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 13	99.98 1	99.99 1	99.96 1	99.77 2	100.00 1	99.81 15	100.00 1	99.85 29

UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 17	99.34 20	99.69 5	99.58 77	99.90 3	99.86 24	99.78 13	99.58 6	99.95 26	99.00 86	99.95 38	99.78 45

pmmvs6		99.67 3	99.70 3	99.60 15	99.90 4	99.27 27	99.53 9	99.76 39	99.64 27	99.84 30	99.83 4	99.50 9	99.87 132	99.36 56	99.92 67	99.64 81

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 26	99.85 16	99.11 64	99.90 1	99.78 36	99.63 29	99.78 39	99.67 30	99.48 10	99.81 216	99.30 61	99.97 21	99.77 48
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
tt0320-xc		99.64 5	99.68 5	99.50 53	99.72 43	98.98 71	99.51 10	99.85 18	99.86 6	99.88 21	99.82 5	99.02 26	99.90 79	99.54 42	99.95 38	99.61 95

mvs_tets		99.63 6	99.67 6	99.49 54	99.88 9	98.61 98	99.34 23	99.71 46	99.27 72	99.90 14	99.74 18	99.68 4	99.97 7	99.55 41	99.99 5	99.88 20

sc_t1		99.62 7	99.66 8	99.53 38	99.82 19	99.09 68	99.50 11	99.63 65	99.88 4	99.86 24	99.80 11	99.03 24	99.89 95	99.48 51	99.93 54	99.60 97

tt0320		99.61 8	99.65 9	99.48 56	99.71 47	98.94 78	99.54 8	99.83 25	99.87 5	99.89 18	99.82 5	98.75 46	99.90 79	99.54 42	99.95 38	99.59 104

jajsoiax		99.58 9	99.61 11	99.48 56	99.87 12	98.61 98	99.28 40	99.66 59	99.09 103	99.89 18	99.68 25	99.53 7	99.97 7	99.50 49	99.99 5	99.87 21

test_fmvsmconf0.01_n		99.57 10	99.63 10	99.36 70	99.87 12	98.13 138	98.08 182	99.95 1	99.45 49	99.98 2	99.75 16	99.80 1	99.97 7	99.82 11	99.99 5	99.99 2

ANet_high		99.57 10	99.67 6	99.28 92	99.89 6	98.09 142	99.14 57	99.93 5	99.82 8	99.93 6	99.81 8	99.17 20	99.94 41	99.31 60	100.00 1	99.82 35

v7n		99.53 12	99.57 13	99.41 66	99.88 9	98.54 106	99.45 14	99.61 70	99.66 24	99.68 56	99.66 32	98.44 77	99.95 26	99.73 26	99.96 28	99.75 57

test_djsdf		99.52 13	99.51 15	99.53 38	99.86 14	98.74 88	99.39 20	99.56 91	99.11 93	99.70 50	99.73 20	99.00 27	99.97 7	99.26 64	99.98 12	99.89 16

anonymousdsp		99.51 14	99.47 21	99.62 9	99.88 9	99.08 69	99.34 23	99.69 50	98.93 124	99.65 62	99.72 21	98.93 32	99.95 26	99.11 76	100.00 1	99.82 35

test_fmvsmconf0.1_n		99.49 15	99.54 14	99.34 79	99.78 24	98.11 139	97.77 237	99.90 11	99.33 64	99.97 3	99.66 32	99.71 3	99.96 14	99.79 18	99.99 5	99.96 8

UA-Net		99.47 16	99.40 27	99.70 2	99.49 130	99.29 24	99.80 4	99.72 44	99.82 8	99.04 175	99.81 8	98.05 116	99.96 14	98.85 96	99.99 5	99.86 27

PS-MVSNAJss		99.46 17	99.49 16	99.35 76	99.90 4	98.15 135	99.20 48	99.65 62	99.48 43	99.92 8	99.71 22	98.07 113	99.96 14	99.53 46	100.00 1	99.93 11

fmvsm_l_conf0.5_n_3		99.45 18	99.48 18	99.34 79	99.59 85	98.21 132	97.82 228	99.84 22	99.41 56	99.92 8	99.41 91	99.51 8	99.95 26	99.84 8	99.97 21	99.87 21

test_fmvsmconf_n		99.44 19	99.48 18	99.31 90	99.64 74	98.10 141	97.68 249	99.84 22	99.29 70	99.92 8	99.57 49	99.60 5	99.96 14	99.74 25	99.98 12	99.89 16

mamv4		99.44 19	99.39 28	99.58 20	99.30 183	99.74 2	99.04 68	99.81 31	99.77 10	99.82 33	99.57 49	97.82 135	99.98 4	99.53 46	99.89 89	99.01 305

pm-mvs1		99.44 19	99.48 18	99.33 85	99.80 21	98.63 95	99.29 36	99.63 65	99.30 69	99.65 62	99.60 45	99.16 22	99.82 200	99.07 79	99.83 114	99.56 123

TransMVSNet (Re)		99.44 19	99.47 21	99.36 70	99.80 21	98.58 101	99.27 42	99.57 84	99.39 57	99.75 44	99.62 40	99.17 20	99.83 190	99.06 81	99.62 224	99.66 75

DTE-MVSNet		99.43 23	99.35 34	99.66 7	99.71 47	99.30 22	99.31 30	99.51 108	99.64 27	99.56 70	99.46 79	98.23 96	99.97 7	98.78 100	99.93 54	99.72 59

TDRefinement		99.42 24	99.38 29	99.55 28	99.76 30	99.33 21	99.68 6	99.71 46	99.38 58	99.53 79	99.61 43	98.64 56	99.80 224	98.24 133	99.84 107	99.52 146

PEN-MVS		99.41 25	99.34 36	99.62 9	99.73 37	99.14 57	99.29 36	99.54 100	99.62 32	99.56 70	99.42 87	98.16 107	99.96 14	98.78 100	99.93 54	99.77 48

nrg030		99.40 26	99.35 34	99.54 31	99.58 87	99.13 60	98.98 75	99.48 120	99.68 20	99.46 94	99.26 124	98.62 59	99.73 279	99.17 73	99.92 67	99.76 53

PS-CasMVS		99.40 26	99.33 37	99.62 9	99.71 47	99.10 65	99.29 36	99.53 103	99.53 40	99.46 94	99.41 91	98.23 96	99.95 26	98.89 94	99.95 38	99.81 38

MIMVSNet1		99.38 28	99.32 39	99.55 28	99.86 14	99.19 42	99.41 17	99.59 75	99.59 35	99.71 48	99.57 49	97.12 190	99.90 79	99.21 69	99.87 95	99.54 134

OurMVSNet-221017-0		99.37 29	99.31 41	99.53 38	99.91 3	98.98 71	99.63 7	99.58 77	99.44 51	99.78 39	99.76 15	96.39 233	99.92 63	99.44 53	99.92 67	99.68 68

Vis-MVSNet		99.34 30	99.36 33	99.27 95	99.73 37	98.26 124	99.17 53	99.78 36	99.11 93	99.27 135	99.48 74	98.82 37	99.95 26	98.94 90	99.93 54	99.59 104
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_fmvsm_n_1920		99.33 31	99.45 23	98.99 147	99.57 92	97.73 189	97.93 212	99.83 25	99.22 77	99.93 6	99.30 113	99.42 11	99.96 14	99.85 5	99.99 5	99.29 247

WR-MVS_H		99.33 31	99.22 53	99.65 8	99.71 47	99.24 30	99.32 26	99.55 95	99.46 48	99.50 87	99.34 104	97.30 179	99.93 52	98.90 92	99.93 54	99.77 48

fmvsm_l_conf0.5_n_9		99.32 33	99.43 24	98.98 151	99.59 85	97.18 225	97.44 285	99.83 25	99.56 38	99.91 12	99.34 104	99.36 13	99.93 52	99.83 9	99.98 12	99.85 29

mmtdpeth		99.30 34	99.42 25	98.92 162	99.58 87	96.89 243	99.48 13	99.92 7	99.92 2	98.26 287	99.80 11	98.33 87	99.91 72	99.56 39	99.95 38	99.97 4

mvs5depth		99.30 34	99.59 12	98.44 246	99.65 68	95.35 307	99.82 3	99.94 2	99.83 7	99.42 103	99.94 2	98.13 110	99.96 14	99.63 34	99.96 28	100.00 1

VPA-MVSNet		99.30 34	99.30 44	99.28 92	99.49 130	98.36 120	99.00 72	99.45 136	99.63 29	99.52 81	99.44 84	98.25 94	99.88 113	99.09 78	99.84 107	99.62 87

sd_testset		99.28 37	99.31 41	99.19 108	99.68 61	98.06 151	99.41 17	99.30 208	99.69 18	99.63 65	99.68 25	99.25 16	99.96 14	97.25 208	99.92 67	99.57 117

Anonymous20231211		99.27 38	99.27 47	99.26 97	99.29 186	98.18 133	99.49 12	99.51 108	99.70 16	99.80 37	99.68 25	96.84 205	99.83 190	99.21 69	99.91 76	99.77 48

FC-MVSNet-test		99.27 38	99.25 51	99.34 79	99.77 27	98.37 117	99.30 35	99.57 84	99.61 34	99.40 108	99.50 67	97.12 190	99.85 154	99.02 85	99.94 49	99.80 40

test_fmvsmvis_n_1920		99.26 40	99.49 16	98.54 232	99.66 67	96.97 236	98.00 199	99.85 18	99.24 74	99.92 8	99.50 67	99.39 12	99.95 26	99.89 3	99.98 12	98.71 355

lecture		99.25 41	99.12 68	99.62 9	99.64 74	99.40 12	98.89 87	99.51 108	99.19 85	99.37 113	99.25 129	98.36 81	99.88 113	98.23 135	99.67 208	99.59 104

testf1		99.25 41	99.16 60	99.51 48	99.89 6	99.63 4	98.71 104	99.69 50	98.90 128	99.43 99	99.35 100	98.86 34	99.67 309	97.81 168	99.81 122	99.24 260

APD_test2		99.25 41	99.16 60	99.51 48	99.89 6	99.63 4	98.71 104	99.69 50	98.90 128	99.43 99	99.35 100	98.86 34	99.67 309	97.81 168	99.81 122	99.24 260

KD-MVS_self_test		99.25 41	99.18 57	99.44 63	99.63 80	99.06 70	98.69 106	99.54 100	99.31 67	99.62 68	99.53 63	97.36 176	99.86 141	99.24 68	99.71 187	99.39 207

ACMH	96.65 7	99.25 41	99.24 52	99.26 97	99.72 43	98.38 115	99.07 64	99.55 95	98.30 175	99.65 62	99.45 83	99.22 17	99.76 260	98.44 124	99.77 150	99.64 81
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SDMVSNet		99.23 46	99.32 39	98.96 154	99.68 61	97.35 211	98.84 94	99.48 120	99.69 18	99.63 65	99.68 25	99.03 24	99.96 14	97.97 157	99.92 67	99.57 117

fmvsm_s_conf0.5_n_3		99.22 47	99.37 32	98.78 182	99.46 142	96.58 259	97.65 255	99.72 44	99.47 46	99.86 24	99.50 67	98.94 30	99.89 95	99.75 24	99.97 21	99.86 27

fmvsm_l_conf0.5_n		99.21 48	99.28 46	99.02 144	99.64 74	97.28 215	97.82 228	99.76 39	98.73 139	99.82 33	99.09 171	98.81 38	99.95 26	99.86 4	99.96 28	99.83 32

CP-MVSNet		99.21 48	99.09 73	99.56 26	99.65 68	98.96 77	99.13 58	99.34 187	99.42 54	99.33 122	99.26 124	97.01 198	99.94 41	98.74 105	99.93 54	99.79 42

fmvsm_s_conf0.1_n_2		99.20 50	99.38 29	98.65 202	99.69 58	96.08 279	97.49 279	99.90 11	99.53 40	99.88 21	99.64 37	98.51 71	99.90 79	99.83 9	99.98 12	99.97 4

fmvsm_l_conf0.5_n_a		99.19 51	99.27 47	98.94 157	99.65 68	97.05 232	97.80 232	99.76 39	98.70 142	99.78 39	99.11 164	98.79 42	99.95 26	99.85 5	99.96 28	99.83 32

fmvsm_s_conf0.5_n_9		99.17 52	99.38 29	98.53 234	99.51 116	95.82 289	97.62 260	99.78 36	99.72 15	99.90 14	99.48 74	98.66 54	99.89 95	99.85 5	99.93 54	99.89 16

fmvsm_s_conf0.1_n_a		99.17 52	99.30 44	98.80 176	99.75 34	96.59 256	97.97 211	99.86 16	98.22 183	99.88 21	99.71 22	98.59 62	99.84 172	99.73 26	99.98 12	99.98 3

TranMVSNet+NR-MVSNet		99.17 52	99.07 76	99.46 62	99.37 167	98.87 81	98.39 146	99.42 156	99.42 54	99.36 116	99.06 173	98.38 80	99.95 26	98.34 129	99.90 83	99.57 117

FMVSNet1		99.17 52	99.17 58	99.17 111	99.55 104	98.24 126	99.20 48	99.44 144	99.21 79	99.43 99	99.55 57	97.82 135	99.86 141	98.42 126	99.89 89	99.41 197

fmvsm_s_conf0.1_n		99.16 56	99.33 37	98.64 204	99.71 47	96.10 274	97.87 223	99.85 18	98.56 159	99.90 14	99.68 25	98.69 52	99.85 154	99.72 28	99.98 12	99.97 4

Elysia		99.15 57	99.14 66	99.18 109	99.63 80	97.92 165	98.50 130	99.43 150	99.67 21	99.70 50	99.13 160	96.66 221	99.98 4	99.54 42	99.96 28	99.64 81

