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 23	100.00 1	99.92 29	100.00 1	99.87 43

mvs_tets		99.90 2	99.90 4	99.90 8	99.96 7	99.79 55	99.72 33	99.88 65	99.92 45	99.98 14	99.93 22	99.94 4	99.98 27	99.77 54	100.00 1	99.92 24

test_fmvsmconf0.01_n		99.89 3	99.88 7	99.91 3	99.98 3	99.76 71	99.12 232	100.00 1	100.00 1	99.99 7	99.91 31	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 26	99.98 3	99.75 79	99.70 38	100.00 1	99.73 108	100.00 1	99.89 41	99.79 22	99.88 232	99.98 1	100.00 1	99.98 5

jajsoiax		99.89 3	99.89 6	99.89 11	99.96 7	99.78 58	99.70 38	99.86 74	99.89 55	99.98 14	99.90 36	99.94 4	99.98 27	99.75 55	100.00 1	99.90 28

mvs5depth		99.88 6	99.91 3	99.80 63	99.92 29	99.42 194	99.94 3	100.00 1	99.97 24	99.89 72	99.99 12	99.63 37	99.97 43	99.87 43	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 62	100.00 1	99.90 49	100.00 1	99.97 14	99.61 41	99.97 43	99.75 55	100.00 1	99.84 51

LTVRE_ROB	99.19 1	99.88 6	99.87 11	99.88 19	99.91 31	99.90 7	99.96 1	99.92 43	99.90 49	99.97 23	99.87 56	99.81 20	99.95 79	99.54 86	99.99 16	99.80 64
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 87	99.01 271	99.99 11	99.99 3	99.98 14	99.88 50	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 58	99.07 252	99.98 12	99.99 3	99.98 14	99.90 36	99.88 11	99.92 148	99.93 25	99.99 16	99.98 5

pmmvs6		99.86 10	99.86 13	99.83 41	99.94 18	99.90 7	99.83 7	99.91 52	99.85 71	99.94 47	99.95 16	99.73 27	99.90 196	99.65 70	99.97 71	99.69 112

fmvsm_l_conf0.5_n_3		99.85 12	99.83 21	99.92 2	99.88 45	99.86 19	99.08 248	99.97 20	99.98 17	99.96 33	99.79 112	99.90 9	99.99 8	99.96 9	99.99 16	99.90 28

fmvsm_s_conf0.1_n_a		99.85 12	99.83 21	99.91 3	99.95 15	99.82 43	99.10 240	99.98 12	99.99 3	99.98 14	99.91 31	99.68 33	99.93 117	99.93 25	99.99 16	99.99 2

test_fmvsmconf_n		99.85 12	99.84 20	99.88 19	99.91 31	99.73 90	98.97 287	99.98 12	99.99 3	99.96 33	99.85 68	99.93 7	99.99 8	99.94 20	99.99 16	99.93 20

mvsany_test3		99.85 12	99.88 7	99.75 95	99.95 15	99.37 210	99.53 91	99.98 12	99.77 106	99.99 7	99.95 16	99.85 14	99.94 96	99.95 14	99.98 49	99.94 17

UniMVSNet_ETH3D		99.85 12	99.83 21	99.90 8	99.89 39	99.91 4	99.89 5	99.71 170	99.93 42	99.95 44	99.89 41	99.71 28	99.96 68	99.51 91	99.97 71	99.84 51

test_fmvsmvis_n_1920		99.84 17	99.86 13	99.81 54	99.88 45	99.55 163	99.17 208	99.98 12	99.99 3	99.96 33	99.84 75	99.96 3	99.99 8	99.96 9	99.99 16	99.88 39

test_fmvsm_n_1920		99.84 17	99.85 17	99.83 41	99.82 87	99.70 108	99.17 208	99.97 20	99.99 3	99.96 33	99.82 89	99.94 4	100.00 1	99.95 14	100.00 1	99.80 64

PS-MVSNAJss		99.84 17	99.82 25	99.89 11	99.96 7	99.77 64	99.68 49	99.85 80	99.95 31	99.98 14	99.92 27	99.28 86	99.98 27	99.75 55	100.00 1	99.94 17

test_djsdf		99.84 17	99.81 28	99.91 3	99.94 18	99.84 27	99.77 19	99.80 112	99.73 108	99.97 23	99.92 27	99.77 25	99.98 27	99.43 103	100.00 1	99.90 28

fmvsm_l_conf0.5_n_9		99.83 21	99.81 28	99.89 11	99.86 57	99.80 52	98.94 296	99.96 28	99.98 17	99.96 33	99.78 124	99.88 11	99.98 27	99.96 9	99.99 16	99.90 28

fmvsm_s_conf0.5_n		99.83 21	99.81 28	99.87 26	99.85 66	99.78 58	99.03 262	99.96 28	99.99 3	99.97 23	99.84 75	99.78 23	99.92 148	99.92 29	99.99 16	99.92 24

test_fmvs3		99.83 21	99.93 2	99.53 214	99.96 7	98.62 324	99.67 53	100.00 1	99.95 31	100.00 1	99.95 16	99.85 14	99.99 8	99.98 1	99.99 16	99.98 5

fmvsm_s_conf0.5_n_9		99.82 24	99.82 25	99.82 46	99.83 78	99.59 150	98.97 287	99.92 43	99.99 3	99.97 23	99.84 75	99.90 9	99.94 96	99.94 20	99.99 16	99.92 24

tt0320-xc		99.82 24	99.82 25	99.82 46	99.82 87	99.84 27	99.82 10	99.92 43	99.94 35	99.94 47	99.93 22	99.34 78	99.92 148	99.70 60	99.96 85	99.70 104

fmvsm_s_conf0.5_n_a		99.82 24	99.79 34	99.89 11	99.85 66	99.82 43	99.03 262	99.96 28	99.99 3	99.97 23	99.84 75	99.58 45	99.93 117	99.92 29	99.98 49	99.93 20

v7n		99.82 24	99.80 32	99.88 19	99.96 7	99.84 27	99.82 10	99.82 97	99.84 75	99.94 47	99.91 31	99.13 109	99.96 68	99.83 45	99.99 16	99.83 55

sc_t1		99.81 28	99.80 32	99.82 46	99.88 45	99.88 12	99.83 7	99.79 121	99.94 35	99.93 52	99.92 27	99.35 77	99.92 148	99.64 73	99.94 120	99.68 118

fmvsm_s_conf0.1_n_2		99.81 28	99.78 39	99.89 11	99.93 24	99.76 71	98.92 299	99.98 12	99.99 3	99.99 7	99.88 50	99.43 61	99.94 96	99.94 20	99.99 16	99.99 2

fmvsm_s_conf0.5_n_6		99.80 30	99.78 39	99.85 32	99.78 129	99.78 58	99.00 275	99.97 20	99.96 27	99.97 23	99.56 290	99.92 8	99.93 117	99.91 32	99.99 16	99.83 55

fmvsm_l_conf0.5_n_a		99.80 30	99.79 34	99.84 38	99.88 45	99.64 130	99.12 232	99.91 52	99.98 17	99.95 44	99.67 209	99.67 34	99.99 8	99.94 20	99.99 16	99.88 39

fmvsm_l_conf0.5_n		99.80 30	99.78 39	99.85 32	99.88 45	99.66 119	99.11 237	99.91 52	99.98 17	99.96 33	99.64 224	99.60 43	99.99 8	99.95 14	99.99 16	99.88 39

anonymousdsp		99.80 30	99.77 45	99.90 8	99.96 7	99.88 12	99.73 30	99.85 80	99.70 123	99.92 59	99.93 22	99.45 58	99.97 43	99.36 116	100.00 1	99.85 48

tt0320		99.79 34	99.79 34	99.81 54	99.82 87	99.84 27	99.82 10	99.90 58	99.94 35	99.94 47	99.94 19	99.07 122	99.92 148	99.68 65	99.97 71	99.67 127

fmvsm_s_conf0.5_n_3		99.79 34	99.77 45	99.85 32	99.81 99	99.71 100	98.97 287	99.92 43	99.98 17	99.97 23	99.86 63	99.53 53	99.95 79	99.88 40	99.99 16	99.89 36

pm-mvs1		99.79 34	99.79 34	99.78 74	99.91 31	99.83 35	99.76 23	99.87 68	99.73 108	99.89 72	99.87 56	99.63 37	99.87 247	99.54 86	99.92 136	99.63 167

fmvsm_s_conf0.5_n_5		99.78 37	99.76 49	99.85 32	99.79 121	99.72 95	98.84 311	99.96 28	99.96 27	99.96 33	99.72 165	99.71 28	99.99 8	99.93 25	99.98 49	99.85 48

fmvsm_s_conf0.5_n_4		99.78 37	99.78 39	99.79 70	99.75 159	99.56 159	98.98 285	99.94 38	99.92 45	99.97 23	99.72 165	99.84 16	99.92 148	99.91 32	99.98 49	99.89 36

fmvsm_s_conf0.5_n_2		99.78 37	99.75 51	99.88 19	99.82 87	99.76 71	98.88 303	99.92 43	99.98 17	99.98 14	99.85 68	99.42 63	99.94 96	99.93 25	99.98 49	99.94 17

mmtdpeth		99.78 37	99.83 21	99.66 143	99.85 66	99.05 278	99.79 15	99.97 20	100.00 1	99.43 283	99.94 19	99.64 35	99.94 96	99.83 45	99.99 16	99.98 5

sd_testset		99.78 37	99.78 39	99.80 63	99.80 107	99.76 71	99.80 14	99.79 121	99.97 24	99.89 72	99.89 41	99.53 53	99.99 8	99.36 116	99.96 85	99.65 149

UA-Net		99.78 37	99.76 49	99.86 30	99.72 176	99.71 100	99.91 4	99.95 36	99.96 27	99.71 175	99.91 31	99.15 104	99.97 43	99.50 93	100.00 1	99.90 28

TransMVSNet (Re)		99.78 37	99.77 45	99.81 54	99.91 31	99.85 22	99.75 25	99.86 74	99.70 123	99.91 62	99.89 41	99.60 43	99.87 247	99.59 78	99.74 268	99.71 101

fmvsm_s_conf0.5_n_10		99.77 44	99.73 54	99.88 19	99.81 99	99.75 79	99.06 253	99.85 80	99.99 3	99.97 23	99.84 75	99.12 111	99.98 27	99.95 14	99.99 16	99.90 28

SDMVSNet		99.77 44	99.77 45	99.76 84	99.80 107	99.65 125	99.63 64	99.86 74	99.97 24	99.89 72	99.89 41	99.52 55	99.99 8	99.42 108	99.96 85	99.65 149

fmvsm_s_conf0.5_n_8		99.76 46	99.72 55	99.88 19	99.82 87	99.75 79	99.02 266	99.87 68	99.98 17	99.98 14	99.81 96	99.07 122	99.97 43	99.91 32	99.99 16	99.92 24

test_cas_vis1_n_1920		99.76 46	99.86 13	99.45 240	99.93 24	98.40 343	99.30 157	99.98 12	99.94 35	99.99 7	99.89 41	99.80 21	99.97 43	99.96 9	99.97 71	99.97 10

test_f		99.75 48	99.88 7	99.37 270	99.96 7	98.21 355	99.51 99	100.00 1	99.94 35	100.00 1	99.93 22	99.58 45	99.94 96	99.97 4	99.99 16	99.97 10

OurMVSNet-221017-0		99.75 48	99.71 56	99.84 38	99.96 7	99.83 35	99.83 7	99.85 80	99.80 95	99.93 52	99.93 22	98.54 208	99.93 117	99.59 78	99.98 49	99.76 83

Vis-MVSNet		99.75 48	99.74 52	99.79 70	99.88 45	99.66 119	99.69 45	99.92 43	99.67 132	99.77 142	99.75 147	99.61 41	99.98 27	99.35 119	99.98 49	99.72 96
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
fmvsm_s_conf0.5_n_7		99.73 51	99.78 39	99.60 180	99.74 167	98.93 292	98.85 309	99.96 28	99.96 27	99.97 23	99.76 139	99.82 18	99.96 68	99.95 14	99.98 49	99.90 28

mamv4		99.73 51	99.74 52	99.70 128	99.66 217	99.87 15	99.69 45	99.93 39	99.93 42	99.93 52	99.86 63	99.07 122	100.00 1	99.66 68	99.92 136	99.24 332

test_vis1_n_1920		99.72 53	99.88 7	99.27 303	99.93 24	97.84 382	99.34 140	100.00 1	99.99 3	99.99 7	99.82 89	99.87 13	99.99 8	99.97 4	99.99 16	99.97 10

test_fmvs2		99.72 53	99.85 17	99.34 278	99.91 31	98.08 369	99.48 107	100.00 1	99.90 49	99.99 7	99.91 31	99.50 57	99.98 27	99.98 1	99.99 16	99.96 13

TDRefinement		99.72 53	99.70 57	99.77 77	99.90 37	99.85 22	99.86 6	99.92 43	99.69 126	99.78 130	99.92 27	99.37 71	99.88 232	98.93 187	99.95 105	99.60 193

XXY-MVS		99.71 56	99.67 64	99.81 54	99.89 39	99.72 95	99.59 80	99.82 97	99.39 204	99.82 107	99.84 75	99.38 69	99.91 177	99.38 112	99.93 132	99.80 64

nrg030		99.70 57	99.66 66	99.82 46	99.76 144	99.84 27	99.61 73	99.70 179	99.93 42	99.78 130	99.68 205	99.10 113	99.78 359	99.45 101	99.96 85	99.83 55

FC-MVSNet-test		99.70 57	99.65 68	99.86 30	99.88 45	99.86 19	99.72 33	99.78 130	99.90 49	99.82 107	99.83 82	98.45 224	99.87 247	99.51 91	99.97 71	99.86 45

Elysia		99.69 59	99.65 68	99.81 54	99.86 57	99.72 95	99.34 140	99.77 135	99.94 35	99.91 62	99.76 139	98.55 204	99.99 8	99.70 60	99.98 49	99.72 96

StellarMVS		99.69 59	99.65 68	99.81 54	99.86 57	99.72 95	99.34 140	99.77 135	99.94 35	99.91 62	99.76 139	98.55 204	99.99 8	99.70 60	99.98 49	99.72 96

GeoE		99.69 59	99.66 66	99.78 74	99.76 144	99.76 71	99.60 79	99.82 97	99.46 183	99.75 151	99.56 290	99.63 37	99.95 79	99.43 103	99.88 172	99.62 178

v10		99.69 59	99.69 60	99.66 143	99.81 99	99.39 205	99.66 57	99.75 148	99.60 157	99.92 59	99.87 56	98.75 175	99.86 266	99.90 36	99.99 16	99.73 92

