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 7	99.98 1	99.99 1	99.96 1	99.77 1	100.00 1	99.81 5	100.00 1	99.85 12

UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 18	99.34 15	99.69 4	99.58 41	99.90 2	99.86 9	99.78 8	99.58 3	99.95 17	99.00 46	99.95 19	99.78 19

pmmvs6		99.67 3	99.70 3	99.60 11	99.90 4	99.27 22	99.53 7	99.76 17	99.64 11	99.84 10	99.83 3	99.50 5	99.87 88	99.36 23	99.92 41	99.64 49

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 21	99.85 16	99.11 59	99.90 1	99.78 15	99.63 13	99.78 14	99.67 20	99.48 6	99.81 162	99.30 28	99.97 12	99.77 21
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 48	99.88 9	98.61 92	99.34 19	99.71 20	99.27 49	99.90 6	99.74 12	99.68 2	99.97 4	99.55 15	99.99 5	99.88 7

jajsoiax		99.58 6	99.61 7	99.48 51	99.87 12	98.61 92	99.28 36	99.66 31	99.09 71	99.89 8	99.68 18	99.53 4	99.97 4	99.50 17	99.99 5	99.87 9

ANet_high		99.57 7	99.67 5	99.28 83	99.89 6	98.09 133	99.14 53	99.93 3	99.82 3	99.93 3	99.81 5	99.17 12	99.94 26	99.31 26	100.00 1	99.82 14

v7n		99.53 8	99.57 8	99.41 60	99.88 9	98.54 100	99.45 10	99.61 37	99.66 10	99.68 26	99.66 22	98.44 46	99.95 17	99.73 9	99.96 15	99.75 28

test_djsdf		99.52 9	99.51 9	99.53 34	99.86 14	98.74 82	99.39 16	99.56 55	99.11 61	99.70 22	99.73 14	99.00 15	99.97 4	99.26 29	99.98 9	99.89 6

anonymousdsp		99.51 10	99.47 12	99.62 6	99.88 9	99.08 63	99.34 19	99.69 23	98.93 86	99.65 31	99.72 15	98.93 19	99.95 17	99.11 38	100.00 1	99.82 14

UA-Net		99.47 11	99.40 15	99.70 2	99.49 99	99.29 19	99.80 3	99.72 19	99.82 3	99.04 126	99.81 5	98.05 76	99.96 11	98.85 54	99.99 5	99.86 11

PS-MVSNAJss		99.46 12	99.49 10	99.35 69	99.90 4	98.15 129	99.20 44	99.65 32	99.48 26	99.92 4	99.71 16	98.07 73	99.96 11	99.53 16	100.00 1	99.93 4

pm-mvs1		99.44 13	99.48 11	99.33 76	99.80 22	98.63 89	99.29 32	99.63 33	99.30 47	99.65 31	99.60 32	99.16 14	99.82 149	99.07 40	99.83 76	99.56 81

TransMVSNet (Re)		99.44 13	99.47 12	99.36 64	99.80 22	98.58 95	99.27 38	99.57 48	99.39 36	99.75 17	99.62 28	99.17 12	99.83 139	99.06 41	99.62 171	99.66 44

DTE-MVSNet		99.43 15	99.35 18	99.66 4	99.71 43	99.30 17	99.31 26	99.51 71	99.64 11	99.56 37	99.46 54	98.23 58	99.97 4	98.78 57	99.93 31	99.72 31

TDRefinement		99.42 16	99.38 16	99.55 23	99.76 30	99.33 16	99.68 5	99.71 20	99.38 37	99.53 44	99.61 30	98.64 33	99.80 169	98.24 90	99.84 69	99.52 102

PEN-MVS		99.41 17	99.34 20	99.62 6	99.73 35	99.14 52	99.29 32	99.54 64	99.62 16	99.56 37	99.42 62	98.16 69	99.96 11	98.78 57	99.93 31	99.77 21

nrg030		99.40 18	99.35 18	99.54 27	99.58 64	99.13 55	98.98 71	99.48 82	99.68 8	99.46 54	99.26 88	98.62 36	99.73 220	99.17 37	99.92 41	99.76 25

PS-CasMVS		99.40 18	99.33 21	99.62 6	99.71 43	99.10 60	99.29 32	99.53 67	99.53 23	99.46 54	99.41 65	98.23 58	99.95 17	98.89 53	99.95 19	99.81 16

MIMVSNet1		99.38 20	99.32 22	99.55 23	99.86 14	99.19 37	99.41 13	99.59 39	99.59 19	99.71 20	99.57 35	97.12 142	99.90 52	99.21 34	99.87 62	99.54 92

OurMVSNet-221017-0		99.37 21	99.31 23	99.53 34	99.91 3	98.98 65	99.63 6	99.58 41	99.44 31	99.78 14	99.76 10	96.39 182	99.92 39	99.44 21	99.92 41	99.68 40

Vis-MVSNet		99.34 22	99.36 17	99.27 86	99.73 35	98.26 118	99.17 49	99.78 15	99.11 61	99.27 91	99.48 52	98.82 24	99.95 17	98.94 49	99.93 31	99.59 66
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
WR-MVS_H		99.33 23	99.22 28	99.65 5	99.71 43	99.24 25	99.32 22	99.55 59	99.46 29	99.50 50	99.34 76	97.30 131	99.93 31	98.90 51	99.93 31	99.77 21

VPA-MVSNet		99.30 24	99.30 24	99.28 83	99.49 99	98.36 114	99.00 68	99.45 93	99.63 13	99.52 46	99.44 59	98.25 56	99.88 71	99.09 39	99.84 69	99.62 53

Anonymous20231211		99.27 25	99.27 25	99.26 88	99.29 142	98.18 126	99.49 8	99.51 71	99.70 7	99.80 12	99.68 18	96.84 157	99.83 139	99.21 34	99.91 47	99.77 21

FC-MVSNet-test		99.27 25	99.25 26	99.34 72	99.77 27	98.37 111	99.30 31	99.57 48	99.61 18	99.40 66	99.50 48	97.12 142	99.85 109	99.02 45	99.94 27	99.80 17

testf1		99.25 27	99.16 32	99.51 43	99.89 6	99.63 3	98.71 89	99.69 23	98.90 88	99.43 59	99.35 72	98.86 21	99.67 247	97.81 116	99.81 83	99.24 206

APD_test2		99.25 27	99.16 32	99.51 43	99.89 6	99.63 3	98.71 89	99.69 23	98.90 88	99.43 59	99.35 72	98.86 21	99.67 247	97.81 116	99.81 83	99.24 206

KD-MVS_self_test		99.25 27	99.18 29	99.44 57	99.63 61	99.06 64	98.69 91	99.54 64	99.31 45	99.62 35	99.53 44	97.36 129	99.86 97	99.24 33	99.71 138	99.39 160

ACMH	96.65 7	99.25 27	99.24 27	99.26 88	99.72 41	98.38 109	99.07 61	99.55 59	98.30 117	99.65 31	99.45 58	99.22 9	99.76 204	98.44 81	99.77 108	99.64 49
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mvsmamba		99.24 31	99.15 37	99.49 48	99.83 19	98.85 74	99.41 13	99.55 59	99.54 22	99.40 66	99.52 46	95.86 208	99.91 47	99.32 25	99.95 19	99.70 37

CP-MVSNet		99.21 32	99.09 42	99.56 21	99.65 56	98.96 70	99.13 54	99.34 133	99.42 34	99.33 80	99.26 88	97.01 150	99.94 26	98.74 61	99.93 31	99.79 18

TranMVSNet+NR-MVSNet		99.17 33	99.07 45	99.46 56	99.37 130	98.87 73	98.39 128	99.42 106	99.42 34	99.36 75	99.06 123	98.38 49	99.95 17	98.34 86	99.90 54	99.57 77

FMVSNet1		99.17 33	99.17 30	99.17 99	99.55 79	98.24 120	99.20 44	99.44 97	99.21 52	99.43 59	99.55 40	97.82 92	99.86 97	98.42 83	99.89 58	99.41 148

test_vis3_rt		99.14 35	99.17 30	99.07 117	99.78 25	98.38 109	98.92 75	99.94 1	97.80 155	99.91 5	99.67 20	97.15 141	98.91 360	99.76 8	99.56 194	99.92 5

FIs		99.14 35	99.09 42	99.29 81	99.70 49	98.28 117	99.13 54	99.52 70	99.48 26	99.24 100	99.41 65	96.79 163	99.82 149	98.69 66	99.88 59	99.76 25

XXY-MVS		99.14 35	99.15 37	99.10 111	99.76 30	97.74 172	98.85 81	99.62 34	98.48 110	99.37 73	99.49 51	98.75 27	99.86 97	98.20 93	99.80 94	99.71 32

CS-MVS		99.13 38	99.10 41	99.24 93	99.06 196	99.15 47	99.36 18	99.88 8	99.36 41	98.21 227	98.46 246	98.68 32	99.93 31	99.03 44	99.85 65	98.64 298

CS-MVS-test		99.13 38	99.09 42	99.26 88	99.13 181	98.97 66	99.31 26	99.88 8	99.44 31	98.16 230	98.51 238	98.64 33	99.93 31	98.91 50	99.85 65	98.88 267

test_fmvs3		99.12 40	99.41 14	98.25 215	99.76 30	95.07 265	99.05 64	99.94 1	97.78 157	99.82 11	99.84 2	98.56 40	99.71 228	99.96 1	99.96 15	99.97 1

casdiffmvs_mvg		99.12 40	99.16 32	98.99 131	99.43 118	97.73 174	98.00 167	99.62 34	99.22 51	99.55 39	99.22 96	98.93 19	99.75 211	98.66 68	99.81 83	99.50 107
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
RRT_MVS		99.09 42	98.94 54	99.55 23	99.87 12	98.82 78	99.48 9	98.16 300	99.49 25	99.59 36	99.65 24	94.79 241	99.95 17	99.45 20	99.96 15	99.88 7

DROMVSNet		99.09 42	99.05 46	99.20 97	99.28 143	98.93 71	99.24 40	99.84 11	99.08 73	98.12 235	98.37 254	98.72 29	99.90 52	99.05 42	99.77 108	98.77 284

ACMH+	96.62 9	99.08 44	99.00 49	99.33 76	99.71 43	98.83 76	98.60 99	99.58 41	99.11 61	99.53 44	99.18 103	98.81 25	99.67 247	96.71 192	99.77 108	99.50 107

bld_raw_dy_0_64		99.07 45	99.00 49	99.29 81	99.85 16	98.18 126	99.11 57	99.40 109	99.33 43	99.38 70	99.44 59	95.21 225	99.97 4	99.31 26	99.98 9	99.73 30

GeoE		99.05 46	98.99 52	99.25 91	99.44 113	98.35 115	98.73 86	99.56 55	98.42 111	98.91 149	98.81 192	98.94 18	99.91 47	98.35 85	99.73 126	99.49 111

Gipuma		99.03 47	99.16 32	98.64 170	99.94 2	98.51 102	99.32 22	99.75 18	99.58 21	98.60 194	99.62 28	98.22 61	99.51 307	97.70 124	99.73 126	97.89 329
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
v8		99.01 48	99.16 32	98.57 181	99.47 108	96.31 228	98.90 76	99.47 88	99.03 77	99.52 46	99.57 35	96.93 153	99.81 162	99.60 11	99.98 9	99.60 60

