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 16	100.00 1	99.85 29

Gipuma		99.03 79	99.16 61	98.64 213	99.94 2	98.51 111	99.32 26	99.75 42	99.58 38	98.60 262	99.62 40	98.22 103	99.51 391	97.70 185	99.73 176	97.89 424
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 29	99.31 41	99.53 39	99.91 3	98.98 72	99.63 7	99.58 85	99.44 52	99.78 39	99.76 15	96.39 243	99.92 64	99.44 54	99.92 68	99.68 70

pmmvs6		99.67 3	99.70 3	99.60 16	99.90 4	99.27 28	99.53 9	99.76 39	99.64 27	99.84 30	99.83 4	99.50 9	99.87 133	99.36 57	99.92 68	99.64 83

PS-MVSNAJss		99.46 17	99.49 16	99.35 79	99.90 4	98.15 138	99.20 48	99.65 67	99.48 44	99.92 8	99.71 22	98.07 117	99.96 14	99.53 47	100.00 1	99.93 11

testf1		99.25 41	99.16 61	99.51 49	99.89 6	99.63 4	98.71 104	99.69 54	98.90 132	99.43 104	99.35 103	98.86 34	99.67 317	97.81 174	99.81 127	99.24 272

APD_test2		99.25 41	99.16 61	99.51 49	99.89 6	99.63 4	98.71 104	99.69 54	98.90 132	99.43 104	99.35 103	98.86 34	99.67 317	97.81 174	99.81 127	99.24 272

ANet_high		99.57 10	99.67 6	99.28 95	99.89 6	98.09 145	99.14 57	99.93 5	99.82 8	99.93 6	99.81 8	99.17 20	99.94 42	99.31 61	100.00 1	99.82 35

anonymousdsp		99.51 14	99.47 21	99.62 10	99.88 9	99.08 70	99.34 23	99.69 54	98.93 128	99.65 63	99.72 21	98.93 32	99.95 26	99.11 77	100.00 1	99.82 35

v7n		99.53 12	99.57 13	99.41 69	99.88 9	98.54 109	99.45 14	99.61 76	99.66 24	99.68 57	99.66 32	98.44 77	99.95 26	99.73 27	99.96 28	99.75 59

mvs_tets		99.63 6	99.67 6	99.49 55	99.88 9	98.61 101	99.34 23	99.71 47	99.27 73	99.90 14	99.74 18	99.68 4	99.97 7	99.55 42	99.99 5	99.88 20

test_fmvsmconf0.01_n		99.57 10	99.63 10	99.36 73	99.87 12	98.13 141	98.08 185	99.95 1	99.45 50	99.98 2	99.75 16	99.80 1	99.97 7	99.82 12	99.99 5	99.99 2

jajsoiax		99.58 9	99.61 11	99.48 57	99.87 12	98.61 101	99.28 40	99.66 63	99.09 107	99.89 18	99.68 25	99.53 7	99.97 7	99.50 50	99.99 5	99.87 21

test_djsdf		99.52 13	99.51 15	99.53 39	99.86 14	98.74 91	99.39 20	99.56 99	99.11 97	99.70 51	99.73 20	99.00 27	99.97 7	99.26 65	99.98 12	99.89 16

MIMVSNet1		99.38 28	99.32 39	99.55 29	99.86 14	99.19 43	99.41 17	99.59 83	99.59 36	99.71 49	99.57 49	97.12 198	99.90 80	99.21 70	99.87 96	99.54 140

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 27	99.85 16	99.11 65	99.90 1	99.78 36	99.63 29	99.78 39	99.67 30	99.48 10	99.81 220	99.30 62	99.97 21	99.77 49
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
UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 17	99.34 20	99.69 5	99.58 85	99.90 3	99.86 24	99.78 13	99.58 6	99.95 26	99.00 87	99.95 38	99.78 46

SixPastTwentyTwo		98.75 127	98.62 140	99.16 117	99.83 18	97.96 165	99.28 40	98.20 371	99.37 60	99.70 51	99.65 36	92.65 349	99.93 53	99.04 84	99.84 110	99.60 99

sc_t1		99.62 7	99.66 8	99.53 39	99.82 19	99.09 69	99.50 11	99.63 71	99.88 4	99.86 24	99.80 11	99.03 24	99.89 96	99.48 52	99.93 55	99.60 99

Baseline_NR-MVSNet		98.98 87	98.86 105	99.36 73	99.82 19	98.55 106	97.47 289	99.57 92	99.37 60	99.21 157	99.61 43	96.76 225	99.83 191	98.06 152	99.83 117	99.71 62

pm-mvs1		99.44 19	99.48 18	99.33 88	99.80 21	98.63 98	99.29 36	99.63 71	99.30 70	99.65 63	99.60 45	99.16 22	99.82 203	99.07 80	99.83 117	99.56 127

TransMVSNet (Re)		99.44 19	99.47 21	99.36 73	99.80 21	98.58 104	99.27 42	99.57 92	99.39 58	99.75 44	99.62 40	99.17 20	99.83 191	99.06 82	99.62 234	99.66 77

K. test v3		98.00 243	97.66 268	99.03 144	99.79 23	97.56 201	99.19 52	92.47 457	99.62 32	99.52 86	99.66 32	89.61 380	99.96 14	99.25 67	99.81 127	99.56 127

test_fmvsmconf0.1_n		99.49 15	99.54 14	99.34 82	99.78 24	98.11 142	97.77 241	99.90 11	99.33 65	99.97 3	99.66 32	99.71 3	99.96 14	99.79 19	99.99 5	99.96 8

APD_test1		98.83 111	98.66 133	99.34 82	99.78 24	99.47 9	98.42 147	99.45 147	98.28 184	98.98 191	99.19 145	97.76 146	99.58 365	96.57 280	99.55 261	98.97 326

test_vis3_rt		99.14 61	99.17 59	99.07 134	99.78 24	98.38 118	98.92 82	99.94 2	97.80 227	99.91 12	99.67 30	97.15 197	98.91 450	99.76 23	99.56 257	99.92 12

EGC-MVSNET		85.24 436	80.54 439	99.34 82	99.77 27	99.20 40	99.08 61	99.29 227	12.08 475	20.84 476	99.42 88	97.55 165	99.85 155	97.08 229	99.72 184	98.96 328

Anonymous20240521		98.69 139	98.87 101	98.16 289	99.77 27	95.11 330	99.08 61	99.44 155	99.34 64	99.33 127	99.55 57	94.10 324	99.94 42	99.25 67	99.96 28	99.42 202

FC-MVSNet-test		99.27 38	99.25 52	99.34 82	99.77 27	98.37 120	99.30 35	99.57 92	99.61 34	99.40 113	99.50 67	97.12 198	99.85 155	99.02 86	99.94 49	99.80 41

test_vis1_n		98.31 207	98.50 160	97.73 323	99.76 30	94.17 358	98.68 107	99.91 9	96.31 341	99.79 38	99.57 49	92.85 345	99.42 411	99.79 19	99.84 110	99.60 99

test_fmvs3		99.12 68	99.41 26	98.25 277	99.76 30	95.07 331	99.05 67	99.94 2	97.78 230	99.82 33	99.84 3	98.56 68	99.71 293	99.96 1	99.96 28	99.97 4

XXY-MVS		99.14 61	99.15 66	99.10 127	99.76 30	97.74 190	98.85 92	99.62 73	98.48 167	99.37 118	99.49 73	98.75 46	99.86 142	98.20 142	99.80 138	99.71 62

TDRefinement		99.42 24	99.38 29	99.55 29	99.76 30	99.33 21	99.68 6	99.71 47	99.38 59	99.53 82	99.61 43	98.64 56	99.80 228	98.24 137	99.84 110	99.52 152

fmvsm_s_conf0.1_n_a		99.17 52	99.30 44	98.80 181	99.75 34	96.59 264	97.97 215	99.86 16	98.22 187	99.88 21	99.71 22	98.59 62	99.84 173	99.73 27	99.98 12	99.98 3

tt0805		98.69 139	98.62 140	98.90 169	99.75 34	99.30 23	99.15 56	96.97 408	98.86 137	98.87 224	97.62 386	98.63 58	98.96 447	99.41 56	98.29 399	98.45 390

test_vis1_n_1920		98.40 190	98.92 94	96.81 385	99.74 36	90.76 436	98.15 173	99.91 9	98.33 175	99.89 18	99.55 57	95.07 295	99.88 114	99.76 23	99.93 55	99.79 43