EC-MVSNet		99.69 59	99.69 60	99.68 132	99.71 180	99.91 4	99.76 23	99.96 28	99.86 65	99.51 265	99.39 341	99.57 47	99.93 117	99.64 73	99.86 193	99.20 345

test_vis1_n		99.68 64	99.79 34	99.36 275	99.94 18	98.18 358	99.52 92	100.00 1	99.86 65	100.00 1	99.88 50	98.99 138	99.96 68	99.97 4	99.96 85	99.95 14

test_fmvs1_n		99.68 64	99.81 28	99.28 298	99.95 15	97.93 378	99.49 105	100.00 1	99.82 85	99.99 7	99.89 41	99.21 95	99.98 27	99.97 4	99.98 49	99.93 20

SPE-MVS-test		99.68 64	99.70 57	99.64 156	99.57 253	99.83 35	99.78 17	99.97 20	99.92 45	99.50 268	99.38 343	99.57 47	99.95 79	99.69 63	99.90 149	99.15 357

v8		99.68 64	99.69 60	99.65 149	99.80 107	99.40 202	99.66 57	99.76 143	99.64 142	99.93 52	99.85 68	98.66 189	99.84 300	99.88 40	99.99 16	99.71 101

DTE-MVSNet		99.68 64	99.61 82	99.88 19	99.80 107	99.87 15	99.67 53	99.71 170	99.72 112	99.84 100	99.78 124	98.67 187	99.97 43	99.30 128	99.95 105	99.80 64

casdiffmvs_mvg		99.68 64	99.68 63	99.69 130	99.81 99	99.59 150	99.29 164	99.90 58	99.71 117	99.79 126	99.73 157	99.54 50	99.84 300	99.36 116	99.96 85	99.65 149
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 70	99.70 57	99.58 186	99.53 276	99.84 27	99.79 15	99.96 28	99.90 49	99.61 225	99.41 333	99.51 56	99.95 79	99.66 68	99.89 163	98.96 399

KinetiMVS		99.66 71	99.63 76	99.76 84	99.89 39	99.57 158	99.37 132	99.82 97	99.95 31	99.90 67	99.63 239	98.57 200	99.97 43	99.65 70	99.94 120	99.74 88

VPA-MVSNet		99.66 71	99.62 78	99.79 70	99.68 209	99.75 79	99.62 67	99.69 187	99.85 71	99.80 120	99.81 96	98.81 163	99.91 177	99.47 98	99.88 172	99.70 104

PS-CasMVS		99.66 71	99.58 91	99.89 11	99.80 107	99.85 22	99.66 57	99.73 158	99.62 147	99.84 100	99.71 175	98.62 193	99.96 68	99.30 128	99.96 85	99.86 45

PEN-MVS		99.66 71	99.59 88	99.89 11	99.83 78	99.87 15	99.66 57	99.73 158	99.70 123	99.84 100	99.73 157	98.56 203	99.96 68	99.29 131	99.94 120	99.83 55

FMVSNet1		99.66 71	99.63 76	99.73 110	99.78 129	99.77 64	99.68 49	99.70 179	99.67 132	99.82 107	99.83 82	98.98 142	99.90 196	99.24 135	99.97 71	99.53 234

MIMVSNet1		99.66 71	99.62 78	99.80 63	99.94 18	99.87 15	99.69 45	99.77 135	99.78 102	99.93 52	99.89 41	97.94 276	99.92 148	99.65 70	99.98 49	99.62 178

FIs		99.65 77	99.58 91	99.84 38	99.84 71	99.85 22	99.66 57	99.75 148	99.86 65	99.74 161	99.79 112	98.27 246	99.85 285	99.37 115	99.93 132	99.83 55

SSC-MVS3.2		99.64 78	99.67 64	99.56 198	99.75 159	98.98 282	98.96 291	99.87 68	99.88 60	99.84 100	99.64 224	99.32 81	99.91 177	99.78 53	99.96 85	99.80 64

viewmacassd2359aftdt		99.63 79	99.61 82	99.68 132	99.84 71	99.61 144	99.14 220	99.87 68	99.71 117	99.75 151	99.77 134	99.54 50	99.72 385	98.91 188	99.96 85	99.70 104

testf1		99.63 79	99.60 86	99.72 118	99.94 18	99.95 2	99.47 110	99.89 61	99.43 195	99.88 82	99.80 102	99.26 90	99.90 196	98.81 197	99.88 172	99.32 317

APD_test2		99.63 79	99.60 86	99.72 118	99.94 18	99.95 2	99.47 110	99.89 61	99.43 195	99.88 82	99.80 102	99.26 90	99.90 196	98.81 197	99.88 172	99.32 317

tt0805		99.63 79	99.57 96	99.81 54	99.87 54	99.88 12	99.58 82	98.70 406	99.72 112	99.91 62	99.60 266	99.43 61	99.81 345	99.81 50	99.53 346	99.73 92

KD-MVS_self_test		99.63 79	99.59 88	99.76 84	99.84 71	99.90 7	99.37 132	99.79 121	99.83 81	99.88 82	99.85 68	98.42 228	99.90 196	99.60 77	99.73 274	99.49 257

casdiffmvs		99.63 79	99.61 82	99.67 136	99.79 121	99.59 150	99.13 227	99.85 80	99.79 99	99.76 146	99.72 165	99.33 80	99.82 329	99.21 141	99.94 120	99.59 200
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		99.63 79	99.62 78	99.66 143	99.80 107	99.62 138	99.44 116	99.80 112	99.71 117	99.72 170	99.69 194	99.15 104	99.83 316	99.32 125	99.94 120	99.53 234

viewdifsd2359ckpt11		99.62 86	99.64 73	99.56 198	99.86 57	99.19 253	99.02 266	99.93 39	99.83 81	99.88 82	99.81 96	98.99 138	99.83 316	99.48 95	99.96 85	99.65 149

viewmsd2359difaftdt		99.62 86	99.64 73	99.56 198	99.86 57	99.19 253	99.02 266	99.93 39	99.83 81	99.88 82	99.81 96	98.99 138	99.83 316	99.48 95	99.96 85	99.65 149

Anonymous20231211		99.62 86	99.57 96	99.76 84	99.61 230	99.60 148	99.81 13	99.73 158	99.82 85	99.90 67	99.90 36	97.97 275	99.86 266	99.42 108	99.96 85	99.80 64

DeepC-MVS	98.90 4	99.62 86	99.61 82	99.67 136	99.72 176	99.44 187	99.24 182	99.71 170	99.27 221	99.93 52	99.90 36	99.70 31	99.93 117	98.99 173	99.99 16	99.64 161
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TestfortrainingZip a		99.61 90	99.53 110	99.85 32	99.76 144	99.84 27	99.38 125	99.78 130	99.58 161	99.81 114	99.66 214	99.02 134	99.90 196	98.96 179	99.79 243	99.81 63

dcpmvs_2		99.61 90	99.64 73	99.53 214	99.79 121	98.82 301	99.58 82	99.97 20	99.95 31	99.96 33	99.76 139	98.44 225	99.99 8	99.34 120	99.96 85	99.78 74

WR-MVS_H		99.61 90	99.53 110	99.87 26	99.80 107	99.83 35	99.67 53	99.75 148	99.58 161	99.85 97	99.69 194	98.18 259	99.94 96	99.28 133	99.95 105	99.83 55

ACMH	98.42 6	99.59 93	99.54 106	99.72 118	99.86 57	99.62 138	99.56 87	99.79 121	98.77 300	99.80 120	99.85 68	99.64 35	99.85 285	98.70 216	99.89 163	99.70 104
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SSM_0404		99.57 94	99.58 91	99.54 210	99.76 144	99.28 228	99.19 199	99.84 87	99.80 95	99.78 130	99.70 185	99.44 59	99.93 117	98.74 206	99.95 105	99.41 293

v1192		99.57 94	99.57 96	99.57 194	99.77 140	99.22 246	99.04 259	99.60 241	99.18 237	99.87 92	99.72 165	99.08 119	99.85 285	99.89 39	99.98 49	99.66 140

EG-PatchMatch MVS		99.57 94	99.56 101	99.62 172	99.77 140	99.33 220	99.26 175	99.76 143	99.32 214	99.80 120	99.78 124	99.29 84	99.87 247	99.15 154	99.91 147	99.66 140

Gipuma		99.57 94	99.59 88	99.49 226	99.98 3	99.71 100	99.72 33	99.84 87	99.81 91	99.94 47	99.78 124	98.91 154	99.71 390	98.41 239	99.95 105	99.05 386
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
SSM_0407		99.56 98	99.56 101	99.54 210	99.71 180	99.24 240	99.15 217	99.84 87	99.80 95	99.78 130	99.70 185	99.44 59	99.93 117	98.74 206	99.90 149	99.45 270

lecture		99.56 98	99.48 118	99.81 54	99.78 129	99.86 19	99.50 100	99.70 179	99.59 159	99.75 151	99.71 175	98.94 147	99.92 148	98.59 225	99.76 257	99.66 140

v1921920		99.56 98	99.57 96	99.55 204	99.75 159	99.11 265	99.05 254	99.61 230	99.15 248	99.88 82	99.71 175	99.08 119	99.87 247	99.90 36	99.97 71	99.66 140

v1240		99.56 98	99.58 91	99.51 220	99.80 107	99.00 279	99.00 275	99.65 210	99.15 248	99.90 67	99.75 147	99.09 115	99.88 232	99.90 36	99.96 85	99.67 127

V42		99.56 98	99.54 106	99.63 163	99.79 121	99.46 179	99.39 122	99.59 247	99.24 227	99.86 94	99.70 185	98.55 204	99.82 329	99.79 52	99.95 105	99.60 193

SSM_04072		99.55 103	99.55 103	99.55 204	99.71 180	99.24 240	99.27 170	99.79 121	99.72 112	99.78 130	99.64 224	99.36 74	99.97 43	98.74 206	99.90 149	99.45 270

MVSMamba_PlusPlus		99.55 103	99.58 91	99.47 233	99.68 209	99.40 202	99.52 92	99.70 179	99.92 45	99.77 142	99.86 63	98.28 244	99.96 68	99.54 86	99.90 149	99.05 386

v144192		99.55 103	99.54 106	99.58 186	99.78 129	99.20 252	99.11 237	99.62 223	99.18 237	99.89 72	99.72 165	98.66 189	99.87 247	99.88 40	99.97 71	99.66 140

test20.03		99.55 103	99.54 106	99.58 186	99.79 121	99.37 210	99.02 266	99.89 61	99.60 157	99.82 107	99.62 248	98.81 163	99.89 217	99.43 103	99.86 193	99.47 265

mamba_0408		99.54 107	99.55 103	99.54 210	99.71 180	99.24 240	99.27 170	99.79 121	99.72 112	99.78 130	99.64 224	99.36 74	99.93 117	98.74 206	99.90 149	99.45 270

v1144		99.54 107	99.53 110	99.59 183	99.79 121	99.28 228	99.10 240	99.61 230	99.20 234	99.84 100	99.73 157	98.67 187	99.84 300	99.86 44	99.98 49	99.64 161

CP-MVSNet		99.54 107	99.43 133	99.87 26	99.76 144	99.82 43	99.57 85	99.61 230	99.54 164	99.80 120	99.64 224	97.79 287	99.95 79	99.21 141	99.94 120	99.84 51

TranMVSNet+NR-MVSNet		99.54 107	99.47 120	99.76 84	99.58 243	99.64 130	99.30 157	99.63 220	99.61 151	99.71 175	99.56 290	98.76 173	99.96 68	99.14 160	99.92 136	99.68 118

SSC-MVS		99.52 111	99.42 135	99.83 41	99.86 57	99.65 125	99.52 92	99.81 108	99.87 62	99.81 114	99.79 112	96.78 331	99.99 8	99.83 45	99.51 350	99.86 45

viewdifsd2359ckpt07		99.51 112	99.50 113	99.52 216	99.80 107	99.19 253	98.92 299	99.88 65	99.72 112	99.64 204	99.62 248	99.06 129	99.81 345	98.96 179	99.94 120	99.56 214

patch_mono-2		99.51 112	99.46 125	99.64 156	99.70 195	99.11 265	99.04 259	99.87 68	99.71 117	99.47 273	99.79 112	98.24 248	99.98 27	99.38 112	99.96 85	99.83 55

viewmanbaseed2359cas		99.50 114	99.47 120	99.61 176	99.73 171	99.52 168	99.03 262	99.83 91	99.49 172	99.65 201	99.64 224	99.18 98	99.71 390	98.73 211	99.92 136	99.58 205

reproduce_model		99.50 114	99.40 139	99.83 41	99.60 232	99.83 35	99.12 232	99.68 190	99.49 172	99.80 120	99.79 112	99.01 135	99.93 117	98.24 252	99.82 221	99.73 92

balanced_conf03		99.50 114	99.50 113	99.50 222	99.42 324	99.49 171	99.52 92	99.75 148	99.86 65	99.78 130	99.71 175	98.20 256	99.90 196	99.39 111	99.88 172	99.10 368

v2v482		99.50 114	99.47 120	99.58 186	99.78 129	99.25 236	99.14 220	99.58 256	99.25 225	99.81 114	99.62 248	98.24 248	99.84 300	99.83 45	99.97 71	99.64 161

ACMH+	98.40 8	99.50 114	99.43 133	99.71 123	99.86 57	99.76 71	99.32 149	99.77 135	99.53 166	99.77 142	99.76 139	99.26 90	99.78 359	97.77 296	99.88 172	99.60 193

Baseline_NR-MVSNet		99.49 119	99.37 146	99.82 46	99.91 31	99.84 27	98.83 314	99.86 74	99.68 128	99.65 201	99.88 50	97.67 295	99.87 247	99.03 170	99.86 193	99.76 83

