MVSNet-Vis-set		98.68 89	98.70 73	98.63 154	99.09 168	96.40 197	97.23 204	98.86 230	99.20 49	99.18 97	98.97 137	97.29 108	99.85 85	98.72 64	99.78 100	99.64 40

CSCG		98.68 89	98.50 98	99.20 79	99.45 105	98.63 66	98.56 86	99.57 43	97.87 138	98.85 141	98.04 248	97.66 82	99.84 100	96.72 159	99.81 88	99.13 213

v7		98.67 91	98.73 66	98.50 181	99.43 112	96.21 207	98.00 138	99.31 130	97.58 154	99.17 98	99.18 91	96.63 155	99.80 151	99.42 27	99.88 64	99.48 114

PGM-MVS		98.66 92	98.37 121	99.55 20	99.53 78	99.18 25	98.23 112	99.49 71	97.01 200	98.69 157	98.88 155	98.00 66	99.89 56	95.87 207	99.59 161	99.58 65

GBi-Net		98.65 93	98.47 104	99.17 80	98.90 205	98.24 92	99.20 35	99.44 88	98.59 98	98.95 126	99.55 41	94.14 237	99.86 77	97.77 107	99.69 137	99.41 142

test1		98.65 93	98.47 104	99.17 80	98.90 205	98.24 92	99.20 35	99.44 88	98.59 98	98.95 126	99.55 41	94.14 237	99.86 77	97.77 107	99.69 137	99.41 142

LCM-MVSNet-Re		98.64 95	98.48 102	99.11 89	98.85 214	98.51 79	98.49 95	99.83 3	98.37 107	99.69 17	99.46 52	98.21 54	99.92 34	94.13 252	99.30 211	98.91 236

mPP-MVS		98.64 95	98.34 125	99.54 25	99.54 76	99.17 26	98.63 79	99.24 154	97.47 165	98.09 197	98.68 181	97.62 87	99.89 56	96.22 190	99.62 154	99.57 70

TSAR-MVS + MP.		98.63 97	98.49 101	99.06 100	99.64 49	97.90 125	98.51 93	98.94 214	96.96 201	99.24 89	98.89 154	97.83 75	99.81 139	96.88 149	99.49 192	99.48 114

v1141		98.63 97	98.70 73	98.41 190	99.39 116	95.96 216	97.64 173	99.21 157	97.92 126	99.35 67	99.08 110	96.61 158	99.78 174	99.25 34	99.90 57	99.50 101

divwei89l23v2f112		98.63 97	98.70 73	98.41 190	99.39 116	95.96 216	97.64 173	99.21 157	97.92 126	99.35 67	99.08 110	96.61 158	99.78 174	99.25 34	99.90 57	99.50 101

v1		98.63 97	98.70 73	98.41 190	99.39 116	95.96 216	97.64 173	99.20 161	97.92 126	99.36 65	99.07 115	96.63 155	99.78 174	99.25 34	99.90 57	99.50 101

LS3D		98.63 97	98.38 120	99.36 55	97.25 316	99.38 6	99.12 48	99.32 128	99.21 46	98.44 181	98.88 155	97.31 105	99.80 151	96.58 169	99.34 205	98.92 234

RPSCF		98.62 102	98.36 122	99.42 49	99.65 46	99.42 5	98.55 87	99.57 43	97.72 145	98.90 133	99.26 79	96.12 177	99.52 279	95.72 214	99.71 127	99.32 172

Regformer-3		98.61 103	98.61 88	98.63 154	99.02 184	96.53 190	97.17 212	98.84 232	99.13 59	99.10 104	98.85 160	97.24 114	99.79 165	98.41 79	99.70 130	99.57 70

v1192		98.60 104	98.66 81	98.41 190	99.27 131	95.88 220	97.52 189	99.36 110	97.41 173	99.33 71	99.20 88	96.37 171	99.82 126	99.57 18	99.92 49	99.55 83

v1144		98.60 104	98.66 81	98.41 190	99.36 120	95.90 219	97.58 183	99.34 120	97.51 161	99.27 81	99.15 101	96.34 172	99.80 151	99.47 24	99.93 39	99.51 96

Regformer-2		98.60 104	98.46 107	99.02 107	98.85 214	97.71 142	96.91 226	99.09 190	98.98 76	99.01 116	98.64 190	97.37 103	99.84 100	97.75 111	99.57 171	99.52 94

MP-MVS-pluss		98.57 107	98.23 133	99.60 12	99.69 42	99.35 9	97.16 214	99.38 102	94.87 257	98.97 123	98.99 132	98.01 65	99.88 63	97.29 130	99.70 130	99.58 65
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
OPM-MVS		98.56 108	98.32 129	99.25 75	99.41 114	98.73 61	97.13 216	99.18 171	97.10 199	98.75 154	98.92 145	98.18 55	99.65 245	96.68 164	99.56 176	99.37 155

VDD-MVS		98.56 108	98.39 118	99.07 95	99.13 163	98.07 107	98.59 84	97.01 295	99.59 19	99.11 102	99.27 77	94.82 220	99.79 165	98.34 81	99.63 153	99.34 167

v2v482		98.56 108	98.62 85	98.37 197	99.42 113	95.81 223	97.58 183	99.16 180	97.90 134	99.28 79	99.01 129	95.98 186	99.79 165	99.33 29	99.90 57	99.51 96

XVG-ACMP-BASELINE		98.56 108	98.34 125	99.22 78	99.54 76	98.59 71	97.71 165	99.46 82	97.25 187	98.98 121	98.99 132	97.54 90	99.84 100	95.88 204	99.74 115	99.23 193

Regformer-1		98.55 112	98.44 111	98.87 124	98.85 214	97.29 159	96.91 226	98.99 213	98.97 77	98.99 119	98.64 190	97.26 112	99.81 139	97.79 105	99.57 171	99.51 96

v1240		98.55 112	98.62 85	98.32 200	99.22 141	95.58 228	97.51 191	99.45 85	97.16 196	99.45 52	99.24 82	96.12 177	99.85 85	99.60 14	99.88 64	99.55 83

IterMVS-LS		98.55 112	98.70 73	98.09 214	99.48 96	94.73 246	97.22 207	99.39 99	98.97 77	99.38 61	99.31 74	96.00 182	99.93 26	98.58 68	99.97 23	99.60 52
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v144192		98.54 115	98.57 92	98.45 187	99.21 147	95.98 214	97.63 176	99.36 110	97.15 198	99.32 76	99.18 91	95.84 193	99.84 100	99.50 22	99.91 54	99.54 86

v1921920		98.54 115	98.60 90	98.38 196	99.20 150	95.76 224	97.56 185	99.36 110	97.23 192	99.38 61	99.17 96	96.02 180	99.84 100	99.57 18	99.90 57	99.54 86

XVG-OURS		98.53 117	98.34 125	99.11 89	99.50 85	98.82 56	95.97 271	99.50 65	97.30 183	99.05 112	98.98 135	99.35 7	99.32 308	95.72 214	99.68 141	99.18 205

UGNet		98.53 117	98.45 109	98.79 133	97.94 291	96.96 176	99.08 49	98.54 258	99.10 64	96.82 271	99.47 51	96.55 161	99.84 100	98.56 73	99.94 33	99.55 83
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
testmv		98.51 119	98.47 104	98.61 159	99.24 135	96.53 190	96.66 241	99.73 10	98.56 104	99.50 43	99.23 85	97.24 114	99.87 72	96.16 195	99.93 39	99.44 132

#test#		98.50 120	98.16 141	99.51 39	99.49 91	99.16 28	98.03 132	99.31 130	96.30 226	98.58 172	98.50 213	97.97 70	99.85 85	95.68 217	99.59 161	99.53 91

XVG-OURS-SEG-HR		98.49 121	98.28 131	99.14 86	99.49 91	98.83 54	96.54 247	99.48 74	97.32 181	99.11 102	98.61 198	99.33 8	99.30 311	96.23 189	98.38 280	99.28 183