StellarMVS		99.15 57	99.14 66	99.18 109	99.63 80	97.92 165	98.50 130	99.43 150	99.67 21	99.70 50	99.13 160	96.66 221	99.98 4	99.54 42	99.96 28	99.64 81

reproduce_model		99.15 57	98.97 87	99.67 4	99.33 177	99.44 10	98.15 170	99.47 128	99.12 92	99.52 81	99.32 111	98.31 88	99.90 79	97.78 171	99.73 170	99.66 75

fmvsm_s_conf0.5_n_2		99.14 60	99.31 41	98.63 208	99.49 130	96.08 279	97.38 289	99.81 31	99.48 43	99.84 30	99.57 49	98.46 75	99.89 95	99.82 11	99.97 21	99.91 13

test_vis3_rt		99.14 60	99.17 58	99.07 131	99.78 24	98.38 115	98.92 82	99.94 2	97.80 221	99.91 12	99.67 30	97.15 189	98.91 438	99.76 22	99.56 247	99.92 12

FIs		99.14 60	99.09 73	99.29 91	99.70 55	98.28 123	99.13 58	99.52 107	99.48 43	99.24 144	99.41 91	96.79 212	99.82 200	98.69 110	99.88 91	99.76 53

XXY-MVS		99.14 60	99.15 65	99.10 124	99.76 30	97.74 187	98.85 92	99.62 67	98.48 163	99.37 113	99.49 73	98.75 46	99.86 141	98.20 138	99.80 133	99.71 60

fmvsm_s_conf0.5_n_8		99.13 64	99.26 49	98.74 193	99.51 116	96.44 266	97.65 255	99.65 62	99.66 24	99.78 39	99.48 74	97.92 126	99.93 52	99.72 28	99.95 38	99.87 21

CS-MVS		99.13 64	99.10 71	99.24 102	99.06 248	99.15 52	99.36 22	99.88 14	99.36 62	98.21 289	98.46 311	98.68 53	99.93 52	99.03 84	99.85 102	98.64 364

SPE-MVS-test		99.13 64	99.09 73	99.26 97	99.13 232	98.97 73	99.31 30	99.88 14	99.44 51	98.16 293	98.51 303	98.64 56	99.93 52	98.91 91	99.85 102	98.88 331

test_fmvs3		99.12 67	99.41 26	98.25 267	99.76 30	95.07 319	99.05 67	99.94 2	97.78 224	99.82 33	99.84 3	98.56 68	99.71 287	99.96 1	99.96 28	99.97 4

casdiffmvs_mvg		99.12 67	99.16 60	98.99 147	99.43 154	97.73 189	98.00 199	99.62 67	99.22 77	99.55 73	99.22 137	98.93 32	99.75 268	98.66 111	99.81 122	99.50 152
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
fmvsm_s_conf0.5_n_a		99.10 69	99.20 56	98.78 182	99.55 104	96.59 256	97.79 233	99.82 30	98.21 184	99.81 36	99.53 63	98.46 75	99.84 172	99.70 31	99.97 21	99.90 15

reproduce-ours		99.09 70	98.90 93	99.67 4	99.27 191	99.49 6	98.00 199	99.42 156	99.05 110	99.48 89	99.27 119	98.29 90	99.89 95	97.61 184	99.71 187	99.62 87

our_new_method		99.09 70	98.90 93	99.67 4	99.27 191	99.49 6	98.00 199	99.42 156	99.05 110	99.48 89	99.27 119	98.29 90	99.89 95	97.61 184	99.71 187	99.62 87

fmvsm_s_conf0.5_n		99.09 70	99.26 49	98.61 213	99.55 104	96.09 277	97.74 243	99.81 31	98.55 160	99.85 27	99.55 57	98.60 61	99.84 172	99.69 33	99.98 12	99.89 16

EC-MVSNet		99.09 70	99.05 77	99.20 106	99.28 188	98.93 79	99.24 44	99.84 22	99.08 107	98.12 298	98.37 320	98.72 49	99.90 79	99.05 82	99.77 150	98.77 349

fmvsm_s_conf0.5_n_6		99.08 74	99.21 55	98.69 198	99.36 168	96.51 261	97.62 260	99.68 55	98.43 165	99.85 27	99.10 167	99.12 23	99.88 113	99.77 21	99.92 67	99.67 73

ACMH+	96.62 9	99.08 74	99.00 83	99.33 85	99.71 47	98.83 83	98.60 114	99.58 77	99.11 93	99.53 79	99.18 145	98.81 38	99.67 309	96.71 257	99.77 150	99.50 152

fmvsm_s_conf0.5_n_5		99.07 76	99.10 71	98.99 147	99.47 140	97.22 220	97.40 287	99.83 25	97.61 236	99.85 27	99.30 113	98.80 40	99.95 26	99.71 30	99.90 83	99.78 45

GeoE		99.05 77	98.99 85	99.25 100	99.44 149	98.35 121	98.73 101	99.56 91	98.42 166	98.91 203	98.81 249	98.94 30	99.91 72	98.35 128	99.73 170	99.49 157

KinetiMVS		99.03 78	99.02 79	99.03 141	99.70 55	97.48 203	98.43 141	99.29 216	99.70 16	99.60 69	99.07 172	96.13 244	99.94 41	99.42 54	99.87 95	99.68 68

Gipuma		99.03 78	99.16 60	98.64 204	99.94 2	98.51 108	99.32 26	99.75 42	99.58 37	98.60 252	99.62 40	98.22 99	99.51 379	97.70 179	99.73 170	97.89 412
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
fmvsm_s_conf0.5_n_4		99.01 80	99.22 53	98.38 253	99.31 179	95.48 300	97.56 270	99.73 43	98.87 131	99.75 44	99.27 119	98.80 40	99.86 141	99.80 16	99.90 83	99.81 38

v8		99.01 80	99.16 60	98.57 220	99.47 140	96.31 271	98.90 83	99.47 128	99.03 113	99.52 81	99.57 49	96.93 201	99.81 216	99.60 35	99.98 12	99.60 97

HPM-MVS_fast		99.01 80	98.82 104	99.57 21	99.71 47	99.35 17	99.00 72	99.50 111	97.33 268	98.94 199	98.86 234	98.75 46	99.82 200	97.53 191	99.71 187	99.56 123

APDe-MVS		98.99 83	98.79 107	99.60 15	99.21 208	99.15 52	98.87 88	99.48 120	97.57 240	99.35 118	99.24 131	97.83 132	99.89 95	97.88 163	99.70 194	99.75 57
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
EG-PatchMatch MVS		98.99 83	99.01 81	98.94 157	99.50 122	97.47 204	98.04 190	99.59 75	98.15 199	99.40 108	99.36 99	98.58 67	99.76 260	98.78 100	99.68 202	99.59 104

COLMAP_ROB	96.50 10	98.99 83	98.85 102	99.41 66	99.58 87	99.10 65	98.74 97	99.56 91	99.09 103	99.33 122	99.19 141	98.40 79	99.72 286	95.98 307	99.76 163	99.42 194
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 86	98.86 101	99.36 70	99.82 19	98.55 103	97.47 282	99.57 84	99.37 59	99.21 150	99.61 43	96.76 215	99.83 190	98.06 148	99.83 114	99.71 60

v10		98.97 87	99.11 69	98.55 227	99.44 149	96.21 273	98.90 83	99.55 95	98.73 139	99.48 89	99.60 45	96.63 224	99.83 190	99.70 31	99.99 5	99.61 95

DeepC-MVS	97.60 4	98.97 87	98.93 90	99.10 124	99.35 173	97.98 158	98.01 198	99.46 132	97.56 242	99.54 75	99.50 67	98.97 28	99.84 172	98.06 148	99.92 67	99.49 157
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 89	99.02 79	98.76 187	99.38 161	97.26 217	98.49 133	99.50 111	98.86 133	99.19 152	99.06 173	98.23 96	99.69 296	98.71 108	99.76 163	99.33 235

casdiffmvs		98.95 90	99.00 83	98.81 174	99.38 161	97.33 212	97.82 228	99.57 84	99.17 89	99.35 118	99.17 149	98.35 85	99.69 296	98.46 123	99.73 170	99.41 197
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 90	98.82 104	99.36 70	99.16 225	98.72 93	99.22 45	99.20 240	99.10 100	99.72 46	98.76 258	96.38 235	99.86 141	98.00 155	99.82 118	99.50 152

Anonymous20240529		98.93 92	98.87 98	99.12 120	99.19 215	98.22 131	99.01 70	98.99 287	99.25 73	99.54 75	99.37 95	97.04 194	99.80 224	97.89 160	99.52 260	99.35 228

DP-MVS		98.93 92	98.81 106	99.28 92	99.21 208	98.45 112	98.46 138	99.33 193	99.63 29	99.48 89	99.15 155	97.23 185	99.75 268	97.17 211	99.66 215	99.63 86

SED-MVS		98.91 94	98.72 115	99.49 54	99.49 130	99.17 44	98.10 179	99.31 200	98.03 202	99.66 59	99.02 185	98.36 81	99.88 113	96.91 233	99.62 224	99.41 197

ACMM	96.08 12	98.91 94	98.73 113	99.48 56	99.55 104	99.14 57	98.07 185	99.37 171	97.62 233	99.04 175	98.96 211	98.84 36	99.79 237	97.43 199	99.65 216	99.49 157
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SSM_0404		98.90 96	99.01 81	98.57 220	99.42 155	96.59 256	98.13 172	99.66 59	99.09 103	99.30 131	99.02 185	98.79 42	99.89 95	97.87 165	99.80 133	99.23 262

DVP-MVS++		98.90 96	98.70 121	99.51 48	98.43 366	99.15 52	99.43 15	99.32 195	98.17 191	99.26 139	99.02 185	98.18 103	99.88 113	97.07 221	99.45 276	99.49 157

tfpnnormal		98.90 96	98.90 93	98.91 163	99.67 65	97.82 179	99.00 72	99.44 144	99.45 49	99.51 86	99.24 131	98.20 102	99.86 141	95.92 309	99.69 197	99.04 301

MTAPA		98.88 99	98.64 130	99.61 13	99.67 65	99.36 16	98.43 141	99.20 240	98.83 137	98.89 207	98.90 224	96.98 200	99.92 63	97.16 212	99.70 194	99.56 123

mvsany_test3		98.87 100	98.92 91	98.74 193	99.38 161	96.94 240	98.58 116	99.10 265	96.49 322	99.96 4	99.81 8	98.18 103	99.45 394	98.97 88	99.79 139	99.83 32

VPNet		98.87 100	98.83 103	99.01 145	99.70 55	97.62 196	98.43 141	99.35 181	99.47 46	99.28 133	99.05 180	96.72 218	99.82 200	98.09 145	99.36 291	99.59 104

UniMVSNet (Re)		98.87 100	98.71 118	99.35 76	99.24 201	98.73 91	97.73 245	99.38 167	98.93 124	99.12 158	98.73 261	96.77 213	99.86 141	98.63 114	99.80 133	99.46 178

SSM_0407		98.86 103	98.96 89	98.55 227	99.27 191	96.50 262	98.04 190	99.66 59	99.09 103	99.22 147	99.02 185	98.79 42	99.87 132	97.87 165	99.72 178	99.27 250

UniMVSNet_NR-MVSNet		98.86 103	98.68 124	99.40 68	99.17 223	98.74 88	97.68 249	99.40 163	99.14 91	99.06 166	98.59 294	96.71 219	99.93 52	98.57 117	99.77 150	99.53 143

APD-MVS_3200maxsize		98.84 105	98.61 138	99.53 38	99.19 215	99.27 27	98.49 133	99.33 193	98.64 144	99.03 178	98.98 206	97.89 129	99.85 154	96.54 276	99.42 284	99.46 178

fmvsm_s_conf0.5_n_7		98.83 106	99.04 78	98.20 272	99.30 183	94.83 324	97.23 302	99.36 175	98.64 144	99.84 30	99.43 86	98.10 112	99.91 72	99.56 39	99.96 28	99.87 21

MVSMamba_PlusPlus		98.83 106	98.98 86	98.36 257	99.32 178	96.58 259	98.90 83	99.41 160	99.75 11	98.72 236	99.50 67	96.17 242	99.94 41	99.27 63	99.78 144	98.57 371

APD_test1		98.83 106	98.66 127	99.34 79	99.78 24	99.47 9	98.42 144	99.45 136	98.28 180	98.98 183	99.19 141	97.76 140	99.58 354	96.57 268	99.55 251	98.97 314

PM-MVS		98.82 109	98.72 115	99.12 120	99.64 74	98.54 106	97.98 207	99.68 55	97.62 233	99.34 120	99.18 145	97.54 160	99.77 254	97.79 170	99.74 167	99.04 301

DU-MVS		98.82 109	98.63 132	99.39 69	99.16 225	98.74 88	97.54 273	99.25 229	98.84 136	99.06 166	98.76 258	96.76 215	99.93 52	98.57 117	99.77 150	99.50 152

SR-MVS-dyc-post		98.81 111	98.55 145	99.57 21	99.20 212	99.38 13	98.48 136	99.30 208	98.64 144	98.95 192	98.96 211	97.49 169	99.86 141	96.56 272	99.39 287	99.45 183

3Dnovator	98.27 2	98.81 111	98.73 113	99.05 138	98.76 308	97.81 182	99.25 43	99.30 208	98.57 156	98.55 261	99.33 107	97.95 124	99.90 79	97.16 212	99.67 208	99.44 187

mamba_0408		98.80 113	98.88 96	98.55 227	99.27 191	96.50 262	98.00 199	99.60 71	98.93 124	99.22 147	98.84 242	98.59 62	99.89 95	97.74 177	99.72 178	99.27 250

SSM_04072		98.80 113	98.88 96	98.56 225	99.27 191	96.50 262	98.00 199	99.60 71	98.93 124	99.22 147	98.84 242	98.59 62	99.90 79	97.74 177	99.72 178	99.27 250

HPM-MVS		98.79 115	98.53 149	99.59 19	99.65 68	99.29 24	99.16 54	99.43 150	96.74 312	98.61 250	98.38 319	98.62 59	99.87 132	96.47 280	99.67 208	99.59 104
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
SteuartSystems-ACMMP		98.79 115	98.54 147	99.54 31	99.73 37	99.16 48	98.23 160	99.31 200	97.92 212	98.90 204	98.90 224	98.00 119	99.88 113	96.15 300	99.72 178	99.58 112
Skip Steuart: Steuart Systems R&D Blog.
dcpmvs_2		98.78 117	99.11 69	97.78 301	99.56 100	93.67 372	99.06 65	99.86 16	99.50 42	99.66 59	99.26 124	97.21 187	99.99 2	98.00 155	99.91 76	99.68 68