TAMVS		99.49 119	99.45 127	99.63 163	99.48 301	99.42 194	99.45 114	99.57 258	99.66 136	99.78 130	99.83 82	97.85 283	99.86 266	99.44 102	99.96 85	99.61 189

viewcassd2359sk11		99.48 121	99.45 127	99.58 186	99.73 171	99.42 194	98.96 291	99.80 112	99.44 188	99.63 209	99.74 152	99.09 115	99.76 371	98.72 213	99.91 147	99.57 211

diffmvs_AUTHOR		99.48 121	99.48 118	99.47 233	99.80 107	98.89 297	98.71 335	99.82 97	99.79 99	99.66 198	99.63 239	98.87 159	99.88 232	99.13 162	99.95 105	99.62 178

ttmdpeth		99.48 121	99.55 103	99.29 295	99.76 144	98.16 360	99.33 146	99.95 36	99.79 99	99.36 303	99.89 41	99.13 109	99.77 368	99.09 165	99.64 311	99.93 20

test_fmvs1		99.48 121	99.65 68	98.97 345	99.54 269	97.16 405	99.11 237	99.98 12	99.78 102	99.96 33	99.81 96	98.72 180	99.97 43	99.95 14	99.97 71	99.79 72

pmmvs-eth3d		99.48 121	99.47 120	99.51 220	99.77 140	99.41 201	98.81 319	99.66 200	99.42 199	99.75 151	99.66 214	99.20 96	99.76 371	98.98 175	99.99 16	99.36 307

EI-MVSNet-UG-set		99.48 121	99.50 113	99.42 250	99.57 253	98.65 320	99.24 182	99.46 310	99.68 128	99.80 120	99.66 214	98.99 138	99.89 217	99.19 146	99.90 149	99.72 96

APDe-MVS		99.48 121	99.36 150	99.85 32	99.55 267	99.81 48	99.50 100	99.69 187	98.99 264	99.75 151	99.71 175	98.79 168	99.93 117	98.46 233	99.85 198	99.80 64
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
PMMVS2		99.48 121	99.45 127	99.57 194	99.76 144	98.99 281	98.09 401	99.90 58	98.95 271	99.78 130	99.58 279	99.57 47	99.93 117	99.48 95	99.95 105	99.79 72

DSMNet-mixed		99.48 121	99.65 68	98.95 348	99.71 180	97.27 402	99.50 100	99.82 97	99.59 159	99.41 292	99.85 68	99.62 40	100.00 1	99.53 89	99.89 163	99.59 200

DP-MVS		99.48 121	99.39 140	99.74 100	99.57 253	99.62 138	99.29 164	99.61 230	99.87 62	99.74 161	99.76 139	98.69 183	99.87 247	98.20 256	99.80 238	99.75 86

viewmambaseed2359dif		99.47 131	99.50 113	99.37 270	99.70 195	98.80 305	98.67 337	99.92 43	99.49 172	99.77 142	99.71 175	99.08 119	99.78 359	99.20 144	99.94 120	99.54 228

EI-MVSNet-Vis-set		99.47 131	99.49 117	99.42 250	99.57 253	98.66 317	99.24 182	99.46 310	99.67 132	99.79 126	99.65 222	98.97 144	99.89 217	99.15 154	99.89 163	99.71 101

reproduce-ours		99.46 133	99.35 153	99.82 46	99.56 264	99.83 35	99.05 254	99.65 210	99.45 186	99.78 130	99.78 124	98.93 148	99.93 117	98.11 266	99.81 231	99.70 104

our_new_method		99.46 133	99.35 153	99.82 46	99.56 264	99.83 35	99.05 254	99.65 210	99.45 186	99.78 130	99.78 124	98.93 148	99.93 117	98.11 266	99.81 231	99.70 104

VPNet		99.46 133	99.37 146	99.71 123	99.82 87	99.59 150	99.48 107	99.70 179	99.81 91	99.69 182	99.58 279	97.66 299	99.86 266	99.17 151	99.44 360	99.67 127

ACMM	98.09 11	99.46 133	99.38 143	99.72 118	99.80 107	99.69 112	99.13 227	99.65 210	98.99 264	99.64 204	99.72 165	99.39 65	99.86 266	98.23 253	99.81 231	99.60 193
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FE-MVSNET		99.45 137	99.36 150	99.71 123	99.84 71	99.64 130	99.16 214	99.91 52	98.65 313	99.73 165	99.73 157	98.54 208	99.82 329	98.71 215	99.96 85	99.67 127

test_vis1_rt		99.45 137	99.46 125	99.41 258	99.71 180	98.63 323	98.99 282	99.96 28	99.03 261	99.95 44	99.12 395	98.75 175	99.84 300	99.82 49	99.82 221	99.77 78

COLMAP_ROB	98.06 12	99.45 137	99.37 146	99.70 128	99.83 78	99.70 108	99.38 125	99.78 130	99.53 166	99.67 192	99.78 124	99.19 97	99.86 266	97.32 337	99.87 185	99.55 218
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
WB-MVS		99.44 140	99.32 160	99.80 63	99.81 99	99.61 144	99.47 110	99.81 108	99.82 85	99.71 175	99.72 165	96.60 335	99.98 27	99.75 55	99.23 391	99.82 62

mvsany_test1		99.44 140	99.45 127	99.40 261	99.37 333	98.64 322	97.90 424	99.59 247	99.27 221	99.92 59	99.82 89	99.74 26	99.93 117	99.55 85	99.87 185	99.63 167

Anonymous20240521		99.44 140	99.42 135	99.49 226	99.89 39	98.96 287	99.62 67	99.76 143	99.85 71	99.82 107	99.88 50	96.39 346	99.97 43	99.59 78	99.98 49	99.55 218

tfpnnormal		99.43 143	99.38 143	99.60 180	99.87 54	99.75 79	99.59 80	99.78 130	99.71 117	99.90 67	99.69 194	98.85 161	99.90 196	97.25 348	99.78 251	99.15 357

HPM-MVS_fast		99.43 143	99.30 167	99.80 63	99.83 78	99.81 48	99.52 92	99.70 179	98.35 350	99.51 265	99.50 311	99.31 82	99.88 232	98.18 260	99.84 203	99.69 112

3Dnovator	99.15 2	99.43 143	99.36 150	99.65 149	99.39 328	99.42 194	99.70 38	99.56 263	99.23 229	99.35 305	99.80 102	99.17 100	99.95 79	98.21 255	99.84 203	99.59 200

viewdifsd2359ckpt13		99.42 146	99.37 146	99.57 194	99.72 176	99.46 179	99.01 271	99.80 112	99.20 234	99.51 265	99.60 266	98.92 151	99.70 394	98.65 222	99.90 149	99.55 218

Anonymous20240529		99.42 146	99.34 155	99.65 149	99.53 276	99.60 148	99.63 64	99.39 332	99.47 180	99.76 146	99.78 124	98.13 261	99.86 266	98.70 216	99.68 298	99.49 257

SixPastTwentyTwo		99.42 146	99.30 167	99.76 84	99.92 29	99.67 117	99.70 38	99.14 383	99.65 139	99.89 72	99.90 36	96.20 353	99.94 96	99.42 108	99.92 136	99.67 127

GBi-Net		99.42 146	99.31 162	99.73 110	99.49 296	99.77 64	99.68 49	99.70 179	99.44 188	99.62 219	99.83 82	97.21 316	99.90 196	98.96 179	99.90 149	99.53 234

test1		99.42 146	99.31 162	99.73 110	99.49 296	99.77 64	99.68 49	99.70 179	99.44 188	99.62 219	99.83 82	97.21 316	99.90 196	98.96 179	99.90 149	99.53 234

MVSFormer		99.41 151	99.44 131	99.31 290	99.57 253	98.40 343	99.77 19	99.80 112	99.73 108	99.63 209	99.30 365	98.02 269	99.98 27	99.43 103	99.69 293	99.55 218

IterMVS-LS		99.41 151	99.47 120	99.25 309	99.81 99	98.09 366	98.85 309	99.76 143	99.62 147	99.83 106	99.64 224	98.54 208	99.97 43	99.15 154	99.99 16	99.68 118
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
SED-MVS		99.40 153	99.28 175	99.77 77	99.69 201	99.82 43	99.20 193	99.54 275	99.13 250	99.82 107	99.63 239	98.91 154	99.92 148	97.85 291	99.70 285	99.58 205

v148		99.40 153	99.41 138	99.39 264	99.76 144	98.94 289	99.09 245	99.59 247	99.17 242	99.81 114	99.61 258	98.41 229	99.69 401	99.32 125	99.94 120	99.53 234

NR-MVSNet		99.40 153	99.31 162	99.68 132	99.43 319	99.55 163	99.73 30	99.50 299	99.46 183	99.88 82	99.36 351	97.54 302	99.87 247	98.97 177	99.87 185	99.63 167

PVSNet_Blended_VisFu		99.40 153	99.38 143	99.44 244	99.90 37	98.66 317	98.94 296	99.91 52	97.97 376	99.79 126	99.73 157	99.05 130	99.97 43	99.15 154	99.99 16	99.68 118

LuminaMVS		99.39 157	99.28 175	99.73 110	99.83 78	99.49 171	99.00 275	99.05 390	99.81 91	99.89 72	99.79 112	96.54 339	99.97 43	99.64 73	99.98 49	99.73 92

EU-MVSNet		99.39 157	99.62 78	98.72 377	99.88 45	96.44 421	99.56 87	99.85 80	99.90 49	99.90 67	99.85 68	98.09 264	99.83 316	99.58 81	99.95 105	99.90 28

CHOSEN 1792x2688		99.39 157	99.30 167	99.65 149	99.88 45	99.25 236	98.78 326	99.88 65	98.66 312	99.96 33	99.79 112	97.45 305	99.93 117	99.34 120	99.99 16	99.78 74

IMVS_0407		99.38 160	99.42 135	99.28 298	99.71 180	98.55 330	99.27 170	99.71 170	99.41 200	99.73 165	99.60 266	99.17 100	99.83 316	98.45 234	99.70 285	99.45 270

DVP-MVS++		99.38 160	99.25 182	99.77 77	99.03 411	99.77 64	99.74 27	99.61 230	99.18 237	99.76 146	99.61 258	99.00 136	99.92 148	97.72 302	99.60 326	99.62 178

EI-MVSNet		99.38 160	99.44 131	99.21 313	99.58 243	98.09 366	99.26 175	99.46 310	99.62 147	99.75 151	99.67 209	98.54 208	99.85 285	99.15 154	99.92 136	99.68 118

UGNet		99.38 160	99.34 155	99.49 226	98.90 422	98.90 296	99.70 38	99.35 341	99.86 65	98.57 406	99.81 96	98.50 219	99.93 117	99.38 112	99.98 49	99.66 140
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
IMVS_0403		99.37 164	99.39 140	99.28 298	99.71 180	98.55 330	99.19 199	99.71 170	99.41 200	99.67 192	99.60 266	99.12 111	99.84 300	98.45 234	99.70 285	99.45 270

UniMVSNet_NR-MVSNet		99.37 164	99.25 182	99.72 118	99.47 307	99.56 159	98.97 287	99.61 230	99.43 195	99.67 192	99.28 369	97.85 283	99.95 79	99.17 151	99.81 231	99.65 149

UniMVSNet (Re)		99.37 164	99.26 180	99.68 132	99.51 285	99.58 155	98.98 285	99.60 241	99.43 195	99.70 179	99.36 351	97.70 291	99.88 232	99.20 144	99.87 185	99.59 200

CSCG		99.37 164	99.29 172	99.60 180	99.71 180	99.46 179	99.43 118	99.85 80	98.79 296	99.41 292	99.60 266	98.92 151	99.92 148	98.02 271	99.92 136	99.43 288

APD_test1		99.36 168	99.28 175	99.61 176	99.89 39	99.89 10	99.32 149	99.74 154	99.18 237	99.69 182	99.75 147	98.41 229	99.84 300	97.85 291	99.70 285	99.10 368

PM-MVS		99.36 168	99.29 172	99.58 186	99.83 78	99.66 119	98.95 294	99.86 74	98.85 286	99.81 114	99.73 157	98.40 233	99.92 148	98.36 242	99.83 211	99.17 353

new-patchmatchnet		99.35 170	99.57 96	98.71 379	99.82 87	96.62 417	98.55 356	99.75 148	99.50 170	99.88 82	99.87 56	99.31 82	99.88 232	99.43 103	100.00 1	99.62 178

Anonymous20231206		99.35 170	99.31 162	99.47 233	99.74 167	99.06 277	99.28 166	99.74 154	99.23 229	99.72 170	99.53 302	97.63 301	99.88 232	99.11 163	99.84 203	99.48 261

MTAPA		99.35 170	99.20 188	99.80 63	99.81 99	99.81 48	99.33 146	99.53 285	99.27 221	99.42 286	99.63 239	98.21 254	99.95 79	97.83 295	99.79 243	99.65 149

FMVSNet2		99.35 170	99.28 175	99.55 204	99.49 296	99.35 217	99.45 114	99.57 258	99.44 188	99.70 179	99.74 152	97.21 316	99.87 247	99.03 170	99.94 120	99.44 282

3Dnovator+	98.92 3	99.35 170	99.24 184	99.67 136	99.35 340	99.47 175	99.62 67	99.50 299	99.44 188	99.12 350	99.78 124	98.77 172	99.94 96	97.87 288	99.72 280	99.62 178

TSAR-MVS + MP.		99.34 175	99.24 184	99.63 163	99.82 87	99.37 210	99.26 175	99.35 341	98.77 300	99.57 236	99.70 185	99.27 89	99.88 232	97.71 304	99.75 261	99.65 149
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
diffmvs		99.34 175	99.32 160	99.39 264	99.67 215	98.77 308	98.57 353	99.81 108	99.61 151	99.48 271	99.41 333	98.47 220	99.86 266	98.97 177	99.90 149	99.53 234
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		99.34 175	99.30 167	99.48 231	99.51 285	99.36 214	98.12 397	99.53 285	99.36 209	99.41 292	99.61 258	99.22 94	99.87 247	99.21 141	99.68 298	99.20 345
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		99.33 178	99.21 187	99.71 123	99.43 319	99.56 159	98.83 314	99.53 285	99.38 205	99.67 192	99.36 351	97.67 295	99.95 79	99.17 151	99.81 231	99.63 167

ab-mvs		99.33 178	99.28 175	99.47 233	99.57 253	99.39 205	99.78 17	99.43 319	98.87 283	99.57 236	99.82 89	98.06 267	99.87 247	98.69 218	99.73 274	99.15 357

DVP-MVS		99.32 180	99.17 192	99.77 77	99.69 201	99.80 52	99.14 220	99.31 350	99.16 244	99.62 219	99.61 258	98.35 237	99.91 177	97.88 285	99.72 280	99.61 189
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		99.31 181	99.16 193	99.74 100	99.53 276	99.75 79	99.27 170	99.61 230	99.19 236	99.57 236	99.64 224	98.76 173	99.90 196	97.29 339	99.62 316	99.56 214

icg_test_0407_2		99.30 182	99.29 172	99.31 290	99.71 180	98.55 330	98.17 391	99.71 170	99.41 200	99.73 165	99.60 266	99.17 100	99.92 148	98.45 234	99.70 285	99.45 270