FMVSNet2		98.49 121	98.40 116	98.75 142	98.90 205	97.14 171	98.61 81	99.13 184	98.59 98	99.19 94	99.28 75	94.14 237	99.82 126	97.97 99	99.80 92	99.29 182

pmmvs-eth3d		98.47 123	98.34 125	98.86 126	99.30 129	97.76 137	97.16 214	99.28 140	95.54 244	99.42 56	99.19 89	97.27 109	99.63 248	97.89 100	99.97 23	99.20 199

MP-MVS		98.46 124	98.09 149	99.54 25	99.57 61	99.22 20	98.50 94	99.19 167	97.61 152	97.58 232	98.66 185	97.40 101	99.88 63	94.72 235	99.60 160	99.54 86

v148		98.45 125	98.60 90	98.00 223	99.44 108	94.98 242	97.44 195	99.06 193	98.30 111	99.32 76	98.97 137	96.65 154	99.62 250	98.37 80	99.85 71	99.39 148

AllTest		98.44 126	98.20 135	99.16 83	99.50 85	98.55 74	98.25 111	99.58 36	96.80 208	98.88 138	99.06 116	97.65 83	99.57 266	94.45 241	99.61 158	99.37 155

VNet		98.42 127	98.30 130	98.79 133	98.79 227	97.29 159	98.23 112	98.66 253	99.31 40	98.85 141	98.80 168	94.80 223	99.78 174	98.13 90	99.13 238	99.31 176

ab-mvs		98.41 128	98.36 122	98.59 163	99.19 151	97.23 162	99.32 17	98.81 238	97.66 147	98.62 165	99.40 64	96.82 143	99.80 151	95.88 204	99.51 186	98.75 253

ACMP	95.32 15	98.41 128	98.09 149	99.36 55	99.51 83	98.79 57	97.68 168	99.38 102	95.76 241	98.81 149	98.82 166	98.36 45	99.82 126	94.75 232	99.77 104	99.48 114
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
SD-MVS		98.40 130	98.68 78	97.54 245	98.96 192	97.99 112	97.88 149	99.36 110	98.20 117	99.63 26	99.04 123	98.76 24	95.33 339	96.56 174	99.74 115	99.31 176

EI-MVSNet		98.40 130	98.51 96	98.04 221	99.10 165	94.73 246	97.20 208	98.87 226	98.97 77	99.06 107	99.02 127	96.00 182	99.80 151	98.58 68	99.82 82	99.60 52

WR-MVS		98.40 130	98.19 137	99.03 104	99.00 186	97.65 145	96.85 230	98.94 214	98.57 102	98.89 135	98.50 213	95.60 198	99.85 85	97.54 118	99.85 71	99.59 58

new-patchmatchnet		98.35 133	98.74 65	97.18 257	99.24 135	92.23 288	96.42 254	99.48 74	98.30 111	99.69 17	99.53 44	97.44 98	99.82 126	98.84 58	99.77 104	99.49 108

HSP-MVS		98.34 134	97.94 161	99.54 25	99.57 61	99.25 18	98.57 85	98.84 232	97.55 159	99.31 78	97.71 262	94.61 228	99.88 63	96.14 197	99.19 228	99.48 114

canonicalmvs		98.34 134	98.26 132	98.58 164	98.46 265	97.82 133	98.96 62	99.46 82	99.19 53	97.46 242	95.46 316	98.59 32	99.46 292	98.08 92	98.71 265	98.46 267

testgi		98.32 136	98.39 118	98.13 212	99.57 61	95.54 229	97.78 157	99.49 71	97.37 176	99.19 94	97.65 266	98.96 19	99.49 286	96.50 179	98.99 251	99.34 167

DeepPCF-MVS	96.93 5	98.32 136	98.01 156	99.23 77	98.39 270	98.97 48	95.03 307	99.18 171	96.88 205	99.33 71	98.78 170	98.16 56	99.28 314	96.74 158	99.62 154	99.44 132

MVS_111021_LR		98.30 138	98.12 146	98.83 129	99.16 158	98.03 110	96.09 268	99.30 137	97.58 154	98.10 196	98.24 232	98.25 48	99.34 305	96.69 163	99.65 151	99.12 214

EPP-MVSNet		98.30 138	98.04 155	99.07 95	99.56 68	97.83 130	99.29 25	98.07 274	99.03 71	98.59 170	99.13 104	92.16 264	99.90 47	96.87 150	99.68 141	99.49 108

DeepC-MVS_fast	96.85 6	98.30 138	98.15 143	98.75 142	98.61 252	97.23 162	97.76 161	99.09 190	97.31 182	98.75 154	98.66 185	97.56 89	99.64 247	96.10 198	99.55 178	99.39 148
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PHI-MVS		98.29 141	97.95 159	99.34 63	98.44 267	99.16 28	98.12 121	99.38 102	96.01 237	98.06 199	98.43 217	97.80 79	99.67 232	95.69 216	99.58 167	99.20 199

Fast-Effi-MVS+-dtu		98.27 142	98.09 149	98.81 131	98.43 268	98.11 101	97.61 179	99.50 65	98.64 94	97.39 246	97.52 273	98.12 59	99.95 13	96.90 148	98.71 265	98.38 273

DELS-MVS		98.27 142	98.20 135	98.48 183	98.86 212	96.70 187	95.60 293	99.20 161	97.73 144	98.45 180	98.71 178	97.50 92	99.82 126	98.21 87	99.59 161	98.93 233
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
Effi-MVS+-dtu		98.26 144	97.90 165	99.35 60	98.02 288	99.49 3	98.02 136	99.16 180	98.29 114	97.64 227	97.99 250	96.44 167	99.95 13	96.66 165	98.93 256	98.60 262

MVSFormer		98.26 144	98.43 113	97.77 230	98.88 210	93.89 268	99.39 13	99.56 49	99.11 60	98.16 192	98.13 237	93.81 244	99.97 3	99.26 32	99.57 171	99.43 137

MVS_111021_HR		98.25 146	98.08 152	98.75 142	99.09 168	97.46 154	95.97 271	99.27 143	97.60 153	97.99 203	98.25 231	98.15 58	99.38 302	96.87 150	99.57 171	99.42 140

TAMVS		98.24 147	98.05 154	98.80 132	99.07 172	97.18 167	97.88 149	98.81 238	96.66 216	99.17 98	99.21 86	94.81 222	99.77 183	96.96 145	99.88 64	99.44 132

Anonymous20231206		98.21 148	98.21 134	98.20 209	99.51 83	95.43 234	98.13 119	99.32 128	96.16 231	98.93 131	98.82 166	96.00 182	99.83 114	97.32 129	99.73 118	99.36 161

VDDNet		98.21 148	97.95 159	99.01 108	99.58 56	97.74 140	99.01 55	97.29 290	99.67 8	98.97 123	99.50 46	90.45 272	99.80 151	97.88 102	99.20 224	99.48 114

IS-MVSNet		98.19 150	97.90 165	99.08 94	99.57 61	97.97 117	99.31 20	98.32 266	99.01 73	98.98 121	99.03 126	91.59 267	99.79 165	95.49 223	99.80 92	99.48 114

MVS_Test		98.18 151	98.36 122	97.67 235	98.48 263	94.73 246	98.18 116	99.02 205	97.69 146	98.04 201	99.11 106	97.22 118	99.56 269	98.57 70	98.90 257	98.71 255

TSAR-MVS + GP.		98.18 151	97.98 157	98.77 138	98.71 234	97.88 126	96.32 258	98.66 253	96.33 223	99.23 92	98.51 210	97.48 96	99.40 298	97.16 134	99.46 193	99.02 222

CNVR-MVS		98.17 153	97.87 168	99.07 95	98.67 244	98.24 92	97.01 219	98.93 217	97.25 187	97.62 228	98.34 224	97.27 109	99.57 266	96.42 184	99.33 206	99.39 148