V42		98.78 117	98.78 109	98.76 187	99.44 149	97.04 233	98.27 157	99.19 244	97.87 216	99.25 143	99.16 151	96.84 205	99.78 248	99.21 69	99.84 107	99.46 178

test20.03		98.78 117	98.77 110	98.78 182	99.46 142	97.20 223	97.78 234	99.24 234	99.04 112	99.41 105	98.90 224	97.65 147	99.76 260	97.70 179	99.79 139	99.39 207

DVP-MVS		98.77 120	98.52 150	99.52 44	99.50 122	99.21 33	98.02 195	98.84 313	97.97 206	99.08 164	99.02 185	97.61 154	99.88 113	96.99 227	99.63 221	99.48 168
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		98.76 121	98.71 118	98.93 159	99.56 100	98.14 137	98.45 140	99.34 187	99.28 71	98.95 192	98.91 221	98.34 86	99.79 237	95.63 324	99.91 76	98.86 333

ACMMP_NAP		98.75 122	98.48 158	99.57 21	99.58 87	99.29 24	97.82 228	99.25 229	96.94 301	98.78 227	99.12 163	98.02 117	99.84 172	97.13 217	99.67 208	99.59 104

SixPastTwentyTwo		98.75 122	98.62 134	99.16 114	99.83 18	97.96 162	99.28 40	98.20 359	99.37 59	99.70 50	99.65 36	92.65 338	99.93 52	99.04 83	99.84 107	99.60 97

ACMMP		98.75 122	98.50 153	99.52 44	99.56 100	99.16 48	98.87 88	99.37 171	97.16 289	98.82 222	99.01 196	97.71 143	99.87 132	96.29 292	99.69 197	99.54 134
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		98.72 125	98.45 163	99.53 38	99.46 142	99.21 33	98.65 108	99.34 187	98.62 149	97.54 341	98.63 287	97.50 166	99.83 190	96.79 246	99.53 257	99.56 123

SSC-MVS		98.71 126	98.74 111	98.62 210	99.72 43	96.08 279	98.74 97	98.64 339	99.74 13	99.67 58	99.24 131	94.57 299	99.95 26	99.11 76	99.24 311	99.82 35

SR-MVS		98.71 126	98.43 166	99.57 21	99.18 222	99.35 17	98.36 149	99.29 216	98.29 178	98.88 211	98.85 237	97.53 162	99.87 132	96.14 301	99.31 299	99.48 168

HFP-MVS		98.71 126	98.44 165	99.51 48	99.49 130	99.16 48	98.52 123	99.31 200	97.47 252	98.58 256	98.50 307	97.97 123	99.85 154	96.57 268	99.59 235	99.53 143

LPG-MVS_test		98.71 126	98.46 162	99.47 60	99.57 92	98.97 73	98.23 160	99.48 120	96.60 317	99.10 162	99.06 173	98.71 50	99.83 190	95.58 327	99.78 144	99.62 87

test_fmvs2		98.70 130	98.97 87	97.89 294	99.54 109	94.05 349	98.55 119	99.92 7	96.78 310	99.72 46	99.78 13	96.60 225	99.67 309	99.91 2	99.90 83	99.94 10

ACMMPR		98.70 130	98.42 168	99.54 31	99.52 114	99.14 57	98.52 123	99.31 200	97.47 252	98.56 259	98.54 298	97.75 141	99.88 113	96.57 268	99.59 235	99.58 112

CP-MVS		98.70 130	98.42 168	99.52 44	99.36 168	99.12 62	98.72 102	99.36 175	97.54 246	98.30 281	98.40 316	97.86 131	99.89 95	96.53 277	99.72 178	99.56 123

tt0805		98.69 133	98.62 134	98.90 166	99.75 34	99.30 22	99.15 56	96.97 396	98.86 133	98.87 215	97.62 374	98.63 58	98.96 435	99.41 55	98.29 387	98.45 378

Anonymous20240521		98.69 133	98.87 98	98.16 277	99.77 27	95.11 318	99.08 61	99.44 144	99.34 63	99.33 122	99.55 57	94.10 313	99.94 41	99.25 66	99.96 28	99.42 194

region2R		98.69 133	98.40 170	99.54 31	99.53 112	99.17 44	98.52 123	99.31 200	97.46 257	98.44 272	98.51 303	97.83 132	99.88 113	96.46 281	99.58 240	99.58 112

EI-MVSNet-UG-set		98.69 133	98.71 118	98.62 210	99.10 236	96.37 268	97.23 302	98.87 304	99.20 81	99.19 152	98.99 201	97.30 179	99.85 154	98.77 103	99.79 139	99.65 80

3Dnovator+	97.89 3	98.69 133	98.51 151	99.24 102	98.81 303	98.40 113	99.02 69	99.19 244	98.99 116	98.07 302	99.28 117	97.11 192	99.84 172	96.84 244	99.32 297	99.47 176

ZNCC-MVS		98.68 138	98.40 170	99.54 31	99.57 92	99.21 33	98.46 138	99.29 216	97.28 274	98.11 299	98.39 317	98.00 119	99.87 132	96.86 243	99.64 218	99.55 130

EI-MVSNet-Vis-set		98.68 138	98.70 121	98.63 208	99.09 239	96.40 267	97.23 302	98.86 309	99.20 81	99.18 156	98.97 208	97.29 181	99.85 154	98.72 107	99.78 144	99.64 81

CSCG		98.68 138	98.50 153	99.20 106	99.45 147	98.63 95	98.56 118	99.57 84	97.87 216	98.85 216	98.04 348	97.66 146	99.84 172	96.72 255	99.81 122	99.13 290

test_f		98.67 141	98.87 98	98.05 286	99.72 43	95.59 293	98.51 128	99.81 31	96.30 332	99.78 39	99.82 5	96.14 243	98.63 445	99.82 11	99.93 54	99.95 9

PGM-MVS		98.66 142	98.37 177	99.55 28	99.53 112	99.18 43	98.23 160	99.49 118	97.01 298	98.69 238	98.88 231	98.00 119	99.89 95	95.87 313	99.59 235	99.58 112

GBi-Net		98.65 143	98.47 160	99.17 111	98.90 282	98.24 126	99.20 48	99.44 144	98.59 152	98.95 192	99.55 57	94.14 309	99.86 141	97.77 172	99.69 197	99.41 197

test1		98.65 143	98.47 160	99.17 111	98.90 282	98.24 126	99.20 48	99.44 144	98.59 152	98.95 192	99.55 57	94.14 309	99.86 141	97.77 172	99.69 197	99.41 197

LCM-MVSNet-Re		98.64 145	98.48 158	99.11 122	98.85 294	98.51 108	98.49 133	99.83 25	98.37 167	99.69 54	99.46 79	98.21 101	99.92 63	94.13 365	99.30 302	98.91 326

mPP-MVS		98.64 145	98.34 181	99.54 31	99.54 109	99.17 44	98.63 110	99.24 234	97.47 252	98.09 301	98.68 275	97.62 152	99.89 95	96.22 295	99.62 224	99.57 117

balanced_conf03		98.63 147	98.72 115	98.38 253	98.66 337	96.68 255	98.90 83	99.42 156	98.99 116	98.97 187	99.19 141	95.81 264	99.85 154	98.77 103	99.77 150	98.60 367

TSAR-MVS + MP.		98.63 147	98.49 157	99.06 137	99.64 74	97.90 168	98.51 128	98.94 289	96.96 299	99.24 144	98.89 230	97.83 132	99.81 216	96.88 240	99.49 271	99.48 168
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
LS3D		98.63 147	98.38 175	99.36 70	97.25 431	99.38 13	99.12 60	99.32 195	99.21 79	98.44 272	98.88 231	97.31 178	99.80 224	96.58 266	99.34 295	98.92 323

RPSCF		98.62 150	98.36 178	99.42 64	99.65 68	99.42 11	98.55 119	99.57 84	97.72 227	98.90 204	99.26 124	96.12 246	99.52 374	95.72 320	99.71 187	99.32 238

GST-MVS		98.61 151	98.30 187	99.52 44	99.51 116	99.20 39	98.26 158	99.25 229	97.44 260	98.67 241	98.39 317	97.68 144	99.85 154	96.00 305	99.51 262	99.52 146

v1192		98.60 152	98.66 127	98.41 249	99.27 191	95.88 285	97.52 275	99.36 175	97.41 261	99.33 122	99.20 140	96.37 236	99.82 200	99.57 37	99.92 67	99.55 130

v1144		98.60 152	98.66 127	98.41 249	99.36 168	95.90 284	97.58 268	99.34 187	97.51 248	99.27 135	99.15 155	96.34 238	99.80 224	99.47 52	99.93 54	99.51 149

DPE-MVS		98.59 154	98.26 193	99.57 21	99.27 191	99.15 52	97.01 316	99.39 165	97.67 229	99.44 98	98.99 201	97.53 162	99.89 95	95.40 331	99.68 202	99.66 75
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
viewmanbaseed2359cas		98.58 155	98.54 147	98.70 197	99.28 188	97.13 231	97.47 282	99.55 95	97.55 244	98.96 191	98.92 219	97.77 139	99.59 347	97.59 187	99.77 150	99.39 207

MP-MVS-pluss		98.57 156	98.23 198	99.60 15	99.69 58	99.35 17	97.16 311	99.38 167	94.87 376	98.97 187	98.99 201	98.01 118	99.88 113	97.29 205	99.70 194	99.58 112
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
OPM-MVS		98.56 157	98.32 185	99.25 100	99.41 158	98.73 91	97.13 313	99.18 248	97.10 292	98.75 233	98.92 219	98.18 103	99.65 325	96.68 259	99.56 247	99.37 217
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
VDD-MVS		98.56 157	98.39 173	99.07 131	99.13 232	98.07 148	98.59 115	97.01 394	99.59 35	99.11 159	99.27 119	94.82 291	99.79 237	98.34 129	99.63 221	99.34 230

v2v482		98.56 157	98.62 134	98.37 256	99.42 155	95.81 290	97.58 268	99.16 255	97.90 214	99.28 133	99.01 196	95.98 256	99.79 237	99.33 58	99.90 83	99.51 149

XVG-ACMP-BASELINE		98.56 157	98.34 181	99.22 105	99.54 109	98.59 100	97.71 246	99.46 132	97.25 277	98.98 183	98.99 201	97.54 160	99.84 172	95.88 310	99.74 167	99.23 262

v1240		98.55 161	98.62 134	98.32 260	99.22 206	95.58 295	97.51 277	99.45 136	97.16 289	99.45 97	99.24 131	96.12 246	99.85 154	99.60 35	99.88 91	99.55 130

IterMVS-LS		98.55 161	98.70 121	98.09 279	99.48 138	94.73 329	97.22 306	99.39 165	98.97 119	99.38 111	99.31 112	96.00 251	99.93 52	98.58 115	99.97 21	99.60 97
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v144192		98.54 163	98.57 143	98.45 244	99.21 208	95.98 282	97.63 259	99.36 175	97.15 291	99.32 128	99.18 145	95.84 263	99.84 172	99.50 49	99.91 76	99.54 134

v1921920		98.54 163	98.60 139	98.38 253	99.20 212	95.76 292	97.56 270	99.36 175	97.23 283	99.38 111	99.17 149	96.02 249	99.84 172	99.57 37	99.90 83	99.54 134

SSC-MVS3.2		98.53 165	98.79 107	97.74 308	99.46 142	93.62 375	96.45 349	99.34 187	99.33 64	98.93 200	98.70 271	97.90 127	99.90 79	99.12 75	99.92 67	99.69 67

SF-MVS		98.53 165	98.27 192	99.32 87	99.31 179	98.75 87	98.19 164	99.41 160	96.77 311	98.83 219	98.90 224	97.80 137	99.82 200	95.68 323	99.52 260	99.38 215

XVG-OURS		98.53 165	98.34 181	99.11 122	99.50 122	98.82 85	95.97 378	99.50 111	97.30 272	99.05 173	98.98 206	99.35 14	99.32 413	95.72 320	99.68 202	99.18 280

UGNet		98.53 165	98.45 163	98.79 179	97.94 395	96.96 238	99.08 61	98.54 343	99.10 100	96.82 382	99.47 77	96.55 227	99.84 172	98.56 120	99.94 49	99.55 130
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
WB-MVS		98.52 169	98.55 145	98.43 247	99.65 68	95.59 293	98.52 123	98.77 324	99.65 26	99.52 81	99.00 199	94.34 305	99.93 52	98.65 112	98.83 359	99.76 53

patch_mono-2		98.51 170	98.63 132	98.17 275	99.38 161	94.78 326	97.36 292	99.69 50	98.16 194	98.49 268	99.29 116	97.06 193	99.97 7	98.29 132	99.91 76	99.76 53

diffmvs_AUTHOR		98.50 171	98.59 141	98.23 270	99.35 173	95.48 300	96.61 340	99.60 71	98.37 167	98.90 204	99.00 199	97.37 175	99.76 260	98.22 136	99.85 102	99.46 178

XVG-OURS-SEG-HR		98.49 172	98.28 189	99.14 118	99.49 130	98.83 83	96.54 343	99.48 120	97.32 270	99.11 159	98.61 291	99.33 15	99.30 416	96.23 294	98.38 383	99.28 249

FMVSNet2		98.49 172	98.40 170	98.75 189	98.90 282	97.14 230	98.61 113	99.13 261	98.59 152	99.19 152	99.28 117	94.14 309	99.82 200	97.97 157	99.80 133	99.29 247

pmmvs-eth3d		98.47 174	98.34 181	98.86 168	99.30 183	97.76 185	97.16 311	99.28 220	95.54 357	99.42 103	99.19 141	97.27 182	99.63 331	97.89 160	99.97 21	99.20 272

