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 20	99.99 3	100.00 1	99.98 13	99.78 18	100.00 1	99.92 24	100.00 1	99.87 36

mvs_tets		99.90 2	99.90 4	99.90 8	99.96 7	99.79 49	99.72 30	99.88 53	99.92 32	99.98 14	99.93 21	99.94 4	99.98 22	99.77 45	100.00 1	99.92 24

test_fmvsmconf0.01_n		99.89 3	99.88 7	99.91 3	99.98 3	99.76 64	99.12 208	100.00 1	100.00 1	99.99 7	99.91 28	99.98 1	100.00 1	99.97 4	100.00 1	99.99 2

test_vis3_rt		99.89 3	99.90 4	99.87 23	99.98 3	99.75 72	99.70 35	100.00 1	99.73 83	100.00 1	99.89 38	99.79 17	99.88 203	99.98 1	100.00 1	99.98 5

jajsoiax		99.89 3	99.89 6	99.89 11	99.96 7	99.78 52	99.70 35	99.86 59	99.89 41	99.98 14	99.90 33	99.94 4	99.98 22	99.75 46	100.00 1	99.90 26

mvs5depth		99.88 6	99.91 3	99.80 50	99.92 29	99.42 172	99.94 3	100.00 1	99.97 20	99.89 57	99.99 12	99.63 31	99.97 36	99.87 35	99.99 16	100.00 1

ANet_high		99.88 6	99.87 11	99.91 3	99.99 1	99.91 4	99.65 59	100.00 1	99.90 35	100.00 1	99.97 14	99.61 35	99.97 36	99.75 46	100.00 1	99.84 43

LTVRE_ROB	99.19 1	99.88 6	99.87 11	99.88 18	99.91 31	99.90 7	99.96 1	99.92 36	99.90 35	99.97 22	99.87 53	99.81 15	99.95 67	99.54 68	99.99 16	99.80 54
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
test_fmvsmconf0.1_n		99.87 9	99.86 13	99.91 3	99.97 6	99.74 78	99.01 242	99.99 11	99.99 3	99.98 14	99.88 47	99.97 2	99.99 8	99.96 9	100.00 1	99.98 5

fmvsm_s_conf0.1_n		99.86 10	99.85 17	99.89 11	99.93 24	99.78 52	99.07 228	99.98 12	99.99 3	99.98 14	99.90 33	99.88 9	99.92 129	99.93 21	99.99 16	99.98 5

pmmvs6		99.86 10	99.86 13	99.83 35	99.94 18	99.90 7	99.83 7	99.91 42	99.85 57	99.94 39	99.95 16	99.73 22	99.90 170	99.65 55	99.97 59	99.69 93

fmvsm_l_conf0.5_n_3		99.85 12	99.83 21	99.92 2	99.88 44	99.86 18	99.08 224	99.97 20	99.98 15	99.96 27	99.79 103	99.90 8	99.99 8	99.96 9	99.99 16	99.90 26

fmvsm_s_conf0.1_n_a		99.85 12	99.83 21	99.91 3	99.95 15	99.82 38	99.10 216	99.98 12	99.99 3	99.98 14	99.91 28	99.68 27	99.93 103	99.93 21	99.99 16	99.99 2

test_fmvsmconf_n		99.85 12	99.84 20	99.88 18	99.91 31	99.73 81	98.97 254	99.98 12	99.99 3	99.96 27	99.85 65	99.93 7	99.99 8	99.94 17	99.99 16	99.93 20

mvsany_test3		99.85 12	99.88 7	99.75 80	99.95 15	99.37 187	99.53 88	99.98 12	99.77 81	99.99 7	99.95 16	99.85 11	99.94 83	99.95 13	99.98 44	99.94 17

UniMVSNet_ETH3D		99.85 12	99.83 21	99.90 8	99.89 39	99.91 4	99.89 5	99.71 137	99.93 29	99.95 36	99.89 38	99.71 23	99.96 57	99.51 73	99.97 59	99.84 43

test_fmvsmvis_n_1920		99.84 17	99.86 13	99.81 45	99.88 44	99.55 144	99.17 188	99.98 12	99.99 3	99.96 27	99.84 72	99.96 3	99.99 8	99.96 9	99.99 16	99.88 32

test_fmvsm_n_1920		99.84 17	99.85 17	99.83 35	99.82 74	99.70 96	99.17 188	99.97 20	99.99 3	99.96 27	99.82 83	99.94 4	100.00 1	99.95 13	100.00 1	99.80 54

PS-MVSNAJss		99.84 17	99.82 25	99.89 11	99.96 7	99.77 57	99.68 46	99.85 65	99.95 24	99.98 14	99.92 25	99.28 73	99.98 22	99.75 46	100.00 1	99.94 17

test_djsdf		99.84 17	99.81 26	99.91 3	99.94 18	99.84 25	99.77 16	99.80 90	99.73 83	99.97 22	99.92 25	99.77 20	99.98 22	99.43 83	100.00 1	99.90 26

fmvsm_s_conf0.5_n		99.83 21	99.81 26	99.87 23	99.85 59	99.78 52	99.03 237	99.96 27	99.99 3	99.97 22	99.84 72	99.78 18	99.92 129	99.92 24	99.99 16	99.92 24

test_fmvs3		99.83 21	99.93 2	99.53 182	99.96 7	98.62 288	99.67 50	100.00 1	99.95 24	100.00 1	99.95 16	99.85 11	99.99 8	99.98 1	99.99 16	99.98 5

fmvsm_s_conf0.5_n_a		99.82 23	99.79 30	99.89 11	99.85 59	99.82 38	99.03 237	99.96 27	99.99 3	99.97 22	99.84 72	99.58 39	99.93 103	99.92 24	99.98 44	99.93 20

v7n		99.82 23	99.80 29	99.88 18	99.96 7	99.84 25	99.82 9	99.82 78	99.84 60	99.94 39	99.91 28	99.13 93	99.96 57	99.83 37	99.99 16	99.83 47

fmvsm_s_conf0.1_n_2		99.81 25	99.78 34	99.89 11	99.93 24	99.76 64	98.92 263	99.98 12	99.99 3	99.99 7	99.88 47	99.43 52	99.94 83	99.94 17	99.99 16	99.99 2

fmvsm_l_conf0.5_n_a		99.80 26	99.79 30	99.84 32	99.88 44	99.64 116	99.12 208	99.91 42	99.98 15	99.95 36	99.67 184	99.67 28	99.99 8	99.94 17	99.99 16	99.88 32

fmvsm_l_conf0.5_n		99.80 26	99.78 34	99.85 29	99.88 44	99.66 107	99.11 213	99.91 42	99.98 15	99.96 27	99.64 196	99.60 37	99.99 8	99.95 13	99.99 16	99.88 32

anonymousdsp		99.80 26	99.77 37	99.90 8	99.96 7	99.88 12	99.73 27	99.85 65	99.70 94	99.92 47	99.93 21	99.45 51	99.97 36	99.36 96	100.00 1	99.85 41

fmvsm_s_conf0.5_n_3		99.79 29	99.77 37	99.85 29	99.81 83	99.71 88	98.97 254	99.92 36	99.98 15	99.97 22	99.86 60	99.53 46	99.95 67	99.88 32	99.99 16	99.89 31

pm-mvs1		99.79 29	99.79 30	99.78 60	99.91 31	99.83 30	99.76 20	99.87 55	99.73 83	99.89 57	99.87 53	99.63 31	99.87 217	99.54 68	99.92 110	99.63 139

fmvsm_s_conf0.5_n_2		99.78 31	99.75 42	99.88 18	99.82 74	99.76 64	98.88 266	99.92 36	99.98 15	99.98 14	99.85 65	99.42 54	99.94 83	99.93 21	99.98 44	99.94 17

mmtdpeth		99.78 31	99.83 21	99.66 123	99.85 59	99.05 245	99.79 12	99.97 20	100.00 1	99.43 241	99.94 19	99.64 29	99.94 83	99.83 37	99.99 16	99.98 5

sd_testset		99.78 31	99.78 34	99.80 50	99.80 90	99.76 64	99.80 11	99.79 96	99.97 20	99.89 57	99.89 38	99.53 46	99.99 8	99.36 96	99.96 72	99.65 124

UA-Net		99.78 31	99.76 41	99.86 27	99.72 146	99.71 88	99.91 4	99.95 32	99.96 23	99.71 143	99.91 28	99.15 88	99.97 36	99.50 75	100.00 1	99.90 26

TransMVSNet (Re)		99.78 31	99.77 37	99.81 45	99.91 31	99.85 20	99.75 22	99.86 59	99.70 94	99.91 50	99.89 38	99.60 37	99.87 217	99.59 60	99.74 229	99.71 84

SDMVSNet		99.77 36	99.77 37	99.76 70	99.80 90	99.65 113	99.63 61	99.86 59	99.97 20	99.89 57	99.89 38	99.52 48	99.99 8	99.42 88	99.96 72	99.65 124

test_cas_vis1_n_1920		99.76 37	99.86 13	99.45 205	99.93 24	98.40 301	99.30 144	99.98 12	99.94 27	99.99 7	99.89 38	99.80 16	99.97 36	99.96 9	99.97 59	99.97 10

test_f		99.75 38	99.88 7	99.37 233	99.96 7	98.21 313	99.51 95	100.00 1	99.94 27	100.00 1	99.93 21	99.58 39	99.94 83	99.97 4	99.99 16	99.97 10

OurMVSNet-221017-0		99.75 38	99.71 45	99.84 32	99.96 7	99.83 30	99.83 7	99.85 65	99.80 73	99.93 42	99.93 21	98.54 175	99.93 103	99.59 60	99.98 44	99.76 73

Vis-MVSNet		99.75 38	99.74 43	99.79 57	99.88 44	99.66 107	99.69 42	99.92 36	99.67 103	99.77 116	99.75 131	99.61 35	99.98 22	99.35 99	99.98 44	99.72 81
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
mamv4		99.73 41	99.74 43	99.70 109	99.66 176	99.87 14	99.69 42	99.93 34	99.93 29	99.93 42	99.86 60	99.07 102	100.00 1	99.66 53	99.92 110	99.24 288

test_vis1_n_1920		99.72 42	99.88 7	99.27 261	99.93 24	97.84 339	99.34 129	100.00 1	99.99 3	99.99 7	99.82 83	99.87 10	99.99 8	99.97 4	99.99 16	99.97 10

test_fmvs2		99.72 42	99.85 17	99.34 240	99.91 31	98.08 327	99.48 102	100.00 1	99.90 35	99.99 7	99.91 28	99.50 50	99.98 22	99.98 1	99.99 16	99.96 13

TDRefinement		99.72 42	99.70 46	99.77 63	99.90 37	99.85 20	99.86 6	99.92 36	99.69 97	99.78 108	99.92 25	99.37 62	99.88 203	98.93 161	99.95 86	99.60 164

XXY-MVS		99.71 45	99.67 53	99.81 45	99.89 39	99.72 86	99.59 77	99.82 78	99.39 165	99.82 87	99.84 72	99.38 60	99.91 151	99.38 92	99.93 106	99.80 54

nrg030		99.70 46	99.66 55	99.82 40	99.76 121	99.84 25	99.61 70	99.70 142	99.93 29	99.78 108	99.68 180	99.10 95	99.78 322	99.45 81	99.96 72	99.83 47

FC-MVSNet-test		99.70 46	99.65 57	99.86 27	99.88 44	99.86 18	99.72 30	99.78 102	99.90 35	99.82 87	99.83 76	98.45 190	99.87 217	99.51 73	99.97 59	99.86 38

GeoE		99.69 48	99.66 55	99.78 60	99.76 121	99.76 64	99.60 76	99.82 78	99.46 149	99.75 124	99.56 251	99.63 31	99.95 67	99.43 83	99.88 140	99.62 150

v10		99.69 48	99.69 49	99.66 123	99.81 83	99.39 182	99.66 54	99.75 115	99.60 128	99.92 47	99.87 53	98.75 146	99.86 236	99.90 28	99.99 16	99.73 78

EC-MVSNet		99.69 48	99.69 49	99.68 113	99.71 149	99.91 4	99.76 20	99.96 27	99.86 51	99.51 224	99.39 299	99.57 41	99.93 103	99.64 57	99.86 160	99.20 301

test_vis1_n		99.68 51	99.79 30	99.36 237	99.94 18	98.18 316	99.52 89	100.00 1	99.86 51	100.00 1	99.88 47	98.99 114	99.96 57	99.97 4	99.96 72	99.95 14

test_fmvs1_n		99.68 51	99.81 26	99.28 258	99.95 15	97.93 336	99.49 100	100.00 1	99.82 67	99.99 7	99.89 38	99.21 82	99.98 22	99.97 4	99.98 44	99.93 20

SPE-MVS-test		99.68 51	99.70 46	99.64 136	99.57 210	99.83 30	99.78 14	99.97 20	99.92 32	99.50 226	99.38 301	99.57 41	99.95 67	99.69 50	99.90 121	99.15 313

v8		99.68 51	99.69 49	99.65 129	99.80 90	99.40 179	99.66 54	99.76 110	99.64 113	99.93 42	99.85 65	98.66 159	99.84 269	99.88 32	99.99 16	99.71 84