PVSNet_Blended_VisFu		98.17 153	98.15 143	98.22 208	99.73 28	95.15 239	97.36 198	99.68 16	94.45 265	98.99 119	99.27 77	96.87 140	99.94 20	97.13 138	99.91 54	99.57 70

HPM-MVS++		98.10 155	97.64 178	99.48 43	99.09 168	99.13 37	97.52 189	98.75 246	97.46 170	96.90 266	97.83 257	96.01 181	99.84 100	95.82 211	99.35 203	99.46 126

APD-MVS		98.10 155	97.67 173	99.42 49	99.11 164	98.93 52	97.76 161	99.28 140	94.97 254	98.72 156	98.77 172	97.04 125	99.85 85	93.79 262	99.54 179	99.49 108
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVP-Stereo		98.08 157	97.92 163	98.57 166	98.96 192	96.79 181	97.90 148	99.18 171	96.41 222	98.46 179	98.95 141	95.93 188	99.60 255	96.51 178	98.98 253	99.31 176
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PMMVS2		98.07 158	98.08 152	98.04 221	99.41 114	94.59 252	94.59 315	99.40 97	97.50 162	98.82 147	98.83 163	96.83 142	99.84 100	97.50 121	99.81 88	99.71 27

MVS_0304		98.02 159	97.88 167	98.46 185	98.22 281	96.39 198	96.50 248	99.49 71	98.03 122	97.24 252	98.33 226	94.80 223	99.90 47	98.31 84	99.95 30	99.08 215

Effi-MVS+		98.02 159	97.82 169	98.62 156	98.53 262	97.19 166	97.33 199	99.68 16	97.30 183	96.68 274	97.46 278	98.56 36	99.80 151	96.63 167	98.20 284	98.86 241

MSLP-MVS++		98.02 159	98.14 145	97.64 239	98.58 255	95.19 238	97.48 192	99.23 156	97.47 165	97.90 207	98.62 196	97.04 125	98.81 331	97.55 117	99.41 197	98.94 232

MCST-MVS		98.00 162	97.63 179	99.10 91	99.24 135	98.17 97	96.89 228	98.73 249	95.66 242	97.92 204	97.70 263	97.17 119	99.66 240	96.18 194	99.23 220	99.47 122

K. test v3		98.00 162	97.66 176	99.03 104	99.79 24	97.56 149	99.19 39	92.47 333	99.62 16	99.52 39	99.66 22	89.61 275	99.96 8	99.25 34	99.81 88	99.56 75

HQP_MVS		97.99 164	97.67 173	98.93 117	99.19 151	97.65 145	97.77 159	99.27 143	98.20 117	97.79 219	97.98 251	94.90 215	99.70 218	94.42 243	99.51 186	99.45 130

no-one		97.98 165	98.10 148	97.61 240	99.55 72	93.82 270	96.70 238	98.94 214	96.18 228	99.52 39	99.41 61	95.90 191	99.81 139	96.72 159	99.99 11	99.20 199

MDA-MVSNet-bldmvs		97.94 166	97.91 164	98.06 219	99.44 108	94.96 243	96.63 243	99.15 183	98.35 108	98.83 144	99.11 106	94.31 234	99.85 85	96.60 168	98.72 262	99.37 155

LF4IMVS		97.90 167	97.69 172	98.52 176	99.17 156	97.66 144	97.19 211	99.47 80	96.31 225	97.85 211	98.20 236	96.71 152	99.52 279	94.62 236	99.72 123	98.38 273

UnsupCasMVSNet_eth		97.89 168	97.60 181	98.75 142	99.31 127	97.17 168	97.62 177	99.35 116	98.72 93	98.76 153	98.68 181	92.57 261	99.74 202	97.76 110	95.60 323	99.34 167

TinyColmap		97.89 168	97.98 157	97.60 241	98.86 212	94.35 254	96.21 263	99.44 88	97.45 172	99.06 107	98.88 155	97.99 68	99.28 314	94.38 247	99.58 167	99.18 205

OMC-MVS		97.88 170	97.49 185	99.04 103	98.89 209	98.63 66	96.94 222	99.25 149	95.02 252	98.53 177	98.51 210	97.27 109	99.47 290	93.50 271	99.51 186	99.01 223

CANet		97.87 171	97.76 170	98.19 210	97.75 296	95.51 231	96.76 234	99.05 197	97.74 143	96.93 261	98.21 235	95.59 199	99.89 56	97.86 104	99.93 39	99.19 204

xiu_mvs_v1_base_debu		97.86 172	98.17 138	96.92 264	98.98 189	93.91 265	96.45 251	99.17 177	97.85 140	98.41 184	97.14 291	98.47 39	99.92 34	98.02 95	99.05 243	96.92 315

xiu_mvs_v1_base		97.86 172	98.17 138	96.92 264	98.98 189	93.91 265	96.45 251	99.17 177	97.85 140	98.41 184	97.14 291	98.47 39	99.92 34	98.02 95	99.05 243	96.92 315

xiu_mvs_v1_base_debi		97.86 172	98.17 138	96.92 264	98.98 189	93.91 265	96.45 251	99.17 177	97.85 140	98.41 184	97.14 291	98.47 39	99.92 34	98.02 95	99.05 243	96.92 315

NCCC		97.86 172	97.47 189	99.05 101	98.61 252	98.07 107	96.98 220	98.90 223	97.63 149	97.04 258	97.93 254	95.99 185	99.66 240	95.31 224	98.82 259	99.43 137

PMVS	91.26 20	97.86 172	97.94 161	97.65 237	99.71 34	97.94 122	98.52 89	98.68 252	98.99 74	97.52 238	99.35 68	97.41 100	98.18 334	91.59 298	99.67 146	96.82 318
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
CPTT-MVS		97.84 177	97.36 195	99.27 72	99.31 127	98.46 82	98.29 108	99.27 143	94.90 256	97.83 216	98.37 221	94.90 215	99.84 100	93.85 261	99.54 179	99.51 96

mvs-test1		97.83 178	97.48 188	98.89 122	98.02 288	99.20 23	97.20 208	99.16 180	98.29 114	96.46 285	97.17 288	96.44 167	99.92 34	96.66 165	97.90 296	97.54 308

mvs_anonymous		97.83 178	98.16 141	96.87 267	98.18 283	91.89 290	97.31 201	98.90 223	97.37 176	98.83 144	99.46 52	96.28 173	99.79 165	98.90 53	98.16 287	98.95 230

IterMVS		97.73 180	98.11 147	96.57 273	99.24 135	90.28 306	95.52 296	99.21 157	98.86 84	99.33 71	99.33 72	93.11 252	99.94 20	98.49 74	99.94 33	99.48 114
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MSDG		97.71 181	97.52 184	98.28 205	98.91 204	96.82 180	94.42 316	99.37 106	97.65 148	98.37 188	98.29 229	97.40 101	99.33 307	94.09 253	99.22 221	98.68 261

CDS-MVSNet		97.69 182	97.35 197	98.69 148	98.73 231	97.02 175	96.92 225	98.75 246	95.89 239	98.59 170	98.67 183	92.08 266	99.74 202	96.72 159	99.81 88	99.32 172
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MS-PatchMatch		97.68 183	97.75 171	97.45 249	98.23 280	93.78 271	97.29 202	98.84 232	96.10 233	98.64 161	98.65 187	96.04 179	99.36 303	96.84 152	99.14 235	99.20 199

Fast-Effi-MVS+		97.67 184	97.38 194	98.57 166	98.71 234	97.43 156	97.23 204	99.45 85	94.82 259	96.13 289	96.51 299	98.52 38	99.91 43	96.19 192	98.83 258	98.37 275

EU-MVSNet		97.66 185	98.50 98	95.13 300	99.63 51	85.84 321	98.35 107	98.21 269	98.23 116	99.54 35	99.46 52	95.02 213	99.68 227	98.24 85	99.87 68	99.87 6

pmmvs5		97.64 186	97.49 185	98.08 217	99.14 162	95.12 241	96.70 238	99.05 197	93.77 275	98.62 165	98.83 163	93.23 249	99.75 193	98.33 83	99.76 113	99.36 161