MP-MVS		98.46 175	98.09 215	99.54 31	99.57 92	99.22 32	98.50 130	99.19 244	97.61 236	97.58 337	98.66 280	97.40 173	99.88 113	94.72 346	99.60 231	99.54 134
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
v148		98.45 176	98.60 139	98.00 289	99.44 149	94.98 321	97.44 285	99.06 270	98.30 175	99.32 128	98.97 208	96.65 223	99.62 334	98.37 127	99.85 102	99.39 207

AllTest		98.44 177	98.20 200	99.16 114	99.50 122	98.55 103	98.25 159	99.58 77	96.80 308	98.88 211	99.06 173	97.65 147	99.57 356	94.45 353	99.61 229	99.37 217

VNet		98.42 178	98.30 187	98.79 179	98.79 307	97.29 214	98.23 160	98.66 336	99.31 67	98.85 216	98.80 250	94.80 294	99.78 248	98.13 142	99.13 330	99.31 242

ab-mvs		98.41 179	98.36 178	98.59 216	99.19 215	97.23 218	99.32 26	98.81 318	97.66 230	98.62 248	99.40 94	96.82 208	99.80 224	95.88 310	99.51 262	98.75 352

ACMP	95.32 15	98.41 179	98.09 215	99.36 70	99.51 116	98.79 86	97.68 249	99.38 167	95.76 351	98.81 224	98.82 247	98.36 81	99.82 200	94.75 343	99.77 150	99.48 168
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_vis1_n_1920		98.40 181	98.92 91	96.81 373	99.74 36	90.76 424	98.15 170	99.91 9	98.33 171	99.89 18	99.55 57	95.07 284	99.88 113	99.76 22	99.93 54	99.79 42

SMA-MVS		98.40 181	98.03 223	99.51 48	99.16 225	99.21 33	98.05 188	99.22 237	94.16 392	98.98 183	99.10 167	97.52 164	99.79 237	96.45 282	99.64 218	99.53 143
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		98.40 181	98.00 226	99.61 13	99.57 92	99.25 29	98.57 117	99.35 181	97.55 244	99.31 130	97.71 367	94.61 298	99.88 113	96.14 301	99.19 322	99.70 65
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		98.40 181	98.68 124	97.54 333	98.96 270	97.99 155	97.88 220	99.36 175	98.20 188	99.63 65	99.04 182	98.76 45	95.33 460	96.56 272	99.74 167	99.31 242
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		98.40 181	98.51 151	98.04 287	99.10 236	94.73 329	97.20 307	98.87 304	98.97 119	99.06 166	99.02 185	96.00 251	99.80 224	98.58 115	99.82 118	99.60 97

WR-MVS		98.40 181	98.19 204	99.03 141	99.00 263	97.65 193	96.85 326	98.94 289	98.57 156	98.89 207	98.50 307	95.60 269	99.85 154	97.54 190	99.85 102	99.59 104

IMVS_0407		98.39 187	98.64 130	97.66 316	99.03 255	94.03 352	98.10 179	99.45 136	98.16 194	99.06 166	98.71 264	98.27 92	99.71 287	97.50 193	99.45 276	99.22 267

LuminaMVS		98.39 187	98.20 200	98.98 151	99.50 122	97.49 201	97.78 234	97.69 374	98.75 138	99.49 88	99.25 129	92.30 342	99.94 41	99.14 74	99.88 91	99.50 152

new-patchmatchnet		98.35 189	98.74 111	97.18 352	99.24 201	92.23 400	96.42 353	99.48 120	98.30 175	99.69 54	99.53 63	97.44 171	99.82 200	98.84 97	99.77 150	99.49 157

IMVS_0403		98.34 190	98.56 144	97.66 316	99.03 255	94.03 352	97.98 207	99.45 136	98.16 194	98.89 207	98.71 264	97.90 127	99.74 273	97.50 193	99.45 276	99.22 267

MGCFI-Net		98.34 190	98.28 189	98.51 236	98.47 360	97.59 197	98.96 77	99.48 120	99.18 88	97.40 353	95.50 426	98.66 54	99.50 380	98.18 139	98.71 367	98.44 381

sasdasda		98.34 190	98.26 193	98.58 217	98.46 362	97.82 179	98.96 77	99.46 132	99.19 85	97.46 348	95.46 429	98.59 62	99.46 392	98.08 146	98.71 367	98.46 375

canonicalmvs		98.34 190	98.26 193	98.58 217	98.46 362	97.82 179	98.96 77	99.46 132	99.19 85	97.46 348	95.46 429	98.59 62	99.46 392	98.08 146	98.71 367	98.46 375

test_cas_vis1_n_1920		98.33 194	98.68 124	97.27 349	99.69 58	92.29 398	98.03 192	99.85 18	97.62 233	99.96 4	99.62 40	93.98 314	99.74 273	99.52 48	99.86 101	99.79 42

testgi		98.32 195	98.39 173	98.13 278	99.57 92	95.54 296	97.78 234	99.49 118	97.37 265	99.19 152	97.65 371	98.96 29	99.49 383	96.50 279	98.99 347	99.34 230

DeepPCF-MVS	96.93 5	98.32 195	98.01 225	99.23 104	98.39 371	98.97 73	95.03 416	99.18 248	96.88 304	99.33 122	98.78 254	98.16 107	99.28 420	96.74 252	99.62 224	99.44 187

test_vis1_n		98.31 197	98.50 153	97.73 311	99.76 30	94.17 346	98.68 107	99.91 9	96.31 330	99.79 38	99.57 49	92.85 334	99.42 399	99.79 18	99.84 107	99.60 97

MVS_111021_LR		98.30 198	98.12 213	98.83 171	99.16 225	98.03 153	96.09 374	99.30 208	97.58 239	98.10 300	98.24 331	98.25 94	99.34 410	96.69 258	99.65 216	99.12 291

EPP-MVSNet		98.30 198	98.04 222	99.07 131	99.56 100	97.83 174	99.29 36	98.07 365	99.03 113	98.59 254	99.13 160	92.16 344	99.90 79	96.87 241	99.68 202	99.49 157

DeepC-MVS_fast	96.85 6	98.30 198	98.15 210	98.75 189	98.61 342	97.23 218	97.76 240	99.09 267	97.31 271	98.75 233	98.66 280	97.56 158	99.64 328	96.10 304	99.55 251	99.39 207
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PHI-MVS		98.29 201	97.95 232	99.34 79	98.44 365	99.16 48	98.12 176	99.38 167	96.01 343	98.06 303	98.43 314	97.80 137	99.67 309	95.69 322	99.58 240	99.20 272

Fast-Effi-MVS+-dtu		98.27 202	98.09 215	98.81 174	98.43 366	98.11 139	97.61 264	99.50 111	98.64 144	97.39 355	97.52 379	98.12 111	99.95 26	96.90 238	98.71 367	98.38 388

DELS-MVS		98.27 202	98.20 200	98.48 241	98.86 291	96.70 253	95.60 398	99.20 240	97.73 226	98.45 271	98.71 264	97.50 166	99.82 200	98.21 137	99.59 235	98.93 322
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
NormalMVS		98.26 204	97.97 231	99.15 117	99.64 74	97.83 174	98.28 154	99.43 150	99.24 74	98.80 225	98.85 237	89.76 367	99.94 41	98.04 150	99.67 208	99.68 68

Effi-MVS+-dtu		98.26 204	97.90 239	99.35 76	98.02 392	99.49 6	98.02 195	99.16 255	98.29 178	97.64 332	97.99 351	96.44 232	99.95 26	96.66 260	98.93 355	98.60 367

MVSFormer		98.26 204	98.43 166	97.77 302	98.88 288	93.89 365	99.39 20	99.56 91	99.11 93	98.16 293	98.13 338	93.81 317	99.97 7	99.26 64	99.57 244	99.43 191

MVS_111021_HR		98.25 207	98.08 218	98.75 189	99.09 239	97.46 205	95.97 378	99.27 223	97.60 238	97.99 310	98.25 330	98.15 109	99.38 405	96.87 241	99.57 244	99.42 194

TAMVS		98.24 208	98.05 221	98.80 176	99.07 243	97.18 225	97.88 220	98.81 318	96.66 316	99.17 157	99.21 138	94.81 293	99.77 254	96.96 231	99.88 91	99.44 187

MM		98.22 209	97.99 227	98.91 163	98.66 337	96.97 236	97.89 219	94.44 433	99.54 39	98.95 192	99.14 158	93.50 321	99.92 63	99.80 16	99.96 28	99.85 29

diffmvs		98.22 209	98.24 197	98.17 275	99.00 263	95.44 304	96.38 355	99.58 77	97.79 223	98.53 264	98.50 307	96.76 215	99.74 273	97.95 159	99.64 218	99.34 230
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		98.21 211	98.21 199	98.20 272	99.51 116	95.43 305	98.13 172	99.32 195	96.16 336	98.93 200	98.82 247	96.00 251	99.83 190	97.32 204	99.73 170	99.36 224

VDDNet		98.21 211	97.95 232	99.01 145	99.58 87	97.74 187	99.01 70	97.29 387	99.67 21	98.97 187	99.50 67	90.45 362	99.80 224	97.88 163	99.20 319	99.48 168

icg_test_0407_2		98.20 213	98.38 175	97.65 318	99.03 255	94.03 352	95.78 392	99.45 136	98.16 194	99.06 166	98.71 264	98.27 92	99.68 305	97.50 193	99.45 276	99.22 267

viewmambaseed2359dif		98.19 214	98.26 193	97.99 290	99.02 260	95.03 320	96.59 342	99.53 103	96.21 333	99.00 180	98.99 201	97.62 152	99.61 341	97.62 183	99.72 178	99.33 235

IS-MVSNet		98.19 214	97.90 239	99.08 129	99.57 92	97.97 159	99.31 30	98.32 354	99.01 115	98.98 183	99.03 184	91.59 350	99.79 237	95.49 329	99.80 133	99.48 168

MVS_Test		98.18 216	98.36 178	97.67 314	98.48 359	94.73 329	98.18 165	99.02 281	97.69 228	98.04 306	99.11 164	97.22 186	99.56 359	98.57 117	98.90 357	98.71 355

TSAR-MVS + GP.		98.18 216	97.98 228	98.77 186	98.71 318	97.88 169	96.32 359	98.66 336	96.33 328	99.23 146	98.51 303	97.48 170	99.40 401	97.16 212	99.46 274	99.02 304

CNVR-MVS		98.17 218	97.87 241	99.07 131	98.67 332	98.24 126	97.01 316	98.93 292	97.25 277	97.62 333	98.34 324	97.27 182	99.57 356	96.42 283	99.33 296	99.39 207

PVSNet_Blended_VisFu		98.17 218	98.15 210	98.22 271	99.73 37	95.15 315	97.36 292	99.68 55	94.45 386	98.99 182	99.27 119	96.87 204	99.94 41	97.13 217	99.91 76	99.57 117

AstraMVS		98.16 220	98.07 220	98.41 249	99.51 116	95.86 286	98.00 199	95.14 428	98.97 119	99.43 99	99.24 131	93.25 322	99.84 172	99.21 69	99.87 95	99.54 134

HPM-MVS++		98.10 221	97.64 259	99.48 56	99.09 239	99.13 60	97.52 275	98.75 329	97.46 257	96.90 377	97.83 362	96.01 250	99.84 172	95.82 317	99.35 293	99.46 178

APD-MVS		98.10 221	97.67 254	99.42 64	99.11 234	98.93 79	97.76 240	99.28 220	94.97 373	98.72 236	98.77 256	97.04 194	99.85 154	93.79 375	99.54 253	99.49 157
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_fmvs1_n		98.09 223	98.28 189	97.52 335	99.68 61	93.47 377	98.63 110	99.93 5	95.41 364	99.68 56	99.64 37	91.88 348	99.48 386	99.82 11	99.87 95	99.62 87

MVP-Stereo		98.08 224	97.92 237	98.57 220	98.96 270	96.79 247	97.90 218	99.18 248	96.41 326	98.46 270	98.95 215	95.93 260	99.60 343	96.51 278	98.98 350	99.31 242
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
IMVS_0404		98.07 225	98.20 200	97.69 313	99.03 255	94.03 352	96.67 336	99.45 136	98.16 194	98.03 307	98.71 264	96.80 211	99.82 200	97.50 193	99.45 276	99.22 267

PMMVS2		98.07 225	98.08 218	98.04 287	99.41 158	94.59 335	94.59 430	99.40 163	97.50 249	98.82 222	98.83 244	96.83 207	99.84 172	97.50 193	99.81 122	99.71 60

SymmetryMVS		98.05 227	97.71 252	99.09 128	99.29 186	97.83 174	98.28 154	97.64 379	99.24 74	98.80 225	98.85 237	89.76 367	99.94 41	98.04 150	99.50 269	99.49 157

ETV-MVS		98.03 228	97.86 242	98.56 225	98.69 327	98.07 148	97.51 277	99.50 111	98.10 200	97.50 345	95.51 425	98.41 78	99.88 113	96.27 293	99.24 311	97.71 424

Effi-MVS+		98.02 229	97.82 244	98.62 210	98.53 356	97.19 224	97.33 294	99.68 55	97.30 272	96.68 386	97.46 383	98.56 68	99.80 224	96.63 262	98.20 390	98.86 333

MSLP-MVS++		98.02 229	98.14 212	97.64 321	98.58 349	95.19 314	97.48 280	99.23 236	97.47 252	97.90 314	98.62 289	97.04 194	98.81 441	97.55 188	99.41 285	98.94 321

guyue		98.01 231	97.93 236	98.26 266	99.45 147	95.48 300	98.08 182	96.24 411	98.89 130	99.34 120	99.14 158	91.32 354	99.82 200	99.07 79	99.83 114	99.48 168

EIA-MVS		98.00 232	97.74 248	98.80 176	98.72 314	98.09 142	98.05 188	99.60 71	97.39 263	96.63 388	95.55 424	97.68 144	99.80 224	96.73 254	99.27 306	98.52 373

MCST-MVS		98.00 232	97.63 260	99.10 124	99.24 201	98.17 134	96.89 325	98.73 332	95.66 352	97.92 312	97.70 369	97.17 188	99.66 320	96.18 299	99.23 314	99.47 176