SteuartSystems-ACMMP		99.30 182	99.14 198	99.76 84	99.87 54	99.66 119	99.18 203	99.60 241	98.55 324	99.57 236	99.67 209	99.03 133	99.94 96	97.01 359	99.80 238	99.69 112
Skip Steuart: Steuart Systems R&D Blog.
testgi		99.29 184	99.26 180	99.37 270	99.75 159	98.81 302	98.84 311	99.89 61	98.38 343	99.75 151	99.04 405	99.36 74	99.86 266	99.08 167	99.25 387	99.45 270

ACMMP_NAP		99.28 185	99.11 207	99.79 70	99.75 159	99.81 48	98.95 294	99.53 285	98.27 359	99.53 256	99.73 157	98.75 175	99.87 247	97.70 307	99.83 211	99.68 118

LCM-MVSNet-Re		99.28 185	99.15 197	99.67 136	99.33 354	99.76 71	99.34 140	99.97 20	98.93 275	99.91 62	99.79 112	98.68 184	99.93 117	96.80 373	99.56 335	99.30 323

mvs_anonymous		99.28 185	99.39 140	98.94 349	99.19 383	97.81 384	99.02 266	99.55 269	99.78 102	99.85 97	99.80 102	98.24 248	99.86 266	99.57 82	99.50 353	99.15 357

MVS_Test		99.28 185	99.31 162	99.19 316	99.35 340	98.79 306	99.36 136	99.49 303	99.17 242	99.21 337	99.67 209	98.78 170	99.66 423	99.09 165	99.66 307	99.10 368

SR-MVS-dyc-post		99.27 189	99.11 207	99.73 110	99.54 269	99.74 87	99.26 175	99.62 223	99.16 244	99.52 258	99.64 224	98.41 229	99.91 177	97.27 342	99.61 323	99.54 228

XVS		99.27 189	99.11 207	99.75 95	99.71 180	99.71 100	99.37 132	99.61 230	99.29 217	98.76 389	99.47 322	98.47 220	99.88 232	97.62 318	99.73 274	99.67 127

ME-MVS		99.26 191	99.10 215	99.73 110	99.60 232	99.65 125	98.75 330	99.45 315	99.31 216	99.65 201	99.66 214	98.00 274	99.86 266	97.69 313	99.79 243	99.67 127

OPM-MVS		99.26 191	99.13 200	99.63 163	99.70 195	99.61 144	98.58 349	99.48 304	98.50 331	99.52 258	99.63 239	99.14 107	99.76 371	97.89 284	99.77 255	99.51 246
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HFP-MVS		99.25 193	99.08 219	99.76 84	99.73 171	99.70 108	99.31 154	99.59 247	98.36 345	99.36 303	99.37 346	98.80 167	99.91 177	97.43 331	99.75 261	99.68 118

HPM-MVS		99.25 193	99.07 223	99.78 74	99.81 99	99.75 79	99.61 73	99.67 195	97.72 391	99.35 305	99.25 376	99.23 93	99.92 148	97.21 351	99.82 221	99.67 127
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
ACMMP		99.25 193	99.08 219	99.74 100	99.79 121	99.68 115	99.50 100	99.65 210	98.07 370	99.52 258	99.69 194	98.57 200	99.92 148	97.18 353	99.79 243	99.63 167
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
viewdifsd2359ckpt09		99.24 196	99.16 193	99.49 226	99.70 195	99.22 246	98.88 303	99.81 108	98.70 308	99.38 300	99.37 346	98.22 253	99.76 371	98.48 231	99.88 172	99.51 246

LS3D		99.24 196	99.11 207	99.61 176	98.38 458	99.79 55	99.57 85	99.68 190	99.61 151	99.15 345	99.71 175	98.70 182	99.91 177	97.54 324	99.68 298	99.13 365

IMVS_0404		99.23 198	99.20 188	99.32 286	99.71 180	98.55 330	98.57 353	99.71 170	99.41 200	99.52 258	99.60 266	98.12 263	99.95 79	98.45 234	99.70 285	99.45 270

xiu_mvs_v1_base_debu		99.23 198	99.34 155	98.91 355	99.59 238	98.23 352	98.47 368	99.66 200	99.61 151	99.68 185	98.94 421	99.39 65	99.97 43	99.18 148	99.55 339	98.51 438

xiu_mvs_v1_base		99.23 198	99.34 155	98.91 355	99.59 238	98.23 352	98.47 368	99.66 200	99.61 151	99.68 185	98.94 421	99.39 65	99.97 43	99.18 148	99.55 339	98.51 438

xiu_mvs_v1_base_debi		99.23 198	99.34 155	98.91 355	99.59 238	98.23 352	98.47 368	99.66 200	99.61 151	99.68 185	98.94 421	99.39 65	99.97 43	99.18 148	99.55 339	98.51 438

region2R		99.23 198	99.05 230	99.77 77	99.76 144	99.70 108	99.31 154	99.59 247	98.41 339	99.32 314	99.36 351	98.73 179	99.93 117	97.29 339	99.74 268	99.67 127

ACMMPR		99.23 198	99.06 225	99.76 84	99.74 167	99.69 112	99.31 154	99.59 247	98.36 345	99.35 305	99.38 343	98.61 195	99.93 117	97.43 331	99.75 261	99.67 127

XVG-ACMP-BASELINE		99.23 198	99.10 215	99.63 163	99.82 87	99.58 155	98.83 314	99.72 167	98.36 345	99.60 228	99.71 175	98.92 151	99.91 177	97.08 357	99.84 203	99.40 296

CP-MVS		99.23 198	99.05 230	99.75 95	99.66 217	99.66 119	99.38 125	99.62 223	98.38 343	99.06 358	99.27 371	98.79 168	99.94 96	97.51 327	99.82 221	99.66 140

DeepC-MVS_fast	98.47 5	99.23 198	99.12 204	99.56 198	99.28 365	99.22 246	98.99 282	99.40 329	99.08 255	99.58 233	99.64 224	98.90 157	99.83 316	97.44 330	99.75 261	99.63 167
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ZNCC-MVS		99.22 207	99.04 236	99.77 77	99.76 144	99.73 90	99.28 166	99.56 263	98.19 364	99.14 347	99.29 368	98.84 162	99.92 148	97.53 326	99.80 238	99.64 161

D2MVS		99.22 207	99.19 190	99.29 295	99.69 201	98.74 310	98.81 319	99.41 322	98.55 324	99.68 185	99.69 194	98.13 261	99.87 247	98.82 195	99.98 49	99.24 332

LPG-MVS_test		99.22 207	99.05 230	99.74 100	99.82 87	99.63 136	99.16 214	99.73 158	97.56 396	99.64 204	99.69 194	99.37 71	99.89 217	96.66 381	99.87 185	99.69 112

CDS-MVSNet		99.22 207	99.13 200	99.50 222	99.35 340	99.11 265	98.96 291	99.54 275	99.46 183	99.61 225	99.70 185	96.31 349	99.83 316	99.34 120	99.88 172	99.55 218
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
test_0402		99.22 207	99.14 198	99.45 240	99.79 121	99.43 191	99.28 166	99.68 190	99.54 164	99.40 297	99.56 290	99.07 122	99.82 329	96.01 412	99.96 85	99.11 366

AllTest		99.21 212	99.07 223	99.63 163	99.78 129	99.64 130	99.12 232	99.83 91	98.63 316	99.63 209	99.72 165	98.68 184	99.75 377	96.38 399	99.83 211	99.51 246

XVG-OURS		99.21 212	99.06 225	99.65 149	99.82 87	99.62 138	97.87 425	99.74 154	98.36 345	99.66 198	99.68 205	99.71 28	99.90 196	96.84 371	99.88 172	99.43 288

Fast-Effi-MVS+-dtu		99.20 214	99.12 204	99.43 248	99.25 371	99.69 112	99.05 254	99.82 97	99.50 170	98.97 362	99.05 403	98.98 142	99.98 27	98.20 256	99.24 389	98.62 428

VDD-MVS		99.20 214	99.11 207	99.44 244	99.43 319	98.98 282	99.50 100	98.32 430	99.80 95	99.56 244	99.69 194	96.99 326	99.85 285	98.99 173	99.73 274	99.50 252

PGM-MVS		99.20 214	99.01 243	99.77 77	99.75 159	99.71 100	99.16 214	99.72 167	97.99 374	99.42 286	99.60 266	98.81 163	99.93 117	96.91 365	99.74 268	99.66 140

SR-MVS		99.19 217	99.00 247	99.74 100	99.51 285	99.72 95	99.18 203	99.60 241	98.85 286	99.47 273	99.58 279	98.38 234	99.92 148	96.92 364	99.54 344	99.57 211

SMA-MVS		99.19 217	99.00 247	99.73 110	99.46 311	99.73 90	99.13 227	99.52 290	97.40 407	99.57 236	99.64 224	98.93 148	99.83 316	97.61 320	99.79 243	99.63 167
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		99.19 217	99.11 207	99.42 250	99.76 144	98.88 298	98.55 356	99.73 158	98.82 291	99.72 170	99.62 248	96.56 336	99.82 329	99.32 125	99.95 105	99.56 214

mPP-MVS		99.19 217	99.00 247	99.76 84	99.76 144	99.68 115	99.38 125	99.54 275	98.34 354	99.01 360	99.50 311	98.53 213	99.93 117	97.18 353	99.78 251	99.66 140

MM		99.18 221	99.05 230	99.55 204	99.35 340	98.81 302	99.05 254	97.79 445	99.99 3	99.48 271	99.59 276	96.29 351	99.95 79	99.94 20	99.98 49	99.88 39

ETV-MVS		99.18 221	99.18 191	99.16 319	99.34 349	99.28 228	99.12 232	99.79 121	99.48 175	98.93 366	98.55 444	99.40 64	99.93 117	98.51 230	99.52 349	98.28 448

VNet		99.18 221	99.06 225	99.56 198	99.24 373	99.36 214	99.33 146	99.31 350	99.67 132	99.47 273	99.57 286	96.48 340	99.84 300	99.15 154	99.30 379	99.47 265

RPSCF		99.18 221	99.02 239	99.64 156	99.83 78	99.85 22	99.44 116	99.82 97	98.33 355	99.50 268	99.78 124	97.90 278	99.65 430	96.78 374	99.83 211	99.44 282

DeepPCF-MVS	98.42 6	99.18 221	99.02 239	99.67 136	99.22 376	99.75 79	97.25 452	99.47 307	98.72 305	99.66 198	99.70 185	99.29 84	99.63 434	98.07 270	99.81 231	99.62 178

EPP-MVSNet		99.17 226	99.00 247	99.66 143	99.80 107	99.43 191	99.70 38	99.24 366	99.48 175	99.56 244	99.77 134	94.89 370	99.93 117	98.72 213	99.89 163	99.63 167

GST-MVS		99.16 227	98.96 260	99.75 95	99.73 171	99.73 90	99.20 193	99.55 269	98.22 361	99.32 314	99.35 356	98.65 191	99.91 177	96.86 368	99.74 268	99.62 178

MVP-Stereo		99.16 227	99.08 219	99.43 248	99.48 301	99.07 275	99.08 248	99.55 269	98.63 316	99.31 319	99.68 205	98.19 257	99.78 359	98.18 260	99.58 332	99.45 270
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
XVG-OURS-SEG-HR		99.16 227	98.99 254	99.66 143	99.84 71	99.64 130	98.25 386	99.73 158	98.39 342	99.63 209	99.43 330	99.70 31	99.90 196	97.34 336	98.64 429	99.44 282

jason		99.16 227	99.11 207	99.32 286	99.75 159	98.44 340	98.26 385	99.39 332	98.70 308	99.74 161	99.30 365	98.54 208	99.97 43	98.48 231	99.82 221	99.55 218
jason: jason.
AstraMVS		99.15 231	99.06 225	99.42 250	99.85 66	98.59 327	99.13 227	97.26 453	99.84 75	99.87 92	99.77 134	96.11 354	99.93 117	99.71 59	99.96 85	99.74 88

DPE-MVS		99.14 232	98.92 267	99.82 46	99.57 253	99.77 64	98.74 331	99.60 241	98.55 324	99.76 146	99.69 194	98.23 252	99.92 148	96.39 398	99.75 261	99.76 83
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MP-MVS-pluss		99.14 232	98.92 267	99.80 63	99.83 78	99.83 35	98.61 342	99.63 220	96.84 427	99.44 279	99.58 279	98.81 163	99.91 177	97.70 307	99.82 221	99.67 127
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
VortexMVS		99.13 234	99.24 184	98.79 372	99.67 215	96.60 419	99.24 182	99.80 112	99.85 71	99.93 52	99.84 75	95.06 368	99.89 217	99.80 51	99.98 49	99.89 36

pmmvs4		99.13 234	99.06 225	99.36 275	99.57 253	99.10 272	98.01 410	99.25 363	98.78 298	99.58 233	99.44 329	98.24 248	99.76 371	98.74 206	99.93 132	99.22 338

MVS_111021_LR		99.13 234	99.03 238	99.42 250	99.58 243	99.32 222	97.91 423	99.73 158	98.68 310	99.31 319	99.48 318	99.09 115	99.66 423	97.70 307	99.77 255	99.29 326

guyue		99.12 237	99.02 239	99.41 258	99.84 71	98.56 328	99.19 199	98.30 431	99.82 85	99.84 100	99.75 147	94.84 371	99.92 148	99.68 65	99.94 120	99.74 88

EIA-MVS		99.12 237	99.01 243	99.45 240	99.36 336	99.62 138	99.34 140	99.79 121	98.41 339	98.84 379	98.89 425	98.75 175	99.84 300	98.15 264	99.51 350	98.89 410

TSAR-MVS + GP.		99.12 237	99.04 236	99.38 267	99.34 349	99.16 259	98.15 393	99.29 354	98.18 365	99.63 209	99.62 248	99.18 98	99.68 413	98.20 256	99.74 268	99.30 323

MVS_111021_HR		99.12 237	99.02 239	99.40 261	99.50 291	99.11 265	97.92 421	99.71 170	98.76 303	99.08 354	99.47 322	99.17 100	99.54 448	97.85 291	99.76 257	99.54 228