N_pmnet		97.63 187	97.17 203	98.99 111	99.27 131	97.86 128	95.98 270	93.41 331	95.25 249	99.47 48	98.90 149	95.63 197	99.85 85	96.91 146	99.73 118	99.27 184

YYNet1		97.60 188	97.67 173	97.39 253	99.04 179	93.04 280	95.27 301	98.38 265	97.25 187	98.92 132	98.95 141	95.48 204	99.73 207	96.99 143	98.74 261	99.41 142

MDA-MVSNet_test_wron		97.60 188	97.66 176	97.41 252	99.04 179	93.09 277	95.27 301	98.42 263	97.26 186	98.88 138	98.95 141	95.43 205	99.73 207	97.02 142	98.72 262	99.41 142

test_normal		97.58 190	97.41 190	98.10 213	99.03 182	95.72 225	96.21 263	97.05 294	96.71 213	98.65 159	98.12 241	93.87 241	99.69 222	97.68 116	99.35 203	98.88 239

pmmvs4		97.58 190	97.28 199	98.51 180	98.84 217	96.93 178	95.40 300	98.52 259	93.60 277	98.61 167	98.65 187	95.10 212	99.60 255	96.97 144	99.79 96	98.99 225

DI_MVS_plusplus_test		97.57 192	97.40 191	98.07 218	99.06 175	95.71 226	96.58 246	96.96 296	96.71 213	98.69 157	98.13 237	93.81 244	99.68 227	97.45 123	99.19 228	98.80 247

PVSNet_BlendedMVS		97.55 193	97.53 183	97.60 241	98.92 201	93.77 272	96.64 242	99.43 92	94.49 261	97.62 228	99.18 91	96.82 143	99.67 232	94.73 233	99.93 39	99.36 161

FMVSNet3		97.50 194	97.24 200	98.29 204	98.08 286	95.83 222	97.86 152	98.91 222	97.89 135	98.95 126	98.95 141	87.06 284	99.81 139	97.77 107	99.69 137	99.23 193

diffmvs		97.49 195	97.36 195	97.91 225	98.38 271	95.70 227	97.95 143	99.31 130	94.87 257	96.14 288	98.78 170	94.84 219	99.43 296	97.69 114	98.26 281	98.59 263

CHOSEN 1792x2688		97.49 195	97.14 206	98.54 174	99.68 43	96.09 212	96.50 248	99.62 28	91.58 301	98.84 143	98.97 137	92.36 262	99.88 63	96.76 157	99.95 30	99.67 31

CLD-MVS		97.49 195	97.16 204	98.48 183	99.07 172	97.03 173	94.71 313	99.21 157	94.46 263	98.06 199	97.16 289	97.57 88	99.48 289	94.46 240	99.78 100	98.95 230
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_prior3		97.48 198	97.00 209	98.95 114	98.69 239	97.95 120	95.74 288	99.03 201	96.48 219	96.11 290	97.63 267	95.92 189	99.59 259	94.16 248	99.20 224	99.30 179

Vis-MVSNet (Re-imp)		97.46 199	97.16 204	98.34 199	99.55 72	96.10 210	98.94 63	98.44 262	98.32 110	98.16 192	98.62 196	88.76 280	99.73 207	93.88 259	99.79 96	99.18 205

jason		97.45 200	97.35 197	97.76 231	99.24 135	93.93 264	95.86 282	98.42 263	94.24 270	98.50 178	98.13 237	94.82 220	99.91 43	97.22 132	99.73 118	99.43 137
jason: jason.
Test4		97.43 201	97.18 202	98.18 211	99.05 177	96.02 213	96.62 244	99.09 190	96.25 227	98.63 164	97.70 263	90.49 271	99.68 227	97.50 121	99.30 211	98.83 243

DSMNet-mixed		97.42 202	97.60 181	96.87 267	99.15 161	91.46 295	98.54 88	99.12 186	92.87 285	97.58 232	99.63 27	96.21 174	99.90 47	95.74 213	99.54 179	99.27 184

USDC		97.41 203	97.40 191	97.44 250	98.94 195	93.67 274	95.17 304	99.53 59	94.03 273	98.97 123	99.10 108	95.29 207	99.34 305	95.84 210	99.73 118	99.30 179

alignmvs		97.35 204	96.88 215	98.78 136	98.54 260	98.09 102	97.71 165	97.69 284	99.20 49	97.59 231	95.90 312	88.12 283	99.55 272	98.18 89	98.96 254	98.70 257

Patchmtry		97.35 204	96.97 210	98.50 181	97.31 315	96.47 193	98.18 116	98.92 220	98.95 81	98.78 150	99.37 65	85.44 297	99.85 85	95.96 203	99.83 79	99.17 209

DP-MVS Recon		97.33 206	96.92 212	98.57 166	99.09 168	97.99 112	96.79 231	99.35 116	93.18 281	97.71 223	98.07 247	95.00 214	99.31 309	93.97 255	99.13 238	98.42 271

QAPM		97.31 207	96.81 219	98.82 130	98.80 226	97.49 152	99.06 53	99.19 167	90.22 313	97.69 225	99.16 97	96.91 134	99.90 47	90.89 305	99.41 197	99.07 217

UnsupCasMVSNet_bld		97.30 208	96.92 212	98.45 187	99.28 130	96.78 185	96.20 265	99.27 143	95.42 247	98.28 190	98.30 228	93.16 251	99.71 216	94.99 228	97.37 303	98.87 240

F-COLMAP		97.30 208	96.68 227	99.14 86	99.19 151	98.39 86	97.27 203	99.30 137	92.93 283	96.62 276	98.00 249	95.73 195	99.68 227	92.62 285	98.46 279	99.35 166

1112_ss		97.29 210	96.86 216	98.58 164	99.34 124	96.32 200	96.75 235	99.58 36	93.14 282	96.89 267	97.48 276	92.11 265	99.86 77	96.91 146	99.54 179	99.57 70

CANet_DTU		97.26 211	97.06 207	97.84 227	97.57 303	94.65 250	96.19 266	98.79 241	97.23 192	95.14 313	98.24 232	93.22 250	99.84 100	97.34 128	99.84 73	99.04 220

Patchmatch-RL test		97.26 211	97.02 208	97.99 224	99.52 80	95.53 230	96.13 267	99.71 12	97.47 165	99.27 81	99.16 97	84.30 305	99.62 250	97.89 100	99.77 104	98.81 246

CDPH-MVS		97.26 211	96.66 230	99.07 95	99.00 186	98.15 98	96.03 269	99.01 208	91.21 307	97.79 219	97.85 256	96.89 139	99.69 222	92.75 283	99.38 200	99.39 148

PatchMatch-RL		97.24 214	96.78 220	98.61 159	99.03 182	97.83 130	96.36 256	99.06 193	93.49 280	97.36 249	97.78 259	95.75 194	99.49 286	93.44 272	98.77 260	98.52 265

sss		97.21 215	96.93 211	98.06 219	98.83 219	95.22 237	96.75 235	98.48 261	94.49 261	97.27 251	97.90 255	92.77 258	99.80 151	96.57 171	99.32 208	99.16 212

LFMVS		97.20 216	96.72 223	98.64 152	98.72 232	96.95 177	98.93 65	94.14 329	99.74 5	98.78 150	99.01 129	84.45 302	99.73 207	97.44 124	99.27 216	99.25 189

HyFIR lowres test		97.19 217	96.60 233	98.96 113	99.62 53	97.28 161	95.17 304	99.50 65	94.21 271	99.01 116	98.32 227	86.61 286	99.99 2	97.10 141	99.84 73	99.60 52

CNLPA		97.17 218	96.71 225	98.55 171	98.56 257	98.05 109	96.33 257	98.93 217	96.91 204	97.06 257	97.39 282	94.38 233	99.45 294	91.66 294	99.18 230	98.14 279

xiu_mvs_v2_base		97.16 219	97.49 185	96.17 284	98.54 260	92.46 284	95.45 298	98.84 232	97.25 187	97.48 241	96.49 300	98.31 47	99.90 47	96.34 187	98.68 267	96.15 325