K. test v3		98.00 232	97.66 257	99.03 141	99.79 23	97.56 198	99.19 52	92.47 445	99.62 32	99.52 81	99.66 32	89.61 369	99.96 14	99.25 66	99.81 122	99.56 123

HQP_MVS		97.99 235	97.67 254	98.93 159	99.19 215	97.65 193	97.77 237	99.27 223	98.20 188	97.79 324	97.98 352	94.90 287	99.70 292	94.42 355	99.51 262	99.45 183

VortexMVS		97.98 236	98.31 186	97.02 360	98.88 288	91.45 408	98.03 192	99.47 128	98.65 143	99.55 73	99.47 77	91.49 352	99.81 216	99.32 59	99.91 76	99.80 40

MDA-MVSNet-bldmvs		97.94 237	97.91 238	98.06 284	99.44 149	94.96 322	96.63 339	99.15 260	98.35 169	98.83 219	99.11 164	94.31 306	99.85 154	96.60 265	98.72 365	99.37 217

ttmdpeth		97.91 238	98.02 224	97.58 327	98.69 327	94.10 348	98.13 172	98.90 298	97.95 208	97.32 358	99.58 47	95.95 259	98.75 443	96.41 284	99.22 315	99.87 21

Anonymous202405211		97.90 239	97.50 267	99.08 129	98.90 282	98.25 125	98.53 122	96.16 412	98.87 131	99.11 159	98.86 234	90.40 363	99.78 248	97.36 202	99.31 299	99.19 277

LF4IMVS		97.90 239	97.69 253	98.52 235	99.17 223	97.66 192	97.19 310	99.47 128	96.31 330	97.85 320	98.20 335	96.71 219	99.52 374	94.62 347	99.72 178	98.38 388

UnsupCasMVSNet_eth		97.89 241	97.60 262	98.75 189	99.31 179	97.17 227	97.62 260	99.35 181	98.72 141	98.76 232	98.68 275	92.57 339	99.74 273	97.76 176	95.60 445	99.34 230

TinyColmap		97.89 241	97.98 228	97.60 325	98.86 291	94.35 340	96.21 365	99.44 144	97.45 259	99.06 166	98.88 231	97.99 122	99.28 420	94.38 359	99.58 240	99.18 280

RRT-MVS		97.88 243	97.98 228	97.61 324	98.15 385	93.77 369	98.97 76	99.64 64	99.16 90	98.69 238	99.42 87	91.60 349	99.89 95	97.63 182	98.52 381	99.16 287

OMC-MVS		97.88 243	97.49 268	99.04 140	98.89 287	98.63 95	96.94 320	99.25 229	95.02 371	98.53 264	98.51 303	97.27 182	99.47 389	93.50 383	99.51 262	99.01 305

CANet		97.87 245	97.76 246	98.19 274	97.75 403	95.51 298	96.76 331	99.05 273	97.74 225	96.93 371	98.21 334	95.59 270	99.89 95	97.86 167	99.93 54	99.19 277

xiu_mvs_v1_base_debu		97.86 246	98.17 206	96.92 366	98.98 267	93.91 362	96.45 349	99.17 252	97.85 218	98.41 275	97.14 395	98.47 72	99.92 63	98.02 152	99.05 336	96.92 437

xiu_mvs_v1_base		97.86 246	98.17 206	96.92 366	98.98 267	93.91 362	96.45 349	99.17 252	97.85 218	98.41 275	97.14 395	98.47 72	99.92 63	98.02 152	99.05 336	96.92 437

xiu_mvs_v1_base_debi		97.86 246	98.17 206	96.92 366	98.98 267	93.91 362	96.45 349	99.17 252	97.85 218	98.41 275	97.14 395	98.47 72	99.92 63	98.02 152	99.05 336	96.92 437

NCCC		97.86 246	97.47 271	99.05 138	98.61 342	98.07 148	96.98 318	98.90 298	97.63 232	97.04 367	97.93 357	95.99 255	99.66 320	95.31 332	98.82 361	99.43 191

PMVS	91.26 20	97.86 246	97.94 234	97.65 318	99.71 47	97.94 164	98.52 123	98.68 335	98.99 116	97.52 343	99.35 100	97.41 172	98.18 451	91.59 414	99.67 208	96.82 440
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
IterMVS-SCA-FT		97.85 251	98.18 205	96.87 369	99.27 191	91.16 418	95.53 400	99.25 229	99.10 100	99.41 105	99.35 100	93.10 327	99.96 14	98.65 112	99.94 49	99.49 157

D2MVS		97.84 252	97.84 243	97.83 297	99.14 230	94.74 328	96.94 320	98.88 302	95.84 349	98.89 207	98.96 211	94.40 303	99.69 296	97.55 188	99.95 38	99.05 297

CPTT-MVS		97.84 252	97.36 276	99.27 95	99.31 179	98.46 111	98.29 153	99.27 223	94.90 375	97.83 321	98.37 320	94.90 287	99.84 172	93.85 374	99.54 253	99.51 149

mvs_anonymous		97.83 254	98.16 209	96.87 369	98.18 383	91.89 402	97.31 296	98.90 298	97.37 265	98.83 219	99.46 79	96.28 239	99.79 237	98.90 92	98.16 394	98.95 317

h-mvs33		97.77 255	97.33 279	99.10 124	99.21 208	97.84 173	98.35 150	98.57 342	99.11 93	98.58 256	99.02 185	88.65 378	99.96 14	98.11 143	96.34 437	99.49 157

test_vis1_rt		97.75 256	97.72 251	97.83 297	98.81 303	96.35 269	97.30 297	99.69 50	94.61 380	97.87 317	98.05 347	96.26 240	98.32 448	98.74 105	98.18 391	98.82 336

IterMVS		97.73 257	98.11 214	96.57 379	99.24 201	90.28 427	95.52 402	99.21 238	98.86 133	99.33 122	99.33 107	93.11 326	99.94 41	98.49 122	99.94 49	99.48 168
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test_fmvs1		97.72 258	97.94 234	97.07 359	98.66 337	92.39 395	97.68 249	99.81 31	95.20 369	99.54 75	99.44 84	91.56 351	99.41 400	99.78 20	99.77 150	99.40 206

MSDG		97.71 259	97.52 266	98.28 265	98.91 281	96.82 245	94.42 433	99.37 171	97.65 231	98.37 280	98.29 329	97.40 173	99.33 412	94.09 366	99.22 315	98.68 362

CDS-MVSNet		97.69 260	97.35 277	98.69 198	98.73 312	97.02 235	96.92 324	98.75 329	95.89 348	98.59 254	98.67 277	92.08 346	99.74 273	96.72 255	99.81 122	99.32 238
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MS-PatchMatch		97.68 261	97.75 247	97.45 341	98.23 381	93.78 368	97.29 298	98.84 313	96.10 338	98.64 245	98.65 282	96.04 248	99.36 406	96.84 244	99.14 328	99.20 272

Fast-Effi-MVS+		97.67 262	97.38 274	98.57 220	98.71 318	97.43 208	97.23 302	99.45 136	94.82 377	96.13 404	96.51 404	98.52 70	99.91 72	96.19 297	98.83 359	98.37 390

EU-MVSNet		97.66 263	98.50 153	95.13 415	99.63 80	85.84 446	98.35 150	98.21 358	98.23 182	99.54 75	99.46 79	95.02 285	99.68 305	98.24 133	99.87 95	99.87 21

pmmvs5		97.64 264	97.49 268	98.08 282	99.14 230	95.12 317	96.70 335	99.05 273	93.77 399	98.62 248	98.83 244	93.23 323	99.75 268	98.33 131	99.76 163	99.36 224

N_pmnet		97.63 265	97.17 286	98.99 147	99.27 191	97.86 171	95.98 377	93.41 442	95.25 366	99.47 93	98.90 224	95.63 268	99.85 154	96.91 233	99.73 170	99.27 250

mvsany_test1		97.60 266	97.54 264	97.77 302	97.72 404	95.35 307	95.36 408	97.13 392	94.13 393	99.71 48	99.33 107	97.93 125	99.30 416	97.60 186	98.94 354	98.67 363

YYNet1		97.60 266	97.67 254	97.39 345	99.04 252	93.04 384	95.27 409	98.38 353	97.25 277	98.92 202	98.95 215	95.48 275	99.73 279	96.99 227	98.74 363	99.41 197

MDA-MVSNet_test_wron		97.60 266	97.66 257	97.41 344	99.04 252	93.09 380	95.27 409	98.42 350	97.26 276	98.88 211	98.95 215	95.43 276	99.73 279	97.02 224	98.72 365	99.41 197

pmmvs4		97.58 269	97.28 280	98.51 236	98.84 295	96.93 241	95.40 407	98.52 345	93.60 401	98.61 250	98.65 282	95.10 283	99.60 343	96.97 230	99.79 139	98.99 310

mvsmamba		97.57 270	97.26 281	98.51 236	98.69 327	96.73 252	98.74 97	97.25 388	97.03 297	97.88 316	99.23 136	90.95 357	99.87 132	96.61 264	99.00 345	98.91 326

PVSNet_BlendedMVS		97.55 271	97.53 265	97.60 325	98.92 278	93.77 369	96.64 338	99.43 150	94.49 382	97.62 333	99.18 145	96.82 208	99.67 309	94.73 344	99.93 54	99.36 224

GDP-MVS		97.50 272	97.11 291	98.67 201	99.02 260	96.85 244	98.16 169	99.71 46	98.32 173	98.52 266	98.54 298	83.39 414	99.95 26	98.79 99	99.56 247	99.19 277

ppachtmachnet_test		97.50 272	97.74 248	96.78 375	98.70 322	91.23 417	94.55 431	99.05 273	96.36 327	99.21 150	98.79 252	96.39 233	99.78 248	96.74 252	99.82 118	99.34 230

FMVSNet3		97.50 272	97.24 283	98.29 264	98.08 390	95.83 288	97.86 224	98.91 297	97.89 215	98.95 192	98.95 215	87.06 384	99.81 216	97.77 172	99.69 197	99.23 262

CHOSEN 1792x2688		97.49 275	97.14 290	98.54 232	99.68 61	96.09 277	96.50 347	99.62 67	91.58 424	98.84 218	98.97 208	92.36 340	99.88 113	96.76 250	99.95 38	99.67 73

CLD-MVS		97.49 275	97.16 287	98.48 241	99.07 243	97.03 234	94.71 423	99.21 238	94.46 384	98.06 303	97.16 393	97.57 157	99.48 386	94.46 352	99.78 144	98.95 317
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
hse-mvs2		97.46 277	97.07 292	98.64 204	98.73 312	97.33 212	97.45 284	97.64 379	99.11 93	98.58 256	97.98 352	88.65 378	99.79 237	98.11 143	97.39 420	98.81 341

Vis-MVSNet (Re-imp)		97.46 277	97.16 287	98.34 259	99.55 104	96.10 274	98.94 80	98.44 348	98.32 173	98.16 293	98.62 289	88.76 374	99.73 279	93.88 372	99.79 139	99.18 280

jason		97.45 279	97.35 277	97.76 305	99.24 201	93.93 361	95.86 387	98.42 350	94.24 390	98.50 267	98.13 338	94.82 291	99.91 72	97.22 209	99.73 170	99.43 191
jason: jason.
CL-MVSNet_self_test		97.44 280	97.22 284	98.08 282	98.57 351	95.78 291	94.30 436	98.79 321	96.58 319	98.60 252	98.19 336	94.74 297	99.64 328	96.41 284	98.84 358	98.82 336

MVS_0304		97.44 280	97.01 296	98.72 195	96.42 449	96.74 251	97.20 307	91.97 449	98.46 164	98.30 281	98.79 252	92.74 336	99.91 72	99.30 61	99.94 49	99.52 146

DSMNet-mixed		97.42 282	97.60 262	96.87 369	99.15 229	91.46 407	98.54 121	99.12 262	92.87 412	97.58 337	99.63 39	96.21 241	99.90 79	95.74 319	99.54 253	99.27 250

USDC		97.41 283	97.40 272	97.44 342	98.94 272	93.67 372	95.17 412	99.53 103	94.03 396	98.97 187	99.10 167	95.29 278	99.34 410	95.84 316	99.73 170	99.30 245

BP-MVS1		97.40 284	96.97 297	98.71 196	99.07 243	96.81 246	98.34 152	97.18 389	98.58 155	98.17 290	98.61 291	84.01 410	99.94 41	98.97 88	99.78 144	99.37 217

our_test_3		97.39 285	97.73 250	96.34 385	98.70 322	89.78 430	94.61 429	98.97 288	96.50 321	99.04 175	98.85 237	95.98 256	99.84 172	97.26 207	99.67 208	99.41 197

c3_l		97.36 286	97.37 275	97.31 346	98.09 389	93.25 379	95.01 417	99.16 255	97.05 294	98.77 230	98.72 263	92.88 332	99.64 328	96.93 232	99.76 163	99.05 297

alignmvs		97.35 287	96.88 304	98.78 182	98.54 354	98.09 142	97.71 246	97.69 374	99.20 81	97.59 336	95.90 418	88.12 383	99.55 363	98.18 139	98.96 352	98.70 358

Patchmtry		97.35 287	96.97 297	98.50 240	97.31 430	96.47 265	98.18 165	98.92 295	98.95 123	98.78 227	99.37 95	85.44 399	99.85 154	95.96 308	99.83 114	99.17 284

DP-MVS Recon		97.33 289	96.92 301	98.57 220	99.09 239	97.99 155	96.79 328	99.35 181	93.18 406	97.71 328	98.07 346	95.00 286	99.31 414	93.97 368	99.13 330	98.42 385

QAPM		97.31 290	96.81 311	98.82 172	98.80 306	97.49 201	99.06 65	99.19 244	90.22 436	97.69 330	99.16 151	96.91 202	99.90 79	90.89 427	99.41 285	99.07 295

UnsupCasMVSNet_bld		97.30 291	96.92 301	98.45 244	99.28 188	96.78 250	96.20 366	99.27 223	95.42 361	98.28 285	98.30 328	93.16 325	99.71 287	94.99 337	97.37 421	98.87 332