DTE-MVSNet		99.68 51	99.61 66	99.88 18	99.80 90	99.87 14	99.67 50	99.71 137	99.72 87	99.84 81	99.78 114	98.67 157	99.97 36	99.30 108	99.95 86	99.80 54

casdiffmvs_mvg		99.68 51	99.68 52	99.69 111	99.81 83	99.59 134	99.29 151	99.90 47	99.71 89	99.79 104	99.73 139	99.54 44	99.84 269	99.36 96	99.96 72	99.65 124
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CS-MVS		99.67 57	99.70 46	99.58 163	99.53 232	99.84 25	99.79 12	99.96 27	99.90 35	99.61 185	99.41 291	99.51 49	99.95 67	99.66 53	99.89 131	98.96 355

VPA-MVSNet		99.66 58	99.62 62	99.79 57	99.68 169	99.75 72	99.62 64	99.69 149	99.85 57	99.80 98	99.81 90	98.81 134	99.91 151	99.47 78	99.88 140	99.70 87

PS-CasMVS		99.66 58	99.58 74	99.89 11	99.80 90	99.85 20	99.66 54	99.73 125	99.62 118	99.84 81	99.71 154	98.62 163	99.96 57	99.30 108	99.96 72	99.86 38

PEN-MVS		99.66 58	99.59 71	99.89 11	99.83 67	99.87 14	99.66 54	99.73 125	99.70 94	99.84 81	99.73 139	98.56 172	99.96 57	99.29 111	99.94 99	99.83 47

FMVSNet1		99.66 58	99.63 61	99.73 94	99.78 109	99.77 57	99.68 46	99.70 142	99.67 103	99.82 87	99.83 76	98.98 116	99.90 170	99.24 115	99.97 59	99.53 200

MIMVSNet1		99.66 58	99.62 62	99.80 50	99.94 18	99.87 14	99.69 42	99.77 105	99.78 77	99.93 42	99.89 38	97.94 239	99.92 129	99.65 55	99.98 44	99.62 150

FIs		99.65 63	99.58 74	99.84 32	99.84 63	99.85 20	99.66 54	99.75 115	99.86 51	99.74 132	99.79 103	98.27 212	99.85 254	99.37 95	99.93 106	99.83 47

SSC-MVS3.2		99.64 64	99.67 53	99.56 172	99.75 133	98.98 249	98.96 257	99.87 55	99.88 46	99.84 81	99.64 196	99.32 68	99.91 151	99.78 44	99.96 72	99.80 54

testf1		99.63 65	99.60 69	99.72 100	99.94 18	99.95 2	99.47 105	99.89 49	99.43 160	99.88 66	99.80 93	99.26 77	99.90 170	98.81 170	99.88 140	99.32 273

APD_test2		99.63 65	99.60 69	99.72 100	99.94 18	99.95 2	99.47 105	99.89 49	99.43 160	99.88 66	99.80 93	99.26 77	99.90 170	98.81 170	99.88 140	99.32 273

tt0805		99.63 65	99.57 78	99.81 45	99.87 52	99.88 12	99.58 79	98.70 364	99.72 87	99.91 50	99.60 232	99.43 52	99.81 309	99.81 42	99.53 302	99.73 78

KD-MVS_self_test		99.63 65	99.59 71	99.76 70	99.84 63	99.90 7	99.37 124	99.79 96	99.83 65	99.88 66	99.85 65	98.42 194	99.90 170	99.60 59	99.73 235	99.49 222

casdiffmvs		99.63 65	99.61 66	99.67 116	99.79 102	99.59 134	99.13 204	99.85 65	99.79 75	99.76 119	99.72 146	99.33 67	99.82 294	99.21 119	99.94 99	99.59 171
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		99.63 65	99.62 62	99.66 123	99.80 90	99.62 123	99.44 111	99.80 90	99.71 89	99.72 138	99.69 169	99.15 88	99.83 284	99.32 105	99.94 99	99.53 200

Anonymous20231211		99.62 71	99.57 78	99.76 70	99.61 188	99.60 132	99.81 10	99.73 125	99.82 67	99.90 53	99.90 33	97.97 238	99.86 236	99.42 88	99.96 72	99.80 54

DeepC-MVS	98.90 4	99.62 71	99.61 66	99.67 116	99.72 146	99.44 165	99.24 166	99.71 137	99.27 180	99.93 42	99.90 33	99.70 25	99.93 103	98.99 149	99.99 16	99.64 134
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
dcpmvs_2		99.61 73	99.64 60	99.53 182	99.79 102	98.82 266	99.58 79	99.97 20	99.95 24	99.96 27	99.76 126	98.44 191	99.99 8	99.34 100	99.96 72	99.78 64

WR-MVS_H		99.61 73	99.53 89	99.87 23	99.80 90	99.83 30	99.67 50	99.75 115	99.58 131	99.85 78	99.69 169	98.18 224	99.94 83	99.28 113	99.95 86	99.83 47

ACMH	98.42 6	99.59 75	99.54 85	99.72 100	99.86 55	99.62 123	99.56 84	99.79 96	98.77 258	99.80 98	99.85 65	99.64 29	99.85 254	98.70 182	99.89 131	99.70 87
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
v1192		99.57 76	99.57 78	99.57 169	99.77 117	99.22 219	99.04 234	99.60 203	99.18 195	99.87 74	99.72 146	99.08 100	99.85 254	99.89 31	99.98 44	99.66 116

EG-PatchMatch MVS		99.57 76	99.56 83	99.62 152	99.77 117	99.33 197	99.26 159	99.76 110	99.32 174	99.80 98	99.78 114	99.29 71	99.87 217	99.15 131	99.91 120	99.66 116

Gipuma		99.57 76	99.59 71	99.49 193	99.98 3	99.71 88	99.72 30	99.84 71	99.81 70	99.94 39	99.78 114	98.91 126	99.71 349	98.41 198	99.95 86	99.05 342
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
v1921920		99.56 79	99.57 78	99.55 176	99.75 133	99.11 234	99.05 229	99.61 192	99.15 206	99.88 66	99.71 154	99.08 100	99.87 217	99.90 28	99.97 59	99.66 116

v1240		99.56 79	99.58 74	99.51 187	99.80 90	99.00 246	99.00 245	99.65 172	99.15 206	99.90 53	99.75 131	99.09 97	99.88 203	99.90 28	99.96 72	99.67 107

V42		99.56 79	99.54 85	99.63 143	99.79 102	99.46 158	99.39 117	99.59 209	99.24 186	99.86 75	99.70 162	98.55 173	99.82 294	99.79 43	99.95 86	99.60 164

MVSMamba_PlusPlus		99.55 82	99.58 74	99.47 199	99.68 169	99.40 179	99.52 89	99.70 142	99.92 32	99.77 116	99.86 60	98.28 210	99.96 57	99.54 68	99.90 121	99.05 342

v144192		99.55 82	99.54 85	99.58 163	99.78 109	99.20 224	99.11 213	99.62 185	99.18 195	99.89 57	99.72 146	98.66 159	99.87 217	99.88 32	99.97 59	99.66 116

test20.03		99.55 82	99.54 85	99.58 163	99.79 102	99.37 187	99.02 240	99.89 49	99.60 128	99.82 87	99.62 215	98.81 134	99.89 189	99.43 83	99.86 160	99.47 230

v1144		99.54 85	99.53 89	99.59 160	99.79 102	99.28 205	99.10 216	99.61 192	99.20 193	99.84 81	99.73 139	98.67 157	99.84 269	99.86 36	99.98 44	99.64 134

CP-MVSNet		99.54 85	99.43 105	99.87 23	99.76 121	99.82 38	99.57 82	99.61 192	99.54 132	99.80 98	99.64 196	97.79 250	99.95 67	99.21 119	99.94 99	99.84 43

TranMVSNet+NR-MVSNet		99.54 85	99.47 94	99.76 70	99.58 200	99.64 116	99.30 144	99.63 182	99.61 122	99.71 143	99.56 251	98.76 144	99.96 57	99.14 137	99.92 110	99.68 99

SSC-MVS		99.52 88	99.42 107	99.83 35	99.86 55	99.65 113	99.52 89	99.81 87	99.87 48	99.81 94	99.79 103	96.78 294	99.99 8	99.83 37	99.51 306	99.86 38

patch_mono-2		99.51 89	99.46 98	99.64 136	99.70 157	99.11 234	99.04 234	99.87 55	99.71 89	99.47 231	99.79 103	98.24 214	99.98 22	99.38 92	99.96 72	99.83 47

reproduce_model		99.50 90	99.40 110	99.83 35	99.60 190	99.83 30	99.12 208	99.68 152	99.49 140	99.80 98	99.79 103	99.01 111	99.93 103	98.24 211	99.82 187	99.73 78

balanced_conf03		99.50 90	99.50 91	99.50 189	99.42 280	99.49 151	99.52 89	99.75 115	99.86 51	99.78 108	99.71 154	98.20 221	99.90 170	99.39 91	99.88 140	99.10 324

v2v482		99.50 90	99.47 94	99.58 163	99.78 109	99.25 212	99.14 198	99.58 218	99.25 184	99.81 94	99.62 215	98.24 214	99.84 269	99.83 37	99.97 59	99.64 134

ACMH+	98.40 8	99.50 90	99.43 105	99.71 105	99.86 55	99.76 64	99.32 136	99.77 105	99.53 134	99.77 116	99.76 126	99.26 77	99.78 322	97.77 255	99.88 140	99.60 164

Baseline_NR-MVSNet		99.49 94	99.37 116	99.82 40	99.91 31	99.84 25	98.83 274	99.86 59	99.68 99	99.65 165	99.88 47	97.67 258	99.87 217	99.03 146	99.86 160	99.76 73

TAMVS		99.49 94	99.45 100	99.63 143	99.48 257	99.42 172	99.45 109	99.57 220	99.66 107	99.78 108	99.83 76	97.85 246	99.86 236	99.44 82	99.96 72	99.61 160

ttmdpeth		99.48 96	99.55 84	99.29 255	99.76 121	98.16 318	99.33 133	99.95 32	99.79 75	99.36 260	99.89 38	99.13 93	99.77 330	99.09 141	99.64 268	99.93 20

test_fmvs1		99.48 96	99.65 57	98.97 302	99.54 226	97.16 362	99.11 213	99.98 12	99.78 77	99.96 27	99.81 90	98.72 151	99.97 36	99.95 13	99.97 59	99.79 62

pmmvs-eth3d		99.48 96	99.47 94	99.51 187	99.77 117	99.41 178	98.81 279	99.66 162	99.42 164	99.75 124	99.66 189	99.20 83	99.76 333	98.98 151	99.99 16	99.36 263

EI-MVSNet-UG-set		99.48 96	99.50 91	99.42 215	99.57 210	98.65 284	99.24 166	99.46 271	99.68 99	99.80 98	99.66 189	98.99 114	99.89 189	99.19 123	99.90 121	99.72 81

APDe-MVS		99.48 96	99.36 119	99.85 29	99.55 224	99.81 43	99.50 96	99.69 149	98.99 222	99.75 124	99.71 154	98.79 139	99.93 103	98.46 196	99.85 165	99.80 54
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
PMMVS2		99.48 96	99.45 100	99.57 169	99.76 121	98.99 248	98.09 356	99.90 47	98.95 229	99.78 108	99.58 240	99.57 41	99.93 103	99.48 77	99.95 86	99.79 62

DSMNet-mixed		99.48 96	99.65 57	98.95 305	99.71 149	97.27 359	99.50 96	99.82 78	99.59 130	99.41 250	99.85 65	99.62 34	100.00 1	99.53 71	99.89 131	99.59 171

DP-MVS		99.48 96	99.39 111	99.74 85	99.57 210	99.62 123	99.29 151	99.61 192	99.87 48	99.74 132	99.76 126	98.69 153	99.87 217	98.20 215	99.80 204	99.75 76

EI-MVSNet-Vis-set		99.47 104	99.49 93	99.42 215	99.57 210	98.66 281	99.24 166	99.46 271	99.67 103	99.79 104	99.65 194	98.97 118	99.89 189	99.15 131	99.89 131	99.71 84

reproduce-ours		99.46 105	99.35 121	99.82 40	99.56 221	99.83 30	99.05 229	99.65 172	99.45 152	99.78 108	99.78 114	98.93 121	99.93 103	98.11 225	99.81 197	99.70 87

our_new_method		99.46 105	99.35 121	99.82 40	99.56 221	99.83 30	99.05 229	99.65 172	99.45 152	99.78 108	99.78 114	98.93 121	99.93 103	98.11 225	99.81 197	99.70 87

VPNet		99.46 105	99.37 116	99.71 105	99.82 74	99.59 134	99.48 102	99.70 142	99.81 70	99.69 150	99.58 240	97.66 262	99.86 236	99.17 128	99.44 316	99.67 107

ACMM	98.09 11	99.46 105	99.38 113	99.72 100	99.80 90	99.69 100	99.13 204	99.65 172	98.99 222	99.64 166	99.72 146	99.39 56	99.86 236	98.23 212	99.81 197	99.60 164
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_vis1_rt		99.45 109	99.46 98	99.41 222	99.71 149	98.63 287	98.99 250	99.96 27	99.03 219	99.95 36	99.12 352	98.75 146	99.84 269	99.82 41	99.82 187	99.77 68