HPM-MVS_fast		99.01 48	98.82 64	99.57 16	99.71 43	99.35 12	99.00 68	99.50 73	97.33 198	98.94 146	98.86 180	98.75 27	99.82 149	97.53 131	99.71 138	99.56 81

APDe-MVS		98.99 50	98.79 67	99.60 11	99.21 157	99.15 47	98.87 78	99.48 82	97.57 172	99.35 77	99.24 93	97.83 89	99.89 62	97.88 113	99.70 143	99.75 28

EG-PatchMatch MVS		98.99 50	99.01 48	98.94 136	99.50 92	97.47 185	98.04 161	99.59 39	98.15 135	99.40 66	99.36 71	98.58 39	99.76 204	98.78 57	99.68 151	99.59 66

COLMAP_ROB	96.50 10	98.99 50	98.85 62	99.41 60	99.58 64	99.10 60	98.74 84	99.56 55	99.09 71	99.33 80	99.19 100	98.40 48	99.72 227	95.98 238	99.76 119	99.42 145
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 61	99.36 64	99.82 21	98.55 97	97.47 222	99.57 48	99.37 38	99.21 103	99.61 30	96.76 166	99.83 139	98.06 101	99.83 76	99.71 32

v10		98.97 54	99.11 39	98.55 186	99.44 113	96.21 230	98.90 76	99.55 59	98.73 96	99.48 51	99.60 32	96.63 173	99.83 139	99.70 10	99.99 5	99.61 59

DeepC-MVS	97.60 4	98.97 54	98.93 55	99.10 111	99.35 135	97.98 148	98.01 166	99.46 90	97.56 174	99.54 40	99.50 48	98.97 16	99.84 125	98.06 101	99.92 41	99.49 111
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
baseline		98.96 56	99.02 47	98.76 160	99.38 124	97.26 195	98.49 116	99.50 73	98.86 91	99.19 105	99.06 123	98.23 58	99.69 235	98.71 64	99.76 119	99.33 186

casdiffmvs		98.95 57	99.00 49	98.81 150	99.38 124	97.33 191	97.82 184	99.57 48	99.17 59	99.35 77	99.17 107	98.35 53	99.69 235	98.46 80	99.73 126	99.41 148
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
NR-MVSNet		98.95 57	98.82 64	99.36 64	99.16 174	98.72 87	99.22 41	99.20 183	99.10 68	99.72 18	98.76 200	96.38 184	99.86 97	98.00 106	99.82 79	99.50 107

Anonymous20240529		98.93 59	98.87 58	99.12 107	99.19 164	98.22 125	99.01 66	98.99 232	99.25 50	99.54 40	99.37 68	97.04 146	99.80 169	97.89 110	99.52 206	99.35 179

DP-MVS		98.93 59	98.81 66	99.28 83	99.21 157	98.45 106	98.46 121	99.33 138	99.63 13	99.48 51	99.15 113	97.23 137	99.75 211	97.17 146	99.66 162	99.63 52

SED-MVS		98.91 61	98.72 73	99.49 48	99.49 99	99.17 39	98.10 153	99.31 145	98.03 139	99.66 28	99.02 135	98.36 50	99.88 71	96.91 168	99.62 171	99.41 148

ACMM	96.08 12	98.91 61	98.73 71	99.48 51	99.55 79	99.14 52	98.07 156	99.37 118	97.62 167	99.04 126	98.96 156	98.84 23	99.79 182	97.43 135	99.65 163	99.49 111
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
DVP-MVS++		98.90 63	98.70 78	99.51 43	98.43 297	99.15 47	99.43 11	99.32 140	98.17 131	99.26 95	99.02 135	98.18 65	99.88 71	97.07 156	99.45 220	99.49 111

tfpnnormal		98.90 63	98.90 57	98.91 140	99.67 54	97.82 165	99.00 68	99.44 97	99.45 30	99.51 49	99.24 93	98.20 64	99.86 97	95.92 240	99.69 146	99.04 238

MTAPA		98.88 65	98.64 86	99.61 9	99.67 54	99.36 11	98.43 124	99.20 183	98.83 95	98.89 152	98.90 170	96.98 152	99.92 39	97.16 147	99.70 143	99.56 81

mvsany_test3		98.87 66	98.92 56	98.74 166	99.38 124	96.94 212	98.58 102	99.10 210	96.49 245	99.96 2	99.81 5	98.18 65	99.45 318	98.97 48	99.79 99	99.83 13

VPNet		98.87 66	98.83 63	99.01 129	99.70 49	97.62 180	98.43 124	99.35 127	99.47 28	99.28 89	99.05 130	96.72 169	99.82 149	98.09 99	99.36 231	99.59 66

UniMVSNet (Re)		98.87 66	98.71 75	99.35 69	99.24 150	98.73 85	97.73 193	99.38 114	98.93 86	99.12 111	98.73 203	96.77 164	99.86 97	98.63 70	99.80 94	99.46 130

UniMVSNet_NR-MVSNet		98.86 69	98.68 81	99.40 62	99.17 172	98.74 82	97.68 197	99.40 109	99.14 60	99.06 119	98.59 230	96.71 170	99.93 31	98.57 73	99.77 108	99.53 99

APD-MVS_3200maxsize		98.84 70	98.61 93	99.53 34	99.19 164	99.27 22	98.49 116	99.33 138	98.64 98	99.03 129	98.98 151	97.89 86	99.85 109	96.54 208	99.42 224	99.46 130

APD_test1		98.83 71	98.66 83	99.34 72	99.78 25	99.47 6	98.42 126	99.45 93	98.28 122	98.98 133	99.19 100	97.76 95	99.58 286	96.57 200	99.55 197	98.97 251

PM-MVS		98.82 72	98.72 73	99.12 107	99.64 59	98.54 100	97.98 169	99.68 28	97.62 167	99.34 79	99.18 103	97.54 114	99.77 199	97.79 118	99.74 123	99.04 238

DU-MVS		98.82 72	98.63 87	99.39 63	99.16 174	98.74 82	97.54 214	99.25 172	98.84 94	99.06 119	98.76 200	96.76 166	99.93 31	98.57 73	99.77 108	99.50 107

SR-MVS-dyc-post		98.81 74	98.55 98	99.57 16	99.20 161	99.38 8	98.48 119	99.30 153	98.64 98	98.95 140	98.96 156	97.49 123	99.86 97	96.56 204	99.39 227	99.45 134

3Dnovator	98.27 2	98.81 74	98.73 71	99.05 124	98.76 247	97.81 167	99.25 39	99.30 153	98.57 107	98.55 203	99.33 78	97.95 84	99.90 52	97.16 147	99.67 157	99.44 138

HPM-MVS		98.79 76	98.53 100	99.59 15	99.65 56	99.29 19	99.16 50	99.43 103	96.74 236	98.61 192	98.38 253	98.62 36	99.87 88	96.47 212	99.67 157	99.59 66
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
SteuartSystems-ACMMP		98.79 76	98.54 99	99.54 27	99.73 35	99.16 43	98.23 139	99.31 145	97.92 146	98.90 150	98.90 170	98.00 79	99.88 71	96.15 231	99.72 133	99.58 72
Skip Steuart: Steuart Systems R&D Blog.
dcpmvs_2		98.78 78	99.11 39	97.78 247	99.56 75	93.67 308	99.06 62	99.86 10	99.50 24	99.66 28	99.26 88	97.21 139	99.99 2	98.00 106	99.91 47	99.68 40

V42		98.78 78	98.78 68	98.76 160	99.44 113	97.04 207	98.27 136	99.19 187	97.87 150	99.25 99	99.16 109	96.84 157	99.78 193	99.21 34	99.84 69	99.46 130

test20.03		98.78 78	98.77 69	98.78 157	99.46 109	97.20 200	97.78 186	99.24 177	99.04 76	99.41 63	98.90 170	97.65 102	99.76 204	97.70 124	99.79 99	99.39 160

DVP-MVS		98.77 81	98.52 101	99.52 39	99.50 92	99.21 28	98.02 163	98.84 256	97.97 142	99.08 117	99.02 135	97.61 108	99.88 71	96.99 162	99.63 168	99.48 121
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0402		98.76 82	98.71 75	98.93 137	99.56 75	98.14 131	98.45 123	99.34 133	99.28 48	98.95 140	98.91 167	98.34 54	99.79 182	95.63 255	99.91 47	98.86 269

ACMMP_NAP		98.75 83	98.48 109	99.57 16	99.58 64	99.29 19	97.82 184	99.25 172	96.94 227	98.78 171	99.12 117	98.02 77	99.84 125	97.13 152	99.67 157	99.59 66

SixPastTwentyTwo		98.75 83	98.62 89	99.16 102	99.83 19	97.96 152	99.28 36	98.20 297	99.37 38	99.70 22	99.65 24	92.65 279	99.93 31	99.04 43	99.84 69	99.60 60

ACMMP		98.75 83	98.50 104	99.52 39	99.56 75	99.16 43	98.87 78	99.37 118	97.16 218	98.82 168	99.01 144	97.71 98	99.87 88	96.29 223	99.69 146	99.54 92
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
XVS		98.72 86	98.45 114	99.53 34	99.46 109	99.21 28	98.65 93	99.34 133	98.62 102	97.54 275	98.63 224	97.50 120	99.83 139	96.79 181	99.53 203	99.56 81

SR-MVS		98.71 87	98.43 117	99.57 16	99.18 171	99.35 12	98.36 130	99.29 160	98.29 120	98.88 156	98.85 183	97.53 116	99.87 88	96.14 232	99.31 239	99.48 121

HFP-MVS		98.71 87	98.44 116	99.51 43	99.49 99	99.16 43	98.52 109	99.31 145	97.47 181	98.58 198	98.50 242	97.97 83	99.85 109	96.57 200	99.59 182	99.53 99

LPG-MVS_test		98.71 87	98.46 113	99.47 54	99.57 68	98.97 66	98.23 139	99.48 82	96.60 241	99.10 115	99.06 123	98.71 30	99.83 139	95.58 258	99.78 104	99.62 53

test_fmvs2		98.70 90	98.97 53	97.89 240	99.54 82	94.05 290	98.55 105	99.92 5	96.78 234	99.72 18	99.78 8	96.60 174	99.67 247	99.91 2	99.90 54	99.94 3

ACMMPR		98.70 90	98.42 119	99.54 27	99.52 87	99.14 52	98.52 109	99.31 145	97.47 181	98.56 201	98.54 234	97.75 96	99.88 71	96.57 200	99.59 182	99.58 72

CP-MVS		98.70 90	98.42 119	99.52 39	99.36 131	99.12 57	98.72 87	99.36 122	97.54 176	98.30 222	98.40 250	97.86 88	99.89 62	96.53 209	99.72 133	99.56 81

tt0805		98.69 93	98.62 89	98.90 142	99.75 34	99.30 17	99.15 52	96.97 331	98.86 91	98.87 160	97.62 307	98.63 35	98.96 357	99.41 22	98.29 315	98.45 306

Anonymous20240521		98.69 93	98.87 58	98.16 223	99.77 27	95.11 264	99.08 58	99.44 97	99.34 42	99.33 80	99.55 40	94.10 257	99.94 26	99.25 31	99.96 15	99.42 145

region2R		98.69 93	98.40 121	99.54 27	99.53 85	99.17 39	98.52 109	99.31 145	97.46 186	98.44 213	98.51 238	97.83 89	99.88 71	96.46 213	99.58 187	99.58 72