F-COLMAP		97.30 291	96.68 318	99.14 118	99.19 215	98.39 114	97.27 301	99.30 208	92.93 410	96.62 389	98.00 350	95.73 266	99.68 305	92.62 401	98.46 382	99.35 228

1112_ss		97.29 293	96.86 305	98.58 217	99.34 176	96.32 270	96.75 332	99.58 77	93.14 407	96.89 378	97.48 381	92.11 345	99.86 141	96.91 233	99.54 253	99.57 117

CANet_DTU		97.26 294	97.06 293	97.84 296	97.57 414	94.65 333	96.19 367	98.79 321	97.23 283	95.14 425	98.24 331	93.22 324	99.84 172	97.34 203	99.84 107	99.04 301

Patchmatch-RL test		97.26 294	97.02 295	97.99 290	99.52 114	95.53 297	96.13 372	99.71 46	97.47 252	99.27 135	99.16 151	84.30 408	99.62 334	97.89 160	99.77 150	98.81 341

CDPH-MVS		97.26 294	96.66 321	99.07 131	99.00 263	98.15 135	96.03 376	99.01 284	91.21 430	97.79 324	97.85 361	96.89 203	99.69 296	92.75 398	99.38 290	99.39 207

PatchMatch-RL		97.24 297	96.78 312	98.61 213	99.03 255	97.83 174	96.36 356	99.06 270	93.49 404	97.36 357	97.78 363	95.75 265	99.49 383	93.44 384	98.77 362	98.52 373

eth_miper_zixun_eth		97.23 298	97.25 282	97.17 354	98.00 393	92.77 388	94.71 423	99.18 248	97.27 275	98.56 259	98.74 260	91.89 347	99.69 296	97.06 223	99.81 122	99.05 297

sss		97.21 299	96.93 299	98.06 284	98.83 297	95.22 313	96.75 332	98.48 347	94.49 382	97.27 359	97.90 358	92.77 335	99.80 224	96.57 268	99.32 297	99.16 287

LFMVS		97.20 300	96.72 315	98.64 204	98.72 314	96.95 239	98.93 81	94.14 439	99.74 13	98.78 227	99.01 196	84.45 405	99.73 279	97.44 198	99.27 306	99.25 257

HyFIR lowres test		97.19 301	96.60 325	98.96 154	99.62 84	97.28 215	95.17 412	99.50 111	94.21 391	99.01 179	98.32 327	86.61 387	99.99 2	97.10 219	99.84 107	99.60 97

miper_lstm_enhance		97.18 302	97.16 287	97.25 351	98.16 384	92.85 386	95.15 414	99.31 200	97.25 277	98.74 235	98.78 254	90.07 364	99.78 248	97.19 210	99.80 133	99.11 292

CNLPA		97.17 303	96.71 316	98.55 227	98.56 352	98.05 152	96.33 358	98.93 292	96.91 303	97.06 366	97.39 386	94.38 304	99.45 394	91.66 411	99.18 324	98.14 399

xiu_mvs_v2_base		97.16 304	97.49 268	96.17 394	98.54 354	92.46 393	95.45 404	98.84 313	97.25 277	97.48 347	96.49 405	98.31 88	99.90 79	96.34 289	98.68 372	96.15 448

AdaColmap		97.14 305	96.71 316	98.46 243	98.34 373	97.80 183	96.95 319	98.93 292	95.58 356	96.92 372	97.66 370	95.87 262	99.53 370	90.97 424	99.14 328	98.04 404

train_agg		97.10 306	96.45 331	99.07 131	98.71 318	98.08 146	95.96 380	99.03 278	91.64 422	95.85 410	97.53 377	96.47 230	99.76 260	93.67 377	99.16 325	99.36 224

OpenMVS	96.65 7	97.09 307	96.68 318	98.32 260	98.32 374	97.16 228	98.86 91	99.37 171	89.48 440	96.29 402	99.15 155	96.56 226	99.90 79	92.90 392	99.20 319	97.89 412

PS-MVSNAJ		97.08 308	97.39 273	96.16 396	98.56 352	92.46 393	95.24 411	98.85 312	97.25 277	97.49 346	95.99 415	98.07 113	99.90 79	96.37 286	98.67 373	96.12 449

miper_ehance_all_eth		97.06 309	97.03 294	97.16 356	97.83 400	93.06 381	94.66 426	99.09 267	95.99 344	98.69 238	98.45 312	92.73 337	99.61 341	96.79 246	99.03 340	98.82 336

lupinMVS		97.06 309	96.86 305	97.65 318	98.88 288	93.89 365	95.48 403	97.97 367	93.53 402	98.16 293	97.58 375	93.81 317	99.91 72	96.77 249	99.57 244	99.17 284

API-MVS		97.04 311	96.91 303	97.42 343	97.88 398	98.23 130	98.18 165	98.50 346	97.57 240	97.39 355	96.75 400	96.77 213	99.15 429	90.16 431	99.02 343	94.88 454

cl____		97.02 312	96.83 308	97.58 327	97.82 401	94.04 351	94.66 426	99.16 255	97.04 295	98.63 246	98.71 264	88.68 377	99.69 296	97.00 225	99.81 122	99.00 309

DIV-MVS_self_test		97.02 312	96.84 307	97.58 327	97.82 401	94.03 352	94.66 426	99.16 255	97.04 295	98.63 246	98.71 264	88.69 375	99.69 296	97.00 225	99.81 122	99.01 305

RPMNet		97.02 312	96.93 299	97.30 347	97.71 407	94.22 342	98.11 177	99.30 208	99.37 59	96.91 374	99.34 104	86.72 386	99.87 132	97.53 191	97.36 423	97.81 417

HQP-MVS		97.00 315	96.49 330	98.55 227	98.67 332	96.79 247	96.29 361	99.04 276	96.05 339	95.55 416	96.84 398	93.84 315	99.54 368	92.82 395	99.26 309	99.32 238

FA-MVS(test-final)		96.99 316	96.82 309	97.50 337	98.70 322	94.78 326	99.34 23	96.99 395	95.07 370	98.48 269	99.33 107	88.41 381	99.65 325	96.13 303	98.92 356	98.07 403

new_pmnet		96.99 316	96.76 313	97.67 314	98.72 314	94.89 323	95.95 382	98.20 359	92.62 415	98.55 261	98.54 298	94.88 290	99.52 374	93.96 369	99.44 283	98.59 370

Test_1112_low_res		96.99 316	96.55 327	98.31 262	99.35 173	95.47 303	95.84 390	99.53 103	91.51 426	96.80 383	98.48 310	91.36 353	99.83 190	96.58 266	99.53 257	99.62 87

PVSNet_Blended		96.88 319	96.68 318	97.47 340	98.92 278	93.77 369	94.71 423	99.43 150	90.98 432	97.62 333	97.36 389	96.82 208	99.67 309	94.73 344	99.56 247	98.98 311

MVSTER		96.86 320	96.55 327	97.79 300	97.91 397	94.21 344	97.56 270	98.87 304	97.49 251	99.06 166	99.05 180	80.72 423	99.80 224	98.44 124	99.82 118	99.37 217

BH-untuned		96.83 321	96.75 314	97.08 357	98.74 311	93.33 378	96.71 334	98.26 356	96.72 313	98.44 272	97.37 388	95.20 280	99.47 389	91.89 407	97.43 418	98.44 381

BH-RMVSNet		96.83 321	96.58 326	97.58 327	98.47 360	94.05 349	96.67 336	97.36 383	96.70 315	97.87 317	97.98 352	95.14 282	99.44 396	90.47 430	98.58 379	99.25 257

PAPM_NR		96.82 323	96.32 334	98.30 263	99.07 243	96.69 254	97.48 280	98.76 326	95.81 350	96.61 390	96.47 407	94.12 312	99.17 427	90.82 428	97.78 408	99.06 296

MG-MVS		96.77 324	96.61 323	97.26 350	98.31 375	93.06 381	95.93 383	98.12 364	96.45 325	97.92 312	98.73 261	93.77 319	99.39 403	91.19 422	99.04 339	99.33 235

test_yl		96.69 325	96.29 335	97.90 292	98.28 376	95.24 311	97.29 298	97.36 383	98.21 184	98.17 290	97.86 359	86.27 389	99.55 363	94.87 341	98.32 384	98.89 328

DCV-MVSNet		96.69 325	96.29 335	97.90 292	98.28 376	95.24 311	97.29 298	97.36 383	98.21 184	98.17 290	97.86 359	86.27 389	99.55 363	94.87 341	98.32 384	98.89 328

WTY-MVS		96.67 327	96.27 337	97.87 295	98.81 303	94.61 334	96.77 330	97.92 369	94.94 374	97.12 362	97.74 366	91.11 356	99.82 200	93.89 371	98.15 395	99.18 280

PatchT		96.65 328	96.35 332	97.54 333	97.40 427	95.32 309	97.98 207	96.64 405	99.33 64	96.89 378	99.42 87	84.32 407	99.81 216	97.69 181	97.49 414	97.48 430

TAPA-MVS	96.21 11	96.63 329	95.95 340	98.65 202	98.93 274	98.09 142	96.93 322	99.28 220	83.58 453	98.13 297	97.78 363	96.13 244	99.40 401	93.52 381	99.29 304	98.45 378
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MIMVSNet		96.62 330	96.25 338	97.71 312	99.04 252	94.66 332	99.16 54	96.92 400	97.23 283	97.87 317	99.10 167	86.11 393	99.65 325	91.65 412	99.21 318	98.82 336

Patchmatch-test		96.55 331	96.34 333	97.17 354	98.35 372	93.06 381	98.40 145	97.79 370	97.33 268	98.41 275	98.67 277	83.68 413	99.69 296	95.16 335	99.31 299	98.77 349

PMMVS		96.51 332	95.98 339	98.09 279	97.53 419	95.84 287	94.92 419	98.84 313	91.58 424	96.05 408	95.58 423	95.68 267	99.66 320	95.59 326	98.09 398	98.76 351

PLC	94.65 16	96.51 332	95.73 345	98.85 169	98.75 310	97.91 167	96.42 353	99.06 270	90.94 433	95.59 413	97.38 387	94.41 302	99.59 347	90.93 425	98.04 404	99.05 297
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
114514_t		96.50 334	95.77 343	98.69 198	99.48 138	97.43 208	97.84 227	99.55 95	81.42 456	96.51 396	98.58 295	95.53 271	99.67 309	93.41 385	99.58 240	98.98 311

test1111		96.49 335	96.82 309	95.52 408	99.42 155	87.08 443	99.22 45	87.14 459	99.11 93	99.46 94	99.58 47	88.69 375	99.86 141	98.80 98	99.95 38	99.62 87

MAR-MVS		96.47 336	95.70 346	98.79 179	97.92 396	99.12 62	98.28 154	98.60 341	92.16 420	95.54 419	96.17 412	94.77 296	99.52 374	89.62 433	98.23 388	97.72 423
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		96.42 337	96.61 323	95.85 400	99.38 161	88.18 438	99.22 45	86.00 461	99.08 107	99.36 116	99.57 49	88.47 380	99.82 200	98.52 121	99.95 38	99.54 134

SCA		96.41 338	96.66 321	95.67 404	98.24 379	88.35 436	95.85 389	96.88 401	96.11 337	97.67 331	98.67 277	93.10 327	99.85 154	94.16 361	99.22 315	98.81 341

DPM-MVS		96.32 339	95.59 352	98.51 236	98.76 308	97.21 222	94.54 432	98.26 356	91.94 421	96.37 400	97.25 391	93.06 329	99.43 397	91.42 417	98.74 363	98.89 328

CMPMVS	75.91 23	96.29 340	95.44 358	98.84 170	96.25 452	98.69 94	97.02 315	99.12 262	88.90 443	97.83 321	98.86 234	89.51 370	98.90 439	91.92 406	99.51 262	98.92 323
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
SD_0403		96.28 341	95.83 342	97.64 321	98.72 314	94.30 341	98.87 88	98.77 324	97.80 221	96.53 393	98.02 349	97.34 177	99.47 389	76.93 458	99.48 272	99.16 287

CR-MVSNet		96.28 341	95.95 340	97.28 348	97.71 407	94.22 342	98.11 177	98.92 295	92.31 418	96.91 374	99.37 95	85.44 399	99.81 216	97.39 201	97.36 423	97.81 417

MonoMVSNet		96.25 343	96.53 329	95.39 412	96.57 445	91.01 419	98.82 95	97.68 376	98.57 156	98.03 307	99.37 95	90.92 358	97.78 453	94.99 337	93.88 453	97.38 433

CVMVSNet		96.25 343	97.21 285	93.38 436	99.10 236	80.56 464	97.20 307	98.19 361	96.94 301	99.00 180	99.02 185	89.50 371	99.80 224	96.36 288	99.59 235	99.78 45

AUN-MVS		96.24 345	95.45 357	98.60 215	98.70 322	97.22 220	97.38 289	97.65 377	95.95 346	95.53 420	97.96 356	82.11 422	99.79 237	96.31 290	97.44 417	98.80 346

EPNet		96.14 346	95.44 358	98.25 267	90.76 465	95.50 299	97.92 215	94.65 431	98.97 119	92.98 447	98.85 237	89.12 373	99.87 132	95.99 306	99.68 202	99.39 207
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
wuyk23d		96.06 347	97.62 261	91.38 440	98.65 341	98.57 102	98.85 92	96.95 398	96.86 306	99.90 14	99.16 151	99.18 19	98.40 447	89.23 435	99.77 150	77.18 460

Syy-MVS		96.04 348	95.56 354	97.49 338	97.10 435	94.48 336	96.18 369	96.58 406	95.65 353	94.77 428	92.29 457	91.27 355	99.36 406	98.17 141	98.05 402	98.63 365

miper_enhance_ethall		96.01 349	95.74 344	96.81 373	96.41 450	92.27 399	93.69 445	98.89 301	91.14 431	98.30 281	97.35 390	90.58 361	99.58 354	96.31 290	99.03 340	98.60 367

