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		99.95 1	99.95 1	99.95 1	99.99 1	99.99 1	99.95 2	99.97 3	99.99 1	100.00 1	99.98 8	99.78 8	100.00 1	99.92 3	100.00 1	99.87 10

mvs_tets		99.90 2	99.90 2	99.90 4	99.96 4	99.79 32	99.72 25	99.88 17	99.92 5	99.98 3	99.93 13	99.94 2	99.98 7	99.77 30	100.00 1	99.92 3

jajsoiax		99.89 3	99.89 3	99.89 6	99.96 4	99.78 34	99.70 29	99.86 21	99.89 10	99.98 3	99.90 22	99.94 2	99.98 7	99.75 31	100.00 1	99.90 5

ANet_high		99.88 4	99.87 4	99.91 2	99.99 1	99.91 2	99.65 54	100.00 1	99.90 6	100.00 1	99.97 9	99.61 17	99.97 16	99.75 31	100.00 1	99.84 15

LTVRE_ROB	99.19 1	99.88 4	99.87 4	99.88 11	99.91 20	99.90 3	99.96 1	99.92 6	99.90 6	99.97 6	99.87 37	99.81 7	99.95 41	99.54 45	99.99 20	99.80 25
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		99.86 6	99.86 6	99.83 23	99.94 14	99.90 3	99.83 7	99.91 10	99.85 18	99.94 20	99.95 11	99.73 10	99.90 114	99.65 35	99.97 46	99.69 57

v52		99.85 7	99.84 7	99.89 6	99.96 4	99.89 5	99.87 4	99.81 55	99.85 18	99.96 8	99.90 22	99.27 41	99.95 41	99.93 1	99.99 20	99.82 23

V4		99.85 7	99.84 7	99.88 11	99.96 4	99.89 5	99.87 4	99.81 55	99.85 18	99.96 8	99.90 22	99.27 41	99.95 41	99.93 1	100.00 1	99.82 23

PS-MVSNAJss		99.84 9	99.82 9	99.89 6	99.96 4	99.77 36	99.68 41	99.85 28	99.95 3	99.98 3	99.92 16	99.28 38	99.98 7	99.75 31	100.00 1	99.94 2

test_djsdf		99.84 9	99.81 10	99.91 2	99.94 14	99.84 17	99.77 13	99.80 59	99.73 43	99.97 6	99.92 16	99.77 9	99.98 7	99.43 54	100.00 1	99.90 5

v7n		99.82 11	99.80 11	99.88 11	99.96 4	99.84 17	99.82 9	99.82 47	99.84 22	99.94 20	99.91 19	99.13 56	99.96 33	99.83 20	99.99 20	99.83 18

anonymousdsp		99.80 12	99.77 13	99.90 4	99.96 4	99.88 7	99.73 21	99.85 28	99.70 50	99.92 30	99.93 13	99.45 22	99.97 16	99.36 64	100.00 1	99.85 14

pm-mvs1		99.79 13	99.79 12	99.78 37	99.91 20	99.83 21	99.76 16	99.87 19	99.73 43	99.89 38	99.87 37	99.63 15	99.87 163	99.54 45	99.92 90	99.63 98

UA-Net		99.78 14	99.76 17	99.86 17	99.72 131	99.71 53	99.91 3	99.95 5	99.96 2	99.71 109	99.91 19	99.15 52	99.97 16	99.50 49	100.00 1	99.90 5

TransMVSNet (Re)		99.78 14	99.77 13	99.81 27	99.91 20	99.85 12	99.75 17	99.86 21	99.70 50	99.91 32	99.89 31	99.60 19	99.87 163	99.59 39	99.74 193	99.71 50

v748		99.76 16	99.74 20	99.84 20	99.95 12	99.83 21	99.82 9	99.80 59	99.82 26	99.95 16	99.87 37	98.72 112	99.93 66	99.72 34	99.98 36	99.75 41

v13		99.76 16	99.77 13	99.73 63	99.86 34	99.55 99	99.77 13	99.86 21	99.79 33	99.96 8	99.91 19	98.90 83	99.87 163	99.91 5	100.00 1	99.78 32

v12		99.75 18	99.77 13	99.72 69	99.85 38	99.53 102	99.75 17	99.86 21	99.78 34	99.96 8	99.90 22	98.88 86	99.86 184	99.91 5	100.00 1	99.77 34

v11		99.75 18	99.76 17	99.71 73	99.85 38	99.49 105	99.73 21	99.84 36	99.75 39	99.95 16	99.90 22	98.93 78	99.86 184	99.92 3	100.00 1	99.77 34

OurMVSNet-221017-0		99.75 18	99.71 24	99.84 20	99.96 4	99.83 21	99.83 7	99.85 28	99.80 31	99.93 25	99.93 13	98.54 142	99.93 66	99.59 39	99.98 36	99.76 37

Vis-MVSNet		99.75 18	99.74 20	99.79 34	99.88 27	99.66 71	99.69 38	99.92 6	99.67 59	99.77 87	99.75 94	99.61 17	99.98 7	99.35 65	99.98 36	99.72 47
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
V9		99.74 22	99.75 19	99.71 73	99.84 41	99.50 103	99.74 19	99.86 21	99.76 38	99.96 8	99.90 22	98.83 89	99.85 202	99.91 5	100.00 1	99.77 34

V14		99.73 23	99.74 20	99.69 80	99.83 45	99.48 108	99.72 25	99.85 28	99.74 40	99.96 8	99.89 31	98.79 97	99.85 202	99.91 5	100.00 1	99.76 37

v15		99.72 24	99.73 23	99.68 83	99.82 52	99.44 120	99.70 29	99.85 28	99.72 46	99.95 16	99.88 34	98.76 105	99.84 218	99.90 9	100.00 1	99.75 41

TDRefinement		99.72 24	99.70 27	99.77 39	99.90 24	99.85 12	99.86 6	99.92 6	99.69 54	99.78 82	99.92 16	99.37 29	99.88 143	98.93 125	99.95 66	99.60 124

XXY-MVS		99.71 26	99.67 31	99.81 27	99.89 26	99.72 52	99.59 66	99.82 47	99.39 116	99.82 65	99.84 50	99.38 27	99.91 95	99.38 61	99.93 87	99.80 25

nrg030		99.70 27	99.66 32	99.82 24	99.76 102	99.84 17	99.61 61	99.70 108	99.93 4	99.78 82	99.68 139	99.10 58	99.78 278	99.45 52	99.96 58	99.83 18

FC-MVSNet-test		99.70 27	99.65 33	99.86 17	99.88 27	99.86 11	99.72 25	99.78 69	99.90 6	99.82 65	99.83 51	98.45 156	99.87 163	99.51 48	99.97 46	99.86 12

v17		99.70 27	99.71 24	99.67 86	99.81 60	99.44 120	99.70 29	99.83 39	99.69 54	99.94 20	99.87 37	98.70 113	99.84 218	99.88 14	99.99 20	99.73 44

v16		99.70 27	99.71 24	99.67 86	99.81 60	99.43 126	99.70 29	99.83 39	99.70 50	99.94 20	99.87 37	98.69 115	99.84 218	99.88 14	99.99 20	99.73 44

v10		99.69 31	99.69 28	99.66 94	99.81 60	99.39 138	99.66 49	99.75 84	99.60 83	99.92 30	99.87 37	98.75 108	99.86 184	99.90 9	99.99 20	99.73 44

v18		99.68 32	99.69 28	99.65 98	99.79 81	99.40 135	99.68 41	99.83 39	99.66 64	99.93 25	99.85 45	98.65 124	99.84 218	99.87 18	99.99 20	99.71 50

v8		99.68 32	99.69 28	99.65 98	99.80 68	99.40 135	99.66 49	99.76 79	99.64 69	99.93 25	99.85 45	98.66 122	99.84 218	99.88 14	99.99 20	99.71 50

DTE-MVSNet		99.68 32	99.61 40	99.88 11	99.80 68	99.87 8	99.67 46	99.71 105	99.72 46	99.84 60	99.78 79	98.67 120	99.97 16	99.30 74	99.95 66	99.80 25

VPA-MVSNet		99.66 35	99.62 37	99.79 34	99.68 150	99.75 43	99.62 57	99.69 114	99.85 18	99.80 74	99.81 61	98.81 90	99.91 95	99.47 51	99.88 114	99.70 54

PS-CasMVS		99.66 35	99.58 44	99.89 6	99.80 68	99.85 12	99.66 49	99.73 92	99.62 73	99.84 60	99.71 113	98.62 130	99.96 33	99.30 74	99.96 58	99.86 12

PEN-MVS		99.66 35	99.59 42	99.89 6	99.83 45	99.87 8	99.66 49	99.73 92	99.70 50	99.84 60	99.73 100	98.56 136	99.96 33	99.29 78	99.94 79	99.83 18

FMVSNet1		99.66 35	99.63 36	99.73 63	99.78 87	99.77 36	99.68 41	99.70 108	99.67 59	99.82 65	99.83 51	98.98 72	99.90 114	99.24 82	99.97 46	99.53 158

MIMVSNet1		99.66 35	99.62 37	99.80 29	99.94 14	99.87 8	99.69 38	99.77 72	99.78 34	99.93 25	99.89 31	97.94 196	99.92 85	99.65 35	99.98 36	99.62 112

FIs		99.65 40	99.58 44	99.84 20	99.84 41	99.85 12	99.66 49	99.75 84	99.86 15	99.74 101	99.79 70	98.27 169	99.85 202	99.37 63	99.93 87	99.83 18

wuykxyi23d		99.65 40	99.64 35	99.69 80	99.92 18	99.20 190	98.89 224	99.99 2	98.73 206	99.95 16	99.80 63	99.84 4	99.99 4	99.64 37	99.98 36	99.89 9

Anonymous20231211		99.62 42	99.57 47	99.76 42	99.61 171	99.60 89	99.81 11	99.73 92	99.82 26	99.90 34	99.90 22	97.97 195	99.86 184	99.42 58	99.96 58	99.80 25

DeepC-MVS	98.90 4	99.62 42	99.61 40	99.67 86	99.72 131	99.44 120	99.24 144	99.71 105	99.27 129	99.93 25	99.90 22	99.70 12	99.93 66	98.99 112	99.99 20	99.64 94
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
WR-MVS_H		99.61 44	99.53 61	99.87 15	99.80 68	99.83 21	99.67 46	99.75 84	99.58 86	99.85 57	99.69 126	98.18 180	99.94 54	99.28 80	99.95 66	99.83 18

ACMH	98.42 6	99.59 45	99.54 53	99.72 69	99.86 34	99.62 84	99.56 71	99.79 67	98.77 198	99.80 74	99.85 45	99.64 14	99.85 202	98.70 141	99.89 108	99.70 54
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
testing_2		99.58 46	99.56 51	99.62 119	99.81 60	99.44 120	99.14 179	99.43 232	99.69 54	99.82 65	99.79 70	99.14 53	99.79 270	99.31 73	99.95 66	99.63 98

v1192		99.57 47	99.57 47	99.57 140	99.77 97	99.22 184	99.04 200	99.60 164	99.18 146	99.87 51	99.72 106	99.08 63	99.85 202	99.89 13	99.98 36	99.66 80

EG-PatchMatch MVS		99.57 47	99.56 51	99.62 119	99.77 97	99.33 157	99.26 139	99.76 79	99.32 124	99.80 74	99.78 79	99.29 36	99.87 163	99.15 95	99.91 100	99.66 80