EI-MVSNet-UG-set		98.69 93	98.71 75	98.62 174	99.10 185	96.37 225	97.23 237	98.87 247	99.20 54	99.19 105	98.99 147	97.30 131	99.85 109	98.77 60	99.79 99	99.65 48

3Dnovator+	97.89 3	98.69 93	98.51 102	99.24 93	98.81 242	98.40 107	99.02 65	99.19 187	98.99 80	98.07 239	99.28 84	97.11 144	99.84 125	96.84 179	99.32 237	99.47 128

ZNCC-MVS		98.68 98	98.40 121	99.54 27	99.57 68	99.21 28	98.46 121	99.29 160	97.28 204	98.11 236	98.39 251	98.00 79	99.87 88	96.86 178	99.64 165	99.55 88

EI-MVSNet-Vis-set		98.68 98	98.70 78	98.63 173	99.09 188	96.40 224	97.23 237	98.86 252	99.20 54	99.18 109	98.97 153	97.29 133	99.85 109	98.72 63	99.78 104	99.64 49

CSCG		98.68 98	98.50 104	99.20 97	99.45 112	98.63 89	98.56 104	99.57 48	97.87 150	98.85 161	98.04 282	97.66 101	99.84 125	96.72 190	99.81 83	99.13 228

test_f		98.67 101	98.87 58	98.05 232	99.72 41	95.59 244	98.51 113	99.81 13	96.30 254	99.78 14	99.82 4	96.14 191	98.63 365	99.82 3	99.93 31	99.95 2

PGM-MVS		98.66 102	98.37 127	99.55 23	99.53 85	99.18 38	98.23 139	99.49 80	97.01 225	98.69 181	98.88 177	98.00 79	99.89 62	95.87 244	99.59 182	99.58 72

GBi-Net		98.65 103	98.47 111	99.17 99	98.90 224	98.24 120	99.20 44	99.44 97	98.59 104	98.95 140	99.55 40	94.14 253	99.86 97	97.77 119	99.69 146	99.41 148

test1		98.65 103	98.47 111	99.17 99	98.90 224	98.24 120	99.20 44	99.44 97	98.59 104	98.95 140	99.55 40	94.14 253	99.86 97	97.77 119	99.69 146	99.41 148

LCM-MVSNet-Re		98.64 105	98.48 109	99.11 109	98.85 234	98.51 102	98.49 116	99.83 12	98.37 112	99.69 24	99.46 54	98.21 63	99.92 39	94.13 294	99.30 242	98.91 263

mPP-MVS		98.64 105	98.34 131	99.54 27	99.54 82	99.17 39	98.63 95	99.24 177	97.47 181	98.09 238	98.68 212	97.62 107	99.89 62	96.22 226	99.62 171	99.57 77

TSAR-MVS + MP.		98.63 107	98.49 108	99.06 123	99.64 59	97.90 156	98.51 113	98.94 234	96.96 226	99.24 100	98.89 176	97.83 89	99.81 162	96.88 175	99.49 216	99.48 121
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
LS3D		98.63 107	98.38 126	99.36 64	97.25 354	99.38 8	99.12 56	99.32 140	99.21 52	98.44 213	98.88 177	97.31 130	99.80 169	96.58 198	99.34 235	98.92 260

RPSCF		98.62 109	98.36 128	99.42 58	99.65 56	99.42 7	98.55 105	99.57 48	97.72 161	98.90 150	99.26 88	96.12 193	99.52 303	95.72 251	99.71 138	99.32 188

GST-MVS		98.61 110	98.30 136	99.52 39	99.51 89	99.20 34	98.26 137	99.25 172	97.44 189	98.67 183	98.39 251	97.68 99	99.85 109	96.00 236	99.51 208	99.52 102

v1192		98.60 111	98.66 83	98.41 202	99.27 145	95.88 238	97.52 216	99.36 122	97.41 191	99.33 80	99.20 99	96.37 185	99.82 149	99.57 13	99.92 41	99.55 88

v1144		98.60 111	98.66 83	98.41 202	99.36 131	95.90 237	97.58 210	99.34 133	97.51 177	99.27 91	99.15 113	96.34 187	99.80 169	99.47 19	99.93 31	99.51 104

DPE-MVS		98.59 113	98.26 141	99.57 16	99.27 145	99.15 47	97.01 249	99.39 112	97.67 163	99.44 58	98.99 147	97.53 116	99.89 62	95.40 262	99.68 151	99.66 44
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MP-MVS-pluss		98.57 114	98.23 144	99.60 11	99.69 51	99.35 12	97.16 244	99.38 114	94.87 291	98.97 137	98.99 147	98.01 78	99.88 71	97.29 141	99.70 143	99.58 72
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
OPM-MVS		98.56 115	98.32 135	99.25 91	99.41 121	98.73 85	97.13 246	99.18 191	97.10 221	98.75 177	98.92 166	98.18 65	99.65 263	96.68 194	99.56 194	99.37 169
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
VDD-MVS		98.56 115	98.39 124	99.07 117	99.13 181	98.07 139	98.59 100	97.01 329	99.59 19	99.11 112	99.27 86	94.82 236	99.79 182	98.34 86	99.63 168	99.34 181

v2v482		98.56 115	98.62 89	98.37 206	99.42 119	95.81 241	97.58 210	99.16 198	97.90 148	99.28 89	99.01 144	95.98 202	99.79 182	99.33 24	99.90 54	99.51 104

XVG-ACMP-BASELINE		98.56 115	98.34 131	99.22 96	99.54 82	98.59 94	97.71 194	99.46 90	97.25 207	98.98 133	98.99 147	97.54 114	99.84 125	95.88 241	99.74 123	99.23 208

v1240		98.55 119	98.62 89	98.32 209	99.22 155	95.58 245	97.51 218	99.45 93	97.16 218	99.45 57	99.24 93	96.12 193	99.85 109	99.60 11	99.88 59	99.55 88

IterMVS-LS		98.55 119	98.70 78	98.09 225	99.48 106	94.73 273	97.22 240	99.39 112	98.97 82	99.38 70	99.31 82	96.00 198	99.93 31	98.58 71	99.97 12	99.60 60
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v144192		98.54 121	98.57 97	98.45 198	99.21 157	95.98 235	97.63 203	99.36 122	97.15 220	99.32 86	99.18 103	95.84 209	99.84 125	99.50 17	99.91 47	99.54 92

v1921920		98.54 121	98.60 94	98.38 205	99.20 161	95.76 243	97.56 212	99.36 122	97.23 213	99.38 70	99.17 107	96.02 196	99.84 125	99.57 13	99.90 54	99.54 92

SF-MVS		98.53 123	98.27 140	99.32 78	99.31 138	98.75 81	98.19 143	99.41 107	96.77 235	98.83 165	98.90 170	97.80 93	99.82 149	95.68 254	99.52 206	99.38 167

XVG-OURS		98.53 123	98.34 131	99.11 109	99.50 92	98.82 78	95.97 297	99.50 73	97.30 202	99.05 124	98.98 151	99.35 7	99.32 335	95.72 251	99.68 151	99.18 220

UGNet		98.53 123	98.45 114	98.79 154	97.94 325	96.96 210	99.08 58	98.54 282	99.10 68	96.82 312	99.47 53	96.55 176	99.84 125	98.56 76	99.94 27	99.55 88
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
patch_mono-2		98.51 126	98.63 87	98.17 221	99.38 124	94.78 270	97.36 228	99.69 23	98.16 134	98.49 209	99.29 83	97.06 145	99.97 4	98.29 89	99.91 47	99.76 25

XVG-OURS-SEG-HR		98.49 127	98.28 138	99.14 105	99.49 99	98.83 76	96.54 273	99.48 82	97.32 200	99.11 112	98.61 228	99.33 8	99.30 338	96.23 225	98.38 312	99.28 198

FMVSNet2		98.49 127	98.40 121	98.75 162	98.90 224	97.14 206	98.61 98	99.13 205	98.59 104	99.19 105	99.28 84	94.14 253	99.82 149	97.97 108	99.80 94	99.29 197

pmmvs-eth3d		98.47 129	98.34 131	98.86 144	99.30 141	97.76 170	97.16 244	99.28 163	95.54 273	99.42 62	99.19 100	97.27 134	99.63 269	97.89 110	99.97 12	99.20 213

MP-MVS		98.46 130	98.09 159	99.54 27	99.57 68	99.22 27	98.50 115	99.19 187	97.61 169	97.58 271	98.66 217	97.40 127	99.88 71	94.72 275	99.60 178	99.54 92
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
v148		98.45 131	98.60 94	98.00 235	99.44 113	94.98 266	97.44 224	99.06 215	98.30 117	99.32 86	98.97 153	96.65 172	99.62 271	98.37 84	99.85 65	99.39 160

AllTest		98.44 132	98.20 146	99.16 102	99.50 92	98.55 97	98.25 138	99.58 41	96.80 232	98.88 156	99.06 123	97.65 102	99.57 288	94.45 282	99.61 176	99.37 169

VNet		98.42 133	98.30 136	98.79 154	98.79 246	97.29 193	98.23 139	98.66 276	99.31 45	98.85 161	98.80 193	94.80 239	99.78 193	98.13 95	99.13 267	99.31 192

ab-mvs		98.41 134	98.36 128	98.59 178	99.19 164	97.23 196	99.32 22	98.81 261	97.66 164	98.62 190	99.40 67	96.82 160	99.80 169	95.88 241	99.51 208	98.75 287

ACMP	95.32 15	98.41 134	98.09 159	99.36 64	99.51 89	98.79 80	97.68 197	99.38 114	95.76 270	98.81 170	98.82 190	98.36 50	99.82 149	94.75 272	99.77 108	99.48 121
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
SMA-MVS		98.40 136	98.03 166	99.51 43	99.16 174	99.21 28	98.05 159	99.22 180	94.16 307	98.98 133	99.10 120	97.52 118	99.79 182	96.45 214	99.64 165	99.53 99
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
MSP-MVS		98.40 136	98.00 168	99.61 9	99.57 68	99.25 24	98.57 103	99.35 127	97.55 175	99.31 88	97.71 300	94.61 244	99.88 71	96.14 232	99.19 259	99.70 37
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
SD-MVS		98.40 136	98.68 81	97.54 269	98.96 212	97.99 145	97.88 177	99.36 122	98.20 128	99.63 34	99.04 132	98.76 26	95.33 375	96.56 204	99.74 123	99.31 192
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
EI-MVSNet		98.40 136	98.51 102	98.04 233	99.10 185	94.73 273	97.20 241	98.87 247	98.97 82	99.06 119	99.02 135	96.00 198	99.80 169	98.58 71	99.82 79	99.60 60

WR-MVS		98.40 136	98.19 148	99.03 127	99.00 205	97.65 177	96.85 259	98.94 234	98.57 107	98.89 152	98.50 242	95.60 214	99.85 109	97.54 130	99.85 65	99.59 66

new-patchmatchnet		98.35 141	98.74 70	97.18 286	99.24 150	92.23 332	96.42 280	99.48 82	98.30 117	99.69 24	99.53 44	97.44 125	99.82 149	98.84 55	99.77 108	99.49 111

canonicalmvs		98.34 142	98.26 141	98.58 179	98.46 294	97.82 165	98.96 72	99.46 90	99.19 58	97.46 282	95.46 356	98.59 38	99.46 317	98.08 100	98.71 300	98.46 304

testgi		98.32 143	98.39 124	98.13 224	99.57 68	95.54 246	97.78 186	99.49 80	97.37 195	99.19 105	97.65 304	98.96 17	99.49 309	96.50 211	98.99 283	99.34 181