FOURS1					99.73 37	99.67 3	99.43 15	99.54 108	99.43 54	99.26 145

PEN-MVS		99.41 25	99.34 36	99.62 10	99.73 37	99.14 58	99.29 36	99.54 108	99.62 32	99.56 73	99.42 88	98.16 111	99.96 14	98.78 101	99.93 55	99.77 49

lessismore_v0				98.97 156	99.73 37	97.53 203		86.71 472		99.37 118	99.52 66	89.93 376	99.92 64	98.99 88	99.72 184	99.44 195

SteuartSystems-ACMMP		98.79 120	98.54 153	99.54 32	99.73 37	99.16 49	98.23 163	99.31 211	97.92 218	98.90 213	98.90 231	98.00 123	99.88 114	96.15 312	99.72 184	99.58 114
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 228	98.15 220	98.22 283	99.73 37	95.15 327	97.36 303	99.68 59	94.45 398	98.99 190	99.27 122	96.87 214	99.94 42	97.13 226	99.91 77	99.57 121

Vis-MVSNet		99.34 30	99.36 33	99.27 98	99.73 37	98.26 127	99.17 53	99.78 36	99.11 97	99.27 141	99.48 74	98.82 37	99.95 26	98.94 91	99.93 55	99.59 106
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
tt0320-xc		99.64 5	99.68 5	99.50 54	99.72 43	98.98 72	99.51 10	99.85 18	99.86 6	99.88 21	99.82 5	99.02 26	99.90 80	99.54 43	99.95 38	99.61 97

SSC-MVS		98.71 131	98.74 116	98.62 219	99.72 43	96.08 288	98.74 97	98.64 351	99.74 13	99.67 59	99.24 135	94.57 310	99.95 26	99.11 77	99.24 323	99.82 35

test_f		98.67 147	98.87 101	98.05 298	99.72 43	95.59 303	98.51 131	99.81 31	96.30 343	99.78 39	99.82 5	96.14 254	98.63 457	99.82 12	99.93 55	99.95 9

ACMH	96.65 7	99.25 41	99.24 53	99.26 100	99.72 43	98.38 118	99.07 64	99.55 103	98.30 179	99.65 63	99.45 83	99.22 17	99.76 264	98.44 127	99.77 155	99.64 83
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0320		99.61 8	99.65 9	99.48 57	99.71 47	98.94 79	99.54 8	99.83 25	99.87 5	99.89 18	99.82 5	98.75 46	99.90 80	99.54 43	99.95 38	99.59 106

fmvsm_s_conf0.1_n		99.16 56	99.33 37	98.64 213	99.71 47	96.10 283	97.87 227	99.85 18	98.56 163	99.90 14	99.68 25	98.69 52	99.85 155	99.72 29	99.98 12	99.97 4

PS-CasMVS		99.40 26	99.33 37	99.62 10	99.71 47	99.10 66	99.29 36	99.53 112	99.53 41	99.46 99	99.41 92	98.23 100	99.95 26	98.89 95	99.95 38	99.81 39

DTE-MVSNet		99.43 23	99.35 34	99.66 7	99.71 47	99.30 23	99.31 30	99.51 118	99.64 27	99.56 73	99.46 79	98.23 100	99.97 7	98.78 101	99.93 55	99.72 61

WR-MVS_H		99.33 31	99.22 54	99.65 8	99.71 47	99.24 31	99.32 26	99.55 103	99.46 49	99.50 92	99.34 107	97.30 187	99.93 53	98.90 93	99.93 55	99.77 49

HPM-MVS_fast		99.01 81	98.82 109	99.57 22	99.71 47	99.35 17	99.00 72	99.50 121	97.33 275	98.94 208	98.86 241	98.75 46	99.82 203	97.53 197	99.71 193	99.56 127

ACMH+	96.62 9	99.08 75	99.00 86	99.33 88	99.71 47	98.83 86	98.60 117	99.58 85	99.11 97	99.53 82	99.18 149	98.81 38	99.67 317	96.71 267	99.77 155	99.50 158

PMVS	91.26 20	97.86 257	97.94 244	97.65 330	99.71 47	97.94 167	98.52 126	98.68 347	98.99 120	97.52 355	99.35 103	97.41 180	98.18 463	91.59 426	99.67 214	96.82 452
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
KinetiMVS		99.03 79	99.02 82	99.03 144	99.70 55	97.48 206	98.43 144	99.29 227	99.70 16	99.60 70	99.07 178	96.13 255	99.94 42	99.42 55	99.87 96	99.68 70

FIs		99.14 61	99.09 74	99.29 94	99.70 55	98.28 126	99.13 58	99.52 117	99.48 44	99.24 151	99.41 92	96.79 222	99.82 203	98.69 111	99.88 92	99.76 55

VPNet		98.87 102	98.83 108	99.01 148	99.70 55	97.62 199	98.43 144	99.35 192	99.47 47	99.28 139	99.05 186	96.72 228	99.82 203	98.09 149	99.36 302	99.59 106

fmvsm_s_conf0.1_n_2		99.20 50	99.38 29	98.65 211	99.69 58	96.08 288	97.49 286	99.90 11	99.53 41	99.88 21	99.64 37	98.51 71	99.90 80	99.83 10	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 204	98.68 130	97.27 361	99.69 58	92.29 410	98.03 196	99.85 18	97.62 240	99.96 4	99.62 40	93.98 325	99.74 277	99.52 49	99.86 103	99.79 43

MP-MVS-pluss		98.57 164	98.23 208	99.60 16	99.69 58	99.35 17	97.16 324	99.38 178	94.87 388	98.97 195	98.99 208	98.01 122	99.88 114	97.29 213	99.70 200	99.58 114
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 46	99.32 39	98.96 157	99.68 61	97.35 214	98.84 94	99.48 130	99.69 18	99.63 66	99.68 25	99.03 24	99.96 14	97.97 162	99.92 68	99.57 121

sd_testset		99.28 37	99.31 41	99.19 111	99.68 61	98.06 154	99.41 17	99.30 219	99.69 18	99.63 66	99.68 25	99.25 16	99.96 14	97.25 216	99.92 68	99.57 121

test_fmvs1_n		98.09 234	98.28 199	97.52 347	99.68 61	93.47 389	98.63 113	99.93 5	95.41 376	99.68 57	99.64 37	91.88 359	99.48 398	99.82 12	99.87 96	99.62 89

CHOSEN 1792x2688		97.49 286	97.14 301	98.54 241	99.68 61	96.09 286	96.50 360	99.62 73	91.58 436	98.84 227	98.97 215	92.36 351	99.88 114	96.76 260	99.95 38	99.67 75

tfpnnormal		98.90 98	98.90 96	98.91 166	99.67 65	97.82 182	99.00 72	99.44 155	99.45 50	99.51 91	99.24 135	98.20 106	99.86 142	95.92 321	99.69 203	99.04 313

MTAPA		98.88 101	98.64 136	99.61 14	99.67 65	99.36 16	98.43 144	99.20 251	98.83 141	98.89 216	98.90 231	96.98 208	99.92 64	97.16 221	99.70 200	99.56 127

test_fmvsmvis_n_1920		99.26 40	99.49 16	98.54 241	99.66 67	96.97 244	98.00 203	99.85 18	99.24 75	99.92 8	99.50 67	99.39 12	99.95 26	99.89 3	99.98 12	98.71 367

mvs5depth		99.30 34	99.59 12	98.44 255	99.65 68	95.35 319	99.82 3	99.94 2	99.83 7	99.42 108	99.94 2	98.13 114	99.96 14	99.63 35	99.96 28	100.00 1

fmvsm_l_conf0.5_n_a		99.19 51	99.27 47	98.94 160	99.65 68	97.05 239	97.80 236	99.76 39	98.70 146	99.78 39	99.11 168	98.79 42	99.95 26	99.85 6	99.96 28	99.83 32