Gipuma		99.57 47	99.59 42	99.49 163	99.98 3	99.71 53	99.72 25	99.84 36	99.81 28	99.94 20	99.78 79	98.91 82	99.71 306	98.41 157	99.95 66	99.05 286
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
v1921920		99.56 50	99.57 47	99.55 149	99.75 111	99.11 199	99.05 198	99.61 150	99.15 153	99.88 46	99.71 113	99.08 63	99.87 163	99.90 9	99.97 46	99.66 80

v1240		99.56 50	99.58 44	99.51 159	99.80 68	99.00 210	99.00 207	99.65 135	99.15 153	99.90 34	99.75 94	99.09 60	99.88 143	99.90 9	99.96 58	99.67 70

v7		99.56 50	99.54 53	99.61 122	99.80 68	99.39 138	99.30 126	99.59 169	99.14 155	99.82 65	99.72 106	98.75 108	99.84 218	99.83 20	99.94 79	99.61 118

V42		99.56 50	99.54 53	99.63 110	99.79 81	99.46 113	99.39 91	99.59 169	99.24 138	99.86 56	99.70 120	98.55 140	99.82 243	99.79 26	99.95 66	99.60 124

v144192		99.55 54	99.54 53	99.58 134	99.78 87	99.20 190	99.11 187	99.62 146	99.18 146	99.89 38	99.72 106	98.66 122	99.87 163	99.88 14	99.97 46	99.66 80

v1neww		99.55 54	99.54 53	99.61 122	99.80 68	99.39 138	99.32 116	99.61 150	99.18 146	99.87 51	99.69 126	98.64 128	99.82 243	99.79 26	99.94 79	99.60 124

v7new		99.55 54	99.54 53	99.61 122	99.80 68	99.39 138	99.32 116	99.61 150	99.18 146	99.87 51	99.69 126	98.64 128	99.82 243	99.79 26	99.94 79	99.60 124

v6		99.55 54	99.54 53	99.61 122	99.80 68	99.39 138	99.32 116	99.60 164	99.18 146	99.87 51	99.68 139	98.65 124	99.82 243	99.79 26	99.95 66	99.61 118

test20.03		99.55 54	99.54 53	99.58 134	99.79 81	99.37 147	99.02 203	99.89 14	99.60 83	99.82 65	99.62 173	98.81 90	99.89 128	99.43 54	99.86 128	99.47 188

v1144		99.54 59	99.53 61	99.59 130	99.79 81	99.28 167	99.10 188	99.61 150	99.20 144	99.84 60	99.73 100	98.67 120	99.84 218	99.86 19	99.98 36	99.64 94

v1141		99.54 59	99.52 63	99.57 140	99.78 87	99.27 171	99.15 174	99.61 150	99.26 133	99.89 38	99.69 126	98.56 136	99.82 243	99.82 23	99.97 46	99.63 98

divwei89l23v2f112		99.54 59	99.52 63	99.57 140	99.78 87	99.27 171	99.15 174	99.61 150	99.26 133	99.89 38	99.69 126	98.56 136	99.82 243	99.82 23	99.96 58	99.63 98

v1		99.54 59	99.52 63	99.58 134	99.77 97	99.28 167	99.15 174	99.61 150	99.26 133	99.88 46	99.68 139	98.56 136	99.82 243	99.82 23	99.97 46	99.63 98

CP-MVSNet		99.54 59	99.43 78	99.87 15	99.76 102	99.82 26	99.57 69	99.61 150	99.54 88	99.80 74	99.64 158	97.79 208	99.95 41	99.21 83	99.94 79	99.84 15

TranMVSNet+NR-MVSNet		99.54 59	99.47 69	99.76 42	99.58 179	99.64 78	99.30 126	99.63 143	99.61 77	99.71 109	99.56 203	98.76 105	99.96 33	99.14 101	99.92 90	99.68 63

testmv		99.53 65	99.51 66	99.59 130	99.73 120	99.31 160	98.48 270	99.92 6	99.57 87	99.87 51	99.79 70	99.12 57	99.91 95	99.16 94	99.99 20	99.55 147

v2v482		99.50 66	99.47 69	99.58 134	99.78 87	99.25 177	99.14 179	99.58 177	99.25 136	99.81 71	99.62 173	98.24 171	99.84 218	99.83 20	99.97 46	99.64 94

ACMH+	98.40 8	99.50 66	99.43 78	99.71 73	99.86 34	99.76 41	99.32 116	99.77 72	99.53 90	99.77 87	99.76 90	99.26 44	99.78 278	97.77 203	99.88 114	99.60 124

Baseline_NR-MVSNet		99.49 68	99.37 88	99.82 24	99.91 20	99.84 17	98.83 235	99.86 21	99.68 57	99.65 129	99.88 34	97.67 217	99.87 163	99.03 109	99.86 128	99.76 37

TAMVS		99.49 68	99.45 73	99.63 110	99.48 230	99.42 130	99.45 84	99.57 180	99.66 64	99.78 82	99.83 51	97.85 203	99.86 184	99.44 53	99.96 58	99.61 118

pmmvs-eth3d		99.48 70	99.47 69	99.51 159	99.77 97	99.41 134	98.81 239	99.66 126	99.42 113	99.75 93	99.66 152	99.20 47	99.76 286	98.98 114	99.99 20	99.36 223

EI-MVSNet-UG-set		99.48 70	99.50 67	99.42 183	99.57 188	98.65 243	99.24 144	99.46 224	99.68 57	99.80 74	99.66 152	98.99 71	99.89 128	99.19 86	99.90 102	99.72 47

APDe-MVS		99.48 70	99.36 91	99.85 19	99.55 202	99.81 27	99.50 76	99.69 114	98.99 171	99.75 93	99.71 113	98.79 97	99.93 66	98.46 155	99.85 131	99.80 25

PMMVS2		99.48 70	99.45 73	99.57 140	99.76 102	98.99 211	98.09 305	99.90 13	98.95 176	99.78 82	99.58 193	99.57 20	99.93 66	99.48 50	99.95 66	99.79 31

DSMNet-mixed		99.48 70	99.65 33	98.95 257	99.71 134	97.27 306	99.50 76	99.82 47	99.59 85	99.41 196	99.85 45	99.62 16	100.00 1	99.53 47	99.89 108	99.59 135

DP-MVS		99.48 70	99.39 82	99.74 57	99.57 188	99.62 84	99.29 134	99.61 150	99.87 13	99.74 101	99.76 90	98.69 115	99.87 163	98.20 175	99.80 167	99.75 41

EI-MVSNet-Vis-set		99.47 76	99.49 68	99.42 183	99.57 188	98.66 241	99.24 144	99.46 224	99.67 59	99.79 79	99.65 157	98.97 74	99.89 128	99.15 95	99.89 108	99.71 50

VPNet		99.46 77	99.37 88	99.71 73	99.82 52	99.59 91	99.48 80	99.70 108	99.81 28	99.69 114	99.58 193	97.66 221	99.86 184	99.17 91	99.44 258	99.67 70

ACMM	98.09 11	99.46 77	99.38 84	99.72 69	99.80 68	99.69 64	99.13 184	99.65 135	98.99 171	99.64 131	99.72 106	99.39 23	99.86 184	98.23 172	99.81 162	99.60 124
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Regformer-4		99.45 79	99.44 75	99.50 161	99.52 209	98.94 217	99.17 166	99.53 196	99.64 69	99.76 90	99.60 185	98.96 77	99.90 114	98.91 126	99.84 135	99.67 70

COLMAP_ROB	98.06 12	99.45 79	99.37 88	99.70 79	99.83 45	99.70 60	99.38 97	99.78 69	99.53 90	99.67 119	99.78 79	99.19 48	99.86 184	97.32 231	99.87 121	99.55 147
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
tfpnnormal		99.43 81	99.38 84	99.60 128	99.87 31	99.75 43	99.59 66	99.78 69	99.71 48	99.90 34	99.69 126	98.85 88	99.90 114	97.25 239	99.78 176	99.15 260

HPM-MVS_fast		99.43 81	99.30 104	99.80 29	99.83 45	99.81 27	99.52 74	99.70 108	98.35 242	99.51 176	99.50 221	99.31 34	99.88 143	98.18 179	99.84 135	99.69 57

3Dnovator	99.15 2	99.43 81	99.36 91	99.65 98	99.39 257	99.42 130	99.70 29	99.56 183	99.23 140	99.35 212	99.80 63	99.17 50	99.95 41	98.21 174	99.84 135	99.59 135

Anonymous20240529		99.42 84	99.34 94	99.65 98	99.53 206	99.60 89	99.63 56	99.39 244	99.47 99	99.76 90	99.78 79	98.13 182	99.86 184	98.70 141	99.68 211	99.49 181

SixPastTwentyTwo		99.42 84	99.30 104	99.76 42	99.92 18	99.67 69	99.70 29	99.14 288	99.65 67	99.89 38	99.90 22	96.20 268	99.94 54	99.42 58	99.92 90	99.67 70

GBi-Net		99.42 84	99.31 99	99.73 63	99.49 224	99.77 36	99.68 41	99.70 108	99.44 106	99.62 142	99.83 51	97.21 240	99.90 114	98.96 119	99.90 102	99.53 158

test1		99.42 84	99.31 99	99.73 63	99.49 224	99.77 36	99.68 41	99.70 108	99.44 106	99.62 142	99.83 51	97.21 240	99.90 114	98.96 119	99.90 102	99.53 158

Regformer-3		99.41 88	99.41 80	99.40 191	99.52 209	98.70 238	99.17 166	99.44 229	99.62 73	99.75 93	99.60 185	98.90 83	99.85 202	98.89 127	99.84 135	99.65 88

MVSFormer		99.41 88	99.44 75	99.31 214	99.57 188	98.40 255	99.77 13	99.80 59	99.73 43	99.63 135	99.30 263	98.02 190	99.98 7	99.43 54	99.69 209	99.55 147

IterMVS-LS		99.41 88	99.47 69	99.25 228	99.81 60	98.09 280	98.85 232	99.76 79	99.62 73	99.83 64	99.64 158	98.54 142	99.97 16	99.15 95	99.99 20	99.68 63
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v148		99.40 91	99.41 80	99.39 194	99.76 102	98.94 217	99.09 192	99.59 169	99.17 151	99.81 71	99.61 182	98.41 159	99.69 313	99.32 71	99.94 79	99.53 158

casdiffmvs1		99.40 91	99.38 84	99.46 171	99.51 213	99.31 160	99.53 73	99.64 140	99.74 40	99.08 256	99.77 86	98.10 183	99.73 298	99.59 39	99.47 254	99.33 229

NR-MVSNet		99.40 91	99.31 99	99.68 83	99.43 246	99.55 99	99.73 21	99.50 212	99.46 103	99.88 46	99.36 249	97.54 224	99.87 163	98.97 118	99.87 121	99.63 98

PVSNet_Blended_VisFu		99.40 91	99.38 84	99.44 178	99.90 24	98.66 241	98.94 222	99.91 10	97.97 265	99.79 79	99.73 100	99.05 68	99.97 16	99.15 95	99.99 20	99.68 63

EU-MVSNet		99.39 95	99.62 37	98.72 284	99.88 27	96.44 317	99.56 71	99.85 28	99.90 6	99.90 34	99.85 45	98.09 184	99.83 235	99.58 42	99.95 66	99.90 5