DeepPCF-MVS	96.93 5	98.32 143	98.01 167	99.23 95	98.39 302	98.97 66	95.03 331	99.18 191	96.88 230	99.33 80	98.78 196	98.16 69	99.28 342	96.74 187	99.62 171	99.44 138

test_vis1_n		98.31 145	98.50 104	97.73 254	99.76 30	94.17 288	98.68 92	99.91 6	96.31 252	99.79 13	99.57 35	92.85 276	99.42 323	99.79 6	99.84 69	99.60 60

MVS_111021_LR		98.30 146	98.12 157	98.83 147	99.16 174	98.03 143	96.09 294	99.30 153	97.58 171	98.10 237	98.24 265	98.25 56	99.34 332	96.69 193	99.65 163	99.12 229

EPP-MVSNet		98.30 146	98.04 165	99.07 117	99.56 75	97.83 162	99.29 32	98.07 304	99.03 77	98.59 196	99.13 116	92.16 283	99.90 52	96.87 176	99.68 151	99.49 111

DeepC-MVS_fast	96.85 6	98.30 146	98.15 154	98.75 162	98.61 276	97.23 196	97.76 190	99.09 212	97.31 201	98.75 177	98.66 217	97.56 112	99.64 266	96.10 235	99.55 197	99.39 160
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PHI-MVS		98.29 149	97.95 171	99.34 72	98.44 296	99.16 43	98.12 150	99.38 114	96.01 263	98.06 240	98.43 248	97.80 93	99.67 247	95.69 253	99.58 187	99.20 213

Fast-Effi-MVS+-dtu		98.27 150	98.09 159	98.81 150	98.43 297	98.11 132	97.61 206	99.50 73	98.64 98	97.39 287	97.52 312	98.12 72	99.95 17	96.90 173	98.71 300	98.38 311

DELS-MVS		98.27 150	98.20 146	98.48 195	98.86 232	96.70 220	95.60 314	99.20 183	97.73 159	98.45 212	98.71 206	97.50 120	99.82 149	98.21 92	99.59 182	98.93 259
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		98.26 152	97.90 177	99.35 69	98.02 322	99.49 5	98.02 163	99.16 198	98.29 120	97.64 266	97.99 284	96.44 181	99.95 17	96.66 195	98.93 289	98.60 299

MVSFormer		98.26 152	98.43 117	97.77 248	98.88 230	93.89 302	99.39 16	99.56 55	99.11 61	98.16 230	98.13 272	93.81 260	99.97 4	99.26 29	99.57 191	99.43 142

MVS_111021_HR		98.25 154	98.08 162	98.75 162	99.09 188	97.46 186	95.97 297	99.27 166	97.60 170	97.99 245	98.25 264	98.15 71	99.38 329	96.87 176	99.57 191	99.42 145

TAMVS		98.24 155	98.05 164	98.80 152	99.07 192	97.18 202	97.88 177	98.81 261	96.66 240	99.17 110	99.21 97	94.81 238	99.77 199	96.96 166	99.88 59	99.44 138

diffmvs		98.22 156	98.24 143	98.17 221	99.00 205	95.44 251	96.38 282	99.58 41	97.79 156	98.53 206	98.50 242	96.76 166	99.74 216	97.95 109	99.64 165	99.34 181
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Anonymous20231206		98.21 157	98.21 145	98.20 219	99.51 89	95.43 252	98.13 148	99.32 140	96.16 257	98.93 147	98.82 190	96.00 198	99.83 139	97.32 140	99.73 126	99.36 175

VDDNet		98.21 157	97.95 171	99.01 129	99.58 64	97.74 172	99.01 66	97.29 324	99.67 9	98.97 137	99.50 48	90.45 294	99.80 169	97.88 113	99.20 256	99.48 121

IS-MVSNet		98.19 159	97.90 177	99.08 115	99.57 68	97.97 149	99.31 26	98.32 292	99.01 79	98.98 133	99.03 134	91.59 288	99.79 182	95.49 260	99.80 94	99.48 121

MVS_Test		98.18 160	98.36 128	97.67 256	98.48 292	94.73 273	98.18 144	99.02 226	97.69 162	98.04 243	99.11 118	97.22 138	99.56 291	98.57 73	98.90 291	98.71 290

TSAR-MVS + GP.		98.18 160	97.98 169	98.77 159	98.71 256	97.88 157	96.32 285	98.66 276	96.33 250	99.23 102	98.51 238	97.48 124	99.40 325	97.16 147	99.46 218	99.02 241

CNVR-MVS		98.17 162	97.87 179	99.07 117	98.67 268	98.24 120	97.01 249	98.93 236	97.25 207	97.62 267	98.34 258	97.27 134	99.57 288	96.42 215	99.33 236	99.39 160

PVSNet_Blended_VisFu		98.17 162	98.15 154	98.22 218	99.73 35	95.15 261	97.36 228	99.68 28	94.45 301	98.99 132	99.27 86	96.87 156	99.94 26	97.13 152	99.91 47	99.57 77

HPM-MVS++		98.10 164	97.64 196	99.48 51	99.09 188	99.13 55	97.52 216	98.75 270	97.46 186	96.90 307	97.83 295	96.01 197	99.84 125	95.82 248	99.35 233	99.46 130

APD-MVS		98.10 164	97.67 191	99.42 58	99.11 183	98.93 71	97.76 190	99.28 163	94.97 288	98.72 180	98.77 198	97.04 146	99.85 109	93.79 304	99.54 199	99.49 111
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_fmvs1_n		98.09 166	98.28 138	97.52 271	99.68 52	93.47 311	98.63 95	99.93 3	95.41 280	99.68 26	99.64 26	91.88 287	99.48 312	99.82 3	99.87 62	99.62 53

MVP-Stereo		98.08 167	97.92 175	98.57 181	98.96 212	96.79 216	97.90 176	99.18 191	96.41 248	98.46 211	98.95 160	95.93 205	99.60 278	96.51 210	98.98 285	99.31 192
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PMMVS2		98.07 168	98.08 162	98.04 233	99.41 121	94.59 279	94.59 345	99.40 109	97.50 178	98.82 168	98.83 187	96.83 159	99.84 125	97.50 133	99.81 83	99.71 32

ETV-MVS		98.03 169	97.86 180	98.56 185	98.69 265	98.07 139	97.51 218	99.50 73	98.10 136	97.50 279	95.51 354	98.41 47	99.88 71	96.27 224	99.24 251	97.71 341

Effi-MVS+		98.02 170	97.82 182	98.62 174	98.53 288	97.19 201	97.33 230	99.68 28	97.30 202	96.68 315	97.46 316	98.56 40	99.80 169	96.63 196	98.20 318	98.86 269

MSLP-MVS++		98.02 170	98.14 156	97.64 260	98.58 281	95.19 260	97.48 220	99.23 179	97.47 181	97.90 249	98.62 226	97.04 146	98.81 363	97.55 128	99.41 225	98.94 258

EIA-MVS		98.00 172	97.74 186	98.80 152	98.72 253	98.09 133	98.05 159	99.60 38	97.39 193	96.63 317	95.55 353	97.68 99	99.80 169	96.73 189	99.27 246	98.52 302

MCST-MVS		98.00 172	97.63 197	99.10 111	99.24 150	98.17 128	96.89 258	98.73 273	95.66 271	97.92 247	97.70 302	97.17 140	99.66 258	96.18 230	99.23 252	99.47 128

K. test v3		98.00 172	97.66 194	99.03 127	99.79 24	97.56 181	99.19 48	92.47 364	99.62 16	99.52 46	99.66 22	89.61 299	99.96 11	99.25 31	99.81 83	99.56 81

HQP_MVS		97.99 175	97.67 191	98.93 137	99.19 164	97.65 177	97.77 188	99.27 166	98.20 128	97.79 258	97.98 285	94.90 232	99.70 231	94.42 284	99.51 208	99.45 134

MDA-MVSNet-bldmvs		97.94 176	97.91 176	98.06 230	99.44 113	94.96 267	96.63 271	99.15 203	98.35 113	98.83 165	99.11 118	94.31 250	99.85 109	96.60 197	98.72 298	99.37 169

Anonymous202405211		97.90 177	97.50 204	99.08 115	98.90 224	98.25 119	98.53 108	96.16 343	98.87 90	99.11 112	98.86 180	90.40 295	99.78 193	97.36 138	99.31 239	99.19 218

LF4IMVS		97.90 177	97.69 190	98.52 190	99.17 172	97.66 176	97.19 243	99.47 88	96.31 252	97.85 254	98.20 269	96.71 170	99.52 303	94.62 276	99.72 133	98.38 311

UnsupCasMVSNet_eth		97.89 179	97.60 199	98.75 162	99.31 138	97.17 203	97.62 204	99.35 127	98.72 97	98.76 176	98.68 212	92.57 280	99.74 216	97.76 123	95.60 362	99.34 181

TinyColmap		97.89 179	97.98 169	97.60 262	98.86 232	94.35 283	96.21 290	99.44 97	97.45 188	99.06 119	98.88 177	97.99 82	99.28 342	94.38 288	99.58 187	99.18 220

OMC-MVS		97.88 181	97.49 205	99.04 126	98.89 229	98.63 89	96.94 253	99.25 172	95.02 286	98.53 206	98.51 238	97.27 134	99.47 315	93.50 311	99.51 208	99.01 242

CANet		97.87 182	97.76 184	98.19 220	97.75 334	95.51 248	96.76 264	99.05 218	97.74 158	96.93 301	98.21 268	95.59 215	99.89 62	97.86 115	99.93 31	99.19 218

xiu_mvs_v1_base_debu		97.86 183	98.17 150	96.92 298	98.98 209	93.91 299	96.45 277	99.17 195	97.85 152	98.41 216	97.14 328	98.47 43	99.92 39	98.02 103	99.05 273	96.92 352

xiu_mvs_v1_base		97.86 183	98.17 150	96.92 298	98.98 209	93.91 299	96.45 277	99.17 195	97.85 152	98.41 216	97.14 328	98.47 43	99.92 39	98.02 103	99.05 273	96.92 352

xiu_mvs_v1_base_debi		97.86 183	98.17 150	96.92 298	98.98 209	93.91 299	96.45 277	99.17 195	97.85 152	98.41 216	97.14 328	98.47 43	99.92 39	98.02 103	99.05 273	96.92 352

NCCC		97.86 183	97.47 208	99.05 124	98.61 276	98.07 139	96.98 251	98.90 242	97.63 166	97.04 298	97.93 290	95.99 201	99.66 258	95.31 263	98.82 294	99.43 142

PMVS	91.26 20	97.86 183	97.94 173	97.65 258	99.71 43	97.94 154	98.52 109	98.68 275	98.99 80	97.52 277	99.35 72	97.41 126	98.18 369	91.59 338	99.67 157	96.82 355
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
IterMVS-SCA-FT		97.85 188	98.18 149	96.87 301	99.27 145	91.16 347	95.53 316	99.25 172	99.10 68	99.41 63	99.35 72	93.10 269	99.96 11	98.65 69	99.94 27	99.49 111

D2MVS		97.84 189	97.84 181	97.83 243	99.14 179	94.74 272	96.94 253	98.88 245	95.84 268	98.89 152	98.96 156	94.40 248	99.69 235	97.55 128	99.95 19	99.05 234