WB-MVS		98.52 178	98.55 151	98.43 256	99.65 68	95.59 303	98.52 126	98.77 336	99.65 26	99.52 86	99.00 206	94.34 316	99.93 53	98.65 113	98.83 371	99.76 55

CP-MVSNet		99.21 48	99.09 74	99.56 27	99.65 68	98.96 78	99.13 58	99.34 198	99.42 55	99.33 127	99.26 128	97.01 206	99.94 42	98.74 106	99.93 55	99.79 43

HPM-MVS		98.79 120	98.53 155	99.59 20	99.65 68	99.29 25	99.16 54	99.43 161	96.74 321	98.61 260	98.38 331	98.62 59	99.87 133	96.47 292	99.67 214	99.59 106
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 156	98.36 186	99.42 67	99.65 68	99.42 11	98.55 122	99.57 92	97.72 234	98.90 213	99.26 128	96.12 257	99.52 386	95.72 332	99.71 193	99.32 249

NormalMVS		98.26 214	97.97 241	99.15 120	99.64 74	97.83 177	98.28 157	99.43 161	99.24 75	98.80 235	98.85 244	89.76 378	99.94 42	98.04 154	99.67 214	99.68 70

lecture		99.25 41	99.12 69	99.62 10	99.64 74	99.40 12	98.89 87	99.51 118	99.19 87	99.37 118	99.25 133	98.36 82	99.88 114	98.23 139	99.67 214	99.59 106

fmvsm_l_conf0.5_n		99.21 48	99.28 46	99.02 147	99.64 74	97.28 221	97.82 232	99.76 39	98.73 143	99.82 33	99.09 176	98.81 38	99.95 26	99.86 4	99.96 28	99.83 32

test_fmvsmconf_n		99.44 19	99.48 18	99.31 93	99.64 74	98.10 144	97.68 255	99.84 22	99.29 71	99.92 8	99.57 49	99.60 5	99.96 14	99.74 26	99.98 12	99.89 16

TSAR-MVS + MP.		98.63 153	98.49 165	99.06 140	99.64 74	97.90 171	98.51 131	98.94 301	96.96 306	99.24 151	98.89 237	97.83 138	99.81 220	96.88 250	99.49 282	99.48 176
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 114	98.72 120	99.12 123	99.64 74	98.54 109	97.98 211	99.68 59	97.62 240	99.34 125	99.18 149	97.54 167	99.77 258	97.79 176	99.74 173	99.04 313

Elysia		99.15 57	99.14 67	99.18 112	99.63 80	97.92 168	98.50 133	99.43 161	99.67 21	99.70 51	99.13 164	96.66 231	99.98 4	99.54 43	99.96 28	99.64 83

StellarMVS		99.15 57	99.14 67	99.18 112	99.63 80	97.92 168	98.50 133	99.43 161	99.67 21	99.70 51	99.13 164	96.66 231	99.98 4	99.54 43	99.96 28	99.64 83

KD-MVS_self_test		99.25 41	99.18 58	99.44 65	99.63 80	99.06 71	98.69 106	99.54 108	99.31 68	99.62 69	99.53 63	97.36 184	99.86 142	99.24 69	99.71 193	99.39 215

EU-MVSNet		97.66 274	98.50 160	95.13 427	99.63 80	85.84 458	98.35 153	98.21 370	98.23 186	99.54 78	99.46 79	95.02 296	99.68 313	98.24 137	99.87 96	99.87 21

HyFIR lowres test		97.19 312	96.60 336	98.96 157	99.62 84	97.28 221	95.17 425	99.50 121	94.21 403	99.01 187	98.32 339	86.61 398	99.99 2	97.10 228	99.84 110	99.60 99

fmvsm_l_conf0.5_n_9		99.32 33	99.43 24	98.98 154	99.59 85	97.18 232	97.44 293	99.83 25	99.56 39	99.91 12	99.34 107	99.36 13	99.93 53	99.83 10	99.98 12	99.85 29

fmvsm_l_conf0.5_n_3		99.45 18	99.48 18	99.34 82	99.59 85	98.21 135	97.82 232	99.84 22	99.41 57	99.92 8	99.41 92	99.51 8	99.95 26	99.84 9	99.97 21	99.87 21

MED-MVS test				99.45 64	99.58 87	98.93 80	98.68 107	99.60 77	96.46 334	99.53 82	98.77 264		99.83 191	96.67 270	99.64 225	99.58 114

TestfortrainingZip a		98.95 91	98.72 120	99.64 9	99.58 87	99.32 22	98.68 107	99.60 77	96.46 334	99.53 82	98.77 264	97.87 136	99.83 191	98.39 130	99.64 225	99.77 49

FE-MVSNET		98.59 161	98.50 160	98.87 170	99.58 87	97.30 219	98.08 185	99.74 43	96.94 308	98.97 195	99.10 171	96.94 210	99.74 277	97.33 211	99.86 103	99.55 134

mmtdpeth		99.30 34	99.42 25	98.92 165	99.58 87	96.89 251	99.48 13	99.92 7	99.92 2	98.26 298	99.80 11	98.33 88	99.91 73	99.56 40	99.95 38	99.97 4

ACMMP_NAP		98.75 127	98.48 166	99.57 22	99.58 87	99.29 25	97.82 232	99.25 240	96.94 308	98.78 237	99.12 167	98.02 121	99.84 173	97.13 226	99.67 214	99.59 106

nrg030		99.40 26	99.35 34	99.54 32	99.58 87	99.13 61	98.98 75	99.48 130	99.68 20	99.46 99	99.26 128	98.62 59	99.73 284	99.17 74	99.92 68	99.76 55

VDDNet		98.21 221	97.95 242	99.01 148	99.58 87	97.74 190	99.01 70	97.29 399	99.67 21	98.97 195	99.50 67	90.45 373	99.80 228	97.88 169	99.20 331	99.48 176

COLMAP_ROB	96.50 10	98.99 84	98.85 107	99.41 69	99.58 87	99.10 66	98.74 97	99.56 99	99.09 107	99.33 127	99.19 145	98.40 79	99.72 292	95.98 319	99.76 168	99.42 202
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_fmvsm_n_1920		99.33 31	99.45 23	98.99 150	99.57 95	97.73 192	97.93 216	99.83 25	99.22 78	99.93 6	99.30 116	99.42 11	99.96 14	99.85 6	99.99 5	99.29 258

ZNCC-MVS		98.68 144	98.40 178	99.54 32	99.57 95	99.21 34	98.46 141	99.29 227	97.28 281	98.11 310	98.39 329	98.00 123	99.87 133	96.86 253	99.64 225	99.55 134

MSP-MVS		98.40 190	98.00 236	99.61 14	99.57 95	99.25 30	98.57 120	99.35 192	97.55 251	99.31 135	97.71 379	94.61 309	99.88 114	96.14 313	99.19 334	99.70 67
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
testgi		98.32 205	98.39 181	98.13 290	99.57 95	95.54 306	97.78 238	99.49 128	97.37 272	99.19 159	97.65 383	98.96 29	99.49 395	96.50 291	98.99 359	99.34 240

MP-MVS		98.46 184	98.09 225	99.54 32	99.57 95	99.22 33	98.50 133	99.19 255	97.61 243	97.58 349	98.66 291	97.40 181	99.88 114	94.72 358	99.60 241	99.54 140
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 131	98.46 170	99.47 61	99.57 95	98.97 74	98.23 163	99.48 130	96.60 326	99.10 169	99.06 179	98.71 50	99.83 191	95.58 339	99.78 149	99.62 89

LGP-MVS_train				99.47 61	99.57 95	98.97 74		99.48 130	96.60 326	99.10 169	99.06 179	98.71 50	99.83 191	95.58 339	99.78 149	99.62 89