CHOSEN 1792x2688		99.39 95	99.30 104	99.65 98	99.88 27	99.25 177	98.78 244	99.88 17	98.66 210	99.96 8	99.79 70	97.45 228	99.93 66	99.34 66	99.99 20	99.78 32

EI-MVSNet		99.38 97	99.44 75	99.21 233	99.58 179	98.09 280	99.26 139	99.46 224	99.62 73	99.75 93	99.67 146	98.54 142	99.85 202	99.15 95	99.92 90	99.68 63

UGNet		99.38 97	99.34 94	99.49 163	98.90 326	98.90 225	99.70 29	99.35 254	99.86 15	98.57 309	99.81 61	98.50 151	99.93 66	99.38 61	99.98 36	99.66 80
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
UniMVSNet_NR-MVSNet		99.37 99	99.25 117	99.72 69	99.47 235	99.56 96	98.97 217	99.61 150	99.43 111	99.67 119	99.28 268	97.85 203	99.95 41	99.17 91	99.81 162	99.65 88

UniMVSNet (Re)		99.37 99	99.26 115	99.68 83	99.51 213	99.58 93	98.98 216	99.60 164	99.43 111	99.70 111	99.36 249	97.70 212	99.88 143	99.20 85	99.87 121	99.59 135

CSCG		99.37 99	99.29 109	99.60 128	99.71 134	99.46 113	99.43 87	99.85 28	98.79 195	99.41 196	99.60 185	98.92 80	99.92 85	98.02 188	99.92 90	99.43 205

PM-MVS		99.36 102	99.29 109	99.58 134	99.83 45	99.66 71	98.95 219	99.86 21	98.85 187	99.81 71	99.73 100	98.40 161	99.92 85	98.36 161	99.83 145	99.17 257

abl_6		99.36 102	99.23 120	99.75 52	99.71 134	99.74 48	99.33 113	99.76 79	99.07 165	99.65 129	99.63 166	99.09 60	99.92 85	97.13 247	99.76 182	99.58 139

new-patchmatchnet		99.35 104	99.57 47	98.71 285	99.82 52	96.62 315	98.55 261	99.75 84	99.50 93	99.88 46	99.87 37	99.31 34	99.88 143	99.43 54	100.00 1	99.62 112

Anonymous20231206		99.35 104	99.31 99	99.47 168	99.74 117	99.06 209	99.28 135	99.74 89	99.23 140	99.72 105	99.53 212	97.63 223	99.88 143	99.11 103	99.84 135	99.48 183

MTAPA		99.35 104	99.20 124	99.80 29	99.81 60	99.81 27	99.33 113	99.53 196	99.27 129	99.42 190	99.63 166	98.21 175	99.95 41	97.83 200	99.79 170	99.65 88

FMVSNet2		99.35 104	99.28 111	99.55 149	99.49 224	99.35 154	99.45 84	99.57 180	99.44 106	99.70 111	99.74 96	97.21 240	99.87 163	99.03 109	99.94 79	99.44 199

3Dnovator+	98.92 3	99.35 104	99.24 118	99.67 86	99.35 265	99.47 109	99.62 57	99.50 212	99.44 106	99.12 253	99.78 79	98.77 103	99.94 54	97.87 197	99.72 205	99.62 112

TSAR-MVS + MP.		99.34 109	99.24 118	99.63 110	99.82 52	99.37 147	99.26 139	99.35 254	98.77 198	99.57 153	99.70 120	99.27 41	99.88 143	97.71 206	99.75 185	99.65 88

Regformer-2		99.34 109	99.27 113	99.53 154	99.41 253	99.10 202	98.99 212	99.53 196	99.47 99	99.66 123	99.52 214	98.80 94	99.89 128	98.31 166	99.74 193	99.60 124

diffmvs1		99.34 109	99.35 93	99.32 211	99.42 250	98.94 217	99.22 151	99.77 72	99.61 77	98.78 290	99.67 146	98.77 103	99.90 114	99.30 74	99.59 231	99.13 267

DELS-MVS		99.34 109	99.30 104	99.48 166	99.51 213	99.36 150	98.12 301	99.53 196	99.36 120	99.41 196	99.61 182	99.22 46	99.87 163	99.21 83	99.68 211	99.20 249
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
DU-MVS		99.33 113	99.21 123	99.71 73	99.43 246	99.56 96	98.83 235	99.53 196	99.38 117	99.67 119	99.36 249	97.67 217	99.95 41	99.17 91	99.81 162	99.63 98

ab-mvs		99.33 113	99.28 111	99.47 168	99.57 188	99.39 138	99.78 12	99.43 232	98.87 185	99.57 153	99.82 58	98.06 187	99.87 163	98.69 143	99.73 200	99.15 260

Regformer-1		99.32 115	99.27 113	99.47 168	99.41 253	98.95 216	98.99 212	99.48 217	99.48 95	99.66 123	99.52 214	98.78 100	99.87 163	98.36 161	99.74 193	99.60 124

APD-MVS_3200maxsize		99.31 116	99.16 126	99.74 57	99.53 206	99.75 43	99.27 138	99.61 150	99.19 145	99.57 153	99.64 158	98.76 105	99.90 114	97.29 233	99.62 225	99.56 144

zzz-MVS		99.30 117	99.14 129	99.80 29	99.81 60	99.81 27	98.73 248	99.53 196	99.27 129	99.42 190	99.63 166	98.21 175	99.95 41	97.83 200	99.79 170	99.65 88

SteuartSystems-ACMMP		99.30 117	99.14 129	99.76 42	99.87 31	99.66 71	99.18 159	99.60 164	98.55 220	99.57 153	99.67 146	99.03 70	99.94 54	97.01 252	99.80 167	99.69 57
Skip Steuart: Steuart Systems R&D Blog.
testgi		99.29 119	99.26 115	99.37 200	99.75 111	98.81 234	98.84 233	99.89 14	98.38 235	99.75 93	99.04 308	99.36 32	99.86 184	99.08 106	99.25 287	99.45 194

ACMMP_Plus		99.28 120	99.11 138	99.79 34	99.75 111	99.81 27	98.95 219	99.53 196	98.27 251	99.53 172	99.73 100	98.75 108	99.87 163	97.70 207	99.83 145	99.68 63

LCM-MVSNet-Re		99.28 120	99.15 128	99.67 86	99.33 280	99.76 41	99.34 111	99.97 3	98.93 179	99.91 32	99.79 70	98.68 117	99.93 66	96.80 263	99.56 235	99.30 236

mvs_anonymous		99.28 120	99.39 82	98.94 258	99.19 301	97.81 291	99.02 203	99.55 186	99.78 34	99.85 57	99.80 63	98.24 171	99.86 184	99.57 43	99.50 250	99.15 260

MVS_Test		99.28 120	99.31 99	99.19 236	99.35 265	98.79 236	99.36 103	99.49 216	99.17 151	99.21 241	99.67 146	98.78 100	99.66 333	99.09 105	99.66 219	99.10 274

no-one		99.28 120	99.23 120	99.45 176	99.87 31	99.08 205	98.95 219	99.52 206	98.88 184	99.77 87	99.83 51	97.78 209	99.90 114	98.46 155	99.99 20	99.38 216

XVS		99.27 125	99.11 138	99.75 52	99.71 134	99.71 53	99.37 101	99.61 150	99.29 125	98.76 292	99.47 228	98.47 153	99.88 143	97.62 214	99.73 200	99.67 70

OPM-MVS		99.26 126	99.13 132	99.63 110	99.70 141	99.61 88	98.58 256	99.48 217	98.50 225	99.52 174	99.63 166	99.14 53	99.76 286	97.89 196	99.77 180	99.51 169

HFP-MVS		99.25 127	99.08 149	99.76 42	99.73 120	99.70 60	99.31 123	99.59 169	98.36 237	99.36 210	99.37 244	98.80 94	99.91 95	97.43 226	99.75 185	99.68 63

HPM-MVS		99.25 127	99.07 153	99.78 37	99.81 60	99.75 43	99.61 61	99.67 122	97.72 278	99.35 212	99.25 274	99.23 45	99.92 85	97.21 243	99.82 154	99.67 70
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
ACMMP		99.25 127	99.08 149	99.74 57	99.79 81	99.68 67	99.50 76	99.65 135	98.07 259	99.52 174	99.69 126	98.57 135	99.92 85	97.18 245	99.79 170	99.63 98
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
casdiffmvs		99.24 130	99.23 120	99.26 224	99.42 250	98.85 232	99.48 80	99.58 177	99.67 59	98.70 297	99.67 146	97.85 203	99.72 300	99.41 60	99.28 282	99.20 249

LS3D		99.24 130	99.11 138	99.61 122	98.38 356	99.79 32	99.57 69	99.68 117	99.61 77	99.15 249	99.71 113	98.70 113	99.91 95	97.54 220	99.68 211	99.13 267

xiu_mvs_v1_base_debu		99.23 132	99.34 94	98.91 262	99.59 176	98.23 269	98.47 271	99.66 126	99.61 77	99.68 116	98.94 322	99.39 23	99.97 16	99.18 88	99.55 241	98.51 316

xiu_mvs_v1_base		99.23 132	99.34 94	98.91 262	99.59 176	98.23 269	98.47 271	99.66 126	99.61 77	99.68 116	98.94 322	99.39 23	99.97 16	99.18 88	99.55 241	98.51 316

xiu_mvs_v1_base_debi		99.23 132	99.34 94	98.91 262	99.59 176	98.23 269	98.47 271	99.66 126	99.61 77	99.68 116	98.94 322	99.39 23	99.97 16	99.18 88	99.55 241	98.51 316

region2R		99.23 132	99.05 159	99.77 39	99.76 102	99.70 60	99.31 123	99.59 169	98.41 232	99.32 220	99.36 249	98.73 111	99.93 66	97.29 233	99.74 193	99.67 70

ACMMPR		99.23 132	99.06 155	99.76 42	99.74 117	99.69 64	99.31 123	99.59 169	98.36 237	99.35 212	99.38 243	98.61 132	99.93 66	97.43 226	99.75 185	99.67 70

XVG-ACMP-BASELINE		99.23 132	99.10 145	99.63 110	99.82 52	99.58 93	98.83 235	99.72 102	98.36 237	99.60 149	99.71 113	98.92 80	99.91 95	97.08 249	99.84 135	99.40 210

CP-MVS		99.23 132	99.05 159	99.75 52	99.66 156	99.66 71	99.38 97	99.62 146	98.38 235	99.06 261	99.27 270	98.79 97	99.94 54	97.51 222	99.82 154	99.66 80

DeepC-MVS_fast	98.47 5	99.23 132	99.12 135	99.56 146	99.28 289	99.22 184	98.99 212	99.40 241	99.08 163	99.58 151	99.64 158	98.90 83	99.83 235	97.44 225	99.75 185	99.63 98
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
LPG-MVS_test		99.22 140	99.05 159	99.74 57	99.82 52	99.63 82	99.16 172	99.73 92	97.56 286	99.64 131	99.69 126	99.37 29	99.89 128	96.66 271	99.87 121	99.69 57

CDS-MVSNet		99.22 140	99.13 132	99.50 161	99.35 265	99.11 199	98.96 218	99.54 191	99.46 103	99.61 147	99.70 120	96.31 265	99.83 235	99.34 66	99.88 114	99.55 147
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
test_0402		99.22 140	99.14 129	99.45 176	99.79 81	99.43 126	99.28 135	99.68 117	99.54 88	99.40 200	99.56 203	99.07 65	99.82 243	96.01 297	99.96 58	99.11 270