CPTT-MVS		97.84 189	97.36 213	99.27 86	99.31 138	98.46 105	98.29 134	99.27 166	94.90 290	97.83 255	98.37 254	94.90 232	99.84 125	93.85 303	99.54 199	99.51 104

mvs_anonymous		97.83 191	98.16 153	96.87 301	98.18 314	91.89 334	97.31 231	98.90 242	97.37 195	98.83 165	99.46 54	96.28 188	99.79 182	98.90 51	98.16 322	98.95 254

h-mvs33		97.77 192	97.33 217	99.10 111	99.21 157	97.84 161	98.35 131	98.57 281	99.11 61	98.58 198	99.02 135	88.65 308	99.96 11	98.11 96	96.34 355	99.49 111

test_vis1_rt		97.75 193	97.72 189	97.83 243	98.81 242	96.35 226	97.30 232	99.69 23	94.61 295	97.87 251	98.05 281	96.26 189	98.32 368	98.74 61	98.18 319	98.82 272

IterMVS		97.73 194	98.11 158	96.57 308	99.24 150	90.28 348	95.52 318	99.21 181	98.86 91	99.33 80	99.33 78	93.11 268	99.94 26	98.49 79	99.94 27	99.48 121
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test_fmvs1		97.72 195	97.94 173	97.07 292	98.66 273	92.39 328	97.68 197	99.81 13	95.20 284	99.54 40	99.44 59	91.56 289	99.41 324	99.78 7	99.77 108	99.40 157

MSDG		97.71 196	97.52 203	98.28 214	98.91 223	96.82 215	94.42 348	99.37 118	97.65 165	98.37 221	98.29 263	97.40 127	99.33 334	94.09 295	99.22 253	98.68 296

CDS-MVSNet		97.69 197	97.35 214	98.69 167	98.73 251	97.02 209	96.92 257	98.75 270	95.89 267	98.59 196	98.67 214	92.08 285	99.74 216	96.72 190	99.81 83	99.32 188
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MS-PatchMatch		97.68 198	97.75 185	97.45 276	98.23 312	93.78 305	97.29 233	98.84 256	96.10 259	98.64 187	98.65 219	96.04 195	99.36 330	96.84 179	99.14 265	99.20 213

Fast-Effi-MVS+		97.67 199	97.38 211	98.57 181	98.71 256	97.43 188	97.23 237	99.45 93	94.82 292	96.13 329	96.51 336	98.52 42	99.91 47	96.19 228	98.83 293	98.37 313

EU-MVSNet		97.66 200	98.50 104	95.13 336	99.63 61	85.84 364	98.35 131	98.21 296	98.23 124	99.54 40	99.46 54	95.02 230	99.68 244	98.24 90	99.87 62	99.87 9

MVS_0304		97.64 201	97.35 214	98.52 190	97.87 330	96.69 221	98.59 100	98.05 306	97.44 189	93.74 364	98.85 183	93.69 264	99.88 71	98.11 96	99.81 83	98.98 247

pmmvs5		97.64 201	97.49 205	98.08 228	99.14 179	95.12 263	96.70 268	99.05 218	93.77 314	98.62 190	98.83 187	93.23 265	99.75 211	98.33 88	99.76 119	99.36 175

N_pmnet		97.63 203	97.17 223	98.99 131	99.27 145	97.86 159	95.98 296	93.41 361	95.25 282	99.47 53	98.90 170	95.63 213	99.85 109	96.91 168	99.73 126	99.27 199

mvsany_test1		97.60 204	97.54 201	97.77 248	97.72 335	95.35 254	95.36 323	97.13 327	94.13 308	99.71 20	99.33 78	97.93 85	99.30 338	97.60 127	98.94 288	98.67 297

YYNet1		97.60 204	97.67 191	97.39 280	99.04 200	93.04 318	95.27 324	98.38 291	97.25 207	98.92 148	98.95 160	95.48 220	99.73 220	96.99 162	98.74 296	99.41 148

MDA-MVSNet_test_wron		97.60 204	97.66 194	97.41 279	99.04 200	93.09 314	95.27 324	98.42 288	97.26 206	98.88 156	98.95 160	95.43 221	99.73 220	97.02 159	98.72 298	99.41 148

pmmvs4		97.58 207	97.28 218	98.51 192	98.84 235	96.93 213	95.40 322	98.52 284	93.60 316	98.61 192	98.65 219	95.10 229	99.60 278	96.97 165	99.79 99	98.99 246

PVSNet_BlendedMVS		97.55 208	97.53 202	97.60 262	98.92 220	93.77 306	96.64 270	99.43 103	94.49 297	97.62 267	99.18 103	96.82 160	99.67 247	94.73 273	99.93 31	99.36 175

ppachtmachnet_test		97.50 209	97.74 186	96.78 306	98.70 260	91.23 346	94.55 346	99.05 218	96.36 249	99.21 103	98.79 195	96.39 182	99.78 193	96.74 187	99.82 79	99.34 181

FMVSNet3		97.50 209	97.24 220	98.29 213	98.08 320	95.83 240	97.86 181	98.91 241	97.89 149	98.95 140	98.95 160	87.06 314	99.81 162	97.77 119	99.69 146	99.23 208

CHOSEN 1792x2688		97.49 211	97.14 227	98.54 189	99.68 52	96.09 233	96.50 275	99.62 34	91.58 339	98.84 164	98.97 153	92.36 281	99.88 71	96.76 185	99.95 19	99.67 43

CLD-MVS		97.49 211	97.16 224	98.48 195	99.07 192	97.03 208	94.71 338	99.21 181	94.46 299	98.06 240	97.16 326	97.57 111	99.48 312	94.46 281	99.78 104	98.95 254
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
hse-mvs2		97.46 213	97.07 228	98.64 170	98.73 251	97.33 191	97.45 223	97.64 317	99.11 61	98.58 198	97.98 285	88.65 308	99.79 182	98.11 96	97.39 339	98.81 276

Vis-MVSNet (Re-imp)		97.46 213	97.16 224	98.34 208	99.55 79	96.10 231	98.94 73	98.44 287	98.32 116	98.16 230	98.62 226	88.76 304	99.73 220	93.88 301	99.79 99	99.18 220

jason		97.45 215	97.35 214	97.76 251	99.24 150	93.93 298	95.86 305	98.42 288	94.24 305	98.50 208	98.13 272	94.82 236	99.91 47	97.22 144	99.73 126	99.43 142
jason: jason.
CL-MVSNet_self_test		97.44 216	97.22 221	98.08 228	98.57 283	95.78 242	94.30 351	98.79 264	96.58 243	98.60 194	98.19 270	94.74 243	99.64 266	96.41 216	98.84 292	98.82 272

DSMNet-mixed		97.42 217	97.60 199	96.87 301	99.15 178	91.46 338	98.54 107	99.12 206	92.87 327	97.58 271	99.63 27	96.21 190	99.90 52	95.74 250	99.54 199	99.27 199

USDC		97.41 218	97.40 209	97.44 277	98.94 214	93.67 308	95.17 327	99.53 67	94.03 311	98.97 137	99.10 120	95.29 223	99.34 332	95.84 247	99.73 126	99.30 195

our_test_3		97.39 219	97.73 188	96.34 312	98.70 260	89.78 350	94.61 344	98.97 233	96.50 244	99.04 126	98.85 183	95.98 202	99.84 125	97.26 143	99.67 157	99.41 148

c3_l		97.36 220	97.37 212	97.31 281	98.09 319	93.25 313	95.01 332	99.16 198	97.05 222	98.77 174	98.72 205	92.88 274	99.64 266	96.93 167	99.76 119	99.05 234

alignmvs		97.35 221	96.88 238	98.78 157	98.54 286	98.09 133	97.71 194	97.69 314	99.20 54	97.59 270	95.90 348	88.12 313	99.55 294	98.18 94	98.96 286	98.70 292

Patchmtry		97.35 221	96.97 232	98.50 194	97.31 353	96.47 223	98.18 144	98.92 239	98.95 85	98.78 171	99.37 68	85.44 329	99.85 109	95.96 239	99.83 76	99.17 224

DP-MVS Recon		97.33 223	96.92 235	98.57 181	99.09 188	97.99 145	96.79 261	99.35 127	93.18 321	97.71 262	98.07 280	95.00 231	99.31 336	93.97 297	99.13 267	98.42 310

QAPM		97.31 224	96.81 245	98.82 148	98.80 245	97.49 184	99.06 62	99.19 187	90.22 351	97.69 264	99.16 109	96.91 154	99.90 52	90.89 349	99.41 225	99.07 232

UnsupCasMVSNet_bld		97.30 225	96.92 235	98.45 198	99.28 143	96.78 219	96.20 291	99.27 166	95.42 277	98.28 224	98.30 262	93.16 267	99.71 228	94.99 267	97.37 340	98.87 268

F-COLMAP		97.30 225	96.68 252	99.14 105	99.19 164	98.39 108	97.27 236	99.30 153	92.93 325	96.62 318	98.00 283	95.73 211	99.68 244	92.62 327	98.46 311	99.35 179

1112_ss		97.29 227	96.86 239	98.58 179	99.34 137	96.32 227	96.75 265	99.58 41	93.14 322	96.89 308	97.48 314	92.11 284	99.86 97	96.91 168	99.54 199	99.57 77

CANet_DTU		97.26 228	97.06 229	97.84 242	97.57 342	94.65 277	96.19 292	98.79 264	97.23 213	95.14 350	98.24 265	93.22 266	99.84 125	97.34 139	99.84 69	99.04 238

Patchmatch-RL test		97.26 228	97.02 231	97.99 236	99.52 87	95.53 247	96.13 293	99.71 20	97.47 181	99.27 91	99.16 109	84.30 338	99.62 271	97.89 110	99.77 108	98.81 276

CDPH-MVS		97.26 228	96.66 255	99.07 117	99.00 205	98.15 129	96.03 295	99.01 229	91.21 345	97.79 258	97.85 294	96.89 155	99.69 235	92.75 324	99.38 230	99.39 160

PatchMatch-RL		97.24 231	96.78 246	98.61 176	99.03 203	97.83 162	96.36 283	99.06 215	93.49 319	97.36 289	97.78 296	95.75 210	99.49 309	93.44 312	98.77 295	98.52 302

eth_miper_zixun_eth		97.23 232	97.25 219	97.17 287	98.00 323	92.77 322	94.71 338	99.18 191	97.27 205	98.56 201	98.74 202	91.89 286	99.69 235	97.06 158	99.81 83	99.05 234

sss		97.21 233	96.93 233	98.06 230	98.83 237	95.22 259	96.75 265	98.48 286	94.49 297	97.27 290	97.90 291	92.77 277	99.80 169	96.57 200	99.32 237	99.16 227

LFMVS		97.20 234	96.72 249	98.64 170	98.72 253	96.95 211	98.93 74	94.14 359	99.74 6	98.78 171	99.01 144	84.45 335	99.73 220	97.44 134	99.27 246	99.25 203

HyFIR lowres test		97.19 235	96.60 260	98.96 134	99.62 63	97.28 194	95.17 327	99.50 73	94.21 306	99.01 130	98.32 261	86.61 317	99.99 2	97.10 154	99.84 69	99.60 60

miper_lstm_enhance		97.18 236	97.16 224	97.25 285	98.16 315	92.85 320	95.15 329	99.31 145	97.25 207	98.74 179	98.78 196	90.07 296	99.78 193	97.19 145	99.80 94	99.11 230