IS-MVSNet		98.19 224	97.90 250	99.08 132	99.57 95	97.97 162	99.31 30	98.32 366	99.01 119	98.98 191	99.03 190	91.59 361	99.79 241	95.49 341	99.80 138	99.48 176

viewdifsd2359ckpt11		98.84 108	99.04 79	98.24 279	99.56 103	95.51 308	97.38 298	99.70 52	99.16 92	99.57 71	99.40 95	98.26 96	99.71 293	98.55 122	99.82 121	99.50 158

viewmsd2359difaftdt		98.84 108	99.04 79	98.24 279	99.56 103	95.51 308	97.38 298	99.70 52	99.16 92	99.57 71	99.40 95	98.26 96	99.71 293	98.55 122	99.82 121	99.50 158

dcpmvs_2		98.78 122	99.11 70	97.78 313	99.56 103	93.67 384	99.06 65	99.86 16	99.50 43	99.66 60	99.26 128	97.21 195	99.99 2	98.00 159	99.91 77	99.68 70

test_0402		98.76 126	98.71 124	98.93 162	99.56 103	98.14 140	98.45 143	99.34 198	99.28 72	98.95 201	98.91 228	98.34 87	99.79 241	95.63 336	99.91 77	98.86 345

EPP-MVSNet		98.30 208	98.04 232	99.07 134	99.56 103	97.83 177	99.29 36	98.07 377	99.03 117	98.59 264	99.13 164	92.16 355	99.90 80	96.87 251	99.68 208	99.49 165

ACMMP		98.75 127	98.50 160	99.52 45	99.56 103	99.16 49	98.87 88	99.37 182	97.16 296	98.82 231	99.01 202	97.71 149	99.87 133	96.29 304	99.69 203	99.54 140
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
fmvsm_s_conf0.5_n_a		99.10 70	99.20 57	98.78 187	99.55 109	96.59 264	97.79 237	99.82 30	98.21 189	99.81 36	99.53 63	98.46 75	99.84 173	99.70 32	99.97 21	99.90 15

fmvsm_s_conf0.5_n		99.09 71	99.26 50	98.61 222	99.55 109	96.09 286	97.74 248	99.81 31	98.55 164	99.85 27	99.55 57	98.60 61	99.84 173	99.69 34	99.98 12	99.89 16

FMVSNet1		99.17 52	99.17 59	99.17 114	99.55 109	98.24 129	99.20 48	99.44 155	99.21 80	99.43 104	99.55 57	97.82 141	99.86 142	98.42 129	99.89 90	99.41 205

Vis-MVSNet (Re-imp)		97.46 288	97.16 298	98.34 268	99.55 109	96.10 283	98.94 80	98.44 360	98.32 177	98.16 304	98.62 300	88.76 385	99.73 284	93.88 384	99.79 144	99.18 292

ACMM	96.08 12	98.91 96	98.73 118	99.48 57	99.55 109	99.14 58	98.07 189	99.37 182	97.62 240	99.04 183	98.96 218	98.84 36	99.79 241	97.43 206	99.65 223	99.49 165
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 136	98.97 90	97.89 306	99.54 114	94.05 361	98.55 122	99.92 7	96.78 319	99.72 47	99.78 13	96.60 235	99.67 317	99.91 2	99.90 84	99.94 10

mPP-MVS		98.64 151	98.34 189	99.54 32	99.54 114	99.17 45	98.63 113	99.24 245	97.47 259	98.09 312	98.68 286	97.62 158	99.89 96	96.22 307	99.62 234	99.57 121

XVG-ACMP-BASELINE		98.56 165	98.34 189	99.22 108	99.54 114	98.59 103	97.71 251	99.46 143	97.25 284	98.98 191	98.99 208	97.54 167	99.84 173	95.88 322	99.74 173	99.23 274

viewmacassd2359aftdt		98.86 105	98.87 101	98.83 175	99.53 117	97.32 218	97.70 253	99.64 69	98.22 187	99.25 149	99.27 122	98.40 79	99.61 351	97.98 161	99.87 96	99.55 134

region2R		98.69 139	98.40 178	99.54 32	99.53 117	99.17 45	98.52 126	99.31 211	97.46 264	98.44 283	98.51 314	97.83 138	99.88 114	96.46 293	99.58 250	99.58 114

PGM-MVS		98.66 148	98.37 185	99.55 29	99.53 117	99.18 44	98.23 163	99.49 128	97.01 305	98.69 248	98.88 238	98.00 123	99.89 96	95.87 325	99.59 245	99.58 114

Patchmatch-RL test		97.26 305	97.02 306	97.99 302	99.52 120	95.53 307	96.13 385	99.71 47	97.47 259	99.27 141	99.16 155	84.30 419	99.62 344	97.89 166	99.77 155	98.81 353

ACMMPR		98.70 136	98.42 176	99.54 32	99.52 120	99.14 58	98.52 126	99.31 211	97.47 259	98.56 270	98.54 309	97.75 147	99.88 114	96.57 280	99.59 245	99.58 114

fmvsm_s_conf0.5_n_9		99.17 52	99.38 29	98.53 243	99.51 122	95.82 298	97.62 266	99.78 36	99.72 15	99.90 14	99.48 74	98.66 54	99.89 96	99.85 6	99.93 55	99.89 16

AstraMVS		98.16 230	98.07 230	98.41 258	99.51 122	95.86 295	98.00 203	95.14 440	98.97 123	99.43 104	99.24 135	93.25 333	99.84 173	99.21 70	99.87 96	99.54 140

fmvsm_s_conf0.5_n_8		99.13 65	99.26 50	98.74 200	99.51 122	96.44 275	97.65 261	99.65 67	99.66 24	99.78 39	99.48 74	97.92 131	99.93 53	99.72 29	99.95 38	99.87 21

GST-MVS		98.61 157	98.30 196	99.52 45	99.51 122	99.20 40	98.26 161	99.25 240	97.44 267	98.67 251	98.39 329	97.68 150	99.85 155	96.00 317	99.51 272	99.52 152

Anonymous20231206		98.21 221	98.21 209	98.20 284	99.51 122	95.43 317	98.13 175	99.32 206	96.16 347	98.93 209	98.82 254	96.00 262	99.83 191	97.32 212	99.73 176	99.36 233

ACMP	95.32 15	98.41 188	98.09 225	99.36 73	99.51 122	98.79 89	97.68 255	99.38 178	95.76 363	98.81 233	98.82 254	98.36 82	99.82 203	94.75 355	99.77 155	99.48 176
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LuminaMVS		98.39 196	98.20 210	98.98 154	99.50 128	97.49 204	97.78 238	97.69 386	98.75 142	99.49 93	99.25 133	92.30 353	99.94 42	99.14 75	99.88 92	99.50 158

DVP-MVS		98.77 125	98.52 156	99.52 45	99.50 128	99.21 34	98.02 199	98.84 325	97.97 212	99.08 171	99.02 191	97.61 160	99.88 114	96.99 237	99.63 231	99.48 176
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_0728_SECOND				99.60 16	99.50 128	99.23 32	98.02 199	99.32 206					99.88 114	96.99 237	99.63 231	99.68 70

test0726					99.50 128	99.21 34	98.17 171	99.35 192	97.97 212	99.26 145	99.06 179	97.61 160

AllTest		98.44 186	98.20 210	99.16 117	99.50 128	98.55 106	98.25 162	99.58 85	96.80 317	98.88 220	99.06 179	97.65 153	99.57 367	94.45 365	99.61 239	99.37 226

TestCases				99.16 117	99.50 128	98.55 106		99.58 85	96.80 317	98.88 220	99.06 179	97.65 153	99.57 367	94.45 365	99.61 239	99.37 226

XVG-OURS		98.53 174	98.34 189	99.11 125	99.50 128	98.82 88	95.97 391	99.50 121	97.30 279	99.05 181	98.98 213	99.35 14	99.32 425	95.72 332	99.68 208	99.18 292