COLMAP_ROB	98.06 12	99.45 109	99.37 116	99.70 109	99.83 67	99.70 96	99.38 120	99.78 102	99.53 134	99.67 158	99.78 114	99.19 84	99.86 236	97.32 294	99.87 152	99.55 186
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
WB-MVS		99.44 111	99.32 128	99.80 50	99.81 83	99.61 129	99.47 105	99.81 87	99.82 67	99.71 143	99.72 146	96.60 298	99.98 22	99.75 46	99.23 347	99.82 53

mvsany_test1		99.44 111	99.45 100	99.40 224	99.37 289	98.64 286	97.90 379	99.59 209	99.27 180	99.92 47	99.82 83	99.74 21	99.93 103	99.55 67	99.87 152	99.63 139

Anonymous20240521		99.44 111	99.42 107	99.49 193	99.89 39	98.96 254	99.62 64	99.76 110	99.85 57	99.82 87	99.88 47	96.39 308	99.97 36	99.59 60	99.98 44	99.55 186

tfpnnormal		99.43 114	99.38 113	99.60 158	99.87 52	99.75 72	99.59 77	99.78 102	99.71 89	99.90 53	99.69 169	98.85 132	99.90 170	97.25 305	99.78 214	99.15 313

HPM-MVS_fast		99.43 114	99.30 135	99.80 50	99.83 67	99.81 43	99.52 89	99.70 142	98.35 306	99.51 224	99.50 269	99.31 69	99.88 203	98.18 219	99.84 170	99.69 93

3Dnovator	99.15 2	99.43 114	99.36 119	99.65 129	99.39 284	99.42 172	99.70 35	99.56 225	99.23 188	99.35 262	99.80 93	99.17 86	99.95 67	98.21 214	99.84 170	99.59 171

Anonymous20240529		99.42 117	99.34 123	99.65 129	99.53 232	99.60 132	99.63 61	99.39 292	99.47 146	99.76 119	99.78 114	98.13 226	99.86 236	98.70 182	99.68 255	99.49 222

SixPastTwentyTwo		99.42 117	99.30 135	99.76 70	99.92 29	99.67 105	99.70 35	99.14 342	99.65 110	99.89 57	99.90 33	96.20 315	99.94 83	99.42 88	99.92 110	99.67 107

GBi-Net		99.42 117	99.31 130	99.73 94	99.49 252	99.77 57	99.68 46	99.70 142	99.44 154	99.62 179	99.83 76	97.21 279	99.90 170	98.96 155	99.90 121	99.53 200

test1		99.42 117	99.31 130	99.73 94	99.49 252	99.77 57	99.68 46	99.70 142	99.44 154	99.62 179	99.83 76	97.21 279	99.90 170	98.96 155	99.90 121	99.53 200

MVSFormer		99.41 121	99.44 103	99.31 251	99.57 210	98.40 301	99.77 16	99.80 90	99.73 83	99.63 170	99.30 322	98.02 233	99.98 22	99.43 83	99.69 250	99.55 186

IterMVS-LS		99.41 121	99.47 94	99.25 267	99.81 83	98.09 324	98.85 271	99.76 110	99.62 118	99.83 86	99.64 196	98.54 175	99.97 36	99.15 131	99.99 16	99.68 99
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
SED-MVS		99.40 123	99.28 142	99.77 63	99.69 161	99.82 38	99.20 176	99.54 237	99.13 208	99.82 87	99.63 208	98.91 126	99.92 129	97.85 250	99.70 246	99.58 176

v148		99.40 123	99.41 109	99.39 227	99.76 121	98.94 256	99.09 221	99.59 209	99.17 200	99.81 94	99.61 224	98.41 195	99.69 358	99.32 105	99.94 99	99.53 200

NR-MVSNet		99.40 123	99.31 130	99.68 113	99.43 275	99.55 144	99.73 27	99.50 260	99.46 149	99.88 66	99.36 308	97.54 265	99.87 217	98.97 153	99.87 152	99.63 139

PVSNet_Blended_VisFu		99.40 123	99.38 113	99.44 209	99.90 37	98.66 281	98.94 261	99.91 42	97.97 332	99.79 104	99.73 139	99.05 107	99.97 36	99.15 131	99.99 16	99.68 99

EU-MVSNet		99.39 127	99.62 62	98.72 333	99.88 44	96.44 377	99.56 84	99.85 65	99.90 35	99.90 53	99.85 65	98.09 228	99.83 284	99.58 63	99.95 86	99.90 26

CHOSEN 1792x2688		99.39 127	99.30 135	99.65 129	99.88 44	99.25 212	98.78 286	99.88 53	98.66 269	99.96 27	99.79 103	97.45 268	99.93 103	99.34 100	99.99 16	99.78 64

DVP-MVS++		99.38 129	99.25 148	99.77 63	99.03 367	99.77 57	99.74 24	99.61 192	99.18 195	99.76 119	99.61 224	99.00 112	99.92 129	97.72 261	99.60 282	99.62 150

EI-MVSNet		99.38 129	99.44 103	99.21 271	99.58 200	98.09 324	99.26 159	99.46 271	99.62 118	99.75 124	99.67 184	98.54 175	99.85 254	99.15 131	99.92 110	99.68 99

UGNet		99.38 129	99.34 123	99.49 193	98.90 378	98.90 262	99.70 35	99.35 301	99.86 51	98.57 363	99.81 90	98.50 185	99.93 103	99.38 92	99.98 44	99.66 116
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		99.37 132	99.25 148	99.72 100	99.47 263	99.56 141	98.97 254	99.61 192	99.43 160	99.67 158	99.28 326	97.85 246	99.95 67	99.17 128	99.81 197	99.65 124

UniMVSNet (Re)		99.37 132	99.26 146	99.68 113	99.51 241	99.58 138	98.98 253	99.60 203	99.43 160	99.70 147	99.36 308	97.70 254	99.88 203	99.20 122	99.87 152	99.59 171

CSCG		99.37 132	99.29 140	99.60 158	99.71 149	99.46 158	99.43 113	99.85 65	98.79 254	99.41 250	99.60 232	98.92 124	99.92 129	98.02 230	99.92 110	99.43 246

APD_test1		99.36 135	99.28 142	99.61 155	99.89 39	99.89 10	99.32 136	99.74 121	99.18 195	99.69 150	99.75 131	98.41 195	99.84 269	97.85 250	99.70 246	99.10 324

PM-MVS		99.36 135	99.29 140	99.58 163	99.83 67	99.66 107	98.95 259	99.86 59	98.85 244	99.81 94	99.73 139	98.40 199	99.92 129	98.36 201	99.83 178	99.17 309

new-patchmatchnet		99.35 137	99.57 78	98.71 335	99.82 74	96.62 374	98.55 312	99.75 115	99.50 138	99.88 66	99.87 53	99.31 69	99.88 203	99.43 83	100.00 1	99.62 150

Anonymous20231206		99.35 137	99.31 130	99.47 199	99.74 140	99.06 244	99.28 153	99.74 121	99.23 188	99.72 138	99.53 262	97.63 264	99.88 203	99.11 139	99.84 170	99.48 226

MTAPA		99.35 137	99.20 153	99.80 50	99.81 83	99.81 43	99.33 133	99.53 246	99.27 180	99.42 244	99.63 208	98.21 219	99.95 67	97.83 254	99.79 209	99.65 124

FMVSNet2		99.35 137	99.28 142	99.55 176	99.49 252	99.35 194	99.45 109	99.57 220	99.44 154	99.70 147	99.74 135	97.21 279	99.87 217	99.03 146	99.94 99	99.44 240

3Dnovator+	98.92 3	99.35 137	99.24 150	99.67 116	99.35 296	99.47 154	99.62 64	99.50 260	99.44 154	99.12 307	99.78 114	98.77 143	99.94 83	97.87 247	99.72 241	99.62 150

TSAR-MVS + MP.		99.34 142	99.24 150	99.63 143	99.82 74	99.37 187	99.26 159	99.35 301	98.77 258	99.57 196	99.70 162	99.27 76	99.88 203	97.71 263	99.75 222	99.65 124
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
diffmvs		99.34 142	99.32 128	99.39 227	99.67 175	98.77 272	98.57 310	99.81 87	99.61 122	99.48 229	99.41 291	98.47 186	99.86 236	98.97 153	99.90 121	99.53 200
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DELS-MVS		99.34 142	99.30 135	99.48 197	99.51 241	99.36 191	98.12 352	99.53 246	99.36 170	99.41 250	99.61 224	99.22 81	99.87 217	99.21 119	99.68 255	99.20 301
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		99.33 145	99.21 152	99.71 105	99.43 275	99.56 141	98.83 274	99.53 246	99.38 166	99.67 158	99.36 308	97.67 258	99.95 67	99.17 128	99.81 197	99.63 139

ab-mvs		99.33 145	99.28 142	99.47 199	99.57 210	99.39 182	99.78 14	99.43 279	98.87 241	99.57 196	99.82 83	98.06 231	99.87 217	98.69 184	99.73 235	99.15 313

DVP-MVS		99.32 147	99.17 156	99.77 63	99.69 161	99.80 47	99.14 198	99.31 310	99.16 202	99.62 179	99.61 224	98.35 203	99.91 151	97.88 244	99.72 241	99.61 160
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
APD-MVS_3200maxsize		99.31 148	99.16 157	99.74 85	99.53 232	99.75 72	99.27 157	99.61 192	99.19 194	99.57 196	99.64 196	98.76 144	99.90 170	97.29 296	99.62 272	99.56 183

SteuartSystems-ACMMP		99.30 149	99.14 161	99.76 70	99.87 52	99.66 107	99.18 183	99.60 203	98.55 280	99.57 196	99.67 184	99.03 110	99.94 83	97.01 316	99.80 204	99.69 93
Skip Steuart: Steuart Systems R&D Blog.
testgi		99.29 150	99.26 146	99.37 233	99.75 133	98.81 267	98.84 272	99.89 49	98.38 299	99.75 124	99.04 362	99.36 65	99.86 236	99.08 143	99.25 343	99.45 235

ACMMP_NAP		99.28 151	99.11 170	99.79 57	99.75 133	99.81 43	98.95 259	99.53 246	98.27 315	99.53 216	99.73 139	98.75 146	99.87 217	97.70 266	99.83 178	99.68 99

LCM-MVSNet-Re		99.28 151	99.15 160	99.67 116	99.33 310	99.76 64	99.34 129	99.97 20	98.93 233	99.91 50	99.79 103	98.68 154	99.93 103	96.80 330	99.56 291	99.30 279

mvs_anonymous		99.28 151	99.39 111	98.94 306	99.19 339	97.81 341	99.02 240	99.55 231	99.78 77	99.85 78	99.80 93	98.24 214	99.86 236	99.57 64	99.50 309	99.15 313

MVS_Test		99.28 151	99.31 130	99.19 274	99.35 296	98.79 270	99.36 127	99.49 264	99.17 200	99.21 294	99.67 184	98.78 141	99.66 380	99.09 141	99.66 264	99.10 324

SR-MVS-dyc-post		99.27 155	99.11 170	99.73 94	99.54 226	99.74 78	99.26 159	99.62 185	99.16 202	99.52 218	99.64 196	98.41 195	99.91 151	97.27 299	99.61 279	99.54 195

XVS		99.27 155	99.11 170	99.75 80	99.71 149	99.71 88	99.37 124	99.61 192	99.29 176	98.76 346	99.47 280	98.47 186	99.88 203	97.62 275	99.73 235	99.67 107

OPM-MVS		99.26 157	99.13 163	99.63 143	99.70 157	99.61 129	98.58 306	99.48 265	98.50 287	99.52 218	99.63 208	99.14 91	99.76 333	97.89 243	99.77 218	99.51 212
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HFP-MVS		99.25 158	99.08 181	99.76 70	99.73 143	99.70 96	99.31 141	99.59 209	98.36 301	99.36 260	99.37 304	98.80 138	99.91 151	97.43 288	99.75 222	99.68 99

HPM-MVS		99.25 158	99.07 185	99.78 60	99.81 83	99.75 72	99.61 70	99.67 157	97.72 347	99.35 262	99.25 333	99.23 80	99.92 129	97.21 308	99.82 187	99.67 107
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
ACMMP		99.25 158	99.08 181	99.74 85	99.79 102	99.68 103	99.50 96	99.65 172	98.07 326	99.52 218	99.69 169	98.57 170	99.92 129	97.18 310	99.79 209	99.63 139
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
LS3D		99.24 161	99.11 170	99.61 155	98.38 414	99.79 49	99.57 82	99.68 152	99.61 122	99.15 302	99.71 154	98.70 152	99.91 151	97.54 281	99.68 255	99.13 321

xiu_mvs_v1_base_debu		99.23 162	99.34 123	98.91 312	99.59 195	98.23 310	98.47 324	99.66 162	99.61 122	99.68 153	98.94 378	99.39 56	99.97 36	99.18 125	99.55 295	98.51 394

xiu_mvs_v1_base		99.23 162	99.34 123	98.91 312	99.59 195	98.23 310	98.47 324	99.66 162	99.61 122	99.68 153	98.94 378	99.39 56	99.97 36	99.18 125	99.55 295	98.51 394

xiu_mvs_v1_base_debi		99.23 162	99.34 123	98.91 312	99.59 195	98.23 310	98.47 324	99.66 162	99.61 122	99.68 153	98.94 378	99.39 56	99.97 36	99.18 125	99.55 295	98.51 394

region2R		99.23 162	99.05 191	99.77 63	99.76 121	99.70 96	99.31 141	99.59 209	98.41 295	99.32 271	99.36 308	98.73 150	99.93 103	97.29 296	99.74 229	99.67 107