FMVSNet5		96.01 349	95.20 368	98.41 249	97.53 419	96.10 274	98.74 97	99.50 111	97.22 286	98.03 307	99.04 182	69.80 446	99.88 113	97.27 206	99.71 187	99.25 257

dmvs_re		95.98 351	95.39 361	97.74 308	98.86 291	97.45 206	98.37 148	95.69 424	97.95 208	96.56 391	95.95 416	90.70 360	97.68 454	88.32 437	96.13 441	98.11 400

baseline1		95.96 352	95.44 358	97.52 335	98.51 358	93.99 359	98.39 146	96.09 415	98.21 184	98.40 279	97.76 365	86.88 385	99.63 331	95.42 330	89.27 458	98.95 317

HY-MVS	95.94 13	95.90 353	95.35 363	97.55 332	97.95 394	94.79 325	98.81 96	96.94 399	92.28 419	95.17 424	98.57 296	89.90 366	99.75 268	91.20 421	97.33 425	98.10 401

MVStest1		95.86 354	95.60 350	96.63 378	95.87 456	91.70 404	97.93 212	98.94 289	98.03 202	99.56 70	99.66 32	71.83 443	98.26 449	99.35 57	99.24 311	99.91 13

GA-MVS		95.86 354	95.32 364	97.49 338	98.60 344	94.15 347	93.83 443	97.93 368	95.49 359	96.68 386	97.42 385	83.21 415	99.30 416	96.22 295	98.55 380	99.01 305

OpenMVS_ROB	95.38 14	95.84 356	95.18 369	97.81 299	98.41 370	97.15 229	97.37 291	98.62 340	83.86 452	98.65 244	98.37 320	94.29 307	99.68 305	88.41 436	98.62 377	96.60 443

cl22		95.79 357	95.39 361	96.98 363	96.77 442	92.79 387	94.40 434	98.53 344	94.59 381	97.89 315	98.17 337	82.82 419	99.24 422	96.37 286	99.03 340	98.92 323

1314		95.74 358	95.60 350	96.17 394	97.53 419	92.75 389	98.07 185	98.31 355	91.22 429	94.25 435	96.68 401	95.53 271	99.03 431	91.64 413	97.18 427	96.74 441

WB-MVSnew		95.73 359	95.57 353	96.23 391	96.70 443	90.70 425	96.07 375	93.86 440	95.60 355	97.04 367	95.45 432	96.00 251	99.55 363	91.04 423	98.31 386	98.43 383

PVSNet	93.40 17	95.67 360	95.70 346	95.57 407	98.83 297	88.57 434	92.50 450	97.72 372	92.69 414	96.49 399	96.44 408	93.72 320	99.43 397	93.61 378	99.28 305	98.71 355

FE-MVS		95.66 361	94.95 374	97.77 302	98.53 356	95.28 310	99.40 19	96.09 415	93.11 408	97.96 311	99.26 124	79.10 432	99.77 254	92.40 404	98.71 367	98.27 394

tttt0517		95.64 362	94.98 372	97.64 321	99.36 168	93.81 367	98.72 102	90.47 453	98.08 201	98.67 241	98.34 324	73.88 441	99.92 63	97.77 172	99.51 262	99.20 272

PatchmatchNet		95.58 363	95.67 348	95.30 414	97.34 429	87.32 442	97.65 255	96.65 404	95.30 365	97.07 365	98.69 273	84.77 402	99.75 268	94.97 339	98.64 374	98.83 335
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
TR-MVS		95.55 364	95.12 370	96.86 372	97.54 417	93.94 360	96.49 348	96.53 408	94.36 389	97.03 369	96.61 403	94.26 308	99.16 428	86.91 443	96.31 438	97.47 431

JIA-IIPM		95.52 365	95.03 371	97.00 361	96.85 440	94.03 352	96.93 322	95.82 420	99.20 81	94.63 432	99.71 22	83.09 416	99.60 343	94.42 355	94.64 449	97.36 434

CHOSEN 280x420		95.51 366	95.47 355	95.65 406	98.25 378	88.27 437	93.25 447	98.88 302	93.53 402	94.65 431	97.15 394	86.17 391	99.93 52	97.41 200	99.93 54	98.73 354

ADS-MVSNet2		95.43 367	94.98 372	96.76 376	98.14 386	91.74 403	97.92 215	97.76 371	90.23 434	96.51 396	98.91 221	85.61 396	99.85 154	92.88 393	96.90 430	98.69 359

PAPR		95.29 368	94.47 379	97.75 306	97.50 425	95.14 316	94.89 420	98.71 334	91.39 428	95.35 423	95.48 428	94.57 299	99.14 430	84.95 446	97.37 421	98.97 314

thisisatest0530		95.27 369	94.45 380	97.74 308	99.19 215	94.37 339	97.86 224	90.20 454	97.17 288	98.22 288	97.65 371	73.53 442	99.90 79	96.90 238	99.35 293	98.95 317

ADS-MVSNet		95.24 370	94.93 375	96.18 393	98.14 386	90.10 429	97.92 215	97.32 386	90.23 434	96.51 396	98.91 221	85.61 396	99.74 273	92.88 393	96.90 430	98.69 359

WBMVS		95.18 371	94.78 377	96.37 384	97.68 412	89.74 431	95.80 391	98.73 332	97.54 246	98.30 281	98.44 313	70.06 445	99.82 200	96.62 263	99.87 95	99.54 134

BH-w/o		95.13 372	94.89 376	95.86 399	98.20 382	91.31 412	95.65 396	97.37 382	93.64 400	96.52 395	95.70 422	93.04 330	99.02 432	88.10 438	95.82 444	97.24 435

tpmrst		95.07 373	95.46 356	93.91 428	97.11 434	84.36 454	97.62 260	96.96 397	94.98 372	96.35 401	98.80 250	85.46 398	99.59 347	95.60 325	96.23 439	97.79 420

pmmvs3		95.03 374	94.40 381	96.93 365	97.70 409	92.53 392	95.08 415	97.71 373	88.57 444	97.71 328	98.08 345	79.39 430	99.82 200	96.19 297	99.11 334	98.43 383

tpmvs		95.02 375	95.25 365	94.33 422	96.39 451	85.87 445	98.08 182	96.83 402	95.46 360	95.51 421	98.69 273	85.91 394	99.53 370	94.16 361	96.23 439	97.58 428

reproduce_monomvs		95.00 376	95.25 365	94.22 424	97.51 424	83.34 456	97.86 224	98.44 348	98.51 161	99.29 132	99.30 113	67.68 451	99.56 359	98.89 94	99.81 122	99.77 48

EPNet_dtu		94.93 377	94.78 377	95.38 413	93.58 461	87.68 440	96.78 329	95.69 424	97.35 267	89.14 458	98.09 344	88.15 382	99.49 383	94.95 340	99.30 302	98.98 311
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
cascas		94.79 378	94.33 384	96.15 397	96.02 455	92.36 397	92.34 452	99.26 228	85.34 451	95.08 426	94.96 438	92.96 331	98.53 446	94.41 358	98.59 378	97.56 429

tpm		94.67 379	94.34 383	95.66 405	97.68 412	88.42 435	97.88 220	94.90 429	94.46 384	96.03 409	98.56 297	78.66 433	99.79 237	95.88 310	95.01 448	98.78 348

test0.0.03 1		94.51 380	93.69 390	96.99 362	96.05 453	93.61 376	94.97 418	93.49 441	96.17 334	97.57 339	94.88 439	82.30 420	99.01 434	93.60 379	94.17 452	98.37 390

thres600view7		94.45 381	93.83 388	96.29 387	99.06 248	91.53 406	97.99 206	94.24 437	98.34 170	97.44 351	95.01 435	79.84 426	99.67 309	84.33 447	98.23 388	97.66 425

PCF-MVS	92.86 18	94.36 382	93.00 400	98.42 248	98.70 322	97.56 198	93.16 448	99.11 264	79.59 457	97.55 340	97.43 384	92.19 343	99.73 279	79.85 455	99.45 276	97.97 409
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
X-MVStestdata		94.32 383	92.59 402	99.53 38	99.46 142	99.21 33	98.65 108	99.34 187	98.62 149	97.54 341	45.85 461	97.50 166	99.83 190	96.79 246	99.53 257	99.56 123

MVS-HIRNet		94.32 383	95.62 349	90.42 441	98.46 362	75.36 465	96.29 361	89.13 456	95.25 366	95.38 422	99.75 16	92.88 332	99.19 426	94.07 367	99.39 287	96.72 442

ET-MVSNet_ETH3D		94.30 385	93.21 396	97.58 327	98.14 386	94.47 337	94.78 422	93.24 444	94.72 378	89.56 456	95.87 419	78.57 435	99.81 216	96.91 233	97.11 429	98.46 375

thres100view900		94.19 386	93.67 391	95.75 403	99.06 248	91.35 411	98.03 192	94.24 437	98.33 171	97.40 353	94.98 437	79.84 426	99.62 334	83.05 449	98.08 399	96.29 444

E-PMN		94.17 387	94.37 382	93.58 432	96.86 439	85.71 448	90.11 456	97.07 393	98.17 191	97.82 323	97.19 392	84.62 404	98.94 436	89.77 432	97.68 411	96.09 450

thres400		94.14 388	93.44 393	96.24 390	98.93 274	91.44 409	97.60 265	94.29 435	97.94 210	97.10 363	94.31 444	79.67 428	99.62 334	83.05 449	98.08 399	97.66 425

thisisatest0515		94.12 389	93.16 397	96.97 364	98.60 344	92.90 385	93.77 444	90.61 452	94.10 394	96.91 374	95.87 419	74.99 440	99.80 224	94.52 350	99.12 333	98.20 396

tfpn200view9		94.03 390	93.44 393	95.78 402	98.93 274	91.44 409	97.60 265	94.29 435	97.94 210	97.10 363	94.31 444	79.67 428	99.62 334	83.05 449	98.08 399	96.29 444

CostFormer		93.97 391	93.78 389	94.51 421	97.53 419	85.83 447	97.98 207	95.96 417	89.29 442	94.99 427	98.63 287	78.63 434	99.62 334	94.54 349	96.50 435	98.09 402

test-LLR		93.90 392	93.85 387	94.04 426	96.53 446	84.62 452	94.05 440	92.39 446	96.17 334	94.12 437	95.07 433	82.30 420	99.67 309	95.87 313	98.18 391	97.82 415

EMVS		93.83 393	94.02 385	93.23 437	96.83 441	84.96 449	89.77 457	96.32 410	97.92 212	97.43 352	96.36 411	86.17 391	98.93 437	87.68 439	97.73 410	95.81 451

testing3-2		93.78 394	93.91 386	93.39 435	98.82 300	81.72 462	97.76 240	95.28 426	98.60 151	96.54 392	96.66 402	65.85 458	99.62 334	96.65 261	98.99 347	98.82 336

baseline2		93.73 395	92.83 401	96.42 383	97.70 409	91.28 414	96.84 327	89.77 455	93.96 398	92.44 450	95.93 417	79.14 431	99.77 254	92.94 391	96.76 434	98.21 395

thres200		93.72 396	93.14 398	95.46 411	98.66 337	91.29 413	96.61 340	94.63 432	97.39 263	96.83 381	93.71 447	79.88 425	99.56 359	82.40 452	98.13 396	95.54 453

EPMVS		93.72 396	93.27 395	95.09 417	96.04 454	87.76 439	98.13 172	85.01 462	94.69 379	96.92 372	98.64 285	78.47 437	99.31 414	95.04 336	96.46 436	98.20 396

testing3		93.51 398	92.09 409	97.75 306	98.60 344	94.40 338	97.32 295	95.26 427	97.56 242	96.79 384	95.50 426	53.57 466	99.77 254	95.26 333	98.97 351	99.08 293

dp		93.47 399	93.59 392	93.13 438	96.64 444	81.62 463	97.66 253	96.42 409	92.80 413	96.11 405	98.64 285	78.55 436	99.59 347	93.31 386	92.18 457	98.16 398

FPMVS		93.44 400	92.23 407	97.08 357	99.25 200	97.86 171	95.61 397	97.16 391	92.90 411	93.76 444	98.65 282	75.94 439	95.66 458	79.30 456	97.49 414	97.73 422

testing91		93.32 401	92.27 406	96.47 382	97.54 417	91.25 415	96.17 371	96.76 403	97.18 287	93.65 445	93.50 449	65.11 460	99.63 331	93.04 390	97.45 416	98.53 372

tpm cat1		93.29 402	93.13 399	93.75 430	97.39 428	84.74 450	97.39 288	97.65 377	83.39 454	94.16 436	98.41 315	82.86 418	99.39 403	91.56 415	95.35 447	97.14 436

UBG		93.25 403	92.32 404	96.04 398	97.72 404	90.16 428	95.92 385	95.91 419	96.03 342	93.95 442	93.04 453	69.60 447	99.52 374	90.72 429	97.98 405	98.45 378

MVS		93.19 404	92.09 409	96.50 381	96.91 438	94.03 352	98.07 185	98.06 366	68.01 459	94.56 433	96.48 406	95.96 258	99.30 416	83.84 448	96.89 432	96.17 446

tpm2		93.09 405	92.58 403	94.62 420	97.56 415	86.53 444	97.66 253	95.79 421	86.15 449	94.07 439	98.23 333	75.95 438	99.53 370	90.91 426	96.86 433	97.81 417

testing11		93.08 406	92.02 411	96.26 389	97.56 415	90.83 423	96.32 359	95.70 422	96.47 324	92.66 449	93.73 446	64.36 461	99.59 347	93.77 376	97.57 412	98.37 390

testing99		93.04 407	91.98 414	96.23 391	97.53 419	90.70 425	96.35 357	95.94 418	96.87 305	93.41 446	93.43 451	63.84 462	99.59 347	93.24 388	97.19 426	98.40 386

dmvs_testset		92.94 408	92.21 408	95.13 415	98.59 347	90.99 420	97.65 255	92.09 448	96.95 300	94.00 440	93.55 448	92.34 341	96.97 457	72.20 459	92.52 455	97.43 432

myMVS_eth3d28		92.92 409	92.31 405	94.77 418	97.84 399	87.59 441	96.19 367	96.11 414	97.08 293	94.27 434	93.49 450	66.07 457	98.78 442	91.78 409	97.93 407	97.92 411