CANet		99.11 241	99.05 230	99.28 298	98.83 432	98.56 328	98.71 335	99.41 322	99.25 225	99.23 332	99.22 383	97.66 299	99.94 96	99.19 146	99.97 71	99.33 314

WR-MVS		99.11 241	98.93 263	99.66 143	99.30 360	99.42 194	98.42 374	99.37 337	99.04 260	99.57 236	99.20 387	96.89 328	99.86 266	98.66 220	99.87 185	99.70 104

PHI-MVS		99.11 241	98.95 261	99.59 183	99.13 392	99.59 150	99.17 208	99.65 210	97.88 384	99.25 328	99.46 325	98.97 144	99.80 353	97.26 344	99.82 221	99.37 304

SF-MVS		99.10 244	98.93 263	99.62 172	99.58 243	99.51 169	99.13 227	99.65 210	97.97 376	99.42 286	99.61 258	98.86 160	99.87 247	96.45 396	99.68 298	99.49 257

NormalMVS		99.09 245	98.91 271	99.62 172	99.78 129	99.11 265	99.36 136	99.77 135	99.82 85	99.68 185	99.53 302	93.30 389	99.99 8	99.24 135	99.76 257	99.74 88

RRT-MVS		99.08 246	99.00 247	99.33 281	99.27 367	98.65 320	99.62 67	99.93 39	99.66 136	99.67 192	99.82 89	95.27 367	99.93 117	98.64 223	99.09 397	99.41 293

mvsmamba		99.08 246	98.95 261	99.45 240	99.36 336	99.18 258	99.39 122	98.81 401	99.37 206	99.35 305	99.70 185	96.36 348	99.94 96	98.66 220	99.59 330	99.22 338

MSDG		99.08 246	98.98 257	99.37 270	99.60 232	99.13 262	97.54 438	99.74 154	98.84 289	99.53 256	99.55 298	99.10 113	99.79 356	97.07 358	99.86 193	99.18 350

Effi-MVS+-dtu		99.07 249	98.92 267	99.52 216	98.89 425	99.78 58	99.15 217	99.66 200	99.34 210	98.92 369	99.24 381	97.69 293	99.98 27	98.11 266	99.28 382	98.81 417

Effi-MVS+		99.06 250	98.97 258	99.34 278	99.31 356	98.98 282	98.31 381	99.91 52	98.81 293	98.79 386	98.94 421	99.14 107	99.84 300	98.79 199	98.74 422	99.20 345

MP-MVS		99.06 250	98.83 280	99.76 84	99.76 144	99.71 100	99.32 149	99.50 299	98.35 350	98.97 362	99.48 318	98.37 235	99.92 148	95.95 418	99.75 261	99.63 167
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MDA-MVSNet-bldmvs		99.06 250	99.05 230	99.07 335	99.80 107	97.83 383	98.89 302	99.72 167	99.29 217	99.63 209	99.70 185	96.47 341	99.89 217	98.17 262	99.82 221	99.50 252

MSLP-MVS++		99.05 253	99.09 217	98.91 355	99.21 378	98.36 348	98.82 318	99.47 307	98.85 286	98.90 372	99.56 290	98.78 170	99.09 464	98.57 227	99.68 298	99.26 329

1112_ss		99.05 253	98.84 278	99.67 136	99.66 217	99.29 226	98.52 362	99.82 97	97.65 394	99.43 283	99.16 389	96.42 343	99.91 177	99.07 168	99.84 203	99.80 64

ACMP	97.51 14	99.05 253	98.84 278	99.67 136	99.78 129	99.55 163	98.88 303	99.66 200	97.11 422	99.47 273	99.60 266	99.07 122	99.89 217	96.18 407	99.85 198	99.58 205
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MSP-MVS		99.04 256	98.79 286	99.81 54	99.78 129	99.73 90	99.35 139	99.57 258	98.54 327	99.54 251	98.99 412	96.81 330	99.93 117	96.97 362	99.53 346	99.77 78
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		99.03 257	99.01 243	99.09 330	99.54 269	97.99 372	98.58 349	99.82 97	97.62 395	99.34 309	99.71 175	98.52 216	99.77 368	97.98 276	99.97 71	99.52 244

IS-MVSNet		99.03 257	98.85 276	99.55 204	99.80 107	99.25 236	99.73 30	99.15 382	99.37 206	99.61 225	99.71 175	94.73 374	99.81 345	97.70 307	99.88 172	99.58 205

MGCFI-Net		99.02 259	99.01 243	99.06 337	99.11 399	98.60 325	99.63 64	99.67 195	99.63 144	98.58 404	97.65 463	99.07 122	99.57 444	98.85 191	98.92 409	99.03 390

sasdasda		99.02 259	99.00 247	99.09 330	99.10 401	98.70 312	99.61 73	99.66 200	99.63 144	98.64 398	97.65 463	99.04 131	99.54 448	98.79 199	98.92 409	99.04 388

xiu_mvs_v2_base		99.02 259	99.11 207	98.77 374	99.37 333	98.09 366	98.13 396	99.51 295	99.47 180	99.42 286	98.54 445	99.38 69	99.97 43	98.83 193	99.33 375	98.24 450

Fast-Effi-MVS+		99.02 259	98.87 274	99.46 237	99.38 331	99.50 170	99.04 259	99.79 121	97.17 418	98.62 400	98.74 435	99.34 78	99.95 79	98.32 246	99.41 365	98.92 406

canonicalmvs		99.02 259	99.00 247	99.09 330	99.10 401	98.70 312	99.61 73	99.66 200	99.63 144	98.64 398	97.65 463	99.04 131	99.54 448	98.79 199	98.92 409	99.04 388

MCST-MVS		99.02 259	98.81 283	99.65 149	99.58 243	99.49 171	98.58 349	99.07 387	98.40 341	99.04 359	99.25 376	98.51 218	99.80 353	97.31 338	99.51 350	99.65 149

SymmetryMVS		99.01 265	98.82 281	99.58 186	99.65 222	99.11 265	99.36 136	99.20 376	99.82 85	99.68 185	99.53 302	93.30 389	99.99 8	99.24 135	99.63 314	99.64 161

SD-MVS		99.01 265	99.30 167	98.15 405	99.50 291	99.40 202	98.94 296	99.61 230	99.22 233	99.75 151	99.82 89	99.54 50	95.51 475	97.48 328	99.87 185	99.54 228
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		99.01 265	98.92 267	99.27 303	99.71 180	99.28 228	98.59 347	99.77 135	98.32 356	99.39 299	99.41 333	98.62 193	99.84 300	96.62 386	99.84 203	98.69 426

IterMVS-SCA-FT		99.00 268	99.16 193	98.51 387	99.75 159	95.90 433	98.07 404	99.84 87	99.84 75	99.89 72	99.73 157	96.01 357	99.99 8	99.33 123	100.00 1	99.63 167

MS-PatchMatch		99.00 268	98.97 258	99.09 330	99.11 399	98.19 356	98.76 328	99.33 344	98.49 333	99.44 279	99.58 279	98.21 254	99.69 401	98.20 256	99.62 316	99.39 299

PS-MVSNAJ		99.00 268	99.08 219	98.76 375	99.37 333	98.10 365	98.00 412	99.51 295	99.47 180	99.41 292	98.50 447	99.28 86	99.97 43	98.83 193	99.34 374	98.20 454

CNVR-MVS		98.99 271	98.80 285	99.56 198	99.25 371	99.43 191	98.54 359	99.27 358	98.58 322	98.80 384	99.43 330	98.53 213	99.70 394	97.22 350	99.59 330	99.54 228

VDDNet		98.97 272	98.82 281	99.42 250	99.71 180	98.81 302	99.62 67	98.68 407	99.81 91	99.38 300	99.80 102	94.25 378	99.85 285	98.79 199	99.32 377	99.59 200

IterMVS		98.97 272	99.16 193	98.42 392	99.74 167	95.64 437	98.06 406	99.83 91	99.83 81	99.85 97	99.74 152	96.10 356	99.99 8	99.27 134	100.00 1	99.63 167
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TinyColmap		98.97 272	98.93 263	99.07 335	99.46 311	98.19 356	97.75 429	99.75 148	98.79 296	99.54 251	99.70 185	98.97 144	99.62 435	96.63 385	99.83 211	99.41 293

HPM-MVS++		98.96 275	98.70 292	99.74 100	99.52 283	99.71 100	98.86 307	99.19 377	98.47 335	98.59 403	99.06 402	98.08 266	99.91 177	96.94 363	99.60 326	99.60 193

lupinMVS		98.96 275	98.87 274	99.24 311	99.57 253	98.40 343	98.12 397	99.18 378	98.28 358	99.63 209	99.13 391	98.02 269	99.97 43	98.22 254	99.69 293	99.35 310

USDC		98.96 275	98.93 263	99.05 338	99.54 269	97.99 372	97.07 458	99.80 112	98.21 362	99.75 151	99.77 134	98.43 226	99.64 432	97.90 283	99.88 172	99.51 246

YYNet1		98.95 278	98.99 254	98.84 366	99.64 223	97.14 407	98.22 388	99.32 346	98.92 277	99.59 231	99.66 214	97.40 307	99.83 316	98.27 249	99.90 149	99.55 218

MDA-MVSNet_test_wron		98.95 278	98.99 254	98.85 364	99.64 223	97.16 405	98.23 387	99.33 344	98.93 275	99.56 244	99.66 214	97.39 309	99.83 316	98.29 247	99.88 172	99.55 218

Test_1112_low_res		98.95 278	98.73 288	99.63 163	99.68 209	99.15 261	98.09 401	99.80 112	97.14 420	99.46 277	99.40 337	96.11 354	99.89 217	99.01 172	99.84 203	99.84 51

CANet_DTU		98.91 281	98.85 276	99.09 330	98.79 438	98.13 361	98.18 389	99.31 350	99.48 175	98.86 377	99.51 308	96.56 336	99.95 79	99.05 169	99.95 105	99.19 348

HyFIR lowres test		98.91 281	98.64 294	99.73 110	99.85 66	99.47 175	98.07 404	99.83 91	98.64 315	99.89 72	99.60 266	92.57 398	100.00 1	99.33 123	99.97 71	99.72 96

HQP_MVS		98.90 283	98.68 293	99.55 204	99.58 243	99.24 240	98.80 322	99.54 275	98.94 272	99.14 347	99.25 376	97.24 314	99.82 329	95.84 422	99.78 251	99.60 193

sss		98.90 283	98.77 287	99.27 303	99.48 301	98.44 340	98.72 333	99.32 346	97.94 380	99.37 302	99.35 356	96.31 349	99.91 177	98.85 191	99.63 314	99.47 265

OMC-MVS		98.90 283	98.72 289	99.44 244	99.39 328	99.42 194	98.58 349	99.64 218	97.31 412	99.44 279	99.62 248	98.59 197	99.69 401	96.17 408	99.79 243	99.22 338

ppachtmachnet_test		98.89 286	99.12 204	98.20 404	99.66 217	95.24 444	97.63 434	99.68 190	99.08 255	99.78 130	99.62 248	98.65 191	99.88 232	98.02 271	99.96 85	99.48 261

new_pmnet		98.88 287	98.89 272	98.84 366	99.70 195	97.62 391	98.15 393	99.50 299	97.98 375	99.62 219	99.54 300	98.15 260	99.94 96	97.55 323	99.84 203	98.95 401

K. test v3		98.87 288	98.60 297	99.69 130	99.93 24	99.46 179	99.74 27	94.97 464	99.78 102	99.88 82	99.88 50	93.66 386	99.97 43	99.61 76	99.95 105	99.64 161

APD-MVS		98.87 288	98.59 299	99.71 123	99.50 291	99.62 138	99.01 271	99.57 258	96.80 429	99.54 251	99.63 239	98.29 243	99.91 177	95.24 434	99.71 283	99.61 189
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
our_test_3		98.85 290	99.09 217	98.13 406	99.66 217	94.90 448	97.72 430	99.58 256	99.07 257	99.64 204	99.62 248	98.19 257	99.93 117	98.41 239	99.95 105	99.55 218

UnsupCasMVSNet_eth		98.83 291	98.57 303	99.59 183	99.68 209	99.45 185	98.99 282	99.67 195	99.48 175	99.55 249	99.36 351	94.92 369	99.86 266	98.95 185	96.57 465	99.45 270

NCCC		98.82 292	98.57 303	99.58 186	99.21 378	99.31 223	98.61 342	99.25 363	98.65 313	98.43 414	99.26 374	97.86 281	99.81 345	96.55 387	99.27 385	99.61 189

PMVS	92.94 21	98.82 292	98.81 283	98.85 364	99.84 71	97.99 372	99.20 193	99.47 307	99.71 117	99.42 286	99.82 89	98.09 264	99.47 456	93.88 453	99.85 198	99.07 384
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
GDP-MVS		98.81 294	98.57 303	99.50 222	99.53 276	99.12 264	99.28 166	99.86 74	99.53 166	99.57 236	99.32 360	90.88 419	99.98 27	99.46 99	99.74 268	99.42 292

FMVSNet3		98.80 295	98.63 296	99.32 286	99.13 392	98.72 311	99.10 240	99.48 304	99.23 229	99.62 219	99.64 224	92.57 398	99.86 266	98.96 179	99.90 149	99.39 299

Patchmtry		98.78 296	98.54 308	99.49 226	98.89 425	99.19 253	99.32 149	99.67 195	99.65 139	99.72 170	99.79 112	91.87 406	99.95 79	98.00 275	99.97 71	99.33 314

Vis-MVSNet (Re-imp)		98.77 297	98.58 302	99.34 278	99.78 129	98.88 298	99.61 73	99.56 263	99.11 254	99.24 331	99.56 290	93.00 396	99.78 359	97.43 331	99.89 163	99.35 310

CLD-MVS		98.76 298	98.57 303	99.33 281	99.57 253	98.97 285	97.53 440	99.55 269	96.41 432	99.27 326	99.13 391	99.07 122	99.78 359	96.73 377	99.89 163	99.23 336
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Anonymous202405211		98.75 299	98.46 313	99.63 163	99.34 349	99.66 119	99.47 110	97.65 446	99.28 220	99.56 244	99.50 311	93.15 392	99.84 300	98.62 224	99.58 332	99.40 296

CPTT-MVS		98.74 300	98.44 316	99.64 156	99.61 230	99.38 207	99.18 203	99.55 269	96.49 431	99.27 326	99.37 346	97.11 322	99.92 148	95.74 425	99.67 304	99.62 178