ACMMPR		99.23 162	99.06 187	99.76 70	99.74 140	99.69 100	99.31 141	99.59 209	98.36 301	99.35 262	99.38 301	98.61 165	99.93 103	97.43 288	99.75 222	99.67 107

XVG-ACMP-BASELINE		99.23 162	99.10 178	99.63 143	99.82 74	99.58 138	98.83 274	99.72 134	98.36 301	99.60 188	99.71 154	98.92 124	99.91 151	97.08 314	99.84 170	99.40 253

CP-MVS		99.23 162	99.05 191	99.75 80	99.66 176	99.66 107	99.38 120	99.62 185	98.38 299	99.06 315	99.27 328	98.79 139	99.94 83	97.51 284	99.82 187	99.66 116

DeepC-MVS_fast	98.47 5	99.23 162	99.12 167	99.56 172	99.28 321	99.22 219	98.99 250	99.40 289	99.08 213	99.58 193	99.64 196	98.90 129	99.83 284	97.44 287	99.75 222	99.63 139
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ZNCC-MVS		99.22 170	99.04 197	99.77 63	99.76 121	99.73 81	99.28 153	99.56 225	98.19 320	99.14 304	99.29 325	98.84 133	99.92 129	97.53 283	99.80 204	99.64 134

D2MVS		99.22 170	99.19 154	99.29 255	99.69 161	98.74 274	98.81 279	99.41 282	98.55 280	99.68 153	99.69 169	98.13 226	99.87 217	98.82 168	99.98 44	99.24 288

LPG-MVS_test		99.22 170	99.05 191	99.74 85	99.82 74	99.63 121	99.16 194	99.73 125	97.56 352	99.64 166	99.69 169	99.37 62	99.89 189	96.66 338	99.87 152	99.69 93

CDS-MVSNet		99.22 170	99.13 163	99.50 189	99.35 296	99.11 234	98.96 257	99.54 237	99.46 149	99.61 185	99.70 162	96.31 311	99.83 284	99.34 100	99.88 140	99.55 186
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
test_0402		99.22 170	99.14 161	99.45 205	99.79 102	99.43 169	99.28 153	99.68 152	99.54 132	99.40 255	99.56 251	99.07 102	99.82 294	96.01 369	99.96 72	99.11 322

AllTest		99.21 175	99.07 185	99.63 143	99.78 109	99.64 116	99.12 208	99.83 73	98.63 272	99.63 170	99.72 146	98.68 154	99.75 337	96.38 356	99.83 178	99.51 212

XVG-OURS		99.21 175	99.06 187	99.65 129	99.82 74	99.62 123	97.87 380	99.74 121	98.36 301	99.66 163	99.68 180	99.71 23	99.90 170	96.84 328	99.88 140	99.43 246

Fast-Effi-MVS+-dtu		99.20 177	99.12 167	99.43 213	99.25 327	99.69 100	99.05 229	99.82 78	99.50 138	98.97 319	99.05 360	98.98 116	99.98 22	98.20 215	99.24 345	98.62 384

VDD-MVS		99.20 177	99.11 170	99.44 209	99.43 275	98.98 249	99.50 96	98.32 388	99.80 73	99.56 204	99.69 169	96.99 289	99.85 254	98.99 149	99.73 235	99.50 217

PGM-MVS		99.20 177	99.01 203	99.77 63	99.75 133	99.71 88	99.16 194	99.72 134	97.99 330	99.42 244	99.60 232	98.81 134	99.93 103	96.91 322	99.74 229	99.66 116

SR-MVS		99.19 180	99.00 207	99.74 85	99.51 241	99.72 86	99.18 183	99.60 203	98.85 244	99.47 231	99.58 240	98.38 200	99.92 129	96.92 321	99.54 300	99.57 181

SMA-MVS		99.19 180	99.00 207	99.73 94	99.46 267	99.73 81	99.13 204	99.52 251	97.40 363	99.57 196	99.64 196	98.93 121	99.83 284	97.61 277	99.79 209	99.63 139
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
pmmvs5		99.19 180	99.11 170	99.42 215	99.76 121	98.88 263	98.55 312	99.73 125	98.82 249	99.72 138	99.62 215	96.56 299	99.82 294	99.32 105	99.95 86	99.56 183

mPP-MVS		99.19 180	99.00 207	99.76 70	99.76 121	99.68 103	99.38 120	99.54 237	98.34 310	99.01 317	99.50 269	98.53 179	99.93 103	97.18 310	99.78 214	99.66 116

MM		99.18 184	99.05 191	99.55 176	99.35 296	98.81 267	99.05 229	97.79 402	99.99 3	99.48 229	99.59 237	96.29 313	99.95 67	99.94 17	99.98 44	99.88 32

ETV-MVS		99.18 184	99.18 155	99.16 277	99.34 305	99.28 205	99.12 208	99.79 96	99.48 141	98.93 323	98.55 400	99.40 55	99.93 103	98.51 194	99.52 305	98.28 404

VNet		99.18 184	99.06 187	99.56 172	99.24 329	99.36 191	99.33 133	99.31 310	99.67 103	99.47 231	99.57 247	96.48 302	99.84 269	99.15 131	99.30 335	99.47 230

RPSCF		99.18 184	99.02 200	99.64 136	99.83 67	99.85 20	99.44 111	99.82 78	98.33 311	99.50 226	99.78 114	97.90 241	99.65 387	96.78 331	99.83 178	99.44 240

DeepPCF-MVS	98.42 6	99.18 184	99.02 200	99.67 116	99.22 332	99.75 72	97.25 407	99.47 268	98.72 263	99.66 163	99.70 162	99.29 71	99.63 390	98.07 229	99.81 197	99.62 150

EPP-MVSNet		99.17 189	99.00 207	99.66 123	99.80 90	99.43 169	99.70 35	99.24 326	99.48 141	99.56 204	99.77 123	94.89 330	99.93 103	98.72 181	99.89 131	99.63 139

GST-MVS		99.16 190	98.96 220	99.75 80	99.73 143	99.73 81	99.20 176	99.55 231	98.22 317	99.32 271	99.35 313	98.65 161	99.91 151	96.86 325	99.74 229	99.62 150

MVP-Stereo		99.16 190	99.08 181	99.43 213	99.48 257	99.07 242	99.08 224	99.55 231	98.63 272	99.31 276	99.68 180	98.19 222	99.78 322	98.18 219	99.58 288	99.45 235
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
XVG-OURS-SEG-HR		99.16 190	98.99 214	99.66 123	99.84 63	99.64 116	98.25 342	99.73 125	98.39 298	99.63 170	99.43 288	99.70 25	99.90 170	97.34 293	98.64 385	99.44 240

jason		99.16 190	99.11 170	99.32 248	99.75 133	98.44 298	98.26 341	99.39 292	98.70 266	99.74 132	99.30 322	98.54 175	99.97 36	98.48 195	99.82 187	99.55 186
jason: jason.
DPE-MVS		99.14 194	98.92 227	99.82 40	99.57 210	99.77 57	98.74 290	99.60 203	98.55 280	99.76 119	99.69 169	98.23 218	99.92 129	96.39 355	99.75 222	99.76 73
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MP-MVS-pluss		99.14 194	98.92 227	99.80 50	99.83 67	99.83 30	98.61 299	99.63 182	96.84 383	99.44 237	99.58 240	98.81 134	99.91 151	97.70 266	99.82 187	99.67 107
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
pmmvs4		99.13 196	99.06 187	99.36 237	99.57 210	99.10 239	98.01 365	99.25 323	98.78 256	99.58 193	99.44 287	98.24 214	99.76 333	98.74 179	99.93 106	99.22 294

MVS_111021_LR		99.13 196	99.03 199	99.42 215	99.58 200	99.32 199	97.91 378	99.73 125	98.68 267	99.31 276	99.48 276	99.09 97	99.66 380	97.70 266	99.77 218	99.29 282

EIA-MVS		99.12 198	99.01 203	99.45 205	99.36 292	99.62 123	99.34 129	99.79 96	98.41 295	98.84 336	98.89 382	98.75 146	99.84 269	98.15 223	99.51 306	98.89 366

TSAR-MVS + GP.		99.12 198	99.04 197	99.38 230	99.34 305	99.16 228	98.15 348	99.29 314	98.18 321	99.63 170	99.62 215	99.18 85	99.68 370	98.20 215	99.74 229	99.30 279

MVS_111021_HR		99.12 198	99.02 200	99.40 224	99.50 247	99.11 234	97.92 376	99.71 137	98.76 261	99.08 311	99.47 280	99.17 86	99.54 404	97.85 250	99.76 220	99.54 195

CANet		99.11 201	99.05 191	99.28 258	98.83 388	98.56 291	98.71 294	99.41 282	99.25 184	99.23 289	99.22 340	97.66 262	99.94 83	99.19 123	99.97 59	99.33 270

WR-MVS		99.11 201	98.93 223	99.66 123	99.30 316	99.42 172	98.42 330	99.37 297	99.04 218	99.57 196	99.20 344	96.89 291	99.86 236	98.66 186	99.87 152	99.70 87

PHI-MVS		99.11 201	98.95 221	99.59 160	99.13 348	99.59 134	99.17 188	99.65 172	97.88 340	99.25 285	99.46 283	98.97 118	99.80 316	97.26 301	99.82 187	99.37 260

SF-MVS		99.10 204	98.93 223	99.62 152	99.58 200	99.51 149	99.13 204	99.65 172	97.97 332	99.42 244	99.61 224	98.86 131	99.87 217	96.45 353	99.68 255	99.49 222

RRT-MVS		99.08 205	99.00 207	99.33 243	99.27 323	98.65 284	99.62 64	99.93 34	99.66 107	99.67 158	99.82 83	95.27 328	99.93 103	98.64 188	99.09 353	99.41 251

mvsmamba		99.08 205	98.95 221	99.45 205	99.36 292	99.18 227	99.39 117	98.81 359	99.37 167	99.35 262	99.70 162	96.36 310	99.94 83	98.66 186	99.59 286	99.22 294

MSDG		99.08 205	98.98 217	99.37 233	99.60 190	99.13 231	97.54 393	99.74 121	98.84 247	99.53 216	99.55 258	99.10 95	99.79 319	97.07 315	99.86 160	99.18 306

Effi-MVS+-dtu		99.07 208	98.92 227	99.52 184	98.89 381	99.78 52	99.15 196	99.66 162	99.34 171	98.92 326	99.24 338	97.69 256	99.98 22	98.11 225	99.28 338	98.81 373

Effi-MVS+		99.06 209	98.97 218	99.34 240	99.31 312	98.98 249	98.31 337	99.91 42	98.81 251	98.79 343	98.94 378	99.14 91	99.84 269	98.79 172	98.74 378	99.20 301

MP-MVS		99.06 209	98.83 239	99.76 70	99.76 121	99.71 88	99.32 136	99.50 260	98.35 306	98.97 319	99.48 276	98.37 201	99.92 129	95.95 375	99.75 222	99.63 139
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MDA-MVSNet-bldmvs		99.06 209	99.05 191	99.07 293	99.80 90	97.83 340	98.89 265	99.72 134	99.29 176	99.63 170	99.70 162	96.47 303	99.89 189	98.17 221	99.82 187	99.50 217

MSLP-MVS++		99.05 212	99.09 179	98.91 312	99.21 334	98.36 306	98.82 278	99.47 268	98.85 244	98.90 329	99.56 251	98.78 141	99.09 420	98.57 191	99.68 255	99.26 285

1112_ss		99.05 212	98.84 237	99.67 116	99.66 176	99.29 203	98.52 318	99.82 78	97.65 350	99.43 241	99.16 346	96.42 305	99.91 151	99.07 144	99.84 170	99.80 54

ACMP	97.51 14	99.05 212	98.84 237	99.67 116	99.78 109	99.55 144	98.88 266	99.66 162	97.11 378	99.47 231	99.60 232	99.07 102	99.89 189	96.18 364	99.85 165	99.58 176
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MSP-MVS		99.04 215	98.79 244	99.81 45	99.78 109	99.73 81	99.35 128	99.57 220	98.54 283	99.54 211	98.99 369	96.81 293	99.93 103	96.97 319	99.53 302	99.77 68
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
PVSNet_BlendedMVS		99.03 216	99.01 203	99.09 288	99.54 226	97.99 330	98.58 306	99.82 78	97.62 351	99.34 266	99.71 154	98.52 182	99.77 330	97.98 235	99.97 59	99.52 210

IS-MVSNet		99.03 216	98.85 235	99.55 176	99.80 90	99.25 212	99.73 27	99.15 341	99.37 167	99.61 185	99.71 154	94.73 333	99.81 309	97.70 266	99.88 140	99.58 176