KD-MVS_2432*1600		92.87 410	91.99 412	95.51 409	91.37 463	89.27 432	94.07 438	98.14 362	95.42 361	97.25 360	96.44 408	67.86 449	99.24 422	91.28 419	96.08 442	98.02 405

miper_refine_blended		92.87 410	91.99 412	95.51 409	91.37 463	89.27 432	94.07 438	98.14 362	95.42 361	97.25 360	96.44 408	67.86 449	99.24 422	91.28 419	96.08 442	98.02 405

ETVMVS		92.60 412	91.08 421	97.18 352	97.70 409	93.65 374	96.54 343	95.70 422	96.51 320	94.68 430	92.39 456	61.80 463	99.50 380	86.97 441	97.41 419	98.40 386

MVE	83.40 22	92.50 413	91.92 415	94.25 423	98.83 297	91.64 405	92.71 449	83.52 463	95.92 347	86.46 461	95.46 429	95.20 280	95.40 459	80.51 454	98.64 374	95.73 452
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test2506		92.39 414	91.89 416	93.89 429	99.38 161	82.28 460	99.32 26	66.03 467	99.08 107	98.77 230	99.57 49	66.26 455	99.84 172	98.71 108	99.95 38	99.54 134

UWE-MVS		92.38 415	91.76 418	94.21 425	97.16 433	84.65 451	95.42 406	88.45 457	95.96 345	96.17 403	95.84 421	66.36 454	99.71 287	91.87 408	98.64 374	98.28 393

gg-mvs-nofinetune		92.37 416	91.20 420	95.85 400	95.80 457	92.38 396	99.31 30	81.84 464	99.75 11	91.83 453	99.74 18	68.29 448	99.02 432	87.15 440	97.12 428	96.16 447

test-mter		92.33 417	91.76 418	94.04 426	96.53 446	84.62 452	94.05 440	92.39 446	94.00 397	94.12 437	95.07 433	65.63 459	99.67 309	95.87 313	98.18 391	97.82 415

IB-MVS	91.63 19	92.24 418	90.90 422	96.27 388	97.22 432	91.24 416	94.36 435	93.33 443	92.37 417	92.24 452	94.58 443	66.20 456	99.89 95	93.16 389	94.63 450	97.66 425
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		92.19 419	91.77 417	93.46 433	96.48 448	82.80 459	94.05 440	91.52 451	94.45 386	94.00 440	94.88 439	66.65 453	99.56 359	95.78 318	98.11 397	98.02 405

testing222		91.96 420	90.37 424	96.72 377	97.47 426	92.59 390	96.11 373	94.76 430	96.83 307	92.90 448	92.87 454	57.92 464	99.55 363	86.93 442	97.52 413	98.00 408

myMVS_eth3d		91.92 421	90.45 423	96.30 386	97.10 435	90.90 421	96.18 369	96.58 406	95.65 353	94.77 428	92.29 457	53.88 465	99.36 406	89.59 434	98.05 402	98.63 365

PAPM		91.88 422	90.34 425	96.51 380	98.06 391	92.56 391	92.44 451	97.17 390	86.35 448	90.38 455	96.01 414	86.61 387	99.21 425	70.65 461	95.43 446	97.75 421

PVSNet_0	89.98 21	91.15 423	90.30 426	93.70 431	97.72 404	84.34 455	90.24 454	97.42 381	90.20 437	93.79 443	93.09 452	90.90 359	98.89 440	86.57 444	72.76 461	97.87 414

UWE-MVS-28		90.22 424	89.28 427	93.02 439	94.50 460	82.87 458	96.52 346	87.51 458	95.21 368	92.36 451	96.04 413	71.57 444	98.25 450	72.04 460	97.77 409	97.94 410

EGC-MVSNET		85.24 425	80.54 428	99.34 79	99.77 27	99.20 39	99.08 61	99.29 216	12.08 463	20.84 464	99.42 87	97.55 159	99.85 154	97.08 220	99.72 178	98.96 316

test_method		79.78 426	79.50 429	80.62 442	80.21 467	45.76 470	70.82 458	98.41 352	31.08 462	80.89 462	97.71 367	84.85 401	97.37 455	91.51 416	80.03 459	98.75 352

tmp_tt		78.77 427	78.73 430	78.90 443	58.45 468	74.76 467	94.20 437	78.26 466	39.16 461	86.71 460	92.82 455	80.50 424	75.19 463	86.16 445	92.29 456	86.74 457

dongtai		76.24 428	75.95 431	77.12 444	92.39 462	67.91 468	90.16 455	59.44 469	82.04 455	89.42 457	94.67 442	49.68 467	81.74 462	48.06 462	77.66 460	81.72 458

kuosan		69.30 429	68.95 432	70.34 445	87.68 466	65.00 469	91.11 453	59.90 468	69.02 458	74.46 463	88.89 460	48.58 468	68.03 464	28.61 463	72.33 462	77.99 459

cdsmvs_eth3d_5k		24.66 430	32.88 433	0.00 448	0.00 471	0.00 473	0.00 459	99.10 265	0.00 466	0.00 467	97.58 375	99.21 18	0.00 467	0.00 466	0.00 465	0.00 463

testmvs		17.12 431	20.53 434	6.87 447	12.05 469	4.20 472	93.62 446	6.73 470	4.62 465	10.41 465	24.33 462	8.28 470	3.56 466	9.69 465	15.07 463	12.86 462

test123		17.04 432	20.11 435	7.82 446	10.25 470	4.91 471	94.80 421	4.47 471	4.93 464	10.00 466	24.28 463	9.69 469	3.64 465	10.14 464	12.43 464	14.92 461

pcd_1.5k_mvsjas		8.17 433	10.90 436	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	98.07 113	0.00 467	0.00 466	0.00 465	0.00 463

ab-mvs-re		8.12 434	10.83 437	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	97.48 381	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

mmdepth		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

monomultidepth		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

test_blank		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

uanet_test		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

DCPMVS		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

sosnet-low-res		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

sosnet		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

uncertanet		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

Regformer		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

uanet		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

WAC-MVS						90.90 421								91.37 418

FOURS1					99.73 37	99.67 3	99.43 15	99.54 100	99.43 53	99.26 139

MSC_two_6792asdad				99.32 87	98.43 366	98.37 117		98.86 309					99.89 95	97.14 215	99.60 231	99.71 60

PC_three_1452									93.27 405	99.40 108	98.54 298	98.22 99	97.00 456	95.17 334	99.45 276	99.49 157

No_MVS				99.32 87	98.43 366	98.37 117		98.86 309					99.89 95	97.14 215	99.60 231	99.71 60

test_one_0601					99.39 160	99.20 39		99.31 200	98.49 162	98.66 243	99.02 185	97.64 150

eth-test2					0.00 471

eth-test					0.00 471

ZD-MVS					99.01 262	98.84 82		99.07 269	94.10 394	98.05 305	98.12 340	96.36 237	99.86 141	92.70 400	99.19 322

RE-MVS-def			98.58 142		99.20 212	99.38 13	98.48 136	99.30 208	98.64 144	98.95 192	98.96 211	97.75 141		96.56 272	99.39 287	99.45 183

IU-MVS					99.49 130	99.15 52		98.87 304	92.97 409	99.41 105				96.76 250	99.62 224	99.66 75

OPU-MVS				98.82 172	98.59 347	98.30 122	98.10 179				98.52 302	98.18 103	98.75 443	94.62 347	99.48 272	99.41 197

test_241102_TWO								99.30 208	98.03 202	99.26 139	99.02 185	97.51 165	99.88 113	96.91 233	99.60 231	99.66 75

test_241102_ONE					99.49 130	99.17 44		99.31 200	97.98 205	99.66 59	98.90 224	98.36 81	99.48 386

9.14			97.78 245		99.07 243		97.53 274	99.32 195	95.53 358	98.54 263	98.70 271	97.58 156	99.76 260	94.32 360	99.46 274

save fliter					99.11 234	97.97 159	96.53 345	99.02 281	98.24 181

test_0728_THIRD									98.17 191	99.08 164	99.02 185	97.89 129	99.88 113	97.07 221	99.71 187	99.70 65

test_0728_SECOND				99.60 15	99.50 122	99.23 31	98.02 195	99.32 195					99.88 113	96.99 227	99.63 221	99.68 68

test0726					99.50 122	99.21 33	98.17 168	99.35 181	97.97 206	99.26 139	99.06 173	97.61 154

GSMVS																98.81 341

test_part2					99.36 168	99.10 65				99.05 173

sam_mvs1												84.74 403				98.81 341

sam_mvs												84.29 409

ambc				98.24 269	98.82 300	95.97 283	98.62 112	99.00 286		99.27 135	99.21 138	96.99 199	99.50 380	96.55 275	99.50 269	99.26 256

MTGPA								99.20 240

test_post1							97.59 267				20.48 465	83.07 417	99.66 320	94.16 361

test_post											21.25 464	83.86 412	99.70 292

patchmatchnet-post											98.77 256	84.37 406	99.85 154

GG-mvs-BLEND				94.76 419	94.54 459	92.13 401	99.31 30	80.47 465		88.73 459	91.01 459	67.59 452	98.16 452	82.30 453	94.53 451	93.98 455

MTMP							97.93 212	91.91 450

gm-plane-assit					94.83 458	81.97 461			88.07 446		94.99 436		99.60 343	91.76 410

test9_res														93.28 387	99.15 327	99.38 215

TEST9					98.71 318	98.08 146	95.96 380	99.03 278	91.40 427	95.85 410	97.53 377	96.52 228	99.76 260

test_8					98.67 332	98.01 154	95.91 386	99.02 281	91.64 422	95.79 412	97.50 380	96.47 230	99.76 260

agg_prior2														92.50 403	99.16 325	99.37 217

agg_prior					98.68 331	97.99 155		99.01 284		95.59 413			99.77 254

TestCases				99.16 114	99.50 122	98.55 103		99.58 77	96.80 308	98.88 211	99.06 173	97.65 147	99.57 356	94.45 353	99.61 229	99.37 217

test_prior4						97.97 159	95.86 387

test_prior2							95.74 394		96.48 323	96.11 405	97.63 373	95.92 261		94.16 361	99.20 319

test_prior				98.95 156	98.69 327	97.95 163		99.03 278					99.59 347			99.30 245

旧先验2							95.76 393		88.56 445	97.52 343			99.66 320	94.48 351

新几何2							95.93 383

新几何1				98.91 163	98.94 272	97.76 185		98.76 326	87.58 447	96.75 385	98.10 342	94.80 294	99.78 248	92.73 399	99.00 345	99.20 272

旧先验1					98.82 300	97.45 206		98.76 326			98.34 324	95.50 274			99.01 344	99.23 262

无先验							95.74 394	98.74 331	89.38 441				99.73 279	92.38 405		99.22 267

原ACMM2							95.53 400

原ACMM1				98.35 258	98.90 282	96.25 272		98.83 317	92.48 416	96.07 407	98.10 342	95.39 277	99.71 287	92.61 402	98.99 347	99.08 293

test222					98.92 278	96.93 241	95.54 399	98.78 323	85.72 450	96.86 380	98.11 341	94.43 301			99.10 335	99.23 262

testdata2													99.79 237	92.80 397

segment_acmp												97.02 197

testdata				98.09 279	98.93 274	95.40 306		98.80 320	90.08 438	97.45 350	98.37 320	95.26 279	99.70 292	93.58 380	98.95 353	99.17 284

testdata1							95.44 405		96.32 329

test12				98.93 159	98.58 349	97.83 174		98.66 336		96.53 393		95.51 273	99.69 296		99.13 330	99.27 250

plane_prior7					99.19 215	97.87 170

plane_prior6					98.99 266	97.70 191						94.90 287

plane_prior5								99.27 223					99.70 292	94.42 355	99.51 262	99.45 183

plane_prior4											97.98 352

plane_prior3						97.78 184			97.41 261	97.79 324

plane_prior2							97.77 237		98.20 188

plane_prior1					99.05 251

plane_prior						97.65 193	97.07 314		96.72 313						99.36 291

n2								0.00 472

nn								0.00 472

door-mid								99.57 84

lessismore_v0				98.97 153	99.73 37	97.53 200		86.71 460		99.37 113	99.52 66	89.93 365	99.92 63	98.99 87	99.72 178	99.44 187

LGP-MVS_train				99.47 60	99.57 92	98.97 73		99.48 120	96.60 317	99.10 162	99.06 173	98.71 50	99.83 190	95.58 327	99.78 144	99.62 87

test11								98.87 304

door								99.41 160

HQP5-MVS						96.79 247

HQP-NCC					98.67 332		96.29 361		96.05 339	95.55 416

ACMP_Plane					98.67 332		96.29 361		96.05 339	95.55 416

BP-MVS														92.82 395

HQP4-MVS										95.56 415			99.54 368			99.32 238

HQP3-MVS								99.04 276							99.26 309

HQP2-MVS												93.84 315

NP-MVS					98.84 295	97.39 210					96.84 398

MDTV_nov1_ep13_2view						74.92 466	97.69 248		90.06 439	97.75 327		85.78 395		93.52 381		98.69 359

MDTV_nov1_ep13			95.22 367		97.06 437	83.20 457	97.74 243	96.16 412	94.37 388	96.99 370	98.83 244	83.95 411	99.53 370	93.90 370	97.95 406

ACMMP++_ref															99.77 150

ACMMP++															99.68 202

Test By Simon												96.52 228

ITE_SJBPF				98.87 167	99.22 206	98.48 110		99.35 181	97.50 249	98.28 285	98.60 293	97.64 150	99.35 409	93.86 373	99.27 306	98.79 347

DeepMVS_CX				93.44 434	98.24 379	94.21 344		94.34 434	64.28 460	91.34 454	94.87 441	89.45 372	92.77 461	77.54 457	93.14 454	93.35 456

High-resolution multi-view benchmark