F-COLMAP		98.74 300	98.45 315	99.62 172	99.57 253	99.47 175	98.84 311	99.65 210	96.31 435	98.93 366	99.19 388	97.68 294	99.87 247	96.52 389	99.37 370	99.53 234

N_pmnet		98.73 302	98.53 309	99.35 277	99.72 176	98.67 314	98.34 378	94.65 465	98.35 350	99.79 126	99.68 205	98.03 268	99.93 117	98.28 248	99.92 136	99.44 282

BP-MVS1		98.72 303	98.46 313	99.50 222	99.53 276	99.00 279	99.34 140	98.53 416	99.65 139	99.73 165	99.38 343	90.62 423	99.96 68	99.50 93	99.86 193	99.55 218

c3_l		98.72 303	98.71 290	98.72 377	99.12 394	97.22 404	97.68 433	99.56 263	98.90 279	99.54 251	99.48 318	96.37 347	99.73 383	97.88 285	99.88 172	99.21 341

CL-MVSNet_self_test		98.71 305	98.56 307	99.15 321	99.22 376	98.66 317	97.14 455	99.51 295	98.09 369	99.54 251	99.27 371	96.87 329	99.74 380	98.43 238	98.96 406	99.03 390

PVSNet_Blended		98.70 306	98.59 299	99.02 340	99.54 269	97.99 372	97.58 437	99.82 97	95.70 443	99.34 309	98.98 415	98.52 216	99.77 368	97.98 276	99.83 211	99.30 323

dmvs_re		98.69 307	98.48 311	99.31 290	99.55 267	99.42 194	99.54 90	98.38 427	99.32 214	98.72 392	98.71 436	96.76 332	99.21 462	96.01 412	99.35 373	99.31 321

eth_miper_zixun_eth		98.68 308	98.71 290	98.60 383	99.10 401	96.84 414	97.52 442	99.54 275	98.94 272	99.58 233	99.48 318	96.25 352	99.76 371	98.01 274	99.93 132	99.21 341

PatchMatch-RL		98.68 308	98.47 312	99.30 294	99.44 316	99.28 228	98.14 395	99.54 275	97.12 421	99.11 351	99.25 376	97.80 286	99.70 394	96.51 390	99.30 379	98.93 404

miper_lstm_enhance		98.65 310	98.60 297	98.82 371	99.20 381	97.33 401	97.78 428	99.66 200	99.01 263	99.59 231	99.50 311	94.62 375	99.85 285	98.12 265	99.90 149	99.26 329

h-mvs33		98.61 311	98.34 327	99.44 244	99.60 232	98.67 314	99.27 170	99.44 316	99.68 128	99.32 314	99.49 315	92.50 401	100.00 1	99.24 135	96.51 466	99.65 149

MGCNet		98.61 311	98.30 332	99.52 216	97.88 470	98.95 288	98.76 328	94.11 469	99.84 75	99.32 314	99.57 286	95.57 363	99.95 79	99.68 65	99.98 49	99.68 118

CVMVSNet		98.61 311	98.88 273	97.80 418	99.58 243	93.60 456	99.26 175	99.64 218	99.66 136	99.72 170	99.67 209	93.26 391	99.93 117	99.30 128	99.81 231	99.87 43

Patchmatch-RL test		98.60 314	98.36 324	99.33 281	99.77 140	99.07 275	98.27 383	99.87 68	98.91 278	99.74 161	99.72 165	90.57 425	99.79 356	98.55 228	99.85 198	99.11 366

RPMNet		98.60 314	98.53 309	98.83 368	99.05 407	98.12 362	99.30 157	99.62 223	99.86 65	99.16 343	99.74 152	92.53 400	99.92 148	98.75 205	98.77 418	98.44 443

AdaColmap		98.60 314	98.35 326	99.38 267	99.12 394	99.22 246	98.67 337	99.42 321	97.84 388	98.81 382	99.27 371	97.32 312	99.81 345	95.14 436	99.53 346	99.10 368

miper_ehance_all_eth		98.59 317	98.59 299	98.59 384	98.98 417	97.07 408	97.49 443	99.52 290	98.50 331	99.52 258	99.37 346	96.41 345	99.71 390	97.86 289	99.62 316	99.00 397

WTY-MVS		98.59 317	98.37 323	99.26 306	99.43 319	98.40 343	98.74 331	99.13 385	98.10 367	99.21 337	99.24 381	94.82 372	99.90 196	97.86 289	98.77 418	99.49 257

CNLPA		98.57 319	98.34 327	99.28 298	99.18 386	99.10 272	98.34 378	99.41 322	98.48 334	98.52 409	98.98 415	97.05 324	99.78 359	95.59 427	99.50 353	98.96 399

CDPH-MVS		98.56 320	98.20 339	99.61 176	99.50 291	99.46 179	98.32 380	99.41 322	95.22 448	99.21 337	99.10 399	98.34 239	99.82 329	95.09 438	99.66 307	99.56 214

UnsupCasMVSNet_bld		98.55 321	98.27 335	99.40 261	99.56 264	99.37 210	97.97 417	99.68 190	97.49 403	99.08 354	99.35 356	95.41 366	99.82 329	97.70 307	98.19 446	99.01 396

cl____		98.54 322	98.41 319	98.92 353	99.03 411	97.80 386	97.46 444	99.59 247	98.90 279	99.60 228	99.46 325	93.85 382	99.78 359	97.97 278	99.89 163	99.17 353

DIV-MVS_self_test		98.54 322	98.42 318	98.92 353	99.03 411	97.80 386	97.46 444	99.59 247	98.90 279	99.60 228	99.46 325	93.87 381	99.78 359	97.97 278	99.89 163	99.18 350

FA-MVS(test-final)		98.52 324	98.32 329	99.10 329	99.48 301	98.67 314	99.77 19	98.60 414	97.35 410	99.63 209	99.80 102	93.07 394	99.84 300	97.92 281	99.30 379	98.78 420

hse-mvs2		98.52 324	98.30 332	99.16 319	99.29 362	98.60 325	98.77 327	99.02 392	99.68 128	99.32 314	99.04 405	92.50 401	99.85 285	99.24 135	97.87 456	99.03 390

MG-MVS		98.52 324	98.39 321	98.94 349	99.15 389	97.39 400	98.18 389	99.21 373	98.89 282	99.23 332	99.63 239	97.37 310	99.74 380	94.22 447	99.61 323	99.69 112

DP-MVS Recon		98.50 327	98.23 336	99.31 290	99.49 296	99.46 179	98.56 355	99.63 220	94.86 454	98.85 378	99.37 346	97.81 285	99.59 442	96.08 409	99.44 360	98.88 411

CMPMVS	77.52 23	98.50 327	98.19 342	99.41 258	98.33 460	99.56 159	99.01 271	99.59 247	95.44 445	99.57 236	99.80 102	95.64 360	99.46 458	96.47 394	99.92 136	99.21 341
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
114514_t		98.49 329	98.11 347	99.64 156	99.73 171	99.58 155	99.24 182	99.76 143	89.94 466	99.42 286	99.56 290	97.76 290	99.86 266	97.74 301	99.82 221	99.47 265

PMMVS		98.49 329	98.29 334	99.11 327	98.96 419	98.42 342	97.54 438	99.32 346	97.53 400	98.47 412	98.15 455	97.88 280	99.82 329	97.46 329	99.24 389	99.09 373

MVSTER		98.47 331	98.22 337	99.24 311	99.06 406	98.35 349	99.08 248	99.46 310	99.27 221	99.75 151	99.66 214	88.61 436	99.85 285	99.14 160	99.92 136	99.52 244

LFMVS		98.46 332	98.19 342	99.26 306	99.24 373	98.52 336	99.62 67	96.94 455	99.87 62	99.31 319	99.58 279	91.04 414	99.81 345	98.68 219	99.42 364	99.45 270

PatchT		98.45 333	98.32 329	98.83 368	98.94 420	98.29 350	99.24 182	98.82 400	99.84 75	99.08 354	99.76 139	91.37 409	99.94 96	98.82 195	99.00 404	98.26 449

MIMVSNet		98.43 334	98.20 339	99.11 327	99.53 276	98.38 347	99.58 82	98.61 412	98.96 268	99.33 311	99.76 139	90.92 416	99.81 345	97.38 334	99.76 257	99.15 357

PVSNet	97.47 15	98.42 335	98.44 316	98.35 395	99.46 311	96.26 426	96.70 463	99.34 343	97.68 393	99.00 361	99.13 391	97.40 307	99.72 385	97.59 322	99.68 298	99.08 379

CHOSEN 280x420		98.41 336	98.41 319	98.40 393	99.34 349	95.89 434	96.94 460	99.44 316	98.80 295	99.25 328	99.52 306	93.51 388	99.98 27	98.94 186	99.98 49	99.32 317

BH-RMVSNet		98.41 336	98.14 345	99.21 313	99.21 378	98.47 337	98.60 344	98.26 432	98.35 350	98.93 366	99.31 363	97.20 319	99.66 423	94.32 445	99.10 396	99.51 246

QAPM		98.40 338	97.99 354	99.65 149	99.39 328	99.47 175	99.67 53	99.52 290	91.70 463	98.78 388	99.80 102	98.55 204	99.95 79	94.71 442	99.75 261	99.53 234

API-MVS		98.38 339	98.39 321	98.35 395	98.83 432	99.26 233	99.14 220	99.18 378	98.59 321	98.66 397	98.78 433	98.61 195	99.57 444	94.14 448	99.56 335	96.21 469

HQP-MVS		98.36 340	98.02 353	99.39 264	99.31 356	98.94 289	97.98 414	99.37 337	97.45 404	98.15 423	98.83 429	96.67 333	99.70 394	94.73 440	99.67 304	99.53 234

PAPM_NR		98.36 340	98.04 351	99.33 281	99.48 301	98.93 292	98.79 325	99.28 357	97.54 399	98.56 408	98.57 442	97.12 321	99.69 401	94.09 449	98.90 413	99.38 301

PLC	97.35 16	98.36 340	97.99 354	99.48 231	99.32 355	99.24 240	98.50 364	99.51 295	95.19 450	98.58 404	98.96 419	96.95 327	99.83 316	95.63 426	99.25 387	99.37 304
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
train_agg		98.35 343	97.95 358	99.57 194	99.35 340	99.35 217	98.11 399	99.41 322	94.90 452	97.92 434	98.99 412	98.02 269	99.85 285	95.38 432	99.44 360	99.50 252

CR-MVSNet		98.35 343	98.20 339	98.83 368	99.05 407	98.12 362	99.30 157	99.67 195	97.39 408	99.16 343	99.79 112	91.87 406	99.91 177	98.78 203	98.77 418	98.44 443

WB-MVSnew		98.34 345	98.14 345	98.96 346	98.14 467	97.90 380	98.27 383	97.26 453	98.63 316	98.80 384	98.00 458	97.77 288	99.90 196	97.37 335	98.98 405	99.09 373

DPM-MVS		98.28 346	97.94 362	99.32 286	99.36 336	99.11 265	97.31 450	98.78 403	96.88 425	98.84 379	99.11 398	97.77 288	99.61 440	94.03 451	99.36 371	99.23 336

alignmvs		98.28 346	97.96 357	99.25 309	99.12 394	98.93 292	99.03 262	98.42 423	99.64 142	98.72 392	97.85 460	90.86 420	99.62 435	98.88 189	99.13 393	99.19 348

test_yl		98.25 348	97.95 358	99.13 325	99.17 387	98.47 337	99.00 275	98.67 409	98.97 266	99.22 335	99.02 410	91.31 410	99.69 401	97.26 344	98.93 407	99.24 332

DCV-MVSNet		98.25 348	97.95 358	99.13 325	99.17 387	98.47 337	99.00 275	98.67 409	98.97 266	99.22 335	99.02 410	91.31 410	99.69 401	97.26 344	98.93 407	99.24 332

MAR-MVS		98.24 350	97.92 364	99.19 316	98.78 440	99.65 125	99.17 208	99.14 383	95.36 446	98.04 430	98.81 432	97.47 304	99.72 385	95.47 430	99.06 398	98.21 452
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		98.23 351	98.32 329	97.99 409	98.97 418	96.62 417	99.49 105	98.42 423	99.62 147	99.40 297	99.79 112	95.51 364	98.58 471	97.68 317	95.98 469	98.76 423

OpenMVS	98.12 10	98.23 351	97.89 367	99.26 306	99.19 383	99.26 233	99.65 62	99.69 187	91.33 464	98.14 427	99.77 134	98.28 244	99.96 68	95.41 431	99.55 339	98.58 433

MVStest1		98.22 353	98.09 348	98.62 381	99.04 410	96.23 427	99.20 193	99.92 43	99.44 188	99.98 14	99.87 56	85.87 449	99.67 418	99.91 32	99.57 334	99.95 14

BH-untuned		98.22 353	98.09 348	98.58 386	99.38 331	97.24 403	98.55 356	98.98 395	97.81 389	99.20 342	98.76 434	97.01 325	99.65 430	94.83 439	98.33 439	98.86 413

HY-MVS	98.23 9	98.21 355	97.95 358	98.99 342	99.03 411	98.24 351	99.61 73	98.72 405	96.81 428	98.73 391	99.51 308	94.06 379	99.86 266	96.91 365	98.20 444	98.86 413

Syy-MVS		98.17 356	97.85 368	99.15 321	98.50 455	98.79 306	98.60 344	99.21 373	97.89 382	96.76 458	96.37 481	95.47 365	99.57 444	99.10 164	98.73 425	99.09 373

EPNet		98.13 357	97.77 372	99.18 318	94.57 478	97.99 372	99.24 182	97.96 439	99.74 107	97.29 451	99.62 248	93.13 393	99.97 43	98.59 225	99.83 211	99.58 205
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SCA		98.11 358	98.36 324	97.36 430	99.20 381	92.99 458	98.17 391	98.49 420	98.24 360	99.10 353	99.57 286	96.01 357	99.94 96	96.86 368	99.62 316	99.14 362

Patchmatch-test		98.10 359	97.98 356	98.48 389	99.27 367	96.48 420	99.40 120	99.07 387	98.81 293	99.23 332	99.57 286	90.11 429	99.87 247	96.69 378	99.64 311	99.09 373

pmmvs3		98.08 360	97.80 369	98.91 355	99.41 326	97.69 390	97.87 425	99.66 200	95.87 439	99.50 268	99.51 308	90.35 427	99.97 43	98.55 228	99.47 357	99.08 379