MGCFI-Net		99.02 218	99.01 203	99.06 295	99.11 355	98.60 289	99.63 61	99.67 157	99.63 115	98.58 361	97.65 419	99.07 102	99.57 400	98.85 164	98.92 365	99.03 346

sasdasda		99.02 218	99.00 207	99.09 288	99.10 357	98.70 276	99.61 70	99.66 162	99.63 115	98.64 355	97.65 419	99.04 108	99.54 404	98.79 172	98.92 365	99.04 344

xiu_mvs_v2_base		99.02 218	99.11 170	98.77 330	99.37 289	98.09 324	98.13 351	99.51 256	99.47 146	99.42 244	98.54 401	99.38 60	99.97 36	98.83 166	99.33 331	98.24 406

Fast-Effi-MVS+		99.02 218	98.87 233	99.46 202	99.38 287	99.50 150	99.04 234	99.79 96	97.17 374	98.62 357	98.74 391	99.34 66	99.95 67	98.32 205	99.41 321	98.92 362

canonicalmvs		99.02 218	99.00 207	99.09 288	99.10 357	98.70 276	99.61 70	99.66 162	99.63 115	98.64 355	97.65 419	99.04 108	99.54 404	98.79 172	98.92 365	99.04 344

MCST-MVS		99.02 218	98.81 241	99.65 129	99.58 200	99.49 151	98.58 306	99.07 346	98.40 297	99.04 316	99.25 333	98.51 184	99.80 316	97.31 295	99.51 306	99.65 124

SD-MVS		99.01 224	99.30 135	98.15 361	99.50 247	99.40 179	98.94 261	99.61 192	99.22 192	99.75 124	99.82 83	99.54 44	95.51 431	97.48 285	99.87 152	99.54 195
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
LF4IMVS		99.01 224	98.92 227	99.27 261	99.71 149	99.28 205	98.59 304	99.77 105	98.32 312	99.39 257	99.41 291	98.62 163	99.84 269	96.62 343	99.84 170	98.69 382

IterMVS-SCA-FT		99.00 226	99.16 157	98.51 343	99.75 133	95.90 389	98.07 359	99.84 71	99.84 60	99.89 57	99.73 139	96.01 318	99.99 8	99.33 103	100.00 1	99.63 139

MS-PatchMatch		99.00 226	98.97 218	99.09 288	99.11 355	98.19 314	98.76 288	99.33 304	98.49 289	99.44 237	99.58 240	98.21 219	99.69 358	98.20 215	99.62 272	99.39 255

PS-MVSNAJ		99.00 226	99.08 181	98.76 331	99.37 289	98.10 323	98.00 367	99.51 256	99.47 146	99.41 250	98.50 403	99.28 73	99.97 36	98.83 166	99.34 330	98.20 410

CNVR-MVS		98.99 229	98.80 243	99.56 172	99.25 327	99.43 169	98.54 315	99.27 318	98.58 278	98.80 341	99.43 288	98.53 179	99.70 352	97.22 307	99.59 286	99.54 195

VDDNet		98.97 230	98.82 240	99.42 215	99.71 149	98.81 267	99.62 64	98.68 365	99.81 70	99.38 258	99.80 93	94.25 337	99.85 254	98.79 172	99.32 333	99.59 171

IterMVS		98.97 230	99.16 157	98.42 348	99.74 140	95.64 393	98.06 361	99.83 73	99.83 65	99.85 78	99.74 135	96.10 317	99.99 8	99.27 114	100.00 1	99.63 139
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TinyColmap		98.97 230	98.93 223	99.07 293	99.46 267	98.19 314	97.75 384	99.75 115	98.79 254	99.54 211	99.70 162	98.97 118	99.62 391	96.63 342	99.83 178	99.41 251

HPM-MVS++		98.96 233	98.70 250	99.74 85	99.52 239	99.71 88	98.86 269	99.19 336	98.47 291	98.59 360	99.06 359	98.08 230	99.91 151	96.94 320	99.60 282	99.60 164

lupinMVS		98.96 233	98.87 233	99.24 269	99.57 210	98.40 301	98.12 352	99.18 337	98.28 314	99.63 170	99.13 348	98.02 233	99.97 36	98.22 213	99.69 250	99.35 266

USDC		98.96 233	98.93 223	99.05 296	99.54 226	97.99 330	97.07 413	99.80 90	98.21 318	99.75 124	99.77 123	98.43 192	99.64 389	97.90 242	99.88 140	99.51 212

YYNet1		98.95 236	98.99 214	98.84 323	99.64 181	97.14 364	98.22 344	99.32 306	98.92 235	99.59 191	99.66 189	97.40 270	99.83 284	98.27 208	99.90 121	99.55 186

MDA-MVSNet_test_wron		98.95 236	98.99 214	98.85 321	99.64 181	97.16 362	98.23 343	99.33 304	98.93 233	99.56 204	99.66 189	97.39 272	99.83 284	98.29 206	99.88 140	99.55 186

Test_1112_low_res		98.95 236	98.73 246	99.63 143	99.68 169	99.15 230	98.09 356	99.80 90	97.14 376	99.46 235	99.40 295	96.11 316	99.89 189	99.01 148	99.84 170	99.84 43

CANet_DTU		98.91 239	98.85 235	99.09 288	98.79 394	98.13 319	98.18 345	99.31 310	99.48 141	98.86 334	99.51 266	96.56 299	99.95 67	99.05 145	99.95 86	99.19 304

HyFIR lowres test		98.91 239	98.64 252	99.73 94	99.85 59	99.47 154	98.07 359	99.83 73	98.64 271	99.89 57	99.60 232	92.57 355	100.00 1	99.33 103	99.97 59	99.72 81

HQP_MVS		98.90 241	98.68 251	99.55 176	99.58 200	99.24 216	98.80 282	99.54 237	98.94 230	99.14 304	99.25 333	97.24 277	99.82 294	95.84 379	99.78 214	99.60 164

sss		98.90 241	98.77 245	99.27 261	99.48 257	98.44 298	98.72 292	99.32 306	97.94 336	99.37 259	99.35 313	96.31 311	99.91 151	98.85 164	99.63 271	99.47 230

OMC-MVS		98.90 241	98.72 247	99.44 209	99.39 284	99.42 172	98.58 306	99.64 180	97.31 368	99.44 237	99.62 215	98.59 167	99.69 358	96.17 365	99.79 209	99.22 294

ppachtmachnet_test		98.89 244	99.12 167	98.20 360	99.66 176	95.24 400	97.63 389	99.68 152	99.08 213	99.78 108	99.62 215	98.65 161	99.88 203	98.02 230	99.96 72	99.48 226

new_pmnet		98.88 245	98.89 231	98.84 323	99.70 157	97.62 348	98.15 348	99.50 260	97.98 331	99.62 179	99.54 260	98.15 225	99.94 83	97.55 280	99.84 170	98.95 357

K. test v3		98.87 246	98.60 255	99.69 111	99.93 24	99.46 158	99.74 24	94.97 420	99.78 77	99.88 66	99.88 47	93.66 345	99.97 36	99.61 58	99.95 86	99.64 134

APD-MVS		98.87 246	98.59 257	99.71 105	99.50 247	99.62 123	99.01 242	99.57 220	96.80 385	99.54 211	99.63 208	98.29 209	99.91 151	95.24 391	99.71 244	99.61 160
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
our_test_3		98.85 248	99.09 179	98.13 362	99.66 176	94.90 404	97.72 385	99.58 218	99.07 215	99.64 166	99.62 215	98.19 222	99.93 103	98.41 198	99.95 86	99.55 186

UnsupCasMVSNet_eth		98.83 249	98.57 261	99.59 160	99.68 169	99.45 163	98.99 250	99.67 157	99.48 141	99.55 209	99.36 308	94.92 329	99.86 236	98.95 159	96.57 421	99.45 235

NCCC		98.82 250	98.57 261	99.58 163	99.21 334	99.31 200	98.61 299	99.25 323	98.65 270	98.43 371	99.26 331	97.86 244	99.81 309	96.55 344	99.27 341	99.61 160

PMVS	92.94 21	98.82 250	98.81 241	98.85 321	99.84 63	97.99 330	99.20 176	99.47 268	99.71 89	99.42 244	99.82 83	98.09 228	99.47 412	93.88 410	99.85 165	99.07 340
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
GDP-MVS		98.81 252	98.57 261	99.50 189	99.53 232	99.12 233	99.28 153	99.86 59	99.53 134	99.57 196	99.32 317	90.88 376	99.98 22	99.46 79	99.74 229	99.42 250

FMVSNet3		98.80 253	98.63 254	99.32 248	99.13 348	98.72 275	99.10 216	99.48 265	99.23 188	99.62 179	99.64 196	92.57 355	99.86 236	98.96 155	99.90 121	99.39 255

Patchmtry		98.78 254	98.54 266	99.49 193	98.89 381	99.19 225	99.32 136	99.67 157	99.65 110	99.72 138	99.79 103	91.87 363	99.95 67	98.00 234	99.97 59	99.33 270

Vis-MVSNet (Re-imp)		98.77 255	98.58 260	99.34 240	99.78 109	98.88 263	99.61 70	99.56 225	99.11 212	99.24 288	99.56 251	93.00 353	99.78 322	97.43 288	99.89 131	99.35 266

CLD-MVS		98.76 256	98.57 261	99.33 243	99.57 210	98.97 252	97.53 395	99.55 231	96.41 388	99.27 283	99.13 348	99.07 102	99.78 322	96.73 334	99.89 131	99.23 292
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Anonymous202405211		98.75 257	98.46 271	99.63 143	99.34 305	99.66 107	99.47 105	97.65 403	99.28 179	99.56 204	99.50 269	93.15 349	99.84 269	98.62 189	99.58 288	99.40 253

CPTT-MVS		98.74 258	98.44 274	99.64 136	99.61 188	99.38 184	99.18 183	99.55 231	96.49 387	99.27 283	99.37 304	97.11 285	99.92 129	95.74 382	99.67 261	99.62 150

F-COLMAP		98.74 258	98.45 273	99.62 152	99.57 210	99.47 154	98.84 272	99.65 172	96.31 391	98.93 323	99.19 345	97.68 257	99.87 217	96.52 346	99.37 326	99.53 200

N_pmnet		98.73 260	98.53 267	99.35 239	99.72 146	98.67 278	98.34 334	94.65 421	98.35 306	99.79 104	99.68 180	98.03 232	99.93 103	98.28 207	99.92 110	99.44 240

BP-MVS1		98.72 261	98.46 271	99.50 189	99.53 232	99.00 246	99.34 129	98.53 374	99.65 110	99.73 136	99.38 301	90.62 380	99.96 57	99.50 75	99.86 160	99.55 186

c3_l		98.72 261	98.71 248	98.72 333	99.12 350	97.22 361	97.68 388	99.56 225	98.90 237	99.54 211	99.48 276	96.37 309	99.73 343	97.88 244	99.88 140	99.21 297

CL-MVSNet_self_test		98.71 263	98.56 265	99.15 279	99.22 332	98.66 281	97.14 410	99.51 256	98.09 325	99.54 211	99.27 328	96.87 292	99.74 340	98.43 197	98.96 362	99.03 346

PVSNet_Blended		98.70 264	98.59 257	99.02 298	99.54 226	97.99 330	97.58 392	99.82 78	95.70 399	99.34 266	98.98 372	98.52 182	99.77 330	97.98 235	99.83 178	99.30 279

dmvs_re		98.69 265	98.48 269	99.31 251	99.55 224	99.42 172	99.54 87	98.38 385	99.32 174	98.72 349	98.71 392	96.76 295	99.21 418	96.01 369	99.35 329	99.31 277

eth_miper_zixun_eth		98.68 266	98.71 248	98.60 339	99.10 357	96.84 371	97.52 397	99.54 237	98.94 230	99.58 193	99.48 276	96.25 314	99.76 333	98.01 233	99.93 106	99.21 297

PatchMatch-RL		98.68 266	98.47 270	99.30 254	99.44 272	99.28 205	98.14 350	99.54 237	97.12 377	99.11 308	99.25 333	97.80 249	99.70 352	96.51 347	99.30 335	98.93 360

miper_lstm_enhance		98.65 268	98.60 255	98.82 328	99.20 337	97.33 358	97.78 383	99.66 162	99.01 221	99.59 191	99.50 269	94.62 334	99.85 254	98.12 224	99.90 121	99.26 285

h-mvs33		98.61 269	98.34 285	99.44 209	99.60 190	98.67 278	99.27 157	99.44 276	99.68 99	99.32 271	99.49 273	92.50 358	100.00 1	99.24 115	96.51 422	99.65 124

MVS_0304		98.61 269	98.30 290	99.52 184	97.88 426	98.95 255	98.76 288	94.11 425	99.84 60	99.32 271	99.57 247	95.57 324	99.95 67	99.68 52	99.98 44	99.68 99

CVMVSNet		98.61 269	98.88 232	97.80 374	99.58 200	93.60 412	99.26 159	99.64 180	99.66 107	99.72 138	99.67 184	93.26 348	99.93 103	99.30 108	99.81 197	99.87 36

Patchmatch-RL test		98.60 272	98.36 282	99.33 243	99.77 117	99.07 242	98.27 339	99.87 55	98.91 236	99.74 132	99.72 146	90.57 382	99.79 319	98.55 192	99.85 165	99.11 322