AdaColmap		97.14 220	96.71 225	98.46 185	98.34 273	97.80 135	96.95 221	98.93 217	95.58 243	96.92 262	97.66 265	95.87 192	99.53 275	90.97 302	99.14 235	98.04 282

train_agg		97.10 221	96.45 239	99.07 95	98.71 234	98.08 105	95.96 275	99.03 201	91.64 298	95.85 296	97.53 271	96.47 165	99.76 187	93.67 264	99.16 231	99.36 161

OpenMVS	96.65 7	97.09 222	96.68 227	98.32 200	98.32 274	97.16 169	98.86 70	99.37 106	89.48 317	96.29 287	99.15 101	96.56 160	99.90 47	92.90 277	99.20 224	97.89 285

PS-MVSNAJ		97.08 223	97.39 193	96.16 286	98.56 257	92.46 284	95.24 303	98.85 231	97.25 187	97.49 240	95.99 307	98.07 60	99.90 47	96.37 185	98.67 268	96.12 326

agg_prior1		97.06 224	96.40 240	99.03 104	98.68 241	97.99 112	95.76 286	99.01 208	91.73 297	95.59 300	97.50 274	96.49 164	99.77 183	93.71 263	99.14 235	99.34 167

test1235678		97.06 224	96.84 218	97.73 233	98.55 259	94.46 253	94.80 311	99.36 110	96.85 207	98.83 144	98.26 230	92.72 259	99.82 126	92.49 288	99.70 130	98.91 236

lupinMVS		97.06 224	96.86 216	97.65 237	98.88 210	93.89 268	95.48 297	97.97 276	93.53 278	98.16 192	97.58 269	93.81 244	99.91 43	96.77 156	99.57 171	99.17 209

API-MVS		97.04 227	96.91 214	97.42 251	97.88 295	98.23 96	98.18 116	98.50 260	97.57 156	97.39 246	96.75 296	96.77 147	99.15 320	90.16 309	99.02 247	94.88 331

HQP-MVS		97.00 228	96.49 238	98.55 171	98.67 244	96.79 181	96.29 259	99.04 199	96.05 234	95.55 304	96.84 294	93.84 242	99.54 273	92.82 280	99.26 218	99.32 172

new_pmnet		96.99 229	96.76 221	97.67 235	98.72 232	94.89 244	95.95 278	98.20 270	92.62 288	98.55 175	98.54 208	94.88 218	99.52 279	93.96 256	99.44 195	98.59 263

Test_1112_low_res		96.99 229	96.55 236	98.31 202	99.35 122	95.47 233	95.84 285	99.53 59	91.51 303	96.80 272	98.48 216	91.36 268	99.83 114	96.58 169	99.53 183	99.62 45

agg_prior3		96.95 231	96.27 244	99.00 110	98.68 241	97.91 123	95.96 275	99.01 208	90.74 310	95.60 299	97.45 279	96.14 175	99.74 202	93.67 264	99.16 231	99.36 161

PVSNet_Blended		96.88 232	96.68 227	97.47 248	98.92 201	93.77 272	94.71 313	99.43 92	90.98 308	97.62 228	97.36 285	96.82 143	99.67 232	94.73 233	99.56 176	98.98 226

MVSTER		96.86 233	96.55 236	97.79 229	97.91 293	94.21 257	97.56 185	98.87 226	97.49 164	99.06 107	99.05 121	80.72 317	99.80 151	98.44 76	99.82 82	99.37 155

BH-untuned		96.83 234	96.75 222	97.08 259	98.74 230	93.33 276	96.71 237	98.26 268	96.72 211	98.44 181	97.37 284	95.20 209	99.47 290	91.89 292	97.43 302	98.44 269

BH-RMVSNet		96.83 234	96.58 234	97.58 243	98.47 264	94.05 260	96.67 240	97.36 288	96.70 215	97.87 208	97.98 251	95.14 211	99.44 295	90.47 308	98.58 273	99.25 189

RPMNet		96.82 236	96.66 230	97.28 254	97.71 298	94.22 255	98.11 122	96.90 301	99.37 35	96.91 264	99.34 70	86.72 285	99.81 139	97.53 119	97.36 305	97.81 291

PAPM_NR		96.82 236	96.32 243	98.30 203	99.07 172	96.69 188	97.48 192	98.76 243	95.81 240	96.61 277	96.47 302	94.12 240	99.17 318	90.82 307	97.78 297	99.06 218

MG-MVS		96.77 238	96.61 232	97.26 256	98.31 275	93.06 278	95.93 279	98.12 273	96.45 221	97.92 204	98.73 176	93.77 247	99.39 300	91.19 301	99.04 246	99.33 171

1121		96.73 239	96.00 247	98.91 120	98.95 194	97.76 137	98.07 127	98.73 249	87.65 324	96.54 278	98.13 237	94.52 230	99.73 207	92.38 289	99.02 247	99.24 192

WTY-MVS		96.67 240	96.27 244	97.87 226	98.81 224	94.61 251	96.77 233	97.92 278	94.94 255	97.12 253	97.74 261	91.11 269	99.82 126	93.89 258	98.15 288	99.18 205

PatchT		96.65 241	96.35 241	97.54 245	97.40 312	95.32 236	97.98 140	96.64 307	99.33 39	96.89 267	99.42 59	84.32 304	99.81 139	97.69 114	97.49 300	97.48 309

TAPA-MVS	96.21 11	96.63 242	95.95 249	98.65 151	98.93 197	98.09 102	96.93 223	99.28 140	83.58 332	98.13 195	97.78 259	96.13 176	99.40 298	93.52 269	99.29 214	98.45 268
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MIMVSNet		96.62 243	96.25 246	97.71 234	99.04 179	94.66 249	99.16 42	96.92 300	97.23 192	97.87 208	99.10 108	86.11 290	99.65 245	91.65 295	99.21 223	98.82 245

LP		96.60 244	96.57 235	96.68 272	97.64 302	91.70 292	98.11 122	97.74 281	97.29 185	97.91 206	99.24 82	88.35 281	99.85 85	97.11 140	95.76 322	98.49 266

Patchmatch-test		96.55 245	96.34 242	97.17 258	98.35 272	93.06 278	98.40 105	97.79 279	97.33 179	98.41 184	98.67 183	83.68 309	99.69 222	95.16 225	99.31 210	98.77 250

PMMVS		96.51 246	95.98 248	98.09 214	97.53 306	95.84 221	94.92 309	98.84 232	91.58 301	96.05 294	95.58 314	95.68 196	99.66 240	95.59 220	98.09 291	98.76 252

PLC	94.65 16	96.51 246	95.73 252	98.85 127	98.75 229	97.91 123	96.42 254	99.06 193	90.94 309	95.59 300	97.38 283	94.41 232	99.59 259	90.93 303	98.04 294	99.05 219
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
114514_t		96.50 248	95.77 251	98.69 148	99.48 96	97.43 156	97.84 154	99.55 54	81.42 334	96.51 281	98.58 201	95.53 200	99.67 232	93.41 273	99.58 167	98.98 226

MAR-MVS		96.47 249	95.70 253	98.79 133	97.92 292	99.12 39	98.28 109	98.60 257	92.16 295	95.54 307	96.17 305	94.77 226	99.52 279	89.62 311	98.23 282	97.72 297
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
Patchmatch-test1		96.44 250	96.72 223	95.60 295	98.24 278	88.35 312	95.85 284	96.88 302	96.11 232	97.67 226	98.57 202	93.10 253	99.69 222	94.79 231	99.22 221	98.77 250