EG-PatchMatch MVS		98.99 84	99.01 84	98.94 160	99.50 128	97.47 207	98.04 194	99.59 83	98.15 204	99.40 113	99.36 102	98.58 67	99.76 264	98.78 101	99.68 208	99.59 106

fmvsm_s_conf0.5_n_2		99.14 61	99.31 41	98.63 217	99.49 136	96.08 288	97.38 298	99.81 31	99.48 44	99.84 30	99.57 49	98.46 75	99.89 96	99.82 12	99.97 21	99.91 13

SED-MVS		98.91 96	98.72 120	99.49 55	99.49 136	99.17 45	98.10 182	99.31 211	98.03 208	99.66 60	99.02 191	98.36 82	99.88 114	96.91 243	99.62 234	99.41 205

IU-MVS					99.49 136	99.15 53		98.87 316	92.97 421	99.41 110				96.76 260	99.62 234	99.66 77

test_241102_ONE					99.49 136	99.17 45		99.31 211	97.98 211	99.66 60	98.90 231	98.36 82	99.48 398

UA-Net		99.47 16	99.40 27	99.70 2	99.49 136	99.29 25	99.80 4	99.72 45	99.82 8	99.04 183	99.81 8	98.05 120	99.96 14	98.85 97	99.99 5	99.86 27

HFP-MVS		98.71 131	98.44 173	99.51 49	99.49 136	99.16 49	98.52 126	99.31 211	97.47 259	98.58 266	98.50 318	97.97 127	99.85 155	96.57 280	99.59 245	99.53 149

VPA-MVSNet		99.30 34	99.30 44	99.28 95	99.49 136	98.36 123	99.00 72	99.45 147	99.63 29	99.52 86	99.44 84	98.25 98	99.88 114	99.09 79	99.84 110	99.62 89

XVG-OURS-SEG-HR		98.49 181	98.28 199	99.14 121	99.49 136	98.83 86	96.54 356	99.48 130	97.32 277	99.11 166	98.61 302	99.33 15	99.30 428	96.23 306	98.38 395	99.28 261

114514_t		96.50 345	95.77 354	98.69 206	99.48 144	97.43 211	97.84 231	99.55 103	81.42 468	96.51 408	98.58 306	95.53 282	99.67 317	93.41 397	99.58 250	98.98 323

IterMVS-LS		98.55 169	98.70 127	98.09 291	99.48 144	94.73 341	97.22 318	99.39 176	98.97 123	99.38 116	99.31 115	96.00 262	99.93 53	98.58 116	99.97 21	99.60 99
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
fmvsm_s_conf0.5_n_10		99.15 57	99.27 47	98.78 187	99.47 146	96.56 269	97.75 247	99.71 47	99.60 35	99.74 46	99.44 84	97.96 128	99.95 26	99.86 4	99.94 49	99.82 35

fmvsm_s_conf0.5_n_5		99.07 77	99.10 72	98.99 150	99.47 146	97.22 226	97.40 295	99.83 25	97.61 243	99.85 27	99.30 116	98.80 40	99.95 26	99.71 31	99.90 84	99.78 46

v8		99.01 81	99.16 61	98.57 229	99.47 146	96.31 280	98.90 83	99.47 139	99.03 117	99.52 86	99.57 49	96.93 211	99.81 220	99.60 36	99.98 12	99.60 99

SSC-MVS3.2		98.53 174	98.79 112	97.74 320	99.46 149	93.62 387	96.45 362	99.34 198	99.33 65	98.93 209	98.70 282	97.90 132	99.90 80	99.12 76	99.92 68	99.69 69

fmvsm_s_conf0.5_n_3		99.22 47	99.37 32	98.78 187	99.46 149	96.58 267	97.65 261	99.72 45	99.47 47	99.86 24	99.50 67	98.94 30	99.89 96	99.75 25	99.97 21	99.86 27

XVS		98.72 130	98.45 171	99.53 39	99.46 149	99.21 34	98.65 111	99.34 198	98.62 153	97.54 353	98.63 298	97.50 173	99.83 191	96.79 256	99.53 267	99.56 127

X-MVStestdata		94.32 394	92.59 413	99.53 39	99.46 149	99.21 34	98.65 111	99.34 198	98.62 153	97.54 353	45.85 473	97.50 173	99.83 191	96.79 256	99.53 267	99.56 127

test20.03		98.78 122	98.77 115	98.78 187	99.46 149	97.20 229	97.78 238	99.24 245	99.04 116	99.41 110	98.90 231	97.65 153	99.76 264	97.70 185	99.79 144	99.39 215

guyue		98.01 242	97.93 246	98.26 275	99.45 154	95.48 312	98.08 185	96.24 423	98.89 134	99.34 125	99.14 162	91.32 365	99.82 203	99.07 80	99.83 117	99.48 176

CSCG		98.68 144	98.50 160	99.20 109	99.45 154	98.63 98	98.56 121	99.57 92	97.87 222	98.85 225	98.04 360	97.66 152	99.84 173	96.72 265	99.81 127	99.13 302

GeoE		99.05 78	98.99 88	99.25 103	99.44 156	98.35 124	98.73 101	99.56 99	98.42 170	98.91 212	98.81 257	98.94 30	99.91 73	98.35 132	99.73 176	99.49 165

v148		98.45 185	98.60 145	98.00 301	99.44 156	94.98 333	97.44 293	99.06 281	98.30 179	99.32 133	98.97 215	96.65 233	99.62 344	98.37 131	99.85 105	99.39 215

v10		98.97 88	99.11 70	98.55 236	99.44 156	96.21 282	98.90 83	99.55 103	98.73 143	99.48 94	99.60 45	96.63 234	99.83 191	99.70 32	99.99 5	99.61 97

V42		98.78 122	98.78 114	98.76 194	99.44 156	97.04 240	98.27 160	99.19 255	97.87 222	99.25 149	99.16 155	96.84 215	99.78 252	99.21 70	99.84 110	99.46 186

MDA-MVSNet-bldmvs		97.94 248	97.91 249	98.06 296	99.44 156	94.96 334	96.63 352	99.15 271	98.35 173	98.83 228	99.11 168	94.31 317	99.85 155	96.60 277	98.72 377	99.37 226

viewdifsd2359ckpt07		98.71 131	98.86 105	98.26 275	99.43 161	95.65 302	97.20 319	99.66 63	99.20 82	99.29 137	99.01 202	98.29 91	99.73 284	97.92 165	99.75 172	99.39 215

casdiffmvs_mvg		99.12 68	99.16 61	98.99 150	99.43 161	97.73 192	98.00 203	99.62 73	99.22 78	99.55 76	99.22 141	98.93 32	99.75 272	98.66 112	99.81 127	99.50 158
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SSM_0404		98.90 98	99.01 84	98.57 229	99.42 163	96.59 264	98.13 175	99.66 63	99.09 107	99.30 136	99.02 191	98.79 42	99.89 96	97.87 171	99.80 138	99.23 274

test1111		96.49 346	96.82 320	95.52 420	99.42 163	87.08 455	99.22 45	87.14 471	99.11 97	99.46 99	99.58 47	88.69 386	99.86 142	98.80 99	99.95 38	99.62 89

v2v482		98.56 165	98.62 140	98.37 265	99.42 163	95.81 299	97.58 274	99.16 266	97.90 220	99.28 139	99.01 202	95.98 267	99.79 241	99.33 59	99.90 84	99.51 155

OPM-MVS		98.56 165	98.32 194	99.25 103	99.41 166	98.73 94	97.13 326	99.18 259	97.10 299	98.75 243	98.92 226	98.18 107	99.65 335	96.68 269	99.56 257	99.37 226
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 236	98.08 228	98.04 299	99.41 166	94.59 347	94.59 443	99.40 174	97.50 256	98.82 231	98.83 251	96.83 217	99.84 173	97.50 200	99.81 127	99.71 62

test_one_0601					99.39 168	99.20 40		99.31 211	98.49 166	98.66 253	99.02 191	97.64 156

mvsany_test3		98.87 102	98.92 94	98.74 200	99.38 169	96.94 248	98.58 119	99.10 276	96.49 331	99.96 4	99.81 8	98.18 107	99.45 406	98.97 89	99.79 144	99.83 32

patch_mono-2		98.51 179	98.63 138	98.17 287	99.38 169	94.78 338	97.36 303	99.69 54	98.16 199	98.49 279	99.29 119	97.06 201	99.97 7	98.29 136	99.91 77	99.76 55

test2506		92.39 425	91.89 427	93.89 441	99.38 169	82.28 472	99.32 26	66.03 479	99.08 111	98.77 240	99.57 49	66.26 466	99.84 173	98.71 109	99.95 38	99.54 140