RPMNet		98.60 272	98.53 267	98.83 325	99.05 363	98.12 320	99.30 144	99.62 185	99.86 51	99.16 300	99.74 135	92.53 357	99.92 129	98.75 178	98.77 374	98.44 399

AdaColmap		98.60 272	98.35 284	99.38 230	99.12 350	99.22 219	98.67 295	99.42 281	97.84 344	98.81 339	99.27 328	97.32 275	99.81 309	95.14 393	99.53 302	99.10 324

miper_ehance_all_eth		98.59 275	98.59 257	98.59 340	98.98 373	97.07 365	97.49 398	99.52 251	98.50 287	99.52 218	99.37 304	96.41 307	99.71 349	97.86 248	99.62 272	99.00 353

WTY-MVS		98.59 275	98.37 281	99.26 264	99.43 275	98.40 301	98.74 290	99.13 344	98.10 323	99.21 294	99.24 338	94.82 331	99.90 170	97.86 248	98.77 374	99.49 222

CNLPA		98.57 277	98.34 285	99.28 258	99.18 342	99.10 239	98.34 334	99.41 282	98.48 290	98.52 366	98.98 372	97.05 287	99.78 322	95.59 384	99.50 309	98.96 355

CDPH-MVS		98.56 278	98.20 297	99.61 155	99.50 247	99.46 158	98.32 336	99.41 282	95.22 404	99.21 294	99.10 356	98.34 205	99.82 294	95.09 395	99.66 264	99.56 183

UnsupCasMVSNet_bld		98.55 279	98.27 293	99.40 224	99.56 221	99.37 187	97.97 372	99.68 152	97.49 359	99.08 311	99.35 313	95.41 327	99.82 294	97.70 266	98.19 402	99.01 352

cl____		98.54 280	98.41 277	98.92 310	99.03 367	97.80 343	97.46 399	99.59 209	98.90 237	99.60 188	99.46 283	93.85 341	99.78 322	97.97 237	99.89 131	99.17 309

DIV-MVS_self_test		98.54 280	98.42 276	98.92 310	99.03 367	97.80 343	97.46 399	99.59 209	98.90 237	99.60 188	99.46 283	93.87 340	99.78 322	97.97 237	99.89 131	99.18 306

FA-MVS(test-final)		98.52 282	98.32 287	99.10 287	99.48 257	98.67 278	99.77 16	98.60 372	97.35 366	99.63 170	99.80 93	93.07 351	99.84 269	97.92 240	99.30 335	98.78 376

hse-mvs2		98.52 282	98.30 290	99.16 277	99.29 318	98.60 289	98.77 287	99.02 350	99.68 99	99.32 271	99.04 362	92.50 358	99.85 254	99.24 115	97.87 412	99.03 346

MG-MVS		98.52 282	98.39 279	98.94 306	99.15 345	97.39 357	98.18 345	99.21 333	98.89 240	99.23 289	99.63 208	97.37 273	99.74 340	94.22 404	99.61 279	99.69 93

DP-MVS Recon		98.50 285	98.23 294	99.31 251	99.49 252	99.46 158	98.56 311	99.63 182	94.86 410	98.85 335	99.37 304	97.81 248	99.59 398	96.08 366	99.44 316	98.88 367

CMPMVS	77.52 23	98.50 285	98.19 300	99.41 222	98.33 416	99.56 141	99.01 242	99.59 209	95.44 401	99.57 196	99.80 93	95.64 321	99.46 414	96.47 351	99.92 110	99.21 297
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
114514_t		98.49 287	98.11 305	99.64 136	99.73 143	99.58 138	99.24 166	99.76 110	89.94 422	99.42 244	99.56 251	97.76 253	99.86 236	97.74 260	99.82 187	99.47 230

PMMVS		98.49 287	98.29 292	99.11 285	98.96 375	98.42 300	97.54 393	99.32 306	97.53 356	98.47 369	98.15 411	97.88 243	99.82 294	97.46 286	99.24 345	99.09 329

MVSTER		98.47 289	98.22 295	99.24 269	99.06 362	98.35 307	99.08 224	99.46 271	99.27 180	99.75 124	99.66 189	88.61 393	99.85 254	99.14 137	99.92 110	99.52 210

LFMVS		98.46 290	98.19 300	99.26 264	99.24 329	98.52 294	99.62 64	96.94 411	99.87 48	99.31 276	99.58 240	91.04 371	99.81 309	98.68 185	99.42 320	99.45 235

PatchT		98.45 291	98.32 287	98.83 325	98.94 376	98.29 308	99.24 166	98.82 358	99.84 60	99.08 311	99.76 126	91.37 366	99.94 83	98.82 168	99.00 360	98.26 405

MIMVSNet		98.43 292	98.20 297	99.11 285	99.53 232	98.38 305	99.58 79	98.61 370	98.96 226	99.33 268	99.76 126	90.92 373	99.81 309	97.38 291	99.76 220	99.15 313

PVSNet	97.47 15	98.42 293	98.44 274	98.35 351	99.46 267	96.26 382	96.70 418	99.34 303	97.68 349	99.00 318	99.13 348	97.40 270	99.72 345	97.59 279	99.68 255	99.08 335

CHOSEN 280x420		98.41 294	98.41 277	98.40 349	99.34 305	95.89 390	96.94 415	99.44 276	98.80 253	99.25 285	99.52 264	93.51 347	99.98 22	98.94 160	99.98 44	99.32 273

BH-RMVSNet		98.41 294	98.14 303	99.21 271	99.21 334	98.47 295	98.60 301	98.26 389	98.35 306	98.93 323	99.31 320	97.20 282	99.66 380	94.32 402	99.10 352	99.51 212

QAPM		98.40 296	97.99 312	99.65 129	99.39 284	99.47 154	99.67 50	99.52 251	91.70 419	98.78 345	99.80 93	98.55 173	99.95 67	94.71 399	99.75 222	99.53 200

API-MVS		98.38 297	98.39 279	98.35 351	98.83 388	99.26 209	99.14 198	99.18 337	98.59 277	98.66 354	98.78 389	98.61 165	99.57 400	94.14 405	99.56 291	96.21 425

HQP-MVS		98.36 298	98.02 311	99.39 227	99.31 312	98.94 256	97.98 369	99.37 297	97.45 360	98.15 380	98.83 385	96.67 296	99.70 352	94.73 397	99.67 261	99.53 200

PAPM_NR		98.36 298	98.04 309	99.33 243	99.48 257	98.93 259	98.79 285	99.28 317	97.54 355	98.56 365	98.57 398	97.12 284	99.69 358	94.09 406	98.90 369	99.38 257

PLC	97.35 16	98.36 298	97.99 312	99.48 197	99.32 311	99.24 216	98.50 320	99.51 256	95.19 406	98.58 361	98.96 376	96.95 290	99.83 284	95.63 383	99.25 343	99.37 260
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
train_agg		98.35 301	97.95 316	99.57 169	99.35 296	99.35 194	98.11 354	99.41 282	94.90 408	97.92 391	98.99 369	98.02 233	99.85 254	95.38 389	99.44 316	99.50 217

CR-MVSNet		98.35 301	98.20 297	98.83 325	99.05 363	98.12 320	99.30 144	99.67 157	97.39 364	99.16 300	99.79 103	91.87 363	99.91 151	98.78 176	98.77 374	98.44 399

WB-MVSnew		98.34 303	98.14 303	98.96 303	98.14 423	97.90 338	98.27 339	97.26 410	98.63 272	98.80 341	98.00 414	97.77 251	99.90 170	97.37 292	98.98 361	99.09 329

DPM-MVS		98.28 304	97.94 320	99.32 248	99.36 292	99.11 234	97.31 405	98.78 361	96.88 381	98.84 336	99.11 355	97.77 251	99.61 396	94.03 408	99.36 327	99.23 292

alignmvs		98.28 304	97.96 315	99.25 267	99.12 350	98.93 259	99.03 237	98.42 381	99.64 113	98.72 349	97.85 416	90.86 377	99.62 391	98.88 162	99.13 349	99.19 304

test_yl		98.25 306	97.95 316	99.13 283	99.17 343	98.47 295	99.00 245	98.67 367	98.97 224	99.22 292	99.02 367	91.31 367	99.69 358	97.26 301	98.93 363	99.24 288

DCV-MVSNet		98.25 306	97.95 316	99.13 283	99.17 343	98.47 295	99.00 245	98.67 367	98.97 224	99.22 292	99.02 367	91.31 367	99.69 358	97.26 301	98.93 363	99.24 288

MAR-MVS		98.24 308	97.92 322	99.19 274	98.78 396	99.65 113	99.17 188	99.14 342	95.36 402	98.04 387	98.81 388	97.47 267	99.72 345	95.47 387	99.06 354	98.21 408
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
MonoMVSNet		98.23 309	98.32 287	97.99 365	98.97 374	96.62 374	99.49 100	98.42 381	99.62 118	99.40 255	99.79 103	95.51 325	98.58 427	97.68 274	95.98 425	98.76 379

OpenMVS	98.12 10	98.23 309	97.89 325	99.26 264	99.19 339	99.26 209	99.65 59	99.69 149	91.33 420	98.14 384	99.77 123	98.28 210	99.96 57	95.41 388	99.55 295	98.58 389

MVStest1		98.22 311	98.09 306	98.62 337	99.04 366	96.23 383	99.20 176	99.92 36	99.44 154	99.98 14	99.87 53	85.87 406	99.67 375	99.91 27	99.57 290	99.95 14

BH-untuned		98.22 311	98.09 306	98.58 342	99.38 287	97.24 360	98.55 312	98.98 353	97.81 345	99.20 299	98.76 390	97.01 288	99.65 387	94.83 396	98.33 395	98.86 369

HY-MVS	98.23 9	98.21 313	97.95 316	98.99 300	99.03 367	98.24 309	99.61 70	98.72 363	96.81 384	98.73 348	99.51 266	94.06 338	99.86 236	96.91 322	98.20 400	98.86 369

Syy-MVS		98.17 314	97.85 326	99.15 279	98.50 411	98.79 270	98.60 301	99.21 333	97.89 338	96.76 414	96.37 437	95.47 326	99.57 400	99.10 140	98.73 381	99.09 329

EPNet		98.13 315	97.77 330	99.18 276	94.57 434	97.99 330	99.24 166	97.96 396	99.74 82	97.29 407	99.62 215	93.13 350	99.97 36	98.59 190	99.83 178	99.58 176
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SCA		98.11 316	98.36 282	97.36 386	99.20 337	92.99 414	98.17 347	98.49 378	98.24 316	99.10 310	99.57 247	96.01 318	99.94 83	96.86 325	99.62 272	99.14 318

Patchmatch-test		98.10 317	97.98 314	98.48 345	99.27 323	96.48 376	99.40 115	99.07 346	98.81 251	99.23 289	99.57 247	90.11 386	99.87 217	96.69 335	99.64 268	99.09 329

pmmvs3		98.08 318	97.80 327	98.91 312	99.41 282	97.69 347	97.87 380	99.66 162	95.87 395	99.50 226	99.51 266	90.35 384	99.97 36	98.55 192	99.47 313	99.08 335

JIA-IIPM		98.06 319	97.92 322	98.50 344	98.59 407	97.02 366	98.80 282	98.51 376	99.88 46	97.89 393	99.87 53	91.89 362	99.90 170	98.16 222	97.68 414	98.59 387

miper_enhance_ethall		98.03 320	97.94 320	98.32 354	98.27 417	96.43 378	96.95 414	99.41 282	96.37 390	99.43 241	98.96 376	94.74 332	99.69 358	97.71 263	99.62 272	98.83 372

TAPA-MVS	97.92 13	98.03 320	97.55 336	99.46 202	99.47 263	99.44 165	98.50 320	99.62 185	86.79 423	99.07 314	99.26 331	98.26 213	99.62 391	97.28 298	99.73 235	99.31 277
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
1314		98.00 322	97.90 324	98.27 359	98.90 378	97.45 354	99.30 144	99.06 348	94.98 407	97.21 409	99.12 352	98.43 192	99.67 375	95.58 385	98.56 388	97.71 417

GA-MVS		97.99 323	97.68 333	98.93 309	99.52 239	98.04 328	97.19 409	99.05 349	98.32 312	98.81 339	98.97 374	89.89 389	99.41 415	98.33 204	99.05 356	99.34 269

MVS-HIRNet		97.86 324	98.22 295	96.76 396	99.28 321	91.53 423	98.38 332	92.60 428	99.13 208	99.31 276	99.96 15	97.18 283	99.68 370	98.34 203	99.83 178	99.07 340

FE-MVS		97.85 325	97.42 339	99.15 279	99.44 272	98.75 273	99.77 16	98.20 391	95.85 396	99.33 268	99.80 93	88.86 392	99.88 203	96.40 354	99.12 350	98.81 373

AUN-MVS		97.82 326	97.38 340	99.14 282	99.27 323	98.53 292	98.72 292	99.02 350	98.10 323	97.18 410	99.03 366	89.26 391	99.85 254	97.94 239	97.91 410	99.03 346