CNLPA		97.17 237	96.71 250	98.55 186	98.56 284	98.05 142	96.33 284	98.93 236	96.91 229	97.06 297	97.39 319	94.38 249	99.45 318	91.66 335	99.18 261	98.14 320

xiu_mvs_v2_base		97.16 238	97.49 205	96.17 317	98.54 286	92.46 326	95.45 320	98.84 256	97.25 207	97.48 281	96.49 337	98.31 55	99.90 52	96.34 220	98.68 303	96.15 363

AdaColmap		97.14 239	96.71 250	98.46 197	98.34 304	97.80 168	96.95 252	98.93 236	95.58 272	96.92 302	97.66 303	95.87 207	99.53 299	90.97 346	99.14 265	98.04 324

iter_conf_final		97.10 240	96.65 257	98.45 198	98.53 288	96.08 234	98.30 133	99.11 208	98.10 136	98.85 161	98.95 160	79.38 359	99.87 88	98.68 67	99.91 47	99.40 157

train_agg		97.10 240	96.45 265	99.07 117	98.71 256	98.08 137	95.96 299	99.03 223	91.64 337	95.85 335	97.53 310	96.47 179	99.76 204	93.67 305	99.16 262	99.36 175

OpenMVS	96.65 7	97.09 242	96.68 252	98.32 209	98.32 305	97.16 204	98.86 80	99.37 118	89.48 355	96.29 328	99.15 113	96.56 175	99.90 52	92.90 318	99.20 256	97.89 329

PS-MVSNAJ		97.08 243	97.39 210	96.16 319	98.56 284	92.46 326	95.24 326	98.85 255	97.25 207	97.49 280	95.99 346	98.07 73	99.90 52	96.37 217	98.67 304	96.12 364

miper_ehance_all_eth		97.06 244	97.03 230	97.16 289	97.83 331	93.06 315	94.66 341	99.09 212	95.99 264	98.69 181	98.45 247	92.73 278	99.61 277	96.79 181	99.03 277	98.82 272

lupinMVS		97.06 244	96.86 239	97.65 258	98.88 230	93.89 302	95.48 319	97.97 307	93.53 317	98.16 230	97.58 308	93.81 260	99.91 47	96.77 184	99.57 191	99.17 224

API-MVS		97.04 246	96.91 237	97.42 278	97.88 329	98.23 124	98.18 144	98.50 285	97.57 172	97.39 287	96.75 333	96.77 164	99.15 351	90.16 352	99.02 280	94.88 369

cl____		97.02 247	96.83 242	97.58 264	97.82 332	94.04 292	94.66 341	99.16 198	97.04 223	98.63 188	98.71 206	88.68 307	99.69 235	97.00 160	99.81 83	99.00 245

DIV-MVS_self_test		97.02 247	96.84 241	97.58 264	97.82 332	94.03 293	94.66 341	99.16 198	97.04 223	98.63 188	98.71 206	88.69 305	99.69 235	97.00 160	99.81 83	99.01 242

RPMNet		97.02 247	96.93 233	97.30 282	97.71 337	94.22 284	98.11 151	99.30 153	99.37 38	96.91 304	99.34 76	86.72 316	99.87 88	97.53 131	97.36 342	97.81 334

HQP-MVS		97.00 250	96.49 264	98.55 186	98.67 268	96.79 216	96.29 286	99.04 221	96.05 260	95.55 341	96.84 331	93.84 258	99.54 297	92.82 321	99.26 249	99.32 188

FA-MVS(test-final)		96.99 251	96.82 243	97.50 273	98.70 260	94.78 270	99.34 19	96.99 330	95.07 285	98.48 210	99.33 78	88.41 311	99.65 263	96.13 234	98.92 290	98.07 323

new_pmnet		96.99 251	96.76 247	97.67 256	98.72 253	94.89 268	95.95 301	98.20 297	92.62 330	98.55 203	98.54 234	94.88 235	99.52 303	93.96 298	99.44 223	98.59 301

Test_1112_low_res		96.99 251	96.55 262	98.31 211	99.35 135	95.47 250	95.84 308	99.53 67	91.51 341	96.80 313	98.48 245	91.36 290	99.83 139	96.58 198	99.53 203	99.62 53

PVSNet_Blended		96.88 254	96.68 252	97.47 275	98.92 220	93.77 306	94.71 338	99.43 103	90.98 347	97.62 267	97.36 322	96.82 160	99.67 247	94.73 273	99.56 194	98.98 247

MVSTER		96.86 255	96.55 262	97.79 246	97.91 327	94.21 286	97.56 212	98.87 247	97.49 180	99.06 119	99.05 130	80.72 351	99.80 169	98.44 81	99.82 79	99.37 169

BH-untuned		96.83 256	96.75 248	97.08 290	98.74 250	93.33 312	96.71 267	98.26 294	96.72 237	98.44 213	97.37 321	95.20 226	99.47 315	91.89 333	97.43 338	98.44 308

BH-RMVSNet		96.83 256	96.58 261	97.58 264	98.47 293	94.05 290	96.67 269	97.36 320	96.70 239	97.87 251	97.98 285	95.14 228	99.44 320	90.47 351	98.58 309	99.25 203

PAPM_NR		96.82 258	96.32 268	98.30 212	99.07 192	96.69 221	97.48 220	98.76 267	95.81 269	96.61 319	96.47 339	94.12 256	99.17 349	90.82 350	97.78 332	99.06 233

MG-MVS		96.77 259	96.61 258	97.26 284	98.31 306	93.06 315	95.93 302	98.12 303	96.45 247	97.92 247	98.73 203	93.77 262	99.39 327	91.19 345	99.04 276	99.33 186

test_yl		96.69 260	96.29 269	97.90 238	98.28 307	95.24 257	97.29 233	97.36 320	98.21 125	98.17 228	97.86 292	86.27 319	99.55 294	94.87 270	98.32 313	98.89 264

DCV-MVSNet		96.69 260	96.29 269	97.90 238	98.28 307	95.24 257	97.29 233	97.36 320	98.21 125	98.17 228	97.86 292	86.27 319	99.55 294	94.87 270	98.32 313	98.89 264

WTY-MVS		96.67 262	96.27 271	97.87 241	98.81 242	94.61 278	96.77 263	97.92 309	94.94 289	97.12 293	97.74 299	91.11 291	99.82 149	93.89 300	98.15 323	99.18 220

PatchT		96.65 263	96.35 266	97.54 269	97.40 350	95.32 255	97.98 169	96.64 339	99.33 43	96.89 308	99.42 62	84.32 337	99.81 162	97.69 126	97.49 335	97.48 347

TAPA-MVS	96.21 11	96.63 264	95.95 275	98.65 169	98.93 216	98.09 133	96.93 255	99.28 163	83.58 368	98.13 234	97.78 296	96.13 192	99.40 325	93.52 309	99.29 244	98.45 306
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MIMVSNet		96.62 265	96.25 272	97.71 255	99.04 200	94.66 276	99.16 50	96.92 335	97.23 213	97.87 251	99.10 120	86.11 323	99.65 263	91.65 336	99.21 255	98.82 272

Patchmatch-test		96.55 266	96.34 267	97.17 287	98.35 303	93.06 315	98.40 127	97.79 310	97.33 198	98.41 216	98.67 214	83.68 342	99.69 235	95.16 265	99.31 239	98.77 284

iter_conf05		96.54 267	96.07 273	97.92 237	97.90 328	94.50 280	97.87 180	99.14 204	97.73 159	98.89 152	98.95 160	75.75 369	99.87 88	98.50 78	99.92 41	99.40 157

PMMVS		96.51 268	95.98 274	98.09 225	97.53 345	95.84 239	94.92 334	98.84 256	91.58 339	96.05 333	95.58 352	95.68 212	99.66 258	95.59 257	98.09 326	98.76 286

PLC	94.65 16	96.51 268	95.73 279	98.85 145	98.75 249	97.91 155	96.42 280	99.06 215	90.94 348	95.59 338	97.38 320	94.41 247	99.59 282	90.93 347	98.04 330	99.05 234
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
114514_t		96.50 270	95.77 277	98.69 167	99.48 106	97.43 188	97.84 183	99.55 59	81.42 370	96.51 322	98.58 231	95.53 216	99.67 247	93.41 313	99.58 187	98.98 247

test1111		96.49 271	96.82 243	95.52 330	99.42 119	87.08 361	99.22 41	87.14 374	99.11 61	99.46 54	99.58 34	88.69 305	99.86 97	98.80 56	99.95 19	99.62 53

MAR-MVS		96.47 272	95.70 280	98.79 154	97.92 326	99.12 57	98.28 135	98.60 280	92.16 335	95.54 344	96.17 344	94.77 242	99.52 303	89.62 354	98.23 316	97.72 340
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
ECVR-MVS		96.42 273	96.61 258	95.85 322	99.38 124	88.18 357	99.22 41	86.00 376	99.08 73	99.36 75	99.57 35	88.47 310	99.82 149	98.52 77	99.95 19	99.54 92

SCA		96.41 274	96.66 255	95.67 326	98.24 310	88.35 355	95.85 307	96.88 336	96.11 258	97.67 265	98.67 214	93.10 269	99.85 109	94.16 290	99.22 253	98.81 276

DPM-MVS		96.32 275	95.59 285	98.51 192	98.76 247	97.21 199	94.54 347	98.26 294	91.94 336	96.37 326	97.25 324	93.06 271	99.43 321	91.42 341	98.74 296	98.89 264

CMPMVS	75.91 23	96.29 276	95.44 289	98.84 146	96.25 369	98.69 88	97.02 248	99.12 206	88.90 358	97.83 255	98.86 180	89.51 300	98.90 361	91.92 332	99.51 208	98.92 260
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
CR-MVSNet		96.28 277	95.95 275	97.28 283	97.71 337	94.22 284	98.11 151	98.92 239	92.31 333	96.91 304	99.37 68	85.44 329	99.81 162	97.39 137	97.36 342	97.81 334

CVMVSNet		96.25 278	97.21 222	93.38 352	99.10 185	80.56 378	97.20 241	98.19 299	96.94 227	99.00 131	99.02 135	89.50 301	99.80 169	96.36 219	99.59 182	99.78 19

AUN-MVS		96.24 279	95.45 288	98.60 177	98.70 260	97.22 198	97.38 226	97.65 315	95.95 265	95.53 345	97.96 289	82.11 350	99.79 182	96.31 221	97.44 337	98.80 281

EPNet		96.14 280	95.44 289	98.25 215	90.76 379	95.50 249	97.92 173	94.65 352	98.97 82	92.98 365	98.85 183	89.12 303	99.87 88	95.99 237	99.68 151	99.39 160
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
wuyk23d		96.06 281	97.62 198	91.38 355	98.65 275	98.57 96	98.85 81	96.95 333	96.86 231	99.90 6	99.16 109	99.18 11	98.40 367	89.23 355	99.77 108	77.18 373

miper_enhance_ethall		96.01 282	95.74 278	96.81 305	96.41 367	92.27 331	93.69 360	98.89 244	91.14 346	98.30 222	97.35 323	90.58 293	99.58 286	96.31 221	99.03 277	98.60 299

FMVSNet5		96.01 282	95.20 297	98.41 202	97.53 345	96.10 231	98.74 84	99.50 73	97.22 216	98.03 244	99.04 132	69.80 373	99.88 71	97.27 142	99.71 138	99.25 203

baseline1		95.96 284	95.44 289	97.52 271	98.51 291	93.99 296	98.39 128	96.09 345	98.21 125	98.40 220	97.76 298	86.88 315	99.63 269	95.42 261	89.27 373	98.95 254