CMPMVS	75.91 23	96.29 251	95.44 260	98.84 128	96.25 331	98.69 64	97.02 218	99.12 186	88.90 320	97.83 216	98.86 158	89.51 276	98.90 328	91.92 291	99.51 186	98.92 234
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
CR-MVSNet		96.28 252	95.95 249	97.28 254	97.71 298	94.22 255	98.11 122	98.92 220	92.31 292	96.91 264	99.37 65	85.44 297	99.81 139	97.39 127	97.36 305	97.81 291

CVMVSNet		96.25 253	97.21 201	93.38 320	99.10 165	80.56 339	97.20 208	98.19 272	96.94 202	99.00 118	99.02 127	89.50 277	99.80 151	96.36 186	99.59 161	99.78 15

EPNet		96.14 254	95.44 260	98.25 206	90.76 341	95.50 232	97.92 145	94.65 319	98.97 77	92.98 328	98.85 160	89.12 279	99.87 72	95.99 201	99.68 141	99.39 148
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
wuyk23d		96.06 255	97.62 180	91.38 323	98.65 250	98.57 73	98.85 71	96.95 298	96.86 206	99.90 5	99.16 97	99.18 12	98.40 333	89.23 312	99.77 104	77.18 336

FMVSNet5		96.01 256	95.20 267	98.41 190	97.53 306	96.10 210	98.74 74	99.50 65	97.22 195	98.03 202	99.04 123	69.80 337	99.88 63	97.27 131	99.71 127	99.25 189

HY-MVS	95.94 13	95.90 257	95.35 262	97.55 244	97.95 290	94.79 245	98.81 73	96.94 299	92.28 293	95.17 312	98.57 202	89.90 274	99.75 193	91.20 300	97.33 307	98.10 280

GA-MVS		95.86 258	95.32 263	97.49 247	98.60 254	94.15 259	93.83 323	97.93 277	95.49 245	96.68 274	97.42 281	83.21 310	99.30 311	96.22 190	98.55 274	99.01 223

OpenMVS_ROB	95.38 14	95.84 259	95.18 268	97.81 228	98.41 269	97.15 170	97.37 197	98.62 256	83.86 331	98.65 159	98.37 221	94.29 235	99.68 227	88.41 314	98.62 271	96.60 321

1314		95.74 260	95.60 257	96.17 284	97.53 306	92.75 281	98.07 127	98.31 267	91.22 306	94.25 320	96.68 297	95.53 200	99.03 322	91.64 296	97.18 308	96.74 319

PVSNet	93.40 17	95.67 261	95.70 253	95.57 296	98.83 219	88.57 310	92.50 329	97.72 282	92.69 287	96.49 284	96.44 303	93.72 248	99.43 296	93.61 266	99.28 215	98.71 255

PatchmatchNet		95.58 262	95.67 255	95.30 299	97.34 314	87.32 316	97.65 172	96.65 306	95.30 248	97.07 256	98.69 179	84.77 299	99.75 193	94.97 229	98.64 269	98.83 243
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
TR-MVS		95.55 263	95.12 269	96.86 270	97.54 305	93.94 263	96.49 250	96.53 309	94.36 268	97.03 259	96.61 298	94.26 236	99.16 319	86.91 319	96.31 318	97.47 310

testus		95.52 264	95.32 263	96.13 288	97.91 293	89.49 309	93.62 324	99.61 30	92.41 290	97.38 248	95.42 318	94.72 227	99.63 248	88.06 316	98.72 262	99.26 187

JIA-IIPM		95.52 264	95.03 271	97.00 261	96.85 323	94.03 261	96.93 223	95.82 314	99.20 49	94.63 317	99.71 14	83.09 311	99.60 255	94.42 243	94.64 327	97.36 311

CHOSEN 280x420		95.51 266	95.47 258	95.65 294	98.25 276	88.27 313	93.25 326	98.88 225	93.53 278	94.65 316	97.15 290	86.17 288	99.93 26	97.41 126	99.93 39	98.73 254

ADS-MVSNet2		95.43 267	94.98 272	96.76 271	98.14 284	91.74 291	97.92 145	97.76 280	90.23 311	96.51 281	98.91 146	85.61 294	99.85 85	92.88 278	96.90 311	98.69 258

PAPR		95.29 268	94.47 276	97.75 232	97.50 310	95.14 240	94.89 310	98.71 251	91.39 305	95.35 311	95.48 315	94.57 229	99.14 321	84.95 326	97.37 303	98.97 229

ADS-MVSNet		95.24 269	94.93 273	96.18 283	98.14 284	90.10 307	97.92 145	97.32 289	90.23 311	96.51 281	98.91 146	85.61 294	99.74 202	92.88 278	96.90 311	98.69 258

BH-w/o		95.13 270	94.89 274	95.86 290	98.20 282	91.31 302	95.65 291	97.37 287	93.64 276	96.52 280	95.70 313	93.04 254	99.02 323	88.10 315	95.82 321	97.24 313

tpmrst		95.07 271	95.46 259	93.91 314	97.11 318	84.36 331	97.62 177	96.96 296	94.98 253	96.35 286	98.80 168	85.46 296	99.59 259	95.60 219	96.23 319	97.79 294

pmmvs3		95.03 272	94.40 281	96.93 263	97.70 300	92.53 283	95.08 306	97.71 283	88.57 321	97.71 223	98.08 246	79.39 327	99.82 126	96.19 192	99.11 241	98.43 270

tpmvs		95.02 273	95.25 265	94.33 308	96.39 330	85.87 320	98.08 125	96.83 303	95.46 246	95.51 308	98.69 179	85.91 291	99.53 275	94.16 248	96.23 319	97.58 306

EPNet_dtu		94.93 274	94.78 275	95.38 298	93.58 340	87.68 315	96.78 232	95.69 316	97.35 178	89.14 336	98.09 245	88.15 282	99.49 286	94.95 230	99.30 211	98.98 226
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
view600		94.87 275	94.41 277	96.26 278	99.22 141	91.37 298	98.49 95	94.45 321	98.75 88	97.85 211	95.98 308	80.38 319	99.75 193	86.06 322	98.49 275	97.66 298

view800		94.87 275	94.41 277	96.26 278	99.22 141	91.37 298	98.49 95	94.45 321	98.75 88	97.85 211	95.98 308	80.38 319	99.75 193	86.06 322	98.49 275	97.66 298

conf0.05thres1000		94.87 275	94.41 277	96.26 278	99.22 141	91.37 298	98.49 95	94.45 321	98.75 88	97.85 211	95.98 308	80.38 319	99.75 193	86.06 322	98.49 275	97.66 298

tfpn		94.87 275	94.41 277	96.26 278	99.22 141	91.37 298	98.49 95	94.45 321	98.75 88	97.85 211	95.98 308	80.38 319	99.75 193	86.06 322	98.49 275	97.66 298

test12356		94.85 279	95.12 269	94.03 313	98.25 276	83.12 334	93.85 322	99.33 125	94.17 272	97.28 250	97.20 286	85.83 292	99.75 193	90.85 306	99.33 206	99.22 197

cascas		94.79 280	94.33 284	96.15 287	96.02 334	92.36 287	92.34 331	99.26 148	85.34 330	95.08 314	94.96 323	92.96 255	98.53 332	94.41 246	98.59 272	97.56 307

tpm		94.67 281	94.34 283	95.66 293	97.68 301	88.42 311	97.88 149	94.90 318	94.46 263	96.03 295	98.56 205	78.66 328	99.79 165	95.88 204	95.01 326	98.78 249

test0.0.03 1		94.51 282	93.69 291	96.99 262	96.05 332	93.61 275	94.97 308	93.49 330	96.17 229	97.57 234	94.88 324	82.30 314	99.01 325	93.60 267	94.17 332	98.37 275

thres600view7		94.45 283	93.83 288	96.29 276	99.06 175	91.53 294	97.99 139	94.24 328	98.34 109	97.44 244	95.01 321	79.84 324	99.67 232	84.33 328	98.23 282	97.66 298