FMVSNet5		97.80 327	97.25 344	99.42 215	98.83 388	98.97 252	99.38 120	99.80 90	98.87 241	99.25 285	99.69 169	80.60 416	99.91 151	98.96 155	99.90 121	99.38 257

ADS-MVSNet2		97.78 328	97.66 335	98.12 363	99.14 346	95.36 397	99.22 173	98.75 362	96.97 379	98.25 376	99.64 196	90.90 374	99.94 83	96.51 347	99.56 291	99.08 335

test1111		97.74 329	98.16 302	96.49 402	99.60 190	89.86 433	99.71 34	91.21 429	99.89 41	99.88 66	99.87 53	93.73 344	99.90 170	99.56 65	99.99 16	99.70 87

ECVR-MVS		97.73 330	98.04 309	96.78 395	99.59 195	90.81 428	99.72 30	90.43 431	99.89 41	99.86 75	99.86 60	93.60 346	99.89 189	99.46 79	99.99 16	99.65 124

baseline1		97.73 330	97.33 341	98.96 303	99.30 316	97.73 345	99.40 115	98.42 381	99.33 173	99.46 235	99.21 342	91.18 369	99.82 294	98.35 202	91.26 429	99.32 273

tpmrst		97.73 330	98.07 308	96.73 399	98.71 403	92.00 418	99.10 216	98.86 355	98.52 285	98.92 326	99.54 260	91.90 361	99.82 294	98.02 230	99.03 358	98.37 401

ADS-MVSNet		97.72 333	97.67 334	97.86 372	99.14 346	94.65 405	99.22 173	98.86 355	96.97 379	98.25 376	99.64 196	90.90 374	99.84 269	96.51 347	99.56 291	99.08 335

PatchmatchNet		97.65 334	97.80 327	97.18 392	98.82 391	92.49 416	99.17 188	98.39 384	98.12 322	98.79 343	99.58 240	90.71 379	99.89 189	97.23 306	99.41 321	99.16 311
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tttt0517		97.62 335	97.20 345	98.90 318	99.76 121	97.40 356	99.48 102	94.36 422	99.06 217	99.70 147	99.49 273	84.55 409	99.94 83	98.73 180	99.65 266	99.36 263

EPNet_dtu		97.62 335	97.79 329	97.11 394	96.67 431	92.31 417	98.51 319	98.04 394	99.24 186	95.77 423	99.47 280	93.78 343	99.66 380	98.98 151	99.62 272	99.37 260
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
wuyk23d		97.58 337	99.13 163	92.93 410	99.69 161	99.49 151	99.52 89	99.77 105	97.97 332	99.96 27	99.79 103	99.84 13	99.94 83	95.85 378	99.82 187	79.36 428

cl22		97.56 338	97.28 342	98.40 349	98.37 415	96.75 372	97.24 408	99.37 297	97.31 368	99.41 250	99.22 340	87.30 395	99.37 416	97.70 266	99.62 272	99.08 335

PAPR		97.56 338	97.07 348	99.04 297	98.80 392	98.11 322	97.63 389	99.25 323	94.56 413	98.02 389	98.25 408	97.43 269	99.68 370	90.90 417	98.74 378	99.33 270

WBMVS		97.50 340	97.18 346	98.48 345	98.85 386	95.89 390	98.44 329	99.52 251	99.53 134	99.52 218	99.42 290	80.10 417	99.86 236	99.24 115	99.95 86	99.68 99

thisisatest0530		97.45 341	96.95 352	98.94 306	99.68 169	97.73 345	99.09 221	94.19 424	98.61 276	99.56 204	99.30 322	84.30 411	99.93 103	98.27 208	99.54 300	99.16 311

TR-MVS		97.44 342	97.15 347	98.32 354	98.53 409	97.46 353	98.47 324	97.91 398	96.85 382	98.21 379	98.51 402	96.42 305	99.51 410	92.16 413	97.29 417	97.98 414

reproduce_monomvs		97.40 343	97.46 337	97.20 391	99.05 363	91.91 419	99.20 176	99.18 337	99.84 60	99.86 75	99.75 131	80.67 414	99.83 284	99.69 50	99.95 86	99.85 41

tpmvs		97.39 344	97.69 332	96.52 401	98.41 413	91.76 420	99.30 144	98.94 354	97.74 346	97.85 396	99.55 258	92.40 360	99.73 343	96.25 361	98.73 381	98.06 413

test0.0.03 1		97.37 345	96.91 355	98.74 332	97.72 427	97.57 349	97.60 391	97.36 409	98.00 328	99.21 294	98.02 412	90.04 387	99.79 319	98.37 200	95.89 426	98.86 369

OpenMVS_ROB	97.31 17	97.36 346	96.84 356	98.89 319	99.29 318	99.45 163	98.87 268	99.48 265	86.54 425	99.44 237	99.74 135	97.34 274	99.86 236	91.61 414	99.28 338	97.37 421

dmvs_testset		97.27 347	96.83 357	98.59 340	99.46 267	97.55 350	99.25 165	96.84 412	98.78 256	97.24 408	97.67 418	97.11 285	98.97 422	86.59 428	98.54 389	99.27 283

BH-w/o		97.20 348	97.01 350	97.76 375	99.08 361	95.69 392	98.03 364	98.52 375	95.76 398	97.96 390	98.02 412	95.62 322	99.47 412	92.82 412	97.25 418	98.12 412

test-LLR		97.15 349	96.95 352	97.74 377	98.18 420	95.02 402	97.38 401	96.10 413	98.00 328	97.81 398	98.58 396	90.04 387	99.91 151	97.69 272	98.78 372	98.31 402

tpm		97.15 349	96.95 352	97.75 376	98.91 377	94.24 407	99.32 136	97.96 396	97.71 348	98.29 374	99.32 317	86.72 403	99.92 129	98.10 228	96.24 424	99.09 329

E-PMN		97.14 351	97.43 338	96.27 404	98.79 394	91.62 422	95.54 423	99.01 352	99.44 154	98.88 330	99.12 352	92.78 354	99.68 370	94.30 403	99.03 358	97.50 418

cascas		96.99 352	96.82 358	97.48 382	97.57 430	95.64 393	96.43 420	99.56 225	91.75 418	97.13 412	97.61 422	95.58 323	98.63 425	96.68 336	99.11 351	98.18 411

thisisatest0515		96.98 353	96.42 361	98.66 336	99.42 280	97.47 352	97.27 406	94.30 423	97.24 370	99.15 302	98.86 384	85.01 407	99.87 217	97.10 312	99.39 323	98.63 383

EMVS		96.96 354	97.28 342	95.99 408	98.76 399	91.03 426	95.26 425	98.61 370	99.34 171	98.92 326	98.88 383	93.79 342	99.66 380	92.87 411	99.05 356	97.30 422

dp		96.86 355	97.07 348	96.24 405	98.68 405	90.30 432	99.19 182	98.38 385	97.35 366	98.23 378	99.59 237	87.23 396	99.82 294	96.27 360	98.73 381	98.59 387

baseline2		96.83 356	96.28 363	98.46 347	99.09 360	96.91 369	98.83 274	93.87 427	97.23 371	96.23 422	98.36 405	88.12 394	99.90 170	96.68 336	98.14 405	98.57 391

ET-MVSNet_ETH3D		96.78 357	96.07 367	98.91 312	99.26 326	97.92 337	97.70 387	96.05 416	97.96 335	92.37 429	98.43 404	87.06 397	99.90 170	98.27 208	97.56 415	98.91 363

tpm cat1		96.78 357	96.98 351	96.16 406	98.85 386	90.59 430	99.08 224	99.32 306	92.37 416	97.73 402	99.46 283	91.15 370	99.69 358	96.07 367	98.80 371	98.21 408

PCF-MVS	96.03 18	96.73 359	95.86 372	99.33 243	99.44 272	99.16 228	96.87 416	99.44 276	86.58 424	98.95 321	99.40 295	94.38 336	99.88 203	87.93 422	99.80 204	98.95 357
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CostFormer		96.71 360	96.79 359	96.46 403	98.90 378	90.71 429	99.41 114	98.68 365	94.69 412	98.14 384	99.34 316	86.32 405	99.80 316	97.60 278	98.07 408	98.88 367

MVE	92.54 22	96.66 361	96.11 366	98.31 356	99.68 169	97.55 350	97.94 374	95.60 419	99.37 167	90.68 430	98.70 394	96.56 299	98.61 426	86.94 427	99.55 295	98.77 378
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
thres600view7		96.60 362	96.16 365	97.93 369	99.63 183	96.09 387	99.18 183	97.57 404	98.77 258	98.72 349	97.32 424	87.04 398	99.72 345	88.57 420	98.62 386	97.98 414

UBG		96.53 363	95.95 369	98.29 358	98.87 384	96.31 381	98.48 323	98.07 393	98.83 248	97.32 405	96.54 435	79.81 419	99.62 391	96.84 328	98.74 378	98.95 357

EPMVS		96.53 363	96.32 362	97.17 393	98.18 420	92.97 415	99.39 117	89.95 432	98.21 318	98.61 358	99.59 237	86.69 404	99.72 345	96.99 317	99.23 347	98.81 373

testing3-2		96.51 365	96.43 360	96.74 398	99.36 292	91.38 425	99.10 216	97.87 400	99.48 141	98.57 363	98.71 392	76.65 426	99.66 380	98.87 163	99.26 342	99.18 306

testing3		96.48 366	95.63 378	99.01 299	99.23 331	97.81 341	98.90 264	99.10 345	98.72 263	97.84 397	97.92 415	72.44 432	99.85 254	97.21 308	99.33 331	99.35 266

thres400		96.40 367	95.89 370	97.92 370	99.58 200	96.11 385	99.00 245	97.54 407	98.43 292	98.52 366	96.98 428	86.85 400	99.67 375	87.62 423	98.51 390	97.98 414

thres100view900		96.39 368	96.03 368	97.47 383	99.63 183	95.93 388	99.18 183	97.57 404	98.75 262	98.70 352	97.31 425	87.04 398	99.67 375	87.62 423	98.51 390	96.81 423

tpm2		96.35 369	96.22 364	96.73 399	98.88 383	91.75 421	99.21 175	98.51 376	93.27 415	97.89 393	99.21 342	84.83 408	99.70 352	96.04 368	98.18 403	98.75 380

FPMVS		96.32 370	95.50 379	98.79 329	99.60 190	98.17 317	98.46 328	98.80 360	97.16 375	96.28 419	99.63 208	82.19 412	99.09 420	88.45 421	98.89 370	99.10 324

tfpn200view9		96.30 371	95.89 370	97.53 380	99.58 200	96.11 385	99.00 245	97.54 407	98.43 292	98.52 366	96.98 428	86.85 400	99.67 375	87.62 423	98.51 390	96.81 423

TESTMET0.1,1		96.24 372	95.84 373	97.41 385	98.24 418	93.84 410	97.38 401	95.84 417	98.43 292	97.81 398	98.56 399	79.77 420	99.89 189	97.77 255	98.77 374	98.52 393

myMVS_eth3d28		96.23 373	95.74 375	97.70 379	98.86 385	95.59 395	98.66 296	98.14 392	98.96 226	97.67 403	97.06 427	76.78 425	98.92 423	97.10 312	98.41 394	98.58 389

test-mter		96.23 373	95.73 376	97.74 377	98.18 420	95.02 402	97.38 401	96.10 413	97.90 337	97.81 398	98.58 396	79.12 423	99.91 151	97.69 272	98.78 372	98.31 402

UWE-MVS		96.21 375	95.78 374	97.49 381	98.53 409	93.83 411	98.04 362	93.94 426	98.96 226	98.46 370	98.17 410	79.86 418	99.87 217	96.99 317	99.06 354	98.78 376

ETVMVS		96.14 376	95.22 387	98.89 319	98.80 392	98.01 329	98.66 296	98.35 387	98.71 265	97.18 410	96.31 439	74.23 431	99.75 337	96.64 341	98.13 407	98.90 364

X-MVStestdata		96.09 377	94.87 390	99.75 80	99.71 149	99.71 88	99.37 124	99.61 192	99.29 176	98.76 346	61.30 440	98.47 186	99.88 203	97.62 275	99.73 235	99.67 107

thres200		96.09 377	95.68 377	97.33 388	99.48 257	96.22 384	98.53 317	97.57 404	98.06 327	98.37 373	96.73 432	86.84 402	99.61 396	86.99 426	98.57 387	96.16 426

testing11		96.05 379	95.41 382	97.97 367	98.78 396	95.27 399	98.59 304	98.23 390	98.86 243	96.56 417	96.91 430	75.20 428	99.69 358	97.26 301	98.29 397	98.93 360

testing91		96.00 380	95.32 385	98.02 364	98.76 399	95.39 396	98.38 332	98.65 369	98.82 249	96.84 413	96.71 433	75.06 429	99.71 349	96.46 352	98.23 399	98.98 354