AllTest		99.21 143	99.07 153	99.63 110	99.78 87	99.64 78	99.12 186	99.83 39	98.63 213	99.63 135	99.72 106	98.68 117	99.75 292	96.38 283	99.83 145	99.51 169

XVG-OURS		99.21 143	99.06 155	99.65 98	99.82 52	99.62 84	97.87 329	99.74 89	98.36 237	99.66 123	99.68 139	99.71 11	99.90 114	96.84 261	99.88 114	99.43 205

Fast-Effi-MVS+-dtu		99.20 145	99.12 135	99.43 181	99.25 292	99.69 64	99.05 198	99.82 47	99.50 93	98.97 266	99.05 305	98.98 72	99.98 7	98.20 175	99.24 289	98.62 309

VDD-MVS		99.20 145	99.11 138	99.44 178	99.43 246	98.98 212	99.50 76	98.32 325	99.80 31	99.56 161	99.69 126	96.99 250	99.85 202	98.99 112	99.73 200	99.50 175

PGM-MVS		99.20 145	99.01 169	99.77 39	99.75 111	99.71 53	99.16 172	99.72 102	97.99 263	99.42 190	99.60 185	98.81 90	99.93 66	96.91 256	99.74 193	99.66 80

SMA-MVS		99.19 148	99.00 171	99.73 63	99.46 239	99.73 49	99.13 184	99.52 206	97.40 294	99.57 153	99.64 158	98.93 78	99.83 235	97.61 216	99.79 170	99.63 98

pmmvs5		99.19 148	99.11 138	99.42 183	99.76 102	98.88 227	98.55 261	99.73 92	98.82 191	99.72 105	99.62 173	96.56 257	99.82 243	99.32 71	99.95 66	99.56 144

mPP-MVS		99.19 148	99.00 171	99.76 42	99.76 102	99.68 67	99.38 97	99.54 191	98.34 246	99.01 263	99.50 221	98.53 146	99.93 66	97.18 245	99.78 176	99.66 80

VNet		99.18 151	99.06 155	99.56 146	99.24 294	99.36 150	99.33 113	99.31 263	99.67 59	99.47 181	99.57 199	96.48 260	99.84 218	99.15 95	99.30 280	99.47 188

RPSCF		99.18 151	99.02 166	99.64 106	99.83 45	99.85 12	99.44 86	99.82 47	98.33 247	99.50 178	99.78 79	97.90 198	99.65 340	96.78 264	99.83 145	99.44 199

DeepPCF-MVS	98.42 6	99.18 151	99.02 166	99.67 86	99.22 296	99.75 43	97.25 350	99.47 221	98.72 207	99.66 123	99.70 120	99.29 36	99.63 343	98.07 187	99.81 162	99.62 112

MVS_0304		99.17 154	99.10 145	99.38 196	99.08 317	98.86 230	98.46 275	99.73 92	99.53 90	99.35 212	99.30 263	97.11 246	99.96 33	99.33 68	99.99 20	99.33 229

diffmvs		99.17 154	99.19 125	99.10 244	99.36 264	98.41 254	99.24 144	99.68 117	99.46 103	98.30 320	99.68 139	98.49 152	99.91 95	99.10 104	99.43 264	98.98 291

EPP-MVSNet		99.17 154	99.00 171	99.66 94	99.80 68	99.43 126	99.70 29	99.24 279	99.48 95	99.56 161	99.77 86	94.89 281	99.93 66	98.72 140	99.89 108	99.63 98

GST-MVS		99.16 157	98.96 181	99.75 52	99.73 120	99.73 49	99.20 156	99.55 186	98.22 253	99.32 220	99.35 254	98.65 124	99.91 95	96.86 259	99.74 193	99.62 112

MVP-Stereo		99.16 157	99.08 149	99.43 181	99.48 230	99.07 207	99.08 195	99.55 186	98.63 213	99.31 223	99.68 139	98.19 178	99.78 278	98.18 179	99.58 233	99.45 194
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
XVG-OURS-SEG-HR		99.16 157	98.99 175	99.66 94	99.84 41	99.64 78	98.25 290	99.73 92	98.39 234	99.63 135	99.43 234	99.70 12	99.90 114	97.34 230	98.64 324	99.44 199

jason		99.16 157	99.11 138	99.32 211	99.75 111	98.44 251	98.26 289	99.39 244	98.70 208	99.74 101	99.30 263	98.54 142	99.97 16	98.48 154	99.82 154	99.55 147
jason: jason.
ESAPD		99.14 161	98.92 186	99.82 24	99.57 188	99.77 36	98.74 246	99.60 164	98.55 220	99.76 90	99.69 126	98.23 174	99.92 85	96.39 282	99.75 185	99.76 37

MP-MVS-pluss		99.14 161	98.92 186	99.80 29	99.83 45	99.83 21	98.61 252	99.63 143	96.84 310	99.44 184	99.58 193	98.81 90	99.91 95	97.70 207	99.82 154	99.67 70
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
pmmvs4		99.13 163	99.06 155	99.36 203	99.57 188	99.10 202	98.01 313	99.25 276	98.78 197	99.58 151	99.44 233	98.24 171	99.76 286	98.74 138	99.93 87	99.22 245

MVS_111021_LR		99.13 163	99.03 165	99.42 183	99.58 179	99.32 159	97.91 328	99.73 92	98.68 209	99.31 223	99.48 225	99.09 60	99.66 333	97.70 207	99.77 180	99.29 239

#test#		99.12 165	98.90 190	99.76 42	99.73 120	99.70 60	99.10 188	99.59 169	97.60 284	99.36 210	99.37 244	98.80 94	99.91 95	96.84 261	99.75 185	99.68 63

TSAR-MVS + GP.		99.12 165	99.04 164	99.38 196	99.34 275	99.16 194	98.15 297	99.29 267	98.18 256	99.63 135	99.62 173	99.18 49	99.68 323	98.20 175	99.74 193	99.30 236

MVS_111021_HR		99.12 165	99.02 166	99.40 191	99.50 219	99.11 199	97.92 326	99.71 105	98.76 201	99.08 256	99.47 228	99.17 50	99.54 352	97.85 199	99.76 182	99.54 155

CANet		99.11 168	99.05 159	99.28 217	98.83 336	98.56 244	98.71 250	99.41 235	99.25 136	99.23 235	99.22 283	97.66 221	99.94 54	99.19 86	99.97 46	99.33 229

WR-MVS		99.11 168	98.93 183	99.66 94	99.30 286	99.42 130	98.42 279	99.37 251	99.04 168	99.57 153	99.20 285	96.89 252	99.86 184	98.66 146	99.87 121	99.70 54

PHI-MVS		99.11 168	98.95 182	99.59 130	99.13 309	99.59 91	99.17 166	99.65 135	97.88 269	99.25 231	99.46 231	98.97 74	99.80 267	97.26 236	99.82 154	99.37 220

MSDG		99.08 171	98.98 178	99.37 200	99.60 173	99.13 197	97.54 339	99.74 89	98.84 190	99.53 172	99.55 208	99.10 58	99.79 270	97.07 250	99.86 128	99.18 255

Effi-MVS+-dtu		99.07 172	98.92 186	99.52 156	98.89 330	99.78 34	99.15 174	99.66 126	99.34 121	98.92 276	99.24 279	97.69 214	99.98 7	98.11 184	99.28 282	98.81 303

Effi-MVS+		99.06 173	98.97 179	99.34 205	99.31 282	98.98 212	98.31 287	99.91 10	98.81 192	98.79 288	98.94 322	99.14 53	99.84 218	98.79 133	98.74 319	99.20 249

MP-MVS		99.06 173	98.83 200	99.76 42	99.76 102	99.71 53	99.32 116	99.50 212	98.35 242	98.97 266	99.48 225	98.37 162	99.92 85	95.95 303	99.75 185	99.63 98
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MDA-MVSNet-bldmvs		99.06 173	99.05 159	99.07 249	99.80 68	97.83 290	98.89 224	99.72 102	99.29 125	99.63 135	99.70 120	96.47 261	99.89 128	98.17 181	99.82 154	99.50 175

MSLP-MVS++		99.05 176	99.09 147	98.91 262	99.21 297	98.36 259	98.82 238	99.47 221	98.85 187	98.90 279	99.56 203	98.78 100	99.09 362	98.57 149	99.68 211	99.26 240

1112_ss		99.05 176	98.84 197	99.67 86	99.66 156	99.29 165	98.52 266	99.82 47	97.65 282	99.43 188	99.16 287	96.42 263	99.91 95	99.07 107	99.84 135	99.80 25

ACMP	97.51 14	99.05 176	98.84 197	99.67 86	99.78 87	99.55 99	98.88 226	99.66 126	97.11 306	99.47 181	99.60 185	99.07 65	99.89 128	96.18 289	99.85 131	99.58 139
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PVSNet_BlendedMVS		99.03 179	99.01 169	99.09 245	99.54 203	97.99 284	98.58 256	99.82 47	97.62 283	99.34 216	99.71 113	98.52 148	99.77 284	97.98 192	99.97 46	99.52 166

IS-MVSNet		99.03 179	98.85 195	99.55 149	99.80 68	99.25 177	99.73 21	99.15 287	99.37 118	99.61 147	99.71 113	94.73 283	99.81 262	97.70 207	99.88 114	99.58 139

xiu_mvs_v2_base		99.02 181	99.11 138	98.77 277	99.37 262	98.09 280	98.13 300	99.51 209	99.47 99	99.42 190	98.54 343	99.38 27	99.97 16	98.83 130	99.33 277	98.24 328

Fast-Effi-MVS+		99.02 181	98.87 193	99.46 171	99.38 260	99.50 103	99.04 200	99.79 67	97.17 301	98.62 304	98.74 336	99.34 33	99.95 41	98.32 165	99.41 267	98.92 296

canonicalmvs		99.02 181	99.00 171	99.09 245	99.10 316	98.70 238	99.61 61	99.66 126	99.63 72	98.64 303	97.65 360	99.04 69	99.54 352	98.79 133	98.92 304	99.04 287

MCST-MVS		99.02 181	98.81 202	99.65 98	99.58 179	99.49 105	98.58 256	99.07 291	98.40 233	99.04 262	99.25 274	98.51 150	99.80 267	97.31 232	99.51 249	99.65 88

HSP-MVS		99.01 185	98.76 206	99.76 42	99.78 87	99.73 49	99.35 104	99.31 263	98.54 222	99.54 169	98.99 311	96.81 253	99.93 66	96.97 254	99.53 247	99.61 118

SD-MVS		99.01 185	99.30 104	98.15 307	99.50 219	99.40 135	98.94 222	99.61 150	99.22 143	99.75 93	99.82 58	99.54 21	95.51 368	97.48 223	99.87 121	99.54 155

LF4IMVS		99.01 185	98.92 186	99.27 219	99.71 134	99.28 167	98.59 255	99.77 72	98.32 248	99.39 201	99.41 238	98.62 130	99.84 218	96.62 274	99.84 135	98.69 307

MS-PatchMatch		99.00 188	98.97 179	99.09 245	99.11 314	98.19 272	98.76 245	99.33 257	98.49 226	99.44 184	99.58 193	98.21 175	99.69 313	98.20 175	99.62 225	99.39 213

PS-MVSNAJ		99.00 188	99.08 149	98.76 278	99.37 262	98.10 279	98.00 315	99.51 209	99.47 99	99.41 196	98.50 345	99.28 38	99.97 16	98.83 130	99.34 275	98.20 332