HY-MVS	95.94 13	95.90 285	95.35 293	97.55 268	97.95 324	94.79 269	98.81 83	96.94 334	92.28 334	95.17 349	98.57 232	89.90 298	99.75 211	91.20 344	97.33 344	98.10 321

GA-MVS		95.86 286	95.32 294	97.49 274	98.60 278	94.15 289	93.83 358	97.93 308	95.49 275	96.68 315	97.42 318	83.21 343	99.30 338	96.22 226	98.55 310	99.01 242

OpenMVS_ROB	95.38 14	95.84 287	95.18 298	97.81 245	98.41 301	97.15 205	97.37 227	98.62 279	83.86 367	98.65 186	98.37 254	94.29 251	99.68 244	88.41 356	98.62 307	96.60 358

cl22		95.79 288	95.39 292	96.98 295	96.77 362	92.79 321	94.40 349	98.53 283	94.59 296	97.89 250	98.17 271	82.82 347	99.24 344	96.37 217	99.03 277	98.92 260

1314		95.74 289	95.60 284	96.17 317	97.53 345	92.75 323	98.07 156	98.31 293	91.22 344	94.25 356	96.68 334	95.53 216	99.03 353	91.64 337	97.18 345	96.74 356

PVSNet	93.40 17	95.67 290	95.70 280	95.57 329	98.83 237	88.57 353	92.50 365	97.72 312	92.69 329	96.49 325	96.44 340	93.72 263	99.43 321	93.61 306	99.28 245	98.71 290

FE-MVS		95.66 291	94.95 303	97.77 248	98.53 288	95.28 256	99.40 15	96.09 345	93.11 323	97.96 246	99.26 88	79.10 361	99.77 199	92.40 330	98.71 300	98.27 315

tttt0517		95.64 292	94.98 301	97.64 260	99.36 131	93.81 304	98.72 87	90.47 370	98.08 138	98.67 183	98.34 258	73.88 371	99.92 39	97.77 119	99.51 208	99.20 213

PatchmatchNet		95.58 293	95.67 282	95.30 335	97.34 352	87.32 360	97.65 202	96.65 338	95.30 281	97.07 296	98.69 210	84.77 332	99.75 211	94.97 268	98.64 305	98.83 271
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
TR-MVS		95.55 294	95.12 299	96.86 304	97.54 344	93.94 297	96.49 276	96.53 340	94.36 304	97.03 299	96.61 335	94.26 252	99.16 350	86.91 360	96.31 356	97.47 348

JIA-IIPM		95.52 295	95.03 300	97.00 293	96.85 360	94.03 293	96.93 255	95.82 348	99.20 54	94.63 354	99.71 16	83.09 344	99.60 278	94.42 284	94.64 366	97.36 349

CHOSEN 280x420		95.51 296	95.47 286	95.65 328	98.25 309	88.27 356	93.25 362	98.88 245	93.53 317	94.65 353	97.15 327	86.17 321	99.93 31	97.41 136	99.93 31	98.73 289

ADS-MVSNet2		95.43 297	94.98 301	96.76 307	98.14 316	91.74 335	97.92 173	97.76 311	90.23 349	96.51 322	98.91 167	85.61 326	99.85 109	92.88 319	96.90 348	98.69 293

PAPR		95.29 298	94.47 307	97.75 252	97.50 349	95.14 262	94.89 335	98.71 274	91.39 343	95.35 348	95.48 355	94.57 245	99.14 352	84.95 363	97.37 340	98.97 251

thisisatest0530		95.27 299	94.45 308	97.74 253	99.19 164	94.37 282	97.86 181	90.20 371	97.17 217	98.22 226	97.65 304	73.53 372	99.90 52	96.90 173	99.35 233	98.95 254

ADS-MVSNet		95.24 300	94.93 304	96.18 316	98.14 316	90.10 349	97.92 173	97.32 323	90.23 349	96.51 322	98.91 167	85.61 326	99.74 216	92.88 319	96.90 348	98.69 293

BH-w/o		95.13 301	94.89 305	95.86 321	98.20 313	91.31 342	95.65 312	97.37 319	93.64 315	96.52 321	95.70 351	93.04 272	99.02 354	88.10 357	95.82 361	97.24 350

tpmrst		95.07 302	95.46 287	93.91 345	97.11 356	84.36 371	97.62 204	96.96 332	94.98 287	96.35 327	98.80 193	85.46 328	99.59 282	95.60 256	96.23 357	97.79 337

pmmvs3		95.03 303	94.40 309	96.93 297	97.70 339	92.53 325	95.08 330	97.71 313	88.57 359	97.71 262	98.08 279	79.39 358	99.82 149	96.19 228	99.11 271	98.43 309

tpmvs		95.02 304	95.25 295	94.33 341	96.39 368	85.87 363	98.08 155	96.83 337	95.46 276	95.51 346	98.69 210	85.91 324	99.53 299	94.16 290	96.23 357	97.58 345

EPNet_dtu		94.93 305	94.78 306	95.38 334	93.58 376	87.68 359	96.78 262	95.69 350	97.35 197	89.14 372	98.09 278	88.15 312	99.49 309	94.95 269	99.30 242	98.98 247
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
cascas		94.79 306	94.33 312	96.15 320	96.02 372	92.36 330	92.34 367	99.26 171	85.34 366	95.08 351	94.96 363	92.96 273	98.53 366	94.41 287	98.59 308	97.56 346

tpm		94.67 307	94.34 311	95.66 327	97.68 341	88.42 354	97.88 177	94.90 351	94.46 299	96.03 334	98.56 233	78.66 362	99.79 182	95.88 241	95.01 365	98.78 283

test0.0.03 1		94.51 308	93.69 317	96.99 294	96.05 370	93.61 310	94.97 333	93.49 360	96.17 255	97.57 273	94.88 364	82.30 348	99.01 356	93.60 307	94.17 369	98.37 313

thres600view7		94.45 309	93.83 315	96.29 313	99.06 196	91.53 337	97.99 168	94.24 357	98.34 114	97.44 284	95.01 360	79.84 354	99.67 247	84.33 364	98.23 316	97.66 342

PCF-MVS	92.86 18	94.36 310	93.00 327	98.42 201	98.70 260	97.56 181	93.16 363	99.11 208	79.59 371	97.55 274	97.43 317	92.19 282	99.73 220	79.85 372	99.45 220	97.97 328
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
X-MVStestdata		94.32 311	92.59 329	99.53 34	99.46 109	99.21 28	98.65 93	99.34 133	98.62 102	97.54 275	45.85 374	97.50 120	99.83 139	96.79 181	99.53 203	99.56 81

MVS-HIRNet		94.32 311	95.62 283	90.42 356	98.46 294	75.36 379	96.29 286	89.13 373	95.25 282	95.38 347	99.75 11	92.88 274	99.19 348	94.07 296	99.39 227	96.72 357

ET-MVSNet_ETH3D		94.30 313	93.21 323	97.58 264	98.14 316	94.47 281	94.78 337	93.24 363	94.72 293	89.56 371	95.87 349	78.57 364	99.81 162	96.91 168	97.11 347	98.46 304

thres100view900		94.19 314	93.67 318	95.75 325	99.06 196	91.35 341	98.03 162	94.24 357	98.33 115	97.40 286	94.98 362	79.84 354	99.62 271	83.05 366	98.08 327	96.29 359

E-PMN		94.17 315	94.37 310	93.58 349	96.86 359	85.71 366	90.11 369	97.07 328	98.17 131	97.82 257	97.19 325	84.62 334	98.94 358	89.77 353	97.68 334	96.09 365

thres400		94.14 316	93.44 320	96.24 315	98.93 216	91.44 339	97.60 207	94.29 355	97.94 144	97.10 294	94.31 368	79.67 356	99.62 271	83.05 366	98.08 327	97.66 342

thisisatest0515		94.12 317	93.16 324	96.97 296	98.60 278	92.90 319	93.77 359	90.61 369	94.10 309	96.91 304	95.87 349	74.99 370	99.80 169	94.52 279	99.12 270	98.20 317

tfpn200view9		94.03 318	93.44 320	95.78 324	98.93 216	91.44 339	97.60 207	94.29 355	97.94 144	97.10 294	94.31 368	79.67 356	99.62 271	83.05 366	98.08 327	96.29 359

CostFormer		93.97 319	93.78 316	94.51 340	97.53 345	85.83 365	97.98 169	95.96 347	89.29 357	94.99 352	98.63 224	78.63 363	99.62 271	94.54 278	96.50 353	98.09 322

test-LLR		93.90 320	93.85 314	94.04 343	96.53 364	84.62 369	94.05 355	92.39 365	96.17 255	94.12 358	95.07 358	82.30 348	99.67 247	95.87 244	98.18 319	97.82 332

EMVS		93.83 321	94.02 313	93.23 353	96.83 361	84.96 367	89.77 370	96.32 342	97.92 146	97.43 285	96.36 343	86.17 321	98.93 359	87.68 358	97.73 333	95.81 366

baseline2		93.73 322	92.83 328	96.42 311	97.70 339	91.28 344	96.84 260	89.77 372	93.96 313	92.44 366	95.93 347	79.14 360	99.77 199	92.94 317	96.76 352	98.21 316

thres200		93.72 323	93.14 325	95.46 333	98.66 273	91.29 343	96.61 272	94.63 353	97.39 193	96.83 311	93.71 370	79.88 353	99.56 291	82.40 369	98.13 324	95.54 368

EPMVS		93.72 323	93.27 322	95.09 337	96.04 371	87.76 358	98.13 148	85.01 377	94.69 294	96.92 302	98.64 222	78.47 366	99.31 336	95.04 266	96.46 354	98.20 317

dp		93.47 325	93.59 319	93.13 354	96.64 363	81.62 377	97.66 200	96.42 341	92.80 328	96.11 330	98.64 222	78.55 365	99.59 282	93.31 314	92.18 372	98.16 319

FPMVS		93.44 326	92.23 331	97.08 290	99.25 149	97.86 159	95.61 313	97.16 326	92.90 326	93.76 363	98.65 219	75.94 368	95.66 373	79.30 373	97.49 335	97.73 339

tpm cat1		93.29 327	93.13 326	93.75 347	97.39 351	84.74 368	97.39 225	97.65 315	83.39 369	94.16 357	98.41 249	82.86 346	99.39 327	91.56 339	95.35 364	97.14 351

MVS		93.19 328	92.09 332	96.50 310	96.91 358	94.03 293	98.07 156	98.06 305	68.01 372	94.56 355	96.48 338	95.96 204	99.30 338	83.84 365	96.89 350	96.17 361

tpm2		93.09 329	92.58 330	94.62 339	97.56 343	86.53 362	97.66 200	95.79 349	86.15 364	94.07 360	98.23 267	75.95 367	99.53 299	90.91 348	96.86 351	97.81 334

KD-MVS_2432*1600		92.87 330	91.99 333	95.51 331	91.37 377	89.27 351	94.07 353	98.14 301	95.42 277	97.25 291	96.44 340	67.86 375	99.24 344	91.28 342	96.08 359	98.02 325

miper_refine_blended		92.87 330	91.99 333	95.51 331	91.37 377	89.27 351	94.07 353	98.14 301	95.42 277	97.25 291	96.44 340	67.86 375	99.24 344	91.28 342	96.08 359	98.02 325