ECVR-MVS		96.42 348	96.61 334	95.85 412	99.38 169	88.18 450	99.22 45	86.00 473	99.08 111	99.36 121	99.57 49	88.47 391	99.82 203	98.52 124	99.95 38	99.54 140

casdiffmvs		98.95 91	99.00 86	98.81 179	99.38 169	97.33 216	97.82 232	99.57 92	99.17 91	99.35 123	99.17 153	98.35 86	99.69 304	98.46 126	99.73 176	99.41 205
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		98.96 90	99.02 82	98.76 194	99.38 169	97.26 223	98.49 136	99.50 121	98.86 137	99.19 159	99.06 179	98.23 100	99.69 304	98.71 109	99.76 168	99.33 246

TranMVSNet+NR-MVSNet		99.17 52	99.07 77	99.46 63	99.37 175	98.87 84	98.39 149	99.42 167	99.42 55	99.36 121	99.06 179	98.38 81	99.95 26	98.34 133	99.90 84	99.57 121

fmvsm_s_conf0.5_n_6		99.08 75	99.21 56	98.69 206	99.36 176	96.51 270	97.62 266	99.68 59	98.43 169	99.85 27	99.10 171	99.12 23	99.88 114	99.77 22	99.92 68	99.67 75

tttt0517		95.64 373	94.98 383	97.64 333	99.36 176	93.81 379	98.72 102	90.47 465	98.08 207	98.67 251	98.34 336	73.88 452	99.92 64	97.77 178	99.51 272	99.20 284

test_part2					99.36 176	99.10 66				99.05 181

v1144		98.60 159	98.66 133	98.41 258	99.36 176	95.90 293	97.58 274	99.34 198	97.51 255	99.27 141	99.15 159	96.34 248	99.80 228	99.47 53	99.93 55	99.51 155

CP-MVS		98.70 136	98.42 176	99.52 45	99.36 176	99.12 63	98.72 102	99.36 186	97.54 253	98.30 292	98.40 328	97.86 137	99.89 96	96.53 289	99.72 184	99.56 127

diffmvs_AUTHOR		98.50 180	98.59 147	98.23 282	99.35 181	95.48 312	96.61 353	99.60 77	98.37 171	98.90 213	99.00 206	97.37 183	99.76 264	98.22 140	99.85 105	99.46 186

Test_1112_low_res		96.99 327	96.55 338	98.31 271	99.35 181	95.47 315	95.84 403	99.53 112	91.51 438	96.80 395	98.48 321	91.36 364	99.83 191	96.58 278	99.53 267	99.62 89

DeepC-MVS	97.60 4	98.97 88	98.93 93	99.10 127	99.35 181	97.98 161	98.01 202	99.46 143	97.56 249	99.54 78	99.50 67	98.97 28	99.84 173	98.06 152	99.92 68	99.49 165
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 304	96.86 316	98.58 226	99.34 184	96.32 279	96.75 345	99.58 85	93.14 419	96.89 390	97.48 393	92.11 356	99.86 142	96.91 243	99.54 263	99.57 121

reproduce_model		99.15 57	98.97 90	99.67 4	99.33 185	99.44 10	98.15 173	99.47 139	99.12 96	99.52 86	99.32 114	98.31 89	99.90 80	97.78 177	99.73 176	99.66 77

MVSMamba_PlusPlus		98.83 111	98.98 89	98.36 266	99.32 186	96.58 267	98.90 83	99.41 171	99.75 11	98.72 246	99.50 67	96.17 253	99.94 42	99.27 64	99.78 149	98.57 383

fmvsm_s_conf0.5_n_4		99.01 81	99.22 54	98.38 262	99.31 187	95.48 312	97.56 276	99.73 44	98.87 135	99.75 44	99.27 122	98.80 40	99.86 142	99.80 17	99.90 84	99.81 39

SF-MVS		98.53 174	98.27 202	99.32 90	99.31 187	98.75 90	98.19 167	99.41 171	96.77 320	98.83 228	98.90 231	97.80 143	99.82 203	95.68 335	99.52 270	99.38 224

CPTT-MVS		97.84 263	97.36 287	99.27 98	99.31 187	98.46 114	98.29 156	99.27 234	94.90 387	97.83 333	98.37 332	94.90 298	99.84 173	93.85 386	99.54 263	99.51 155

UnsupCasMVSNet_eth		97.89 252	97.60 273	98.75 196	99.31 187	97.17 234	97.62 266	99.35 192	98.72 145	98.76 242	98.68 286	92.57 350	99.74 277	97.76 182	95.60 457	99.34 240

fmvsm_s_conf0.5_n_7		98.83 111	99.04 79	98.20 284	99.30 191	94.83 336	97.23 314	99.36 186	98.64 148	99.84 30	99.43 87	98.10 116	99.91 73	99.56 40	99.96 28	99.87 21

pmmvs-eth3d		98.47 183	98.34 189	98.86 172	99.30 191	97.76 188	97.16 324	99.28 231	95.54 369	99.42 108	99.19 145	97.27 190	99.63 341	97.89 166	99.97 21	99.20 284

mamv4		99.44 19	99.39 28	99.58 21	99.30 191	99.74 2	99.04 68	99.81 31	99.77 10	99.82 33	99.57 49	97.82 141	99.98 4	99.53 47	99.89 90	99.01 317

viewcassd2359sk11		98.55 169	98.51 157	98.67 209	99.29 194	96.99 243	97.39 296	99.54 108	97.73 232	98.81 233	99.08 177	97.55 165	99.66 328	97.52 199	99.67 214	99.36 233

SymmetryMVS		98.05 238	97.71 263	99.09 131	99.29 194	97.83 177	98.28 157	97.64 391	99.24 75	98.80 235	98.85 244	89.76 378	99.94 42	98.04 154	99.50 280	99.49 165

Anonymous20231211		99.27 38	99.27 47	99.26 100	99.29 194	98.18 136	99.49 12	99.51 118	99.70 16	99.80 37	99.68 25	96.84 215	99.83 191	99.21 70	99.91 77	99.77 49

viewmanbaseed2359cas		98.58 163	98.54 153	98.70 204	99.28 197	97.13 238	97.47 289	99.55 103	97.55 251	98.96 200	98.92 226	97.77 145	99.59 358	97.59 193	99.77 155	99.39 215

UnsupCasMVSNet_bld		97.30 302	96.92 312	98.45 253	99.28 197	96.78 258	96.20 379	99.27 234	95.42 373	98.28 296	98.30 340	93.16 336	99.71 293	94.99 349	97.37 433	98.87 344

EC-MVSNet		99.09 71	99.05 78	99.20 109	99.28 197	98.93 80	99.24 44	99.84 22	99.08 111	98.12 309	98.37 332	98.72 49	99.90 80	99.05 83	99.77 155	98.77 361

mamba_0408		98.80 118	98.88 99	98.55 236	99.27 200	96.50 271	98.00 203	99.60 77	98.93 128	99.22 154	98.84 249	98.59 62	99.89 96	97.74 183	99.72 184	99.27 262

SSM_04072		98.80 118	98.88 99	98.56 234	99.27 200	96.50 271	98.00 203	99.60 77	98.93 128	99.22 154	98.84 249	98.59 62	99.90 80	97.74 183	99.72 184	99.27 262