CNVR-MVS		98.99 190	98.80 204	99.56 146	99.25 292	99.43 126	98.54 264	99.27 271	98.58 218	98.80 287	99.43 234	98.53 146	99.70 307	97.22 241	99.59 231	99.54 155

VDDNet		98.97 191	98.82 201	99.42 183	99.71 134	98.81 234	99.62 57	98.68 309	99.81 28	99.38 208	99.80 63	94.25 287	99.85 202	98.79 133	99.32 278	99.59 135

IterMVS		98.97 191	99.16 126	98.42 295	99.74 117	95.64 335	98.06 310	99.83 39	99.83 25	99.85 57	99.74 96	96.10 271	99.99 4	99.27 81	100.00 1	99.63 98
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TinyColmap		98.97 191	98.93 183	99.07 249	99.46 239	98.19 272	97.75 332	99.75 84	98.79 195	99.54 169	99.70 120	98.97 74	99.62 344	96.63 273	99.83 145	99.41 209

HPM-MVS++		98.96 194	98.70 209	99.74 57	99.52 209	99.71 53	98.86 229	99.19 283	98.47 228	98.59 307	99.06 304	98.08 186	99.91 95	96.94 255	99.60 230	99.60 124

lupinMVS		98.96 194	98.87 193	99.24 230	99.57 188	98.40 255	98.12 301	99.18 284	98.28 250	99.63 135	99.13 289	98.02 190	99.97 16	98.22 173	99.69 209	99.35 226

USDC		98.96 194	98.93 183	99.05 251	99.54 203	97.99 284	97.07 352	99.80 59	98.21 254	99.75 93	99.77 86	98.43 157	99.64 342	97.90 195	99.88 114	99.51 169

YYNet1		98.95 197	98.99 175	98.84 271	99.64 162	97.14 309	98.22 292	99.32 259	98.92 181	99.59 150	99.66 152	97.40 230	99.83 235	98.27 170	99.90 102	99.55 147

MDA-MVSNet_test_wron		98.95 197	98.99 175	98.85 269	99.64 162	97.16 308	98.23 291	99.33 257	98.93 179	99.56 161	99.66 152	97.39 232	99.83 235	98.29 168	99.88 114	99.55 147

Test_1112_low_res		98.95 197	98.73 207	99.63 110	99.68 150	99.15 196	98.09 305	99.80 59	97.14 303	99.46 183	99.40 239	96.11 270	99.89 128	99.01 111	99.84 135	99.84 15

test1235678		98.93 200	98.84 197	99.19 236	99.46 239	98.55 245	97.53 341	99.77 72	98.76 201	99.69 114	99.48 225	96.69 254	99.90 114	98.30 167	99.91 100	99.11 270

CANet_DTU		98.91 201	98.85 195	99.09 245	98.79 341	98.13 275	98.18 294	99.31 263	99.48 95	98.86 282	99.51 218	96.56 257	99.95 41	99.05 108	99.95 66	99.19 252

HyFIR lowres test		98.91 201	98.64 214	99.73 63	99.85 38	99.47 109	98.07 309	99.83 39	98.64 212	99.89 38	99.60 185	92.57 301	100.00 1	99.33 68	99.97 46	99.72 47

HQP_MVS		98.90 203	98.68 211	99.55 149	99.58 179	99.24 180	98.80 240	99.54 191	98.94 177	99.14 251	99.25 274	97.24 238	99.82 243	95.84 306	99.78 176	99.60 124

sss		98.90 203	98.77 205	99.27 219	99.48 230	98.44 251	98.72 249	99.32 259	97.94 267	99.37 209	99.35 254	96.31 265	99.91 95	98.85 129	99.63 224	99.47 188

OMC-MVS		98.90 203	98.72 208	99.44 178	99.39 257	99.42 130	98.58 256	99.64 140	97.31 298	99.44 184	99.62 173	98.59 134	99.69 313	96.17 290	99.79 170	99.22 245

ppachtmachnet_test		98.89 206	99.12 135	98.20 305	99.66 156	95.24 341	97.63 335	99.68 117	99.08 163	99.78 82	99.62 173	98.65 124	99.88 143	98.02 188	99.96 58	99.48 183

new_pmnet		98.88 207	98.89 191	98.84 271	99.70 141	97.62 298	98.15 297	99.50 212	97.98 264	99.62 142	99.54 210	98.15 181	99.94 54	97.55 219	99.84 135	98.95 293

K. test v3		98.87 208	98.60 216	99.69 80	99.93 17	99.46 113	99.74 19	94.97 364	99.78 34	99.88 46	99.88 34	93.66 291	99.97 16	99.61 38	99.95 66	99.64 94

APD-MVS		98.87 208	98.59 217	99.71 73	99.50 219	99.62 84	99.01 205	99.57 180	96.80 312	99.54 169	99.63 166	98.29 167	99.91 95	95.24 327	99.71 206	99.61 118
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
our_test_3		98.85 210	99.09 147	98.13 308	99.66 156	94.90 344	97.72 333	99.58 177	99.07 165	99.64 131	99.62 173	98.19 178	99.93 66	98.41 157	99.95 66	99.55 147

mvs-test1		98.83 211	98.70 209	99.22 232	98.89 330	99.65 76	98.88 226	99.66 126	99.34 121	98.29 321	98.94 322	97.69 214	99.96 33	98.11 184	98.54 335	98.04 336

UnsupCasMVSNet_eth		98.83 211	98.57 220	99.59 130	99.68 150	99.45 118	98.99 212	99.67 122	99.48 95	99.55 166	99.36 249	94.92 280	99.86 184	98.95 123	96.57 360	99.45 194

test_normal		98.82 213	98.67 212	99.27 219	99.56 200	98.83 233	98.22 292	98.01 329	99.03 169	99.49 180	99.24 279	96.21 267	99.76 286	98.69 143	99.56 235	99.22 245

NCCC		98.82 213	98.57 220	99.58 134	99.21 297	99.31 160	98.61 252	99.25 276	98.65 211	98.43 317	99.26 272	97.86 202	99.81 262	96.55 276	99.27 286	99.61 118

PMVS	92.94 21	98.82 213	98.81 202	98.85 269	99.84 41	97.99 284	99.20 156	99.47 221	99.71 48	99.42 190	99.82 58	98.09 184	99.47 356	93.88 342	99.85 131	99.07 284
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
DI_MVS_plusplus_test		98.80 216	98.65 213	99.27 219	99.57 188	98.90 225	98.44 277	97.95 332	99.02 170	99.51 176	99.23 282	96.18 269	99.76 286	98.52 153	99.42 265	99.14 264

FMVSNet3		98.80 216	98.63 215	99.32 211	99.13 309	98.72 237	99.10 188	99.48 217	99.23 140	99.62 142	99.64 158	92.57 301	99.86 184	98.96 119	99.90 102	99.39 213

Patchmtry		98.78 218	98.54 223	99.49 163	98.89 330	99.19 192	99.32 116	99.67 122	99.65 67	99.72 105	99.79 70	91.87 307	99.95 41	98.00 191	99.97 46	99.33 229

Vis-MVSNet (Re-imp)		98.77 219	98.58 219	99.34 205	99.78 87	98.88 227	99.61 61	99.56 183	99.11 158	99.24 234	99.56 203	93.00 299	99.78 278	97.43 226	99.89 108	99.35 226

CLD-MVS		98.76 220	98.57 220	99.33 207	99.57 188	98.97 214	97.53 341	99.55 186	96.41 321	99.27 228	99.13 289	99.07 65	99.78 278	96.73 268	99.89 108	99.23 244
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Anonymous202405211		98.75 221	98.46 226	99.63 110	99.34 275	99.66 71	99.47 83	97.65 340	99.28 128	99.56 161	99.50 221	93.15 295	99.84 218	98.62 147	99.58 233	99.40 210

CPTT-MVS		98.74 222	98.44 228	99.64 106	99.61 171	99.38 144	99.18 159	99.55 186	96.49 320	99.27 228	99.37 244	97.11 246	99.92 85	95.74 310	99.67 216	99.62 112

F-COLMAP		98.74 222	98.45 227	99.62 119	99.57 188	99.47 109	98.84 233	99.65 135	96.31 322	98.93 274	99.19 286	97.68 216	99.87 163	96.52 277	99.37 273	99.53 158

N_pmnet		98.73 224	98.53 224	99.35 204	99.72 131	98.67 240	98.34 284	94.65 365	98.35 242	99.79 79	99.68 139	98.03 188	99.93 66	98.28 169	99.92 90	99.44 199

PVSNet_Blended		98.70 225	98.59 217	99.02 254	99.54 203	97.99 284	97.58 338	99.82 47	95.70 333	99.34 216	98.98 314	98.52 148	99.77 284	97.98 192	99.83 145	99.30 236

PatchMatch-RL		98.68 226	98.47 225	99.30 216	99.44 244	99.28 167	98.14 299	99.54 191	97.12 305	99.11 254	99.25 274	97.80 207	99.70 307	96.51 278	99.30 280	98.93 295

Test4		98.65 227	98.44 228	99.27 219	99.57 188	98.86 230	98.43 278	99.41 235	98.85 187	99.57 153	98.95 321	93.05 297	99.75 292	98.57 149	99.56 235	99.19 252

test_prior3		98.62 228	98.34 241	99.46 171	99.35 265	99.22 184	97.95 322	99.39 244	97.87 270	98.05 334	99.05 305	97.90 198	99.69 313	95.99 299	99.49 252	99.48 183

CVMVSNet		98.61 229	98.88 192	97.80 321	99.58 179	93.60 349	99.26 139	99.64 140	99.66 64	99.72 105	99.67 146	93.26 294	99.93 66	99.30 74	99.81 162	99.87 10

Patchmatch-RL test		98.60 230	98.36 239	99.33 207	99.77 97	99.07 207	98.27 288	99.87 19	98.91 182	99.74 101	99.72 106	90.57 323	99.79 270	98.55 151	99.85 131	99.11 270

AdaColmap		98.60 230	98.35 240	99.38 196	99.12 311	99.22 184	98.67 251	99.42 234	97.84 274	98.81 285	99.27 270	97.32 236	99.81 262	95.14 328	99.53 247	99.10 274

WTY-MVS		98.59 232	98.37 238	99.26 224	99.43 246	98.40 255	98.74 246	99.13 290	98.10 258	99.21 241	99.24 279	94.82 282	99.90 114	97.86 198	98.77 315	99.49 181

CNLPA		98.57 233	98.34 241	99.28 217	99.18 303	99.10 202	98.34 284	99.41 235	98.48 227	98.52 311	98.98 314	97.05 248	99.78 278	95.59 318	99.50 250	98.96 292

1121		98.56 234	98.24 246	99.52 156	99.49 224	99.24 180	99.30 126	99.22 281	95.77 331	98.52 311	99.29 267	97.39 232	99.85 202	95.79 308	99.34 275	99.46 192

CDPH-MVS		98.56 234	98.20 250	99.61 122	99.50 219	99.46 113	98.32 286	99.41 235	95.22 339	99.21 241	99.10 295	98.34 164	99.82 243	95.09 330	99.66 219	99.56 144

UnsupCasMVSNet_bld		98.55 236	98.27 245	99.40 191	99.56 200	99.37 147	97.97 321	99.68 117	97.49 290	99.08 256	99.35 254	95.41 279	99.82 243	97.70 207	98.19 346	99.01 290