MVE	83.40 22	92.50 332	91.92 335	94.25 342	98.83 237	91.64 336	92.71 364	83.52 378	95.92 266	86.46 375	95.46 356	95.20 226	95.40 374	80.51 371	98.64 305	95.73 367
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test2506		92.39 333	91.89 336	93.89 346	99.38 124	82.28 375	99.32 22	66.03 382	99.08 73	98.77 174	99.57 35	66.26 379	99.84 125	98.71 64	99.95 19	99.54 92

gg-mvs-nofinetune		92.37 334	91.20 339	95.85 322	95.80 373	92.38 329	99.31 26	81.84 379	99.75 5	91.83 368	99.74 12	68.29 374	99.02 354	87.15 359	97.12 346	96.16 362

test-mter		92.33 335	91.76 338	94.04 343	96.53 364	84.62 369	94.05 355	92.39 365	94.00 312	94.12 358	95.07 358	65.63 381	99.67 247	95.87 244	98.18 319	97.82 332

IB-MVS	91.63 19	92.24 336	90.90 340	96.27 314	97.22 355	91.24 345	94.36 350	93.33 362	92.37 332	92.24 367	94.58 367	66.20 380	99.89 62	93.16 316	94.63 367	97.66 342
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		92.19 337	91.77 337	93.46 350	96.48 366	82.80 374	94.05 355	91.52 368	94.45 301	94.00 361	94.88 364	66.65 378	99.56 291	95.78 249	98.11 325	98.02 325

PAPM		91.88 338	90.34 341	96.51 309	98.06 321	92.56 324	92.44 366	97.17 325	86.35 363	90.38 370	96.01 345	86.61 317	99.21 347	70.65 375	95.43 363	97.75 338

PVSNet_0	89.98 21	91.15 339	90.30 342	93.70 348	97.72 335	84.34 372	90.24 368	97.42 318	90.20 352	93.79 362	93.09 371	90.90 292	98.89 362	86.57 361	72.76 375	97.87 331

EGC-MVSNET		85.24 340	80.54 343	99.34 72	99.77 27	99.20 34	99.08 58	99.29 160	12.08 376	20.84 377	99.42 62	97.55 113	99.85 109	97.08 155	99.72 133	98.96 253

test_method		79.78 341	79.50 344	80.62 357	80.21 380	45.76 382	70.82 371	98.41 290	31.08 375	80.89 376	97.71 300	84.85 331	97.37 371	91.51 340	80.03 374	98.75 287

tmp_tt		78.77 342	78.73 345	78.90 358	58.45 381	74.76 381	94.20 352	78.26 381	39.16 374	86.71 374	92.82 372	80.50 352	75.19 377	86.16 362	92.29 371	86.74 372

cdsmvs_eth3d_5k		24.66 343	32.88 346	0.00 361	0.00 384	0.00 385	0.00 372	99.10 210	0.00 379	0.00 380	97.58 308	99.21 10	0.00 380	0.00 378	0.00 378	0.00 376

testmvs		17.12 344	20.53 347	6.87 360	12.05 382	4.20 384	93.62 361	6.73 383	4.62 378	10.41 378	24.33 375	8.28 383	3.56 379	9.69 377	15.07 376	12.86 375

test123		17.04 345	20.11 348	7.82 359	10.25 383	4.91 383	94.80 336	4.47 384	4.93 377	10.00 379	24.28 376	9.69 382	3.64 378	10.14 376	12.43 377	14.92 374

pcd_1.5k_mvsjas		8.17 346	10.90 349	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	98.07 73	0.00 380	0.00 378	0.00 378	0.00 376

ab-mvs-re		8.12 347	10.83 350	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	97.48 314	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

test_blank		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

uanet_test		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

DCPMVS		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

sosnet-low-res		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

sosnet		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

uncertanet		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

Regformer		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

uanet		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

FOURS1					99.73 35	99.67 2	99.43 11	99.54 64	99.43 33	99.26 95

MSC_two_6792asdad				99.32 78	98.43 297	98.37 111		98.86 252					99.89 62	97.14 150	99.60 178	99.71 32

PC_three_1452									93.27 320	99.40 66	98.54 234	98.22 61	97.00 372	95.17 264	99.45 220	99.49 111

No_MVS				99.32 78	98.43 297	98.37 111		98.86 252					99.89 62	97.14 150	99.60 178	99.71 32

test_one_0601					99.39 123	99.20 34		99.31 145	98.49 109	98.66 185	99.02 135	97.64 105

eth-test2					0.00 384

eth-test					0.00 384

ZD-MVS					99.01 204	98.84 75		99.07 214	94.10 309	98.05 242	98.12 274	96.36 186	99.86 97	92.70 326	99.19 259

RE-MVS-def			98.58 96		99.20 161	99.38 8	98.48 119	99.30 153	98.64 98	98.95 140	98.96 156	97.75 96		96.56 204	99.39 227	99.45 134

IU-MVS					99.49 99	99.15 47		98.87 247	92.97 324	99.41 63				96.76 185	99.62 171	99.66 44

OPU-MVS				98.82 148	98.59 280	98.30 116	98.10 153				98.52 237	98.18 65	98.75 364	94.62 276	99.48 217	99.41 148

test_241102_TWO								99.30 153	98.03 139	99.26 95	99.02 135	97.51 119	99.88 71	96.91 168	99.60 178	99.66 44

test_241102_ONE					99.49 99	99.17 39		99.31 145	97.98 141	99.66 28	98.90 170	98.36 50	99.48 312

9.14			97.78 183		99.07 192		97.53 215	99.32 140	95.53 274	98.54 205	98.70 209	97.58 110	99.76 204	94.32 289	99.46 218

save fliter					99.11 183	97.97 149	96.53 274	99.02 226	98.24 123

test_0728_THIRD									98.17 131	99.08 117	99.02 135	97.89 86	99.88 71	97.07 156	99.71 138	99.70 37

test_0728_SECOND				99.60 11	99.50 92	99.23 26	98.02 163	99.32 140					99.88 71	96.99 162	99.63 168	99.68 40

test0726					99.50 92	99.21 28	98.17 147	99.35 127	97.97 142	99.26 95	99.06 123	97.61 108

GSMVS																98.81 276

test_part2					99.36 131	99.10 60				99.05 124

sam_mvs1												84.74 333				98.81 276

sam_mvs												84.29 339

ambc				98.24 217	98.82 240	95.97 236	98.62 97	99.00 231		99.27 91	99.21 97	96.99 151	99.50 308	96.55 207	99.50 215	99.26 202

MTGPA								99.20 183

test_post1							97.59 209				20.48 378	83.07 345	99.66 258	94.16 290

test_post											21.25 377	83.86 341	99.70 231

patchmatchnet-post											98.77 198	84.37 336	99.85 109

GG-mvs-BLEND				94.76 338	94.54 375	92.13 333	99.31 26	80.47 380		88.73 373	91.01 373	67.59 377	98.16 370	82.30 370	94.53 368	93.98 370

MTMP							97.93 172	91.91 367

gm-plane-assit					94.83 374	81.97 376			88.07 361		94.99 361		99.60 278	91.76 334

test9_res														93.28 315	99.15 264	99.38 167

TEST9					98.71 256	98.08 137	95.96 299	99.03 223	91.40 342	95.85 335	97.53 310	96.52 177	99.76 204

test_8					98.67 268	98.01 144	95.91 304	99.02 226	91.64 337	95.79 337	97.50 313	96.47 179	99.76 204

agg_prior2														92.50 329	99.16 262	99.37 169

agg_prior					98.68 267	97.99 145		99.01 229		95.59 338			99.77 199

TestCases				99.16 102	99.50 92	98.55 97		99.58 41	96.80 232	98.88 156	99.06 123	97.65 102	99.57 288	94.45 282	99.61 176	99.37 169

test_prior4						97.97 149	95.86 305

test_prior2							95.74 310		96.48 246	96.11 330	97.63 306	95.92 206		94.16 290	99.20 256

test_prior				98.95 135	98.69 265	97.95 153		99.03 223					99.59 282			99.30 195

旧先验2							95.76 309		88.56 360	97.52 277			99.66 258	94.48 280

新几何2							95.93 302

新几何1				98.91 140	98.94 214	97.76 170		98.76 267	87.58 362	96.75 314	98.10 276	94.80 239	99.78 193	92.73 325	99.00 282	99.20 213

旧先验1					98.82 240	97.45 187		98.76 267			98.34 258	95.50 219			99.01 281	99.23 208

无先验							95.74 310	98.74 272	89.38 356				99.73 220	92.38 331		99.22 212

原ACMM2							95.53 316

原ACMM1				98.35 207	98.90 224	96.25 229		98.83 260	92.48 331	96.07 332	98.10 276	95.39 222	99.71 228	92.61 328	98.99 283	99.08 231

test222					98.92 220	96.93 213	95.54 315	98.78 266	85.72 365	96.86 310	98.11 275	94.43 246			99.10 272	99.23 208

testdata2													99.79 182	92.80 323

segment_acmp												97.02 149

testdata				98.09 225	98.93 216	95.40 253		98.80 263	90.08 353	97.45 283	98.37 254	95.26 224	99.70 231	93.58 308	98.95 287	99.17 224

testdata1							95.44 321		96.32 251

test12				98.93 137	98.58 281	97.83 162		98.66 276		96.53 320		95.51 218	99.69 235		99.13 267	99.27 199

plane_prior7					99.19 164	97.87 158

plane_prior6					98.99 208	97.70 175						94.90 232

plane_prior5								99.27 166					99.70 231	94.42 284	99.51 208	99.45 134

plane_prior4											97.98 285

plane_prior3						97.78 169			97.41 191	97.79 258

plane_prior2							97.77 188		98.20 128

plane_prior1					99.05 199

plane_prior						97.65 177	97.07 247		96.72 237						99.36 231

n2								0.00 385

nn								0.00 385

door-mid								99.57 48

lessismore_v0				98.97 133	99.73 35	97.53 183		86.71 375		99.37 73	99.52 46	89.93 297	99.92 39	98.99 47	99.72 133	99.44 138

LGP-MVS_train				99.47 54	99.57 68	98.97 66		99.48 82	96.60 241	99.10 115	99.06 123	98.71 30	99.83 139	95.58 258	99.78 104	99.62 53

test11								98.87 247

door								99.41 107

HQP5-MVS						96.79 216

HQP-NCC					98.67 268		96.29 286		96.05 260	95.55 341

ACMP_Plane					98.67 268		96.29 286		96.05 260	95.55 341

BP-MVS														92.82 321

HQP4-MVS										95.56 340			99.54 297			99.32 188

HQP3-MVS								99.04 221							99.26 249

HQP2-MVS												93.84 258

NP-MVS					98.84 235	97.39 190					96.84 331

MDTV_nov1_ep13_2view						74.92 380	97.69 196		90.06 354	97.75 261		85.78 325		93.52 309		98.69 293

MDTV_nov1_ep13			95.22 296		97.06 357	83.20 373	97.74 192	96.16 343	94.37 303	96.99 300	98.83 187	83.95 340	99.53 299	93.90 299	97.95 331

ACMMP++_ref															99.77 108

ACMMP++															99.68 151

Test By Simon												96.52 177

ITE_SJBPF				98.87 143	99.22 155	98.48 104		99.35 127	97.50 178	98.28 224	98.60 229	97.64 105	99.35 331	93.86 302	99.27 246	98.79 282

DeepMVS_CX				93.44 351	98.24 310	94.21 286		94.34 354	64.28 373	91.34 369	94.87 366	89.45 302	92.77 376	77.54 374	93.14 370	93.35 371

High-resolution multi-view benchmark