PCF-MVS	92.86 18	94.36 284	93.00 298	98.42 189	98.70 238	97.56 149	93.16 327	99.11 188	79.59 335	97.55 235	97.43 280	92.19 263	99.73 207	79.85 335	99.45 194	97.97 284
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
X-MVStestdata		94.32 285	92.59 299	99.53 32	99.46 102	99.21 21	98.65 77	99.34 120	98.62 96	97.54 236	45.85 338	97.50 92	99.83 114	96.79 154	99.53 183	99.56 75

MVS-HIRNet		94.32 285	95.62 256	90.42 324	98.46 265	75.36 340	96.29 259	89.13 339	95.25 249	95.38 310	99.75 7	92.88 257	99.19 317	94.07 254	99.39 199	96.72 320

E-PMN		94.17 287	94.37 282	93.58 317	96.86 322	85.71 323	90.11 334	97.07 293	98.17 120	97.82 218	97.19 287	84.62 301	98.94 326	89.77 310	97.68 299	96.09 327

thres400		94.14 288	93.44 293	96.24 282	98.93 197	91.44 296	97.60 180	94.29 326	97.94 124	97.10 254	94.31 329	79.67 325	99.62 250	83.05 330	98.08 292	97.66 298

PatchFormer-LS_test		94.08 289	93.91 286	94.59 306	96.93 320	86.86 318	97.55 187	96.57 308	94.27 269	94.38 319	93.64 334	80.96 316	99.59 259	96.44 183	94.48 330	97.31 312

tfpn200view9		94.03 290	93.44 293	95.78 292	98.93 197	91.44 296	97.60 180	94.29 326	97.94 124	97.10 254	94.31 329	79.67 325	99.62 250	83.05 330	98.08 292	96.29 322

1111		93.99 291	93.72 290	94.80 303	99.33 125	85.20 325	95.97 271	99.39 99	97.88 136	98.64 161	98.56 205	57.79 345	99.80 151	96.02 199	99.87 68	99.40 147

CostFormer		93.97 292	93.78 289	94.51 307	97.53 306	85.83 322	97.98 140	95.96 313	89.29 319	94.99 315	98.63 194	78.63 329	99.62 250	94.54 238	96.50 316	98.09 281

test-LLR		93.90 293	93.85 287	94.04 311	96.53 326	84.62 329	94.05 319	92.39 334	96.17 229	94.12 322	95.07 319	82.30 314	99.67 232	95.87 207	98.18 285	97.82 289

EMVS		93.83 294	94.02 285	93.23 321	96.83 324	84.96 327	89.77 335	96.32 311	97.92 126	97.43 245	96.36 304	86.17 288	98.93 327	87.68 317	97.73 298	95.81 328

thres200		93.72 295	93.14 296	95.46 297	98.66 249	91.29 303	96.61 245	94.63 320	97.39 175	96.83 270	93.71 332	79.88 323	99.56 269	82.40 332	98.13 289	95.54 330

EPMVS		93.72 295	93.27 295	95.09 301	96.04 333	87.76 314	98.13 119	85.01 341	94.69 260	96.92 262	98.64 190	78.47 331	99.31 309	95.04 226	96.46 317	98.20 277

dp		93.47 297	93.59 292	93.13 322	96.64 325	81.62 338	97.66 170	96.42 310	92.80 286	96.11 290	98.64 190	78.55 330	99.59 259	93.31 274	92.18 336	98.16 278

FPMVS		93.44 298	92.23 303	97.08 259	99.25 134	97.86 128	95.61 292	97.16 292	92.90 284	93.76 327	98.65 187	75.94 334	95.66 337	79.30 336	97.49 300	97.73 296

tpm cat1		93.29 299	93.13 297	93.75 315	97.39 313	84.74 328	97.39 196	97.65 285	83.39 333	94.16 321	98.41 218	82.86 313	99.39 300	91.56 299	95.35 325	97.14 314

MVS		93.19 300	92.09 304	96.50 275	96.91 321	94.03 261	98.07 127	98.06 275	68.01 336	94.56 318	96.48 301	95.96 187	99.30 311	83.84 329	96.89 313	96.17 323

tpm2		93.09 301	92.58 300	94.62 305	97.56 304	86.53 319	97.66 170	95.79 315	86.15 328	94.07 324	98.23 234	75.95 333	99.53 275	90.91 304	96.86 314	97.81 291

tpmp4_e23		92.91 302	92.45 301	94.29 309	97.41 311	85.62 324	97.95 143	96.77 304	87.55 326	91.33 333	98.57 202	74.21 335	99.59 259	91.62 297	96.64 315	97.65 305

DWT-MVSNet_test		92.75 303	92.05 305	94.85 302	96.48 328	87.21 317	97.83 155	94.99 317	92.22 294	92.72 329	94.11 331	70.75 336	99.46 292	95.01 227	94.33 331	97.87 287

MVE	83.40 22	92.50 304	91.92 306	94.25 310	98.83 219	91.64 293	92.71 328	83.52 342	95.92 238	86.46 339	95.46 316	95.20 209	95.40 338	80.51 334	98.64 269	95.73 329
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
gg-mvs-nofinetune		92.37 305	91.20 309	95.85 291	95.80 335	92.38 286	99.31 20	81.84 343	99.75 4	91.83 331	99.74 8	68.29 338	99.02 323	87.15 318	97.12 309	96.16 324

test-mter		92.33 306	91.76 308	94.04 311	96.53 326	84.62 329	94.05 319	92.39 334	94.00 274	94.12 322	95.07 319	65.63 344	99.67 232	95.87 207	98.18 285	97.82 289

IB-MVS	91.63 19	92.24 307	90.90 310	96.27 277	97.22 317	91.24 304	94.36 317	93.33 332	92.37 291	92.24 330	94.58 328	66.20 342	99.89 56	93.16 276	94.63 328	97.66 298
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
TESTMET0.1,1		92.19 308	91.77 307	93.46 318	96.48 328	82.80 336	94.05 319	91.52 337	94.45 265	94.00 325	94.88 324	66.65 341	99.56 269	95.78 212	98.11 290	98.02 283

PAPM		91.88 309	90.34 311	96.51 274	98.06 287	92.56 282	92.44 330	97.17 291	86.35 327	90.38 335	96.01 306	86.61 286	99.21 316	70.65 338	95.43 324	97.75 295

PNet_i23d		91.80 310	92.35 302	90.14 325	98.65 250	73.10 343	89.22 336	99.02 205	95.23 251	97.87 208	97.82 258	78.45 332	98.89 329	88.73 313	86.14 337	98.42 271

test2356		91.64 311	90.19 314	96.00 289	94.30 338	89.58 308	90.84 332	96.68 305	91.76 296	95.48 309	93.69 333	67.05 340	99.52 279	84.83 327	97.08 310	98.91 236

PVSNet_0	89.98 21	91.15 312	90.30 312	93.70 316	97.72 297	84.34 332	90.24 333	97.42 286	90.20 314	93.79 326	93.09 335	90.90 270	98.89 329	86.57 320	72.76 338	97.87 287

testpf		89.08 313	90.27 313	85.50 326	94.03 339	82.85 335	96.87 229	91.09 338	91.61 300	90.96 334	94.86 327	66.15 343	95.83 336	94.58 237	92.27 335	77.82 335