SSM_0407		98.86 105	98.96 92	98.55 236	99.27 200	96.50 271	98.04 194	99.66 63	99.09 107	99.22 154	99.02 191	98.79 42	99.87 133	97.87 171	99.72 184	99.27 262

reproduce-ours		99.09 71	98.90 96	99.67 4	99.27 200	99.49 6	98.00 203	99.42 167	99.05 114	99.48 94	99.27 122	98.29 91	99.89 96	97.61 190	99.71 193	99.62 89

our_new_method		99.09 71	98.90 96	99.67 4	99.27 200	99.49 6	98.00 203	99.42 167	99.05 114	99.48 94	99.27 122	98.29 91	99.89 96	97.61 190	99.71 193	99.62 89

DPE-MVS		98.59 161	98.26 203	99.57 22	99.27 200	99.15 53	97.01 329	99.39 176	97.67 236	99.44 103	98.99 208	97.53 169	99.89 96	95.40 343	99.68 208	99.66 77
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 262	98.18 215	96.87 381	99.27 200	91.16 430	95.53 413	99.25 240	99.10 104	99.41 110	99.35 103	93.10 338	99.96 14	98.65 113	99.94 49	99.49 165

v1192		98.60 159	98.66 133	98.41 258	99.27 200	95.88 294	97.52 281	99.36 186	97.41 268	99.33 127	99.20 144	96.37 246	99.82 203	99.57 38	99.92 68	99.55 134

N_pmnet		97.63 276	97.17 297	98.99 150	99.27 200	97.86 174	95.98 390	93.41 454	95.25 378	99.47 98	98.90 231	95.63 279	99.85 155	96.91 243	99.73 176	99.27 262

viewdifsd2359ckpt13		98.39 196	98.29 198	98.70 204	99.26 209	97.19 230	97.51 283	99.48 130	96.94 308	98.58 266	98.82 254	97.47 178	99.55 374	97.21 218	99.33 307	99.34 240

FPMVS		93.44 411	92.23 418	97.08 369	99.25 210	97.86 174	95.61 410	97.16 403	92.90 423	93.76 456	98.65 293	75.94 450	95.66 470	79.30 468	97.49 426	97.73 434

ME-MVS		98.61 157	98.33 193	99.44 65	99.24 211	98.93 80	97.45 291	99.06 281	98.14 205	99.06 173	98.77 264	96.97 209	99.82 203	96.67 270	99.64 225	99.58 114

new-patchmatchnet		98.35 199	98.74 116	97.18 364	99.24 211	92.23 412	96.42 366	99.48 130	98.30 179	99.69 55	99.53 63	97.44 179	99.82 203	98.84 98	99.77 155	99.49 165

MCST-MVS		98.00 243	97.63 271	99.10 127	99.24 211	98.17 137	96.89 338	98.73 344	95.66 364	97.92 324	97.70 381	97.17 196	99.66 328	96.18 311	99.23 326	99.47 184

UniMVSNet (Re)		98.87 102	98.71 124	99.35 79	99.24 211	98.73 94	97.73 250	99.38 178	98.93 128	99.12 165	98.73 272	96.77 223	99.86 142	98.63 115	99.80 138	99.46 186

jason		97.45 290	97.35 288	97.76 317	99.24 211	93.93 373	95.86 400	98.42 362	94.24 402	98.50 278	98.13 350	94.82 302	99.91 73	97.22 217	99.73 176	99.43 199
jason: jason.
IterMVS		97.73 268	98.11 224	96.57 391	99.24 211	90.28 439	95.52 415	99.21 249	98.86 137	99.33 127	99.33 110	93.11 337	99.94 42	98.49 125	99.94 49	99.48 176
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 169	98.62 140	98.32 269	99.22 217	95.58 305	97.51 283	99.45 147	97.16 296	99.45 102	99.24 135	96.12 257	99.85 155	99.60 36	99.88 92	99.55 134

ITE_SJBPF				98.87 170	99.22 217	98.48 113		99.35 192	97.50 256	98.28 296	98.60 304	97.64 156	99.35 421	93.86 385	99.27 318	98.79 359

h-mvs33		97.77 266	97.33 290	99.10 127	99.21 219	97.84 176	98.35 153	98.57 354	99.11 97	98.58 266	99.02 191	88.65 389	99.96 14	98.11 147	96.34 449	99.49 165

v144192		98.54 172	98.57 149	98.45 253	99.21 219	95.98 291	97.63 265	99.36 186	97.15 298	99.32 133	99.18 149	95.84 274	99.84 173	99.50 50	99.91 77	99.54 140

APDe-MVS		98.99 84	98.79 112	99.60 16	99.21 219	99.15 53	98.87 88	99.48 130	97.57 247	99.35 123	99.24 135	97.83 138	99.89 96	97.88 169	99.70 200	99.75 59
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 94	98.81 111	99.28 95	99.21 219	98.45 115	98.46 141	99.33 204	99.63 29	99.48 94	99.15 159	97.23 193	99.75 272	97.17 220	99.66 222	99.63 88

SR-MVS-dyc-post		98.81 116	98.55 151	99.57 22	99.20 223	99.38 13	98.48 139	99.30 219	98.64 148	98.95 201	98.96 218	97.49 176	99.86 142	96.56 284	99.39 298	99.45 191

RE-MVS-def			98.58 148		99.20 223	99.38 13	98.48 139	99.30 219	98.64 148	98.95 201	98.96 218	97.75 147		96.56 284	99.39 298	99.45 191

v1921920		98.54 172	98.60 145	98.38 262	99.20 223	95.76 301	97.56 276	99.36 186	97.23 290	99.38 116	99.17 153	96.02 260	99.84 173	99.57 38	99.90 84	99.54 140

thisisatest0530		95.27 380	94.45 391	97.74 320	99.19 226	94.37 351	97.86 228	90.20 466	97.17 295	98.22 299	97.65 383	73.53 453	99.90 80	96.90 248	99.35 304	98.95 329

Anonymous20240529		98.93 94	98.87 101	99.12 123	99.19 226	98.22 134	99.01 70	98.99 299	99.25 74	99.54 78	99.37 98	97.04 202	99.80 228	97.89 166	99.52 270	99.35 238

APD-MVS_3200maxsize		98.84 108	98.61 144	99.53 39	99.19 226	99.27 28	98.49 136	99.33 204	98.64 148	99.03 186	98.98 213	97.89 134	99.85 155	96.54 288	99.42 295	99.46 186

HQP_MVS		97.99 246	97.67 265	98.93 162	99.19 226	97.65 196	97.77 241	99.27 234	98.20 193	97.79 336	97.98 364	94.90 298	99.70 300	94.42 367	99.51 272	99.45 191

plane_prior7					99.19 226	97.87 173

ab-mvs		98.41 188	98.36 186	98.59 225	99.19 226	97.23 224	99.32 26	98.81 330	97.66 237	98.62 258	99.40 95	96.82 218	99.80 228	95.88 322	99.51 272	98.75 364

F-COLMAP		97.30 302	96.68 329	99.14 121	99.19 226	98.39 117	97.27 313	99.30 219	92.93 422	96.62 401	98.00 362	95.73 277	99.68 313	92.62 413	98.46 394	99.35 238

viewdifsd2359ckpt09		98.13 231	97.92 247	98.77 192	99.18 233	97.35 214	97.29 309	99.53 112	95.81 361	98.09 312	98.47 322	96.34 248	99.66 328	97.02 233	99.51 272	99.29 258

SR-MVS		98.71 131	98.43 174	99.57 22	99.18 233	99.35 17	98.36 152	99.29 227	98.29 182	98.88 220	98.85 244	97.53 169	99.87 133	96.14 313	99.31 311	99.48 176

UniMVSNet_NR-MVSNet		98.86 105	98.68 130	99.40 71	99.17 235	98.74 91	97.68 255	99.40 174	99.14 95	99.06 173	98.59 305	96.71 229	99.93 53	98.57 118	99.77 155	99.53 149

LF4IMVS		97.90 250	97.69 264	98.52 244	99.17 235	97.66 195	97.19 323	99.47 139	96.31 341	97.85 332	98.20 347	96.71 229	99.52 386	94.62 359	99.72 184	98.38 400