RPMNet		98.53 237	98.44 228	98.83 273	99.05 320	98.12 276	99.30 126	98.78 304	99.86 15	99.16 247	99.74 96	92.53 303	99.91 95	98.75 137	98.77 315	98.44 319

MG-MVS		98.52 238	98.39 235	98.94 258	99.15 306	97.39 305	98.18 294	99.21 282	98.89 183	99.23 235	99.63 166	97.37 234	99.74 296	94.22 338	99.61 229	99.69 57

DP-MVS Recon		98.50 239	98.23 247	99.31 214	99.49 224	99.46 113	98.56 260	99.63 143	94.86 345	98.85 283	99.37 244	97.81 206	99.59 349	96.08 292	99.44 258	98.88 298

CMPMVS	77.52 23	98.50 239	98.19 253	99.41 190	98.33 357	99.56 96	99.01 205	99.59 169	95.44 336	99.57 153	99.80 63	95.64 275	99.46 359	96.47 281	99.92 90	99.21 248
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
114514_t		98.49 241	98.11 256	99.64 106	99.73 120	99.58 93	99.24 144	99.76 79	89.94 360	99.42 190	99.56 203	97.76 210	99.86 184	97.74 205	99.82 154	99.47 188

PMMVS		98.49 241	98.29 244	99.11 242	98.96 323	98.42 253	97.54 339	99.32 259	97.53 289	98.47 316	98.15 350	97.88 201	99.82 243	97.46 224	99.24 289	99.09 277

MVSTER		98.47 243	98.22 248	99.24 230	99.06 319	98.35 260	99.08 195	99.46 224	99.27 129	99.75 93	99.66 152	88.61 333	99.85 202	99.14 101	99.92 90	99.52 166

LFMVS		98.46 244	98.19 253	99.26 224	99.24 294	98.52 247	99.62 57	96.94 349	99.87 13	99.31 223	99.58 193	91.04 314	99.81 262	98.68 145	99.42 265	99.45 194

PatchT		98.45 245	98.32 243	98.83 273	98.94 324	98.29 267	99.24 144	98.82 302	99.84 22	99.08 256	99.76 90	91.37 310	99.94 54	98.82 132	99.00 301	98.26 326

test12356		98.43 246	98.39 235	98.55 289	99.46 239	96.36 318	97.32 348	99.81 55	97.60 284	99.62 142	99.37 244	94.57 284	99.89 128	97.80 202	99.92 90	99.40 210

MIMVSNet		98.43 246	98.20 250	99.11 242	99.53 206	98.38 258	99.58 68	98.61 313	98.96 175	99.33 218	99.76 90	90.92 316	99.81 262	97.38 229	99.76 182	99.15 260

PVSNet	97.47 15	98.42 248	98.44 228	98.35 299	99.46 239	96.26 319	96.70 357	99.34 256	97.68 281	99.00 264	99.13 289	97.40 230	99.72 300	97.59 218	99.68 211	99.08 280

CHOSEN 280x420		98.41 249	98.41 233	98.40 297	99.34 275	95.89 329	96.94 353	99.44 229	98.80 194	99.25 231	99.52 214	93.51 292	99.98 7	98.94 124	99.98 36	99.32 234

BH-RMVSNet		98.41 249	98.14 255	99.21 233	99.21 297	98.47 248	98.60 254	98.26 326	98.35 242	98.93 274	99.31 260	97.20 243	99.66 333	94.32 336	99.10 295	99.51 169

QAPM		98.40 251	97.99 262	99.65 98	99.39 257	99.47 109	99.67 46	99.52 206	91.70 357	98.78 290	99.80 63	98.55 140	99.95 41	94.71 334	99.75 185	99.53 158

API-MVS		98.38 252	98.39 235	98.35 299	98.83 336	99.26 173	99.14 179	99.18 284	98.59 217	98.66 302	98.78 333	98.61 132	99.57 351	94.14 339	99.56 235	96.21 361

HQP-MVS		98.36 253	98.02 261	99.39 194	99.31 282	98.94 217	97.98 318	99.37 251	97.45 291	98.15 328	98.83 329	96.67 255	99.70 307	94.73 332	99.67 216	99.53 158

PAPM_NR		98.36 253	98.04 260	99.33 207	99.48 230	98.93 222	98.79 243	99.28 270	97.54 288	98.56 310	98.57 341	97.12 245	99.69 313	94.09 340	98.90 306	99.38 216

PLC	97.35 16	98.36 253	97.99 262	99.48 166	99.32 281	99.24 180	98.50 268	99.51 209	95.19 341	98.58 308	98.96 319	96.95 251	99.83 235	95.63 317	99.25 287	99.37 220
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
train_agg		98.35 256	97.95 266	99.57 140	99.35 265	99.35 154	98.11 303	99.41 235	94.90 343	97.92 339	98.99 311	98.02 190	99.85 202	95.38 325	99.44 258	99.50 175

CR-MVSNet		98.35 256	98.20 250	98.83 273	99.05 320	98.12 276	99.30 126	99.67 122	97.39 295	99.16 247	99.79 70	91.87 307	99.91 95	98.78 136	98.77 315	98.44 319

LP		98.34 258	98.44 228	98.05 310	98.88 333	95.31 340	99.28 135	98.74 306	99.12 157	98.98 265	99.79 70	93.40 293	99.93 66	98.38 159	99.41 267	98.90 297

agg_prior1		98.33 259	97.92 270	99.57 140	99.35 265	99.36 150	97.99 317	99.39 244	94.85 346	97.76 349	98.98 314	98.03 188	99.85 202	95.49 320	99.44 258	99.51 169

alignmvs		98.28 260	97.96 265	99.25 228	99.12 311	98.93 222	99.03 202	98.42 322	99.64 69	98.72 295	97.85 353	90.86 319	99.62 344	98.88 128	99.13 293	99.19 252

0601test		98.25 261	97.95 266	99.13 240	99.17 304	98.47 248	99.00 207	98.67 311	98.97 173	99.22 239	99.02 309	91.31 311	99.69 313	97.26 236	98.93 302	99.24 242

Anonymous20240521		98.25 261	97.95 266	99.13 240	99.17 304	98.47 248	99.00 207	98.67 311	98.97 173	99.22 239	99.02 309	91.31 311	99.69 313	97.26 236	98.93 302	99.24 242

agg_prior3		98.24 263	97.81 276	99.53 154	99.34 275	99.26 173	98.09 305	99.39 244	94.21 351	97.77 348	98.96 319	97.74 211	99.84 218	95.38 325	99.44 258	99.50 175

MAR-MVS		98.24 263	97.92 270	99.19 236	98.78 343	99.65 76	99.17 166	99.14 288	95.36 337	98.04 336	98.81 331	97.47 227	99.72 300	95.47 322	99.06 296	98.21 330
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
OpenMVS	98.12 10	98.23 265	97.89 274	99.26 224	99.19 301	99.26 173	99.65 54	99.69 114	91.33 358	98.14 332	99.77 86	98.28 168	99.96 33	95.41 324	99.55 241	98.58 313

BH-untuned		98.22 266	98.09 257	98.58 288	99.38 260	97.24 307	98.55 261	98.98 297	97.81 276	99.20 246	98.76 334	97.01 249	99.65 340	94.83 331	98.33 341	98.86 300

HY-MVS	98.23 9	98.21 267	97.95 266	98.99 255	99.03 322	98.24 268	99.61 61	98.72 307	96.81 311	98.73 294	99.51 218	94.06 288	99.86 184	96.91 256	98.20 344	98.86 300

testus		98.15 268	98.06 259	98.40 297	99.11 314	95.95 324	96.77 355	99.89 14	95.83 329	99.23 235	98.47 346	97.50 226	99.84 218	96.58 275	99.20 292	99.39 213

Patchmatch-test1		98.13 269	98.40 234	97.31 335	99.20 300	92.99 351	98.17 296	98.49 319	98.24 252	99.10 255	99.52 214	96.01 272	99.83 235	97.22 241	99.62 225	99.12 269

EPNet		98.13 269	97.77 280	99.18 239	94.57 370	97.99 284	99.24 144	97.96 330	99.74 40	97.29 355	99.62 173	93.13 296	99.97 16	98.59 148	99.83 145	99.58 139
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Patchmatch-test		98.10 271	97.98 264	98.48 294	99.27 291	96.48 316	99.40 90	99.07 291	98.81 192	99.23 235	99.57 199	90.11 327	99.87 163	96.69 269	99.64 223	99.09 277

pmmvs3		98.08 272	97.80 277	98.91 262	99.41 253	97.69 296	97.87 329	99.66 126	95.87 328	99.50 178	99.51 218	90.35 325	99.97 16	98.55 151	99.47 254	99.08 280

JIA-IIPM		98.06 273	97.92 270	98.50 293	98.59 351	97.02 310	98.80 240	98.51 317	99.88 12	97.89 341	99.87 37	91.89 306	99.90 114	98.16 182	97.68 356	98.59 311

TAPA-MVS	97.92 13	98.03 274	97.55 286	99.46 171	99.47 235	99.44 120	98.50 268	99.62 146	86.79 361	99.07 260	99.26 272	98.26 170	99.62 344	97.28 235	99.73 200	99.31 235
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
1314		98.00 275	97.90 273	98.27 304	98.90 326	97.45 303	99.30 126	99.06 293	94.98 342	97.21 356	99.12 293	98.43 157	99.67 328	95.58 319	98.56 334	97.71 348

GA-MVS		97.99 276	97.68 283	98.93 261	99.52 209	98.04 283	97.19 351	99.05 294	98.32 248	98.81 285	98.97 317	89.89 330	99.41 360	98.33 164	99.05 297	99.34 228

MVS-HIRNet		97.86 277	98.22 248	96.76 339	99.28 289	91.53 361	98.38 281	92.60 369	99.13 156	99.31 223	99.96 10	97.18 244	99.68 323	98.34 163	99.83 145	99.07 284

FMVSNet5		97.80 278	97.25 289	99.42 183	98.83 336	98.97 214	99.38 97	99.80 59	98.87 185	99.25 231	99.69 126	80.60 368	99.91 95	98.96 119	99.90 102	99.38 216

ADS-MVSNet2		97.78 279	97.66 285	98.12 309	99.14 307	95.36 338	99.22 151	98.75 305	96.97 307	98.25 324	99.64 158	90.90 317	99.94 54	96.51 278	99.56 235	99.08 280

tpmrst		97.73 280	98.07 258	96.73 341	98.71 348	92.00 355	99.10 188	98.86 299	98.52 223	98.92 276	99.54 210	91.90 305	99.82 243	98.02 188	99.03 299	98.37 321

ADS-MVSNet		97.72 281	97.67 284	97.86 319	99.14 307	94.65 345	99.22 151	98.86 299	96.97 307	98.25 324	99.64 158	90.90 317	99.84 218	96.51 278	99.56 235	99.08 280

PatchmatchNet		97.65 282	97.80 277	97.18 336	98.82 339	92.49 353	99.17 166	98.39 323	98.12 257	98.79 288	99.58 193	90.71 321	99.89 128	97.23 240	99.41 267	99.16 258
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tttt0517		97.62 283	97.20 290	98.90 267	99.76 102	97.40 304	99.48 80	94.36 366	99.06 167	99.70 111	99.49 224	84.55 359	99.94 54	98.73 139	99.65 221	99.36 223