KD-MVS_2432*1600		95.89 381	95.41 382	97.31 389	94.96 432	93.89 408	97.09 411	99.22 330	97.23 371	98.88 330	99.04 362	79.23 421	99.54 404	96.24 362	96.81 419	98.50 397

miper_refine_blended		95.89 381	95.41 382	97.31 389	94.96 432	93.89 408	97.09 411	99.22 330	97.23 371	98.88 330	99.04 362	79.23 421	99.54 404	96.24 362	96.81 419	98.50 397

gg-mvs-nofinetune		95.87 383	95.17 389	97.97 367	98.19 419	96.95 367	99.69 42	89.23 433	99.89 41	96.24 421	99.94 19	81.19 413	99.51 410	93.99 409	98.20 400	97.44 419

testing99		95.86 384	95.19 388	97.87 371	98.76 399	95.03 401	98.62 298	98.44 380	98.68 267	96.67 416	96.66 434	74.31 430	99.69 358	96.51 347	98.03 409	98.90 364

PVSNet_0	95.53 19	95.85 385	95.31 386	97.47 383	98.78 396	93.48 413	95.72 422	99.40 289	96.18 393	97.37 404	97.73 417	95.73 320	99.58 399	95.49 386	81.40 430	99.36 263

tmp_tt		95.75 386	95.42 381	96.76 396	89.90 436	94.42 406	98.86 269	97.87 400	78.01 427	99.30 281	99.69 169	97.70 254	95.89 429	99.29 111	98.14 405	99.95 14

MVS		95.72 387	94.63 393	98.99 300	98.56 408	97.98 335	99.30 144	98.86 355	72.71 429	97.30 406	99.08 357	98.34 205	99.74 340	89.21 418	98.33 395	99.26 285

UWE-MVS-28		95.64 388	95.47 380	96.14 407	97.98 424	90.39 431	98.49 322	95.81 418	99.02 220	98.03 388	98.19 409	84.49 410	99.28 417	88.75 419	98.47 393	98.75 380

myMVS_eth3d		95.63 389	94.73 391	98.34 353	98.50 411	96.36 379	98.60 301	99.21 333	97.89 338	96.76 414	96.37 437	72.10 433	99.57 400	94.38 401	98.73 381	99.09 329

PAPM		95.61 390	94.71 392	98.31 356	99.12 350	96.63 373	96.66 419	98.46 379	90.77 421	96.25 420	98.68 395	93.01 352	99.69 358	81.60 429	97.86 413	98.62 384

testing222		95.60 391	94.59 394	98.61 338	98.66 406	97.45 354	98.54 315	97.90 399	98.53 284	96.54 418	96.47 436	70.62 435	99.81 309	95.91 377	98.15 404	98.56 392

IB-MVS	95.41 20	95.30 392	94.46 396	97.84 373	98.76 399	95.33 398	97.33 404	96.07 415	96.02 394	95.37 426	97.41 423	76.17 427	99.96 57	97.54 281	95.44 428	98.22 407
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
test2506		94.73 393	94.59 394	95.15 409	99.59 195	85.90 435	99.75 22	74.01 437	99.89 41	99.71 143	99.86 60	79.00 424	99.90 170	99.52 72	99.99 16	99.65 124

test_method		91.72 394	92.32 397	89.91 412	93.49 435	70.18 438	90.28 426	99.56 225	61.71 430	95.39 425	99.52 264	93.90 339	99.94 83	98.76 177	98.27 398	99.62 150

dongtai		89.37 395	88.91 398	90.76 411	99.19 339	77.46 436	95.47 424	87.82 435	92.28 417	94.17 428	98.82 387	71.22 434	95.54 430	63.85 430	97.34 416	99.27 283

EGC-MVSNET		89.05 396	85.52 399	99.64 136	99.89 39	99.78 52	99.56 84	99.52 251	24.19 431	49.96 432	99.83 76	99.15 88	99.92 129	97.71 263	99.85 165	99.21 297

kuosan		85.65 397	84.57 400	88.90 413	97.91 425	77.11 437	96.37 421	87.62 436	85.24 426	85.45 431	96.83 431	69.94 436	90.98 432	45.90 431	95.83 427	98.62 384

test123		29.31 398	33.05 403	18.08 414	25.93 438	12.24 439	97.53 395	10.93 439	11.78 432	24.21 433	50.08 444	21.04 437	8.60 433	23.51 432	32.43 432	33.39 429

testmvs		28.94 399	33.33 401	15.79 415	26.03 437	9.81 440	96.77 417	15.67 438	11.55 433	23.87 434	50.74 443	19.03 438	8.53 434	23.21 433	33.07 431	29.03 430

cdsmvs_eth3d_5k		24.88 400	33.17 402	0.00 416	0.00 439	0.00 441	0.00 427	99.62 185	0.00 434	0.00 435	99.13 348	99.82 14	0.00 435	0.00 434	0.00 433	0.00 431

pcd_1.5k_mvsjas		16.61 401	22.14 404	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	100.00 1	99.28 73	0.00 435	0.00 434	0.00 433	0.00 431

mmdepth		8.33 402	11.11 405	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	100.00 1	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

monomultidepth		8.33 402	11.11 405	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	100.00 1	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

test_blank		8.33 402	11.11 405	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	100.00 1	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

uanet_test		8.33 402	11.11 405	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	100.00 1	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

DCPMVS		8.33 402	11.11 405	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	100.00 1	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

sosnet-low-res		8.33 402	11.11 405	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	100.00 1	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

sosnet		8.33 402	11.11 405	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	100.00 1	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

uncertanet		8.33 402	11.11 405	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	100.00 1	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

Regformer		8.33 402	11.11 405	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	100.00 1	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

uanet		8.33 402	11.11 405	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	100.00 1	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

ab-mvs-re		8.26 412	11.02 415	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	99.16 346	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

WAC-MVS						96.36 379								95.20 392

FOURS1					99.83 67	99.89 10	99.74 24	99.71 137	99.69 97	99.63 170

MSC_two_6792asdad				99.74 85	99.03 367	99.53 147		99.23 327					99.92 129	97.77 255	99.69 250	99.78 64

PC_three_1452									97.56 352	99.68 153	99.41 291	99.09 97	97.09 428	96.66 338	99.60 282	99.62 150

No_MVS				99.74 85	99.03 367	99.53 147		99.23 327					99.92 129	97.77 255	99.69 250	99.78 64

test_one_0601					99.63 183	99.76 64		99.55 231	99.23 188	99.31 276	99.61 224	98.59 167

eth-test2					0.00 439

eth-test					0.00 439

ZD-MVS					99.43 275	99.61 129		99.43 279	96.38 389	99.11 308	99.07 358	97.86 244	99.92 129	94.04 407	99.49 311

RE-MVS-def			99.13 163		99.54 226	99.74 78	99.26 159	99.62 185	99.16 202	99.52 218	99.64 196	98.57 170		97.27 299	99.61 279	99.54 195

IU-MVS					99.69 161	99.77 57		99.22 330	97.50 358	99.69 150				97.75 259	99.70 246	99.77 68

OPU-MVS				99.29 255	99.12 350	99.44 165	99.20 176				99.40 295	99.00 112	98.84 424	96.54 345	99.60 282	99.58 176

test_241102_TWO								99.54 237	99.13 208	99.76 119	99.63 208	98.32 208	99.92 129	97.85 250	99.69 250	99.75 76

test_241102_ONE					99.69 161	99.82 38		99.54 237	99.12 211	99.82 87	99.49 273	98.91 126	99.52 409

9.14			98.64 252		99.45 271		98.81 279	99.60 203	97.52 357	99.28 282	99.56 251	98.53 179	99.83 284	95.36 390	99.64 268

save fliter					99.53 232	99.25 212	98.29 338	99.38 296	99.07 215

test_0728_THIRD									99.18 195	99.62 179	99.61 224	98.58 169	99.91 151	97.72 261	99.80 204	99.77 68

test_0728_SECOND				99.83 35	99.70 157	99.79 49	99.14 198	99.61 192					99.92 129	97.88 244	99.72 241	99.77 68

test0726					99.69 161	99.80 47	99.24 166	99.57 220	99.16 202	99.73 136	99.65 194	98.35 203

GSMVS																99.14 318

test_part2					99.62 187	99.67 105				99.55 209

sam_mvs1												90.81 378				99.14 318

sam_mvs												90.52 383

ambc				99.20 273	99.35 296	98.53 292	99.17 188	99.46 271		99.67 158	99.80 93	98.46 189	99.70 352	97.92 240	99.70 246	99.38 257

MTGPA								99.53 246

test_post1							99.14 198				51.63 442	89.54 390	99.82 294	96.86 325

test_post											52.41 441	90.25 385	99.86 236

patchmatchnet-post											99.62 215	90.58 381	99.94 83

GG-mvs-BLEND				97.36 386	97.59 428	96.87 370	99.70 35	88.49 434		94.64 427	97.26 426	80.66 415	99.12 419	91.50 415	96.50 423	96.08 427

MTMP							99.09 221	98.59 373

gm-plane-assit					97.59 428	89.02 434			93.47 414		98.30 406		99.84 269	96.38 356

test9_res														95.10 394	99.44 316	99.50 217

TEST9					99.35 296	99.35 194	98.11 354	99.41 282	94.83 411	97.92 391	98.99 369	98.02 233	99.85 254

test_8					99.34 305	99.31 200	98.08 358	99.40 289	94.90 408	97.87 395	98.97 374	98.02 233	99.84 269

agg_prior2														94.58 400	99.46 315	99.50 217

agg_prior					99.35 296	99.36 191		99.39 292		97.76 401			99.85 254

TestCases				99.63 143	99.78 109	99.64 116		99.83 73	98.63 272	99.63 170	99.72 146	98.68 154	99.75 337	96.38 356	99.83 178	99.51 212

test_prior4						99.19 225	98.00 367

test_prior2							97.95 373		97.87 341	98.05 386	99.05 360	97.90 241		95.99 372	99.49 311

test_prior				99.46 202	99.35 296	99.22 219		99.39 292					99.69 358			99.48 226

旧先验2							97.94 374		95.33 403	98.94 322			99.88 203	96.75 332

新几何2							98.04 362

新几何1				99.52 184	99.50 247	99.22 219		99.26 320	95.66 400	98.60 359	99.28 326	97.67 258	99.89 189	95.95 375	99.32 333	99.45 235

旧先验1					99.49 252	99.29 203		99.26 320			99.39 299	97.67 258			99.36 327	99.46 234

无先验							98.01 365	99.23 327	95.83 397				99.85 254	95.79 381		99.44 240

原ACMM2							97.92 376

原ACMM1				99.37 233	99.47 263	98.87 265		99.27 318	96.74 386	98.26 375	99.32 317	97.93 240	99.82 294	95.96 374	99.38 324	99.43 246

test222					99.51 241	99.08 241	97.83 382	99.29 314	95.21 405	98.68 353	99.31 320	97.28 276			99.38 324	99.43 246

testdata2													99.89 189	95.99 372

segment_acmp												98.37 201

testdata				99.42 215	99.51 241	98.93 259		99.30 313	96.20 392	98.87 333	99.40 295	98.33 207	99.89 189	96.29 359	99.28 338	99.44 240

testdata1							97.72 385		97.86 343

test12				99.54 181	99.29 318	99.33 197		99.16 340		98.43 371		97.54 265	99.82 294		99.47 313	99.48 226

plane_prior7					99.58 200	99.38 184

plane_prior6					99.47 263	99.26 209						97.24 277

plane_prior5								99.54 237					99.82 294	95.84 379	99.78 214	99.60 164

plane_prior4											99.25 333

plane_prior3						99.31 200			98.36 301	99.14 304

plane_prior2							98.80 282		98.94 230

plane_prior1					99.51 241

plane_prior						99.24 216	98.42 330		97.87 341						99.71 244

n2								0.00 440

nn								0.00 440

door-mid								99.83 73

lessismore_v0				99.64 136	99.86 55	99.38 184		90.66 430		99.89 57	99.83 76	94.56 335	99.97 36	99.56 65	99.92 110	99.57 181

LGP-MVS_train				99.74 85	99.82 74	99.63 121		99.73 125	97.56 352	99.64 166	99.69 169	99.37 62	99.89 189	96.66 338	99.87 152	99.69 93

test11								99.29 314

door								99.77 105

HQP5-MVS						98.94 256

HQP-NCC					99.31 312		97.98 369		97.45 360	98.15 380

ACMP_Plane					99.31 312		97.98 369		97.45 360	98.15 380

BP-MVS														94.73 397

HQP4-MVS										98.15 380			99.70 352			99.53 200

HQP3-MVS								99.37 297							99.67 261

HQP2-MVS												96.67 296

NP-MVS					99.40 283	99.13 231					98.83 385

MDTV_nov1_ep13_2view						91.44 424	99.14 198		97.37 365	99.21 294		91.78 365		96.75 332		99.03 346

MDTV_nov1_ep13			97.73 331		98.70 404	90.83 427	99.15 196	98.02 395	98.51 286	98.82 338	99.61 224	90.98 372	99.66 380	96.89 324	98.92 365

ACMMP++_ref															99.94 99

ACMMP++															99.79 209

Test By Simon												98.41 195

ITE_SJBPF				99.38 230	99.63 183	99.44 165		99.73 125	98.56 279	99.33 268	99.53 262	98.88 130	99.68 370	96.01 369	99.65 266	99.02 351

DeepMVS_CX				97.98 366	99.69 161	96.95 367		99.26 320	75.51 428	95.74 424	98.28 407	96.47 303	99.62 391	91.23 416	97.89 411	97.38 420

High-resolution multi-view benchmark