JIA-IIPM		98.06 361	97.92 364	98.50 388	98.59 451	97.02 409	98.80 322	98.51 418	99.88 60	97.89 436	99.87 56	91.89 405	99.90 196	98.16 263	97.68 458	98.59 431

miper_enhance_ethall		98.03 362	97.94 362	98.32 398	98.27 461	96.43 422	96.95 459	99.41 322	96.37 434	99.43 283	98.96 419	94.74 373	99.69 401	97.71 304	99.62 316	98.83 416

TAPA-MVS	97.92 13	98.03 362	97.55 378	99.46 237	99.47 307	99.44 187	98.50 364	99.62 223	86.79 467	99.07 357	99.26 374	98.26 247	99.62 435	97.28 341	99.73 274	99.31 321
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
1314		98.00 364	97.90 366	98.27 403	98.90 422	97.45 397	99.30 157	99.06 389	94.98 451	97.21 453	99.12 395	98.43 226	99.67 418	95.58 428	98.56 432	97.71 461

GA-MVS		97.99 365	97.68 375	98.93 352	99.52 283	98.04 370	97.19 454	99.05 390	98.32 356	98.81 382	98.97 417	89.89 432	99.41 459	98.33 245	99.05 400	99.34 313

MVS-HIRNet		97.86 366	98.22 337	96.76 440	99.28 365	91.53 467	98.38 376	92.60 472	99.13 250	99.31 319	99.96 15	97.18 320	99.68 413	98.34 244	99.83 211	99.07 384

FE-MVS		97.85 367	97.42 381	99.15 321	99.44 316	98.75 309	99.77 19	98.20 434	95.85 440	99.33 311	99.80 102	88.86 435	99.88 232	96.40 397	99.12 394	98.81 417

AUN-MVS		97.82 368	97.38 382	99.14 324	99.27 367	98.53 334	98.72 333	99.02 392	98.10 367	97.18 454	99.03 409	89.26 434	99.85 285	97.94 280	97.91 454	99.03 390

FMVSNet5		97.80 369	97.25 386	99.42 250	98.83 432	98.97 285	99.38 125	99.80 112	98.87 283	99.25 328	99.69 194	80.60 459	99.91 177	98.96 179	99.90 149	99.38 301

ADS-MVSNet2		97.78 370	97.66 377	98.12 407	99.14 390	95.36 441	99.22 190	98.75 404	96.97 423	98.25 419	99.64 224	90.90 417	99.94 96	96.51 390	99.56 335	99.08 379

test1111		97.74 371	98.16 344	96.49 446	99.60 232	89.86 477	99.71 37	91.21 473	99.89 55	99.88 82	99.87 56	93.73 385	99.90 196	99.56 83	99.99 16	99.70 104

ECVR-MVS		97.73 372	98.04 351	96.78 439	99.59 238	90.81 472	99.72 33	90.43 475	99.89 55	99.86 94	99.86 63	93.60 387	99.89 217	99.46 99	99.99 16	99.65 149

baseline1		97.73 372	97.33 383	98.96 346	99.30 360	97.73 388	99.40 120	98.42 423	99.33 213	99.46 277	99.21 385	91.18 412	99.82 329	98.35 243	91.26 473	99.32 317

tpmrst		97.73 372	98.07 350	96.73 443	98.71 447	92.00 462	99.10 240	98.86 397	98.52 329	98.92 369	99.54 300	91.90 404	99.82 329	98.02 271	99.03 402	98.37 445

ADS-MVSNet		97.72 375	97.67 376	97.86 416	99.14 390	94.65 449	99.22 190	98.86 397	96.97 423	98.25 419	99.64 224	90.90 417	99.84 300	96.51 390	99.56 335	99.08 379

PatchmatchNet		97.65 376	97.80 369	97.18 436	98.82 435	92.49 460	99.17 208	98.39 426	98.12 366	98.79 386	99.58 279	90.71 422	99.89 217	97.23 349	99.41 365	99.16 355
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tttt0517		97.62 377	97.20 387	98.90 361	99.76 144	97.40 399	99.48 107	94.36 466	99.06 259	99.70 179	99.49 315	84.55 452	99.94 96	98.73 211	99.65 309	99.36 307

EPNet_dtu		97.62 377	97.79 371	97.11 438	96.67 475	92.31 461	98.51 363	98.04 437	99.24 227	95.77 467	99.47 322	93.78 384	99.66 423	98.98 175	99.62 316	99.37 304
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
wuyk23d		97.58 379	99.13 200	92.93 454	99.69 201	99.49 171	99.52 92	99.77 135	97.97 376	99.96 33	99.79 112	99.84 16	99.94 96	95.85 421	99.82 221	79.36 472

cl22		97.56 380	97.28 384	98.40 393	98.37 459	96.75 415	97.24 453	99.37 337	97.31 412	99.41 292	99.22 383	87.30 438	99.37 460	97.70 307	99.62 316	99.08 379

PAPR		97.56 380	97.07 390	99.04 339	98.80 436	98.11 364	97.63 434	99.25 363	94.56 457	98.02 432	98.25 452	97.43 306	99.68 413	90.90 460	98.74 422	99.33 314

WBMVS		97.50 382	97.18 388	98.48 389	98.85 430	95.89 434	98.44 373	99.52 290	99.53 166	99.52 258	99.42 332	80.10 460	99.86 266	99.24 135	99.95 105	99.68 118

thisisatest0530		97.45 383	96.95 394	98.94 349	99.68 209	97.73 388	99.09 245	94.19 468	98.61 320	99.56 244	99.30 365	84.30 454	99.93 117	98.27 249	99.54 344	99.16 355

TR-MVS		97.44 384	97.15 389	98.32 398	98.53 453	97.46 396	98.47 368	97.91 441	96.85 426	98.21 422	98.51 446	96.42 343	99.51 454	92.16 456	97.29 461	97.98 458

SD_0403		97.42 385	96.90 398	98.98 344	99.54 269	97.90 380	99.52 92	99.54 275	99.34 210	97.87 438	98.85 428	98.72 180	99.64 432	78.93 473	99.83 211	99.40 296

reproduce_monomvs		97.40 386	97.46 379	97.20 435	99.05 407	91.91 463	99.20 193	99.18 378	99.84 75	99.86 94	99.75 147	80.67 457	99.83 316	99.69 63	99.95 105	99.85 48

tpmvs		97.39 387	97.69 374	96.52 445	98.41 457	91.76 464	99.30 157	98.94 396	97.74 390	97.85 440	99.55 298	92.40 403	99.73 383	96.25 404	98.73 425	98.06 457

test0.0.03 1		97.37 388	96.91 397	98.74 376	97.72 471	97.57 392	97.60 436	97.36 452	98.00 372	99.21 337	98.02 456	90.04 430	99.79 356	98.37 241	95.89 470	98.86 413

OpenMVS_ROB	97.31 17	97.36 389	96.84 399	98.89 362	99.29 362	99.45 185	98.87 306	99.48 304	86.54 469	99.44 279	99.74 152	97.34 311	99.86 266	91.61 457	99.28 382	97.37 465

dmvs_testset		97.27 390	96.83 400	98.59 384	99.46 311	97.55 393	99.25 181	96.84 456	98.78 298	97.24 452	97.67 462	97.11 322	98.97 466	86.59 471	98.54 433	99.27 327

BH-w/o		97.20 391	97.01 392	97.76 419	99.08 405	95.69 436	98.03 409	98.52 417	95.76 442	97.96 433	98.02 456	95.62 361	99.47 456	92.82 455	97.25 462	98.12 456

test-LLR		97.15 392	96.95 394	97.74 421	98.18 464	95.02 446	97.38 446	96.10 457	98.00 372	97.81 442	98.58 440	90.04 430	99.91 177	97.69 313	98.78 416	98.31 446

tpm		97.15 392	96.95 394	97.75 420	98.91 421	94.24 451	99.32 149	97.96 439	97.71 392	98.29 417	99.32 360	86.72 446	99.92 148	98.10 269	96.24 468	99.09 373

E-PMN		97.14 394	97.43 380	96.27 448	98.79 438	91.62 466	95.54 468	99.01 394	99.44 188	98.88 373	99.12 395	92.78 397	99.68 413	94.30 446	99.03 402	97.50 462

cascas		96.99 395	96.82 401	97.48 426	97.57 474	95.64 437	96.43 465	99.56 263	91.75 462	97.13 456	97.61 466	95.58 362	98.63 469	96.68 379	99.11 395	98.18 455

thisisatest0515		96.98 396	96.42 404	98.66 380	99.42 324	97.47 395	97.27 451	94.30 467	97.24 414	99.15 345	98.86 427	85.01 450	99.87 247	97.10 355	99.39 367	98.63 427

EMVS		96.96 397	97.28 384	95.99 452	98.76 443	91.03 470	95.26 470	98.61 412	99.34 210	98.92 369	98.88 426	93.79 383	99.66 423	92.87 454	99.05 400	97.30 466

dp		96.86 398	97.07 390	96.24 449	98.68 449	90.30 476	99.19 199	98.38 427	97.35 410	98.23 421	99.59 276	87.23 439	99.82 329	96.27 403	98.73 425	98.59 431

baseline2		96.83 399	96.28 406	98.46 391	99.09 404	96.91 412	98.83 314	93.87 471	97.23 415	96.23 466	98.36 449	88.12 437	99.90 196	96.68 379	98.14 449	98.57 435

ET-MVSNet_ETH3D		96.78 400	96.07 410	98.91 355	99.26 370	97.92 379	97.70 432	96.05 460	97.96 379	92.37 473	98.43 448	87.06 440	99.90 196	98.27 249	97.56 459	98.91 407

tpm cat1		96.78 400	96.98 393	96.16 450	98.85 430	90.59 474	99.08 248	99.32 346	92.37 460	97.73 446	99.46 325	91.15 413	99.69 401	96.07 410	98.80 415	98.21 452

PCF-MVS	96.03 18	96.73 402	95.86 415	99.33 281	99.44 316	99.16 259	96.87 461	99.44 316	86.58 468	98.95 364	99.40 337	94.38 377	99.88 232	87.93 465	99.80 238	98.95 401
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CostFormer		96.71 403	96.79 402	96.46 447	98.90 422	90.71 473	99.41 119	98.68 407	94.69 456	98.14 427	99.34 359	86.32 448	99.80 353	97.60 321	98.07 452	98.88 411

MVE	92.54 22	96.66 404	96.11 409	98.31 400	99.68 209	97.55 393	97.94 419	95.60 463	99.37 206	90.68 474	98.70 438	96.56 336	98.61 470	86.94 470	99.55 339	98.77 422
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
thres600view7		96.60 405	96.16 408	97.93 413	99.63 225	96.09 431	99.18 203	97.57 447	98.77 300	98.72 392	97.32 468	87.04 441	99.72 385	88.57 463	98.62 430	97.98 458

UBG		96.53 406	95.95 412	98.29 402	98.87 428	96.31 425	98.48 367	98.07 436	98.83 290	97.32 449	96.54 479	79.81 462	99.62 435	96.84 371	98.74 422	98.95 401

EPMVS		96.53 406	96.32 405	97.17 437	98.18 464	92.97 459	99.39 122	89.95 476	98.21 362	98.61 401	99.59 276	86.69 447	99.72 385	96.99 360	99.23 391	98.81 417

testing3-2		96.51 408	96.43 403	96.74 442	99.36 336	91.38 469	99.10 240	97.87 443	99.48 175	98.57 406	98.71 436	76.65 469	99.66 423	98.87 190	99.26 386	99.18 350

testing3		96.48 409	95.63 421	99.01 341	99.23 375	97.81 384	98.90 301	99.10 386	98.72 305	97.84 441	97.92 459	72.44 475	99.85 285	97.21 351	99.33 375	99.35 310

thres400		96.40 410	95.89 413	97.92 414	99.58 243	96.11 429	99.00 275	97.54 450	98.43 336	98.52 409	96.98 472	86.85 443	99.67 418	87.62 466	98.51 434	97.98 458

thres100view900		96.39 411	96.03 411	97.47 427	99.63 225	95.93 432	99.18 203	97.57 447	98.75 304	98.70 395	97.31 469	87.04 441	99.67 418	87.62 466	98.51 434	96.81 467

tpm2		96.35 412	96.22 407	96.73 443	98.88 427	91.75 465	99.21 192	98.51 418	93.27 459	97.89 436	99.21 385	84.83 451	99.70 394	96.04 411	98.18 447	98.75 424

FPMVS		96.32 413	95.50 422	98.79 372	99.60 232	98.17 359	98.46 372	98.80 402	97.16 419	96.28 463	99.63 239	82.19 455	99.09 464	88.45 464	98.89 414	99.10 368

tfpn200view9		96.30 414	95.89 413	97.53 424	99.58 243	96.11 429	99.00 275	97.54 450	98.43 336	98.52 409	96.98 472	86.85 443	99.67 418	87.62 466	98.51 434	96.81 467

TESTMET0.1,1		96.24 415	95.84 416	97.41 429	98.24 462	93.84 454	97.38 446	95.84 461	98.43 336	97.81 442	98.56 443	79.77 463	99.89 217	97.77 296	98.77 418	98.52 437

myMVS_eth3d28		96.23 416	95.74 418	97.70 423	98.86 429	95.59 439	98.66 339	98.14 435	98.96 268	97.67 447	97.06 471	76.78 468	98.92 467	97.10 355	98.41 438	98.58 433

test-mter		96.23 416	95.73 419	97.74 421	98.18 464	95.02 446	97.38 446	96.10 457	97.90 381	97.81 442	98.58 440	79.12 466	99.91 177	97.69 313	98.78 416	98.31 446

UWE-MVS		96.21 418	95.78 417	97.49 425	98.53 453	93.83 455	98.04 407	93.94 470	98.96 268	98.46 413	98.17 454	79.86 461	99.87 247	96.99 360	99.06 398	98.78 420

ETVMVS		96.14 419	95.22 430	98.89 362	98.80 436	98.01 371	98.66 339	98.35 429	98.71 307	97.18 454	96.31 483	74.23 474	99.75 377	96.64 384	98.13 451	98.90 408