.test1245		79.71 314	84.30 315	65.96 328	99.33 125	85.20 325	95.97 271	99.39 99	97.88 136	98.64 161	98.56 205	57.79 345	99.80 151	96.02 199	15.07 339	12.86 338

tmp_tt		78.77 315	78.73 316	78.90 327	58.45 342	74.76 342	94.20 318	78.26 345	39.16 338	86.71 338	92.82 336	80.50 318	75.19 341	86.16 321	92.29 334	86.74 334

pcd1.5k->3k		41.59 316	44.35 317	33.30 329	99.87 12	0.00 346	0.00 337	99.58 36	0.00 341	0.00 342	0.00 343	99.70 2	0.00 344	0.00 341	99.99 11	99.91 2

cdsmvs_eth3d_5k		24.66 317	32.88 318	0.00 332	0.00 345	0.00 346	0.00 337	99.10 189	0.00 341	0.00 342	97.58 269	99.21 11	0.00 344	0.00 341	0.00 342	0.00 340

testmvs		17.12 318	20.53 319	6.87 331	12.05 343	4.20 345	93.62 324	6.73 346	4.62 340	10.41 340	24.33 339	8.28 348	3.56 343	9.69 340	15.07 339	12.86 338

test123		17.04 319	20.11 320	7.82 330	10.25 344	4.91 344	94.80 311	4.47 347	4.93 339	10.00 341	24.28 340	9.69 347	3.64 342	10.14 339	12.43 341	14.92 337

pcd_1.5k_mvsjas		8.17 320	10.90 321	0.00 332	0.00 345	0.00 346	0.00 337	0.00 348	0.00 341	0.00 342	0.00 343	98.07 60	0.00 344	0.00 341	0.00 342	0.00 340

ab-mvs-re		8.12 321	10.83 322	0.00 332	0.00 345	0.00 346	0.00 337	0.00 348	0.00 341	0.00 342	97.48 276	0.00 349	0.00 344	0.00 341	0.00 342	0.00 340

sosnet-low-res		0.00 322	0.00 323	0.00 332	0.00 345	0.00 346	0.00 337	0.00 348	0.00 341	0.00 342	0.00 343	0.00 349	0.00 344	0.00 341	0.00 342	0.00 340

sosnet		0.00 322	0.00 323	0.00 332	0.00 345	0.00 346	0.00 337	0.00 348	0.00 341	0.00 342	0.00 343	0.00 349	0.00 344	0.00 341	0.00 342	0.00 340

uncertanet		0.00 322	0.00 323	0.00 332	0.00 345	0.00 346	0.00 337	0.00 348	0.00 341	0.00 342	0.00 343	0.00 349	0.00 344	0.00 341	0.00 342	0.00 340

Regformer		0.00 322	0.00 323	0.00 332	0.00 345	0.00 346	0.00 337	0.00 348	0.00 341	0.00 342	0.00 343	0.00 349	0.00 344	0.00 341	0.00 342	0.00 340

uanet		0.00 322	0.00 323	0.00 332	0.00 345	0.00 346	0.00 337	0.00 348	0.00 341	0.00 342	0.00 343	0.00 349	0.00 344	0.00 341	0.00 342	0.00 340

ESAPD								99.25 149

sam_mvs1												84.74 300

sam_mvs												84.29 306

semantic-postprocess				96.87 267	99.27 131	91.16 305		99.25 149	99.10 64	99.41 57	99.35 68	92.91 256	99.96 8	98.65 66	99.94 33	99.49 108

ambc				98.24 207	98.82 222	95.97 215	98.62 80	99.00 212		99.27 81	99.21 86	96.99 130	99.50 285	96.55 175	99.50 191	99.26 187

MTGPA								99.20 161

test_post1							97.59 182				20.48 342	83.07 312	99.66 240	94.16 248

test_post											21.25 341	83.86 308	99.70 218

patchmatchnet-post											98.77 172	84.37 303	99.85 85

GG-mvs-BLEND				94.76 304	94.54 337	92.13 289	99.31 20	80.47 344		88.73 337	91.01 337	67.59 339	98.16 335	82.30 333	94.53 329	93.98 332

MTMP								91.91 336

gm-plane-assit					94.83 336	81.97 337			88.07 323		94.99 322		99.60 255	91.76 293

test9_res														93.28 275	99.15 234	99.38 154

TEST9					98.71 234	98.08 105	95.96 275	99.03 201	91.40 304	95.85 296	97.53 271	96.52 162	99.76 187

test_8					98.67 244	98.01 111	95.91 281	99.02 205	91.64 298	95.79 298	97.50 274	96.47 165	99.76 187

agg_prior2														92.50 287	99.16 231	99.37 155

agg_prior					98.68 241	97.99 112		99.01 208		95.59 300			99.77 183

TestCases				99.16 83	99.50 85	98.55 74		99.58 36	96.80 208	98.88 138	99.06 116	97.65 83	99.57 266	94.45 241	99.61 158	99.37 155

test_prior4						97.97 117	95.86 282

test_prior2							95.74 288		96.48 219	96.11 290	97.63 267	95.92 189		94.16 248	99.20 224

test_prior				98.95 114	98.69 239	97.95 120		99.03 201					99.59 259			99.30 179

旧先验2							95.76 286		88.56 322	97.52 238			99.66 240	94.48 239

新几何2							95.93 279

新几何1				98.91 120	98.94 195	97.76 137		98.76 243	87.58 325	96.75 273	98.10 243	94.80 223	99.78 174	92.73 284	99.00 250	99.20 199

旧先验1					98.82 222	97.45 155		98.76 243			98.34 224	95.50 203			99.01 249	99.23 193

无先验							95.74 288	98.74 248	89.38 318				99.73 207	92.38 289		99.22 197

原ACMM2							95.53 295

原ACMM1				98.35 198	98.90 205	96.25 206		98.83 237	92.48 289	96.07 293	98.10 243	95.39 206	99.71 216	92.61 286	98.99 251	99.08 215

test222					98.92 201	96.93 178	95.54 294	98.78 242	85.72 329	96.86 269	98.11 242	94.43 231			99.10 242	99.23 193

testdata2													99.79 165	92.80 282

segment_acmp												97.02 128

testdata				98.09 214	98.93 197	95.40 235		98.80 240	90.08 315	97.45 243	98.37 221	95.26 208	99.70 218	93.58 268	98.95 255	99.17 209

testdata1							95.44 299		96.32 224

test12				98.93 117	98.58 255	97.83 130		98.66 253		96.53 279		95.51 202	99.69 222		99.13 238	99.27 184

plane_prior7					99.19 151	97.87 127

plane_prior6					98.99 188	97.70 143						94.90 215

plane_prior5								99.27 143					99.70 218	94.42 243	99.51 186	99.45 130

plane_prior4											97.98 251

plane_prior3						97.78 136			97.41 173	97.79 219

plane_prior2							97.77 159		98.20 117

plane_prior1					99.05 177

plane_prior						97.65 145	97.07 217		96.72 211						99.36 201

n2								0.00 348

nn								0.00 348

door-mid								99.57 43

lessismore_v0				98.97 112	99.73 28	97.53 151		86.71 340		99.37 63	99.52 45	89.93 273	99.92 34	98.99 51	99.72 123	99.44 132

LGP-MVS_train				99.47 46	99.57 61	98.97 48		99.48 74	96.60 217	99.10 104	99.06 116	98.71 27	99.83 114	95.58 221	99.78 100	99.62 45

test11								98.87 226

door								99.41 96

HQP5-MVS						96.79 181

HQP-NCC					98.67 244		96.29 259		96.05 234	95.55 304

ACMP_Plane					98.67 244		96.29 259		96.05 234	95.55 304

BP-MVS														92.82 280

HQP4-MVS										95.56 303			99.54 273			99.32 172

HQP3-MVS								99.04 199							99.26 218

HQP2-MVS												93.84 242

NP-MVS					98.84 217	97.39 158					96.84 294

MDTV_nov1_ep13_2view						74.92 341	97.69 167		90.06 316	97.75 222		85.78 293		93.52 269		98.69 258

MDTV_nov1_ep13			95.22 266		97.06 319	83.20 333	97.74 163	96.16 312	94.37 267	96.99 260	98.83 163	83.95 307	99.53 275	93.90 257	97.95 295

ACMMP++_ref															99.77 104

ACMMP++															99.68 141

Test By Simon												96.52 162

ITE_SJBPF				98.87 124	99.22 141	98.48 81		99.35 116	97.50 162	98.28 190	98.60 199	97.64 86	99.35 304	93.86 260	99.27 216	98.79 248

DeepMVS_CX				93.44 319	98.24 278	94.21 257		94.34 325	64.28 337	91.34 332	94.87 326	89.45 278	92.77 340	77.54 337	93.14 333	93.35 333

High-resolution multi-view benchmark