EPNet_dtu		97.62 283	97.79 279	97.11 338	96.67 369	92.31 354	98.51 267	98.04 327	99.24 138	95.77 364	99.47 228	93.78 290	99.66 333	98.98 114	99.62 225	99.37 220
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
wuyk23d		97.58 285	99.13 132	92.93 353	99.69 143	99.49 105	99.52 74	99.77 72	97.97 265	99.96 8	99.79 70	99.84 4	99.94 54	95.85 305	99.82 154	79.36 365

PAPR		97.56 286	97.07 292	99.04 252	98.80 340	98.11 278	97.63 335	99.25 276	94.56 349	98.02 337	98.25 349	97.43 229	99.68 323	90.90 349	98.74 319	99.33 229

thisisatest0530		97.45 287	96.95 297	98.94 258	99.68 150	97.73 292	99.09 192	94.19 368	98.61 216	99.56 161	99.30 263	84.30 360	99.93 66	98.27 170	99.54 246	99.16 258

TR-MVS		97.44 288	97.15 291	98.32 301	98.53 353	97.46 302	98.47 271	97.91 333	96.85 309	98.21 327	98.51 344	96.42 263	99.51 354	92.16 345	97.29 357	97.98 341

tpmvs		97.39 289	97.69 282	96.52 345	98.41 355	91.76 358	99.30 126	98.94 298	97.74 277	97.85 344	99.55 208	92.40 304	99.73 298	96.25 288	98.73 321	98.06 335

test0.0.03 1		97.37 290	96.91 300	98.74 283	97.72 363	97.57 299	97.60 337	97.36 348	98.00 261	99.21 241	98.02 351	90.04 328	99.79 270	98.37 160	95.89 363	98.86 300

OpenMVS_ROB	97.31 17	97.36 291	96.84 301	98.89 268	99.29 287	99.45 118	98.87 228	99.48 217	86.54 363	99.44 184	99.74 96	97.34 235	99.86 184	91.61 346	99.28 282	97.37 353

1111		97.29 292	96.71 311	99.04 252	99.65 160	97.72 293	98.35 282	99.80 59	99.40 114	99.66 123	99.43 234	75.10 372	99.87 163	98.98 114	99.98 36	99.52 166

tfpn1000		97.28 293	96.83 302	98.64 287	99.67 155	97.68 297	99.41 88	95.47 362	97.14 303	99.43 188	99.07 303	85.87 355	99.88 143	96.78 264	98.67 323	98.34 323

thresconf0.02		97.25 294	96.74 305	98.75 279	99.73 120	98.35 260	99.35 104	95.78 355	96.54 314	99.39 201	99.08 296	86.57 348	99.88 143	95.69 311	98.57 327	98.02 337

tfpn_n400		97.25 294	96.74 305	98.75 279	99.73 120	98.35 260	99.35 104	95.78 355	96.54 314	99.39 201	99.08 296	86.57 348	99.88 143	95.69 311	98.57 327	98.02 337

tfpnconf		97.25 294	96.74 305	98.75 279	99.73 120	98.35 260	99.35 104	95.78 355	96.54 314	99.39 201	99.08 296	86.57 348	99.88 143	95.69 311	98.57 327	98.02 337

tfpnview11		97.25 294	96.74 305	98.75 279	99.73 120	98.35 260	99.35 104	95.78 355	96.54 314	99.39 201	99.08 296	86.57 348	99.88 143	95.69 311	98.57 327	98.02 337

BH-w/o		97.20 298	97.01 295	97.76 322	99.08 317	95.69 334	98.03 312	98.52 316	95.76 332	97.96 338	98.02 351	95.62 276	99.47 356	92.82 344	97.25 358	98.12 334

conf0.01		97.19 299	96.74 305	98.51 290	99.73 120	98.35 260	99.35 104	95.78 355	96.54 314	99.39 201	99.08 296	86.57 348	99.88 143	95.69 311	98.57 327	97.30 354

conf0.002		97.19 299	96.74 305	98.51 290	99.73 120	98.35 260	99.35 104	95.78 355	96.54 314	99.39 201	99.08 296	86.57 348	99.88 143	95.69 311	98.57 327	97.30 354

test-LLR		97.15 301	96.95 297	97.74 324	98.18 360	95.02 342	97.38 344	96.10 351	98.00 261	97.81 345	98.58 339	90.04 328	99.91 95	97.69 212	98.78 313	98.31 324

tpm		97.15 301	96.95 297	97.75 323	98.91 325	94.24 347	99.32 116	97.96 330	97.71 279	98.29 321	99.32 258	86.72 346	99.92 85	98.10 186	96.24 362	99.09 277

E-PMN		97.14 303	97.43 287	96.27 347	98.79 341	91.62 360	95.54 361	99.01 296	99.44 106	98.88 280	99.12 293	92.78 300	99.68 323	94.30 337	99.03 299	97.50 350

PNet_i23d		97.02 304	97.87 275	94.49 352	99.69 143	84.81 371	95.18 364	99.85 28	97.83 275	99.32 220	99.57 199	95.53 278	99.47 356	96.09 291	97.74 355	99.18 255

cascas		96.99 305	96.82 303	97.48 329	97.57 366	95.64 335	96.43 359	99.56 183	91.75 356	97.13 357	97.61 361	95.58 277	98.63 365	96.68 270	99.11 294	98.18 333

thisisatest0515		96.98 306	96.42 317	98.66 286	99.42 250	97.47 301	97.27 349	94.30 367	97.24 300	99.15 249	98.86 328	85.01 357	99.87 163	97.10 248	99.39 270	98.63 308

EMVS		96.96 307	97.28 288	95.99 351	98.76 345	91.03 363	95.26 363	98.61 313	99.34 121	98.92 276	98.88 327	93.79 289	99.66 333	92.87 343	99.05 297	97.30 354

PatchFormer-LS_test		96.95 308	97.07 292	96.62 344	98.76 345	91.85 357	99.18 159	98.45 321	97.29 299	97.73 351	97.22 369	88.77 332	99.76 286	98.13 183	98.04 350	98.25 327

tfpn_ndepth		96.93 309	96.43 316	98.42 295	99.60 173	97.72 293	99.22 151	95.16 363	95.91 327	99.26 230	98.79 332	85.56 356	99.87 163	96.03 296	98.35 340	97.68 349

view600		96.86 310	96.52 312	97.88 315	99.69 143	95.87 330	99.39 91	97.68 336	99.11 158	98.96 268	97.82 355	87.40 334	99.79 270	89.78 350	98.83 308	97.98 341

view800		96.86 310	96.52 312	97.88 315	99.69 143	95.87 330	99.39 91	97.68 336	99.11 158	98.96 268	97.82 355	87.40 334	99.79 270	89.78 350	98.83 308	97.98 341

conf0.05thres1000		96.86 310	96.52 312	97.88 315	99.69 143	95.87 330	99.39 91	97.68 336	99.11 158	98.96 268	97.82 355	87.40 334	99.79 270	89.78 350	98.83 308	97.98 341

tfpn		96.86 310	96.52 312	97.88 315	99.69 143	95.87 330	99.39 91	97.68 336	99.11 158	98.96 268	97.82 355	87.40 334	99.79 270	89.78 350	98.83 308	97.98 341

dp		96.86 310	97.07 292	96.24 349	98.68 350	90.30 368	99.19 158	98.38 324	97.35 297	98.23 326	99.59 191	87.23 338	99.82 243	96.27 287	98.73 321	98.59 311

tpm cat1		96.78 315	96.98 296	96.16 350	98.85 335	90.59 367	99.08 195	99.32 259	92.37 355	97.73 351	99.46 231	91.15 313	99.69 313	96.07 293	98.80 312	98.21 330

PCF-MVS	96.03 18	96.73 316	95.86 328	99.33 207	99.44 244	99.16 194	96.87 354	99.44 229	86.58 362	98.95 272	99.40 239	94.38 286	99.88 143	87.93 358	99.80 167	98.95 293
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CostFormer		96.71 317	96.79 304	96.46 346	98.90 326	90.71 365	99.41 88	98.68 309	94.69 348	98.14 332	99.34 257	86.32 354	99.80 267	97.60 217	98.07 349	98.88 298

MVE	92.54 22	96.66 318	96.11 322	98.31 302	99.68 150	97.55 300	97.94 324	95.60 361	99.37 118	90.68 368	98.70 337	96.56 257	98.61 366	86.94 364	99.55 241	98.77 305
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
thres600view7		96.60 319	96.16 320	97.93 313	99.63 164	96.09 323	99.18 159	97.57 341	98.77 198	98.72 295	97.32 364	87.04 339	99.72 300	88.57 355	98.62 325	97.98 341

EPMVS		96.53 320	96.32 318	97.17 337	98.18 360	92.97 352	99.39 91	89.95 371	98.21 254	98.61 305	99.59 191	86.69 347	99.72 300	96.99 253	99.23 291	98.81 303

tfpn111		96.50 321	96.12 321	97.65 326	99.63 164	95.93 325	99.18 159	97.57 341	98.75 203	98.70 297	97.31 365	87.04 339	99.72 300	88.27 357	98.61 326	97.30 354

conf200view11		96.43 322	96.03 324	97.63 327	99.63 164	95.93 325	99.18 159	97.57 341	98.75 203	98.70 297	97.31 365	87.04 339	99.67 328	87.62 359	98.51 336	97.30 354

thres400		96.40 323	95.89 326	97.92 314	99.58 179	96.11 321	99.00 207	97.54 346	98.43 229	98.52 311	96.98 370	86.85 343	99.67 328	87.62 359	98.51 336	97.98 341

thres100view900		96.39 324	96.03 324	97.47 330	99.63 164	95.93 325	99.18 159	97.57 341	98.75 203	98.70 297	97.31 365	87.04 339	99.67 328	87.62 359	98.51 336	96.81 359

tpm2		96.35 325	96.22 319	96.73 341	98.88 333	91.75 359	99.21 155	98.51 317	93.27 354	97.89 341	99.21 284	84.83 358	99.70 307	96.04 295	98.18 347	98.75 306

FPMVS		96.32 326	95.50 333	98.79 276	99.60 173	98.17 274	98.46 275	98.80 303	97.16 302	96.28 360	99.63 166	82.19 363	99.09 362	88.45 356	98.89 307	99.10 274

tfpn200view9		96.30 327	95.89 326	97.53 328	99.58 179	96.11 321	99.00 207	97.54 346	98.43 229	98.52 311	96.98 370	86.85 343	99.67 328	87.62 359	98.51 336	96.81 359

TESTMET0.1,1		96.24 328	95.84 329	97.41 332	98.24 358	93.84 348	97.38 344	95.84 354	98.43 229	97.81 345	98.56 342	79.77 369	99.89 128	97.77 203	98.77 315	98.52 315

test-mter		96.23 329	95.73 331	97.74 324	98.18 360	95.02 342	97.38 344	96.10 351	97.90 268	97.81 345	98.58 339	79.12 370	99.91 95	97.69 212	98.78 313	98.31 324

tpmp4_e23		96.11 330	96.06 323	96.27 347	98.90 326	90.70 366	99.34 111	99.03 295	93.72 352	96.56 359	99.31 260	83.63 361	99.75 292	96.06 294	98.02 351	98.35 322