X-MVStestdata		96.09 420	94.87 433	99.75 95	99.71 180	99.71 100	99.37 132	99.61 230	99.29 217	98.76 389	61.30 484	98.47 220	99.88 232	97.62 318	99.73 274	99.67 127

thres200		96.09 420	95.68 420	97.33 432	99.48 301	96.22 428	98.53 361	97.57 447	98.06 371	98.37 416	96.73 476	86.84 445	99.61 440	86.99 469	98.57 431	96.16 470

testing11		96.05 422	95.41 425	97.97 411	98.78 440	95.27 443	98.59 347	98.23 433	98.86 285	96.56 461	96.91 474	75.20 471	99.69 401	97.26 344	98.29 441	98.93 404

testing91		96.00 423	95.32 428	98.02 408	98.76 443	95.39 440	98.38 376	98.65 411	98.82 291	96.84 457	96.71 477	75.06 472	99.71 390	96.46 395	98.23 443	98.98 398

KD-MVS_2432*1600		95.89 424	95.41 425	97.31 433	94.96 476	93.89 452	97.09 456	99.22 370	97.23 415	98.88 373	99.04 405	79.23 464	99.54 448	96.24 405	96.81 463	98.50 441

miper_refine_blended		95.89 424	95.41 425	97.31 433	94.96 476	93.89 452	97.09 456	99.22 370	97.23 415	98.88 373	99.04 405	79.23 464	99.54 448	96.24 405	96.81 463	98.50 441

gg-mvs-nofinetune		95.87 426	95.17 432	97.97 411	98.19 463	96.95 410	99.69 45	89.23 477	99.89 55	96.24 465	99.94 19	81.19 456	99.51 454	93.99 452	98.20 444	97.44 463

testing99		95.86 427	95.19 431	97.87 415	98.76 443	95.03 445	98.62 341	98.44 422	98.68 310	96.67 460	96.66 478	74.31 473	99.69 401	96.51 390	98.03 453	98.90 408

PVSNet_0	95.53 19	95.85 428	95.31 429	97.47 427	98.78 440	93.48 457	95.72 467	99.40 329	96.18 437	97.37 448	97.73 461	95.73 359	99.58 443	95.49 429	81.40 474	99.36 307

tmp_tt		95.75 429	95.42 424	96.76 440	89.90 480	94.42 450	98.86 307	97.87 443	78.01 471	99.30 324	99.69 194	97.70 291	95.89 473	99.29 131	98.14 449	99.95 14

MVS		95.72 430	94.63 436	98.99 342	98.56 452	97.98 377	99.30 157	98.86 397	72.71 473	97.30 450	99.08 400	98.34 239	99.74 380	89.21 461	98.33 439	99.26 329

UWE-MVS-28		95.64 431	95.47 423	96.14 451	97.98 468	90.39 475	98.49 366	95.81 462	99.02 262	98.03 431	98.19 453	84.49 453	99.28 461	88.75 462	98.47 437	98.75 424

myMVS_eth3d		95.63 432	94.73 434	98.34 397	98.50 455	96.36 423	98.60 344	99.21 373	97.89 382	96.76 458	96.37 481	72.10 476	99.57 444	94.38 444	98.73 425	99.09 373

PAPM		95.61 433	94.71 435	98.31 400	99.12 394	96.63 416	96.66 464	98.46 421	90.77 465	96.25 464	98.68 439	93.01 395	99.69 401	81.60 472	97.86 457	98.62 428

testing222		95.60 434	94.59 437	98.61 382	98.66 450	97.45 397	98.54 359	97.90 442	98.53 328	96.54 462	96.47 480	70.62 478	99.81 345	95.91 420	98.15 448	98.56 436

IB-MVS	95.41 20	95.30 435	94.46 439	97.84 417	98.76 443	95.33 442	97.33 449	96.07 459	96.02 438	95.37 470	97.41 467	76.17 470	99.96 68	97.54 324	95.44 472	98.22 451
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		94.73 436	94.59 437	95.15 453	99.59 238	85.90 479	99.75 25	74.01 481	99.89 55	99.71 175	99.86 63	79.00 467	99.90 196	99.52 90	99.99 16	99.65 149

test_method		91.72 437	92.32 440	89.91 456	93.49 479	70.18 482	90.28 471	99.56 263	61.71 474	95.39 469	99.52 306	93.90 380	99.94 96	98.76 204	98.27 442	99.62 178

dongtai		89.37 438	88.91 441	90.76 455	99.19 383	77.46 480	95.47 469	87.82 479	92.28 461	94.17 472	98.82 431	71.22 477	95.54 474	63.85 474	97.34 460	99.27 327

EGC-MVSNET		89.05 439	85.52 442	99.64 156	99.89 39	99.78 58	99.56 87	99.52 290	24.19 475	49.96 476	99.83 82	99.15 104	99.92 148	97.71 304	99.85 198	99.21 341

kuosan		85.65 440	84.57 443	88.90 457	97.91 469	77.11 481	96.37 466	87.62 480	85.24 470	85.45 475	96.83 475	69.94 479	90.98 476	45.90 475	95.83 471	98.62 428

test123		29.31 441	33.05 446	18.08 458	25.93 482	12.24 483	97.53 440	10.93 483	11.78 476	24.21 477	50.08 488	21.04 480	8.60 477	23.51 476	32.43 476	33.39 473

testmvs		28.94 442	33.33 444	15.79 459	26.03 481	9.81 484	96.77 462	15.67 482	11.55 477	23.87 478	50.74 487	19.03 481	8.53 478	23.21 477	33.07 475	29.03 474

cdsmvs_eth3d_5k		24.88 443	33.17 445	0.00 460	0.00 483	0.00 485	0.00 472	99.62 223	0.00 478	0.00 479	99.13 391	99.82 18	0.00 479	0.00 478	0.00 477	0.00 475

pcd_1.5k_mvsjas		16.61 444	22.14 447	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	100.00 1	99.28 86	0.00 479	0.00 478	0.00 477	0.00 475

mmdepth		8.33 445	11.11 448	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	100.00 1	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

monomultidepth		8.33 445	11.11 448	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	100.00 1	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

test_blank		8.33 445	11.11 448	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	100.00 1	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

uanet_test		8.33 445	11.11 448	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	100.00 1	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

DCPMVS		8.33 445	11.11 448	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	100.00 1	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

sosnet-low-res		8.33 445	11.11 448	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	100.00 1	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

sosnet		8.33 445	11.11 448	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	100.00 1	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

uncertanet		8.33 445	11.11 448	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	100.00 1	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

Regformer		8.33 445	11.11 448	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	100.00 1	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

uanet		8.33 445	11.11 448	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	100.00 1	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

ab-mvs-re		8.26 455	11.02 458	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	99.16 389	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

MED-MVS test				99.74 100	99.76 144	99.65 125	99.38 125	99.78 130	99.58 161	99.81 114	99.66 214		99.90 196	97.69 313	99.79 243	99.67 127

TestfortrainingZip							99.38 125

WAC-MVS						96.36 423								95.20 435

FOURS1					99.83 78	99.89 10	99.74 27	99.71 170	99.69 126	99.63 209

MSC_two_6792asdad				99.74 100	99.03 411	99.53 166		99.23 367					99.92 148	97.77 296	99.69 293	99.78 74

PC_three_1452									97.56 396	99.68 185	99.41 333	99.09 115	97.09 472	96.66 381	99.60 326	99.62 178

No_MVS				99.74 100	99.03 411	99.53 166		99.23 367					99.92 148	97.77 296	99.69 293	99.78 74

test_one_0601					99.63 225	99.76 71		99.55 269	99.23 229	99.31 319	99.61 258	98.59 197

eth-test2					0.00 483

eth-test					0.00 483

ZD-MVS					99.43 319	99.61 144		99.43 319	96.38 433	99.11 351	99.07 401	97.86 281	99.92 148	94.04 450	99.49 355

RE-MVS-def			99.13 200		99.54 269	99.74 87	99.26 175	99.62 223	99.16 244	99.52 258	99.64 224	98.57 200		97.27 342	99.61 323	99.54 228

IU-MVS					99.69 201	99.77 64		99.22 370	97.50 402	99.69 182				97.75 300	99.70 285	99.77 78

OPU-MVS				99.29 295	99.12 394	99.44 187	99.20 193				99.40 337	99.00 136	98.84 468	96.54 388	99.60 326	99.58 205

test_241102_TWO								99.54 275	99.13 250	99.76 146	99.63 239	98.32 242	99.92 148	97.85 291	99.69 293	99.75 86

test_241102_ONE					99.69 201	99.82 43		99.54 275	99.12 253	99.82 107	99.49 315	98.91 154	99.52 453

9.14			98.64 294		99.45 315		98.81 319	99.60 241	97.52 401	99.28 325	99.56 290	98.53 213	99.83 316	95.36 433	99.64 311

save fliter					99.53 276	99.25 236	98.29 382	99.38 336	99.07 257

test_0728_THIRD									99.18 237	99.62 219	99.61 258	98.58 199	99.91 177	97.72 302	99.80 238	99.77 78

test_0728_SECOND				99.83 41	99.70 195	99.79 55	99.14 220	99.61 230					99.92 148	97.88 285	99.72 280	99.77 78

test0726					99.69 201	99.80 52	99.24 182	99.57 258	99.16 244	99.73 165	99.65 222	98.35 237

GSMVS																99.14 362

test_part2					99.62 229	99.67 117				99.55 249

sam_mvs1												90.81 421				99.14 362

sam_mvs												90.52 426

ambc				99.20 315	99.35 340	98.53 334	99.17 208	99.46 310		99.67 192	99.80 102	98.46 223	99.70 394	97.92 281	99.70 285	99.38 301

MTGPA								99.53 285

test_post1							99.14 220				51.63 486	89.54 433	99.82 329	96.86 368

test_post											52.41 485	90.25 428	99.86 266

patchmatchnet-post											99.62 248	90.58 424	99.94 96

GG-mvs-BLEND				97.36 430	97.59 472	96.87 413	99.70 38	88.49 478		94.64 471	97.26 470	80.66 458	99.12 463	91.50 458	96.50 467	96.08 471

MTMP							99.09 245	98.59 415

gm-plane-assit					97.59 472	89.02 478			93.47 458		98.30 450		99.84 300	96.38 399

test9_res														95.10 437	99.44 360	99.50 252

TEST9					99.35 340	99.35 217	98.11 399	99.41 322	94.83 455	97.92 434	98.99 412	98.02 269	99.85 285

test_8					99.34 349	99.31 223	98.08 403	99.40 329	94.90 452	97.87 438	98.97 417	98.02 269	99.84 300

agg_prior2														94.58 443	99.46 359	99.50 252

agg_prior					99.35 340	99.36 214		99.39 332		97.76 445			99.85 285

TestCases				99.63 163	99.78 129	99.64 130		99.83 91	98.63 316	99.63 209	99.72 165	98.68 184	99.75 377	96.38 399	99.83 211	99.51 246

test_prior4						99.19 253	98.00 412

test_prior2							97.95 418		97.87 385	98.05 429	99.05 403	97.90 278		95.99 415	99.49 355

test_prior				99.46 237	99.35 340	99.22 246		99.39 332					99.69 401			99.48 261

旧先验2							97.94 419		95.33 447	98.94 365			99.88 232	96.75 375

新几何2							98.04 407

新几何1				99.52 216	99.50 291	99.22 246		99.26 360	95.66 444	98.60 402	99.28 369	97.67 295	99.89 217	95.95 418	99.32 377	99.45 270

旧先验1					99.49 296	99.29 226		99.26 360			99.39 341	97.67 295			99.36 371	99.46 269

无先验							98.01 410	99.23 367	95.83 441				99.85 285	95.79 424		99.44 282

原ACMM2							97.92 421

原ACMM1				99.37 270	99.47 307	98.87 300		99.27 358	96.74 430	98.26 418	99.32 360	97.93 277	99.82 329	95.96 417	99.38 368	99.43 288

test222					99.51 285	99.08 274	97.83 427	99.29 354	95.21 449	98.68 396	99.31 363	97.28 313			99.38 368	99.43 288

testdata2													99.89 217	95.99 415

segment_acmp												98.37 235

testdata				99.42 250	99.51 285	98.93 292		99.30 353	96.20 436	98.87 376	99.40 337	98.33 241	99.89 217	96.29 402	99.28 382	99.44 282

testdata1							97.72 430		97.86 387

test12				99.54 210	99.29 362	99.33 220		99.16 381		98.43 414		97.54 302	99.82 329		99.47 357	99.48 261

plane_prior7					99.58 243	99.38 207

plane_prior6					99.47 307	99.26 233						97.24 314

plane_prior5								99.54 275					99.82 329	95.84 422	99.78 251	99.60 193

plane_prior4											99.25 376

plane_prior3						99.31 223			98.36 345	99.14 347

plane_prior2							98.80 322		98.94 272

plane_prior1					99.51 285

plane_prior						99.24 240	98.42 374		97.87 385						99.71 283

n2								0.00 484

nn								0.00 484

door-mid								99.83 91

lessismore_v0				99.64 156	99.86 57	99.38 207		90.66 474		99.89 72	99.83 82	94.56 376	99.97 43	99.56 83	99.92 136	99.57 211

LGP-MVS_train				99.74 100	99.82 87	99.63 136		99.73 158	97.56 396	99.64 204	99.69 194	99.37 71	99.89 217	96.66 381	99.87 185	99.69 112

test11								99.29 354

door								99.77 135

HQP5-MVS						98.94 289

HQP-NCC					99.31 356		97.98 414		97.45 404	98.15 423

ACMP_Plane					99.31 356		97.98 414		97.45 404	98.15 423

BP-MVS														94.73 440

HQP4-MVS										98.15 423			99.70 394			99.53 234

HQP3-MVS								99.37 337							99.67 304

HQP2-MVS												96.67 333

NP-MVS					99.40 327	99.13 262					98.83 429

MDTV_nov1_ep13_2view						91.44 468	99.14 220		97.37 409	99.21 337		91.78 408		96.75 375		99.03 390

MDTV_nov1_ep13			97.73 373		98.70 448	90.83 471	99.15 217	98.02 438	98.51 330	98.82 381	99.61 258	90.98 415	99.66 423	96.89 367	98.92 409

ACMMP++_ref															99.94 120

ACMMP++															99.79 243

Test By Simon												98.41 229

ITE_SJBPF				99.38 267	99.63 225	99.44 187		99.73 158	98.56 323	99.33 311	99.53 302	98.88 158	99.68 413	96.01 412	99.65 309	99.02 395

DeepMVS_CX				97.98 410	99.69 201	96.95 410		99.26 360	75.51 472	95.74 468	98.28 451	96.47 341	99.62 435	91.23 459	97.89 455	97.38 464

High-resolution multi-view benchmark