X-MVStestdata		96.09 331	94.87 339	99.75 52	99.71 134	99.71 53	99.37 101	99.61 150	99.29 125	98.76 292	61.30 373	98.47 153	99.88 143	97.62 214	99.73 200	99.67 70

thres200		96.09 331	95.68 332	97.33 334	99.48 230	96.22 320	98.53 265	97.57 341	98.06 260	98.37 319	96.73 372	86.84 345	99.61 348	86.99 363	98.57 327	96.16 362

DWT-MVSNet_test		96.03 333	95.80 330	96.71 343	98.50 354	91.93 356	99.25 143	97.87 334	95.99 326	96.81 358	97.61 361	81.02 365	99.66 333	97.20 244	97.98 352	98.54 314

test2356		95.99 334	95.26 337	98.18 306	96.93 368	95.53 337	95.31 362	98.71 308	95.67 334	98.48 315	97.83 354	80.72 366	99.88 143	95.47 322	98.21 343	99.11 270

gg-mvs-nofinetune		95.87 335	95.17 338	97.97 312	98.19 359	96.95 311	99.69 38	89.23 372	99.89 10	96.24 362	99.94 12	81.19 364	99.51 354	93.99 341	98.20 344	97.44 351

PVSNet_0	95.53 19	95.85 336	95.31 335	97.47 330	98.78 343	93.48 350	95.72 360	99.40 241	96.18 324	97.37 353	97.73 359	95.73 274	99.58 350	95.49 320	81.40 365	99.36 223

tmp_tt		95.75 337	95.42 334	96.76 339	89.90 371	94.42 346	98.86 229	97.87 334	78.01 364	99.30 227	99.69 126	97.70 212	95.89 367	99.29 78	98.14 348	99.95 1

MVS		95.72 338	94.63 341	98.99 255	98.56 352	97.98 289	99.30 126	98.86 299	72.71 366	97.30 354	99.08 296	98.34 164	99.74 296	89.21 354	98.33 341	99.26 240

PAPM		95.61 339	94.71 340	98.31 302	99.12 311	96.63 314	96.66 358	98.46 320	90.77 359	96.25 361	98.68 338	93.01 298	99.69 313	81.60 365	97.86 354	98.62 309

IB-MVS	95.41 20	95.30 340	94.46 342	97.84 320	98.76 345	95.33 339	97.33 347	96.07 353	96.02 325	95.37 366	97.41 363	76.17 371	99.96 33	97.54 220	95.44 364	98.22 329
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
testpf		94.48 341	95.31 335	91.99 354	97.22 367	89.64 369	98.86 229	96.52 350	94.36 350	96.09 363	98.76 334	82.21 362	98.73 364	97.05 251	96.74 359	87.60 364

.test1245		85.84 342	89.27 343	75.54 355	99.65 160	97.72 293	98.35 282	99.80 59	99.40 114	99.66 123	99.43 234	75.10 372	99.87 163	98.98 114	33.07 366	29.03 367

pcd1.5k->3k		49.97 343	55.52 344	33.31 356	99.95 12	0.00 374	0.00 365	99.81 55	0.00 369	0.00 371	100.00 1	99.96 1	0.00 371	0.00 368	100.00 1	99.92 3

v1.0		41.33 344	55.11 345	0.00 359	99.62 169	0.00 374	0.00 365	99.53 196	97.71 279	99.55 166	99.57 199	0.00 376	0.00 371	0.00 368	0.00 369	0.00 369

test123		29.31 345	33.05 348	18.08 357	25.93 373	12.24 372	97.53 341	10.93 375	11.78 367	24.21 369	50.08 377	21.04 374	8.60 369	23.51 366	32.43 368	33.39 366

testmvs		28.94 346	33.33 346	15.79 358	26.03 372	9.81 373	96.77 355	15.67 374	11.55 368	23.87 370	50.74 376	19.03 375	8.53 370	23.21 367	33.07 366	29.03 367

cdsmvs_eth3d_5k		24.88 347	33.17 347	0.00 359	0.00 374	0.00 374	0.00 365	99.62 146	0.00 369	0.00 371	99.13 289	99.82 6	0.00 371	0.00 368	0.00 369	0.00 369

pcd_1.5k_mvsjas		16.61 348	22.14 349	0.00 359	0.00 374	0.00 374	0.00 365	0.00 376	0.00 369	0.00 371	100.00 1	99.28 38	0.00 371	0.00 368	0.00 369	0.00 369

sosnet-low-res		8.33 349	11.11 350	0.00 359	0.00 374	0.00 374	0.00 365	0.00 376	0.00 369	0.00 371	100.00 1	0.00 376	0.00 371	0.00 368	0.00 369	0.00 369

sosnet		8.33 349	11.11 350	0.00 359	0.00 374	0.00 374	0.00 365	0.00 376	0.00 369	0.00 371	100.00 1	0.00 376	0.00 371	0.00 368	0.00 369	0.00 369

uncertanet		8.33 349	11.11 350	0.00 359	0.00 374	0.00 374	0.00 365	0.00 376	0.00 369	0.00 371	100.00 1	0.00 376	0.00 371	0.00 368	0.00 369	0.00 369

Regformer		8.33 349	11.11 350	0.00 359	0.00 374	0.00 374	0.00 365	0.00 376	0.00 369	0.00 371	100.00 1	0.00 376	0.00 371	0.00 368	0.00 369	0.00 369

uanet		8.33 349	11.11 350	0.00 359	0.00 374	0.00 374	0.00 365	0.00 376	0.00 369	0.00 371	100.00 1	0.00 376	0.00 371	0.00 368	0.00 369	0.00 369

ab-mvs-re		8.26 354	11.02 355	0.00 359	0.00 374	0.00 374	0.00 365	0.00 376	0.00 369	0.00 371	99.16 287	0.00 376	0.00 371	0.00 368	0.00 369	0.00 369

GSMVS																99.14 264

test_part2					99.62 169	99.67 69				99.55 166

test_part1				0.00 359		0.00 374	0.00 365	99.53 196				0.00 376	0.00 371	0.00 368	0.00 369	0.00 369

sam_mvs1												90.81 320				99.14 264

sam_mvs												90.52 324

semantic-postprocess				98.51 290	99.75 111	95.90 328		99.84 36	99.84 22	99.89 38	99.73 100	95.96 273	99.99 4	99.33 68	100.00 1	99.63 98

ambc				99.20 235	99.35 265	98.53 246	99.17 166	99.46 224		99.67 119	99.80 63	98.46 155	99.70 307	97.92 194	99.70 208	99.38 216

MTGPA								99.53 196

test_post1							99.14 179				51.63 375	89.54 331	99.82 243	96.86 259

test_post											52.41 374	90.25 326	99.86 184

patchmatchnet-post											99.62 173	90.58 322	99.94 54

GG-mvs-BLEND				97.36 333	97.59 364	96.87 313	99.70 29	88.49 373		94.64 367	97.26 368	80.66 367	99.12 361	91.50 347	96.50 361	96.08 363

MTMP							99.09 192	98.59 315

gm-plane-assit					97.59 364	89.02 370			93.47 353		98.30 347		99.84 218	96.38 283

test9_res														95.10 329	99.44 258	99.50 175

TEST9					99.35 265	99.35 154	98.11 303	99.41 235	94.83 347	97.92 339	98.99 311	98.02 190	99.85 202

test_8					99.34 275	99.31 160	98.08 308	99.40 241	94.90 343	97.87 343	98.97 317	98.02 190	99.84 218

agg_prior2														94.58 335	99.46 257	99.50 175

agg_prior					99.35 265	99.36 150		99.39 244		97.76 349			99.85 202

TestCases				99.63 110	99.78 87	99.64 78		99.83 39	98.63 213	99.63 135	99.72 106	98.68 117	99.75 292	96.38 283	99.83 145	99.51 169

test_prior4						99.19 192	98.00 315

test_prior2							97.95 322		97.87 270	98.05 334	99.05 305	97.90 198		95.99 299	99.49 252

test_prior				99.46 171	99.35 265	99.22 184		99.39 244					99.69 313			99.48 183

旧先验2							97.94 324		95.33 338	98.94 273			99.88 143	96.75 266

新几何2							98.04 311

新几何1				99.52 156	99.50 219	99.22 184		99.26 273	95.66 335	98.60 306	99.28 268	97.67 217	99.89 128	95.95 303	99.32 278	99.45 194

旧先验1					99.49 224	99.29 165		99.26 273			99.39 242	97.67 217			99.36 274	99.46 192

无先验							98.01 313	99.23 280	95.83 329				99.85 202	95.79 308		99.44 199

原ACMM2							97.92 326

原ACMM1				99.37 200	99.47 235	98.87 229		99.27 271	96.74 313	98.26 323	99.32 258	97.93 197	99.82 243	95.96 302	99.38 271	99.43 205

test222					99.51 213	99.08 205	97.83 331	99.29 267	95.21 340	98.68 301	99.31 260	97.28 237			99.38 271	99.43 205

testdata2													99.89 128	95.99 299

segment_acmp												98.37 162

testdata				99.42 183	99.51 213	98.93 222		99.30 266	96.20 323	98.87 281	99.40 239	98.33 166	99.89 128	96.29 286	99.28 282	99.44 199

testdata1							97.72 333		97.86 273

test12				99.54 153	99.29 287	99.33 157		99.16 286		98.43 317		97.54 224	99.82 243		99.47 254	99.48 183

plane_prior7					99.58 179	99.38 144

plane_prior6					99.47 235	99.26 173						97.24 238

plane_prior5								99.54 191					99.82 243	95.84 306	99.78 176	99.60 124

plane_prior4											99.25 274

plane_prior3						99.31 160			98.36 237	99.14 251

plane_prior2							98.80 240		98.94 177

plane_prior1					99.51 213

plane_prior						99.24 180	98.42 279		97.87 270						99.71 206

n2								0.00 376

nn								0.00 376

door-mid								99.83 39

lessismore_v0				99.64 106	99.86 34	99.38 144		90.66 370		99.89 38	99.83 51	94.56 285	99.97 16	99.56 44	99.92 90	99.57 143

LGP-MVS_train				99.74 57	99.82 52	99.63 82		99.73 92	97.56 286	99.64 131	99.69 126	99.37 29	99.89 128	96.66 271	99.87 121	99.69 57

test11								99.29 267

door								99.77 72

HQP5-MVS						98.94 217

HQP-NCC					99.31 282		97.98 318		97.45 291	98.15 328

ACMP_Plane					99.31 282		97.98 318		97.45 291	98.15 328

BP-MVS														94.73 332

HQP4-MVS										98.15 328			99.70 307			99.53 158

HQP3-MVS								99.37 251							99.67 216

HQP2-MVS												96.67 255

NP-MVS					99.40 256	99.13 197					98.83 329

MDTV_nov1_ep13_2view						91.44 362	99.14 179		97.37 296	99.21 241		91.78 309		96.75 266		99.03 288

MDTV_nov1_ep13			97.73 281		98.70 349	90.83 364	99.15 174	98.02 328	98.51 224	98.82 284	99.61 182	90.98 315	99.66 333	96.89 258	98.92 304

ACMMP++_ref															99.94 79

ACMMP++															99.79 170

Test By Simon												98.41 159

ITE_SJBPF				99.38 196	99.63 164	99.44 120		99.73 92	98.56 219	99.33 218	99.53 212	98.88 86	99.68 323	96.01 297	99.65 221	99.02 289

DeepMVS_CX				97.98 311	99.69 143	96.95 311		99.26 273	75.51 365	95.74 365	98.28 348	96.47 261	99.62 344	91.23 348	97.89 353	97.38 352

High-resolution multi-view benchmark