SMA-MVS		98.40 190	98.03 233	99.51 49	99.16 237	99.21 34	98.05 192	99.22 248	94.16 404	98.98 191	99.10 171	97.52 171	99.79 241	96.45 294	99.64 225	99.53 149
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
DU-MVS		98.82 114	98.63 138	99.39 72	99.16 237	98.74 91	97.54 279	99.25 240	98.84 140	99.06 173	98.76 269	96.76 225	99.93 53	98.57 118	99.77 155	99.50 158

NR-MVSNet		98.95 91	98.82 109	99.36 73	99.16 237	98.72 96	99.22 45	99.20 251	99.10 104	99.72 47	98.76 269	96.38 245	99.86 142	98.00 159	99.82 121	99.50 158

MVS_111021_LR		98.30 208	98.12 223	98.83 175	99.16 237	98.03 156	96.09 387	99.30 219	97.58 246	98.10 311	98.24 343	98.25 98	99.34 422	96.69 268	99.65 223	99.12 303

DSMNet-mixed		97.42 293	97.60 273	96.87 381	99.15 241	91.46 419	98.54 124	99.12 273	92.87 424	97.58 349	99.63 39	96.21 252	99.90 80	95.74 331	99.54 263	99.27 262

D2MVS		97.84 263	97.84 254	97.83 309	99.14 242	94.74 340	96.94 333	98.88 314	95.84 360	98.89 216	98.96 218	94.40 314	99.69 304	97.55 194	99.95 38	99.05 309

pmmvs5		97.64 275	97.49 279	98.08 294	99.14 242	95.12 329	96.70 348	99.05 285	93.77 411	98.62 258	98.83 251	93.23 334	99.75 272	98.33 135	99.76 168	99.36 233

SPE-MVS-test		99.13 65	99.09 74	99.26 100	99.13 244	98.97 74	99.31 30	99.88 14	99.44 52	98.16 304	98.51 314	98.64 56	99.93 53	98.91 92	99.85 105	98.88 343

VDD-MVS		98.56 165	98.39 181	99.07 134	99.13 244	98.07 151	98.59 118	97.01 406	99.59 36	99.11 166	99.27 122	94.82 302	99.79 241	98.34 133	99.63 231	99.34 240

save fliter					99.11 246	97.97 162	96.53 358	99.02 293	98.24 185

APD-MVS		98.10 232	97.67 265	99.42 67	99.11 246	98.93 80	97.76 244	99.28 231	94.97 385	98.72 246	98.77 264	97.04 202	99.85 155	93.79 387	99.54 263	99.49 165
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 139	98.71 124	98.62 219	99.10 248	96.37 277	97.23 314	98.87 316	99.20 82	99.19 159	98.99 208	97.30 187	99.85 155	98.77 104	99.79 144	99.65 82

EI-MVSNet		98.40 190	98.51 157	98.04 299	99.10 248	94.73 341	97.20 319	98.87 316	98.97 123	99.06 173	99.02 191	96.00 262	99.80 228	98.58 116	99.82 121	99.60 99

CVMVSNet		96.25 354	97.21 296	93.38 448	99.10 248	80.56 476	97.20 319	98.19 373	96.94 308	99.00 188	99.02 191	89.50 382	99.80 228	96.36 300	99.59 245	99.78 46

EI-MVSNet-Vis-set		98.68 144	98.70 127	98.63 217	99.09 251	96.40 276	97.23 314	98.86 321	99.20 82	99.18 163	98.97 215	97.29 189	99.85 155	98.72 108	99.78 149	99.64 83

HPM-MVS++		98.10 232	97.64 270	99.48 57	99.09 251	99.13 61	97.52 281	98.75 341	97.46 264	96.90 389	97.83 374	96.01 261	99.84 173	95.82 329	99.35 304	99.46 186

DP-MVS Recon		97.33 300	96.92 312	98.57 229	99.09 251	97.99 158	96.79 341	99.35 192	93.18 418	97.71 340	98.07 358	95.00 297	99.31 426	93.97 380	99.13 342	98.42 397

MVS_111021_HR		98.25 217	98.08 228	98.75 196	99.09 251	97.46 208	95.97 391	99.27 234	97.60 245	97.99 322	98.25 342	98.15 113	99.38 417	96.87 251	99.57 254	99.42 202

BP-MVS1		97.40 295	96.97 308	98.71 203	99.07 255	96.81 254	98.34 155	97.18 401	98.58 159	98.17 301	98.61 302	84.01 421	99.94 42	98.97 89	99.78 149	99.37 226

9.14			97.78 256		99.07 255		97.53 280	99.32 206	95.53 370	98.54 274	98.70 282	97.58 162	99.76 264	94.32 372	99.46 285

PAPM_NR		96.82 334	96.32 345	98.30 272	99.07 255	96.69 262	97.48 287	98.76 338	95.81 361	96.61 402	96.47 419	94.12 323	99.17 439	90.82 440	97.78 420	99.06 308

TAMVS		98.24 218	98.05 231	98.80 181	99.07 255	97.18 232	97.88 224	98.81 330	96.66 325	99.17 164	99.21 142	94.81 304	99.77 258	96.96 241	99.88 92	99.44 195

CLD-MVS		97.49 286	97.16 298	98.48 250	99.07 255	97.03 241	94.71 436	99.21 249	94.46 396	98.06 315	97.16 405	97.57 163	99.48 398	94.46 364	99.78 149	98.95 329
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CS-MVS		99.13 65	99.10 72	99.24 105	99.06 260	99.15 53	99.36 22	99.88 14	99.36 63	98.21 300	98.46 323	98.68 53	99.93 53	99.03 85	99.85 105	98.64 376

thres100view900		94.19 397	93.67 402	95.75 415	99.06 260	91.35 423	98.03 196	94.24 449	98.33 175	97.40 365	94.98 449	79.84 437	99.62 344	83.05 461	98.08 411	96.29 456

thres600view7		94.45 392	93.83 399	96.29 399	99.06 260	91.53 418	97.99 210	94.24 449	98.34 174	97.44 363	95.01 447	79.84 437	99.67 317	84.33 459	98.23 400	97.66 437

plane_prior1					99.05 263

YYNet1		97.60 277	97.67 265	97.39 357	99.04 264	93.04 396	95.27 422	98.38 365	97.25 284	98.92 211	98.95 222	95.48 286	99.73 284	96.99 237	98.74 375	99.41 205

MDA-MVSNet_test_wron		97.60 277	97.66 268	97.41 356	99.04 264	93.09 392	95.27 422	98.42 362	97.26 283	98.88 220	98.95 222	95.43 287	99.73 284	97.02 233	98.72 377	99.41 205

MIMVSNet		96.62 341	96.25 349	97.71 324	99.04 264	94.66 344	99.16 54	96.92 412	97.23 290	97.87 329	99.10 171	86.11 404	99.65 335	91.65 424	99.21 330	98.82 348

icg_test_0407_2		98.20 223	98.38 183	97.65 330	99.03 267	94.03 364	95.78 405	99.45 147	98.16 199	99.06 173	98.71 275	98.27 94	99.68 313	97.50 200	99.45 287	99.22 279

IMVS_0407		98.39 196	98.64 136	97.66 328	99.03 267	94.03 364	98.10 182	99.45 147	98.16 199	99.06 173	98.71 275	98.27 94	99.71 293	97.50 200	99.45 287	99.22 279

IMVS_0404		98.07 236	98.20 210	97.69 325	99.03 267	94.03 364	96.67 349	99.45 147	98.16 199	98.03 319	98.71 275	96.80 221	99.82 203	97.50 200	99.45 287	99.22 279

IMVS_0403		98.34 200	98.56 150	97.66 328	99.03 267	94.03 364	97.98 211	99.45 147	98.16 199	98.89 216	98.71 275	97.90 132	99.74 277	97.50 200	99.45 287	99.22 279

PatchMatch-RL		97.24 308	96.78 323	98.61 222	99.03 267	97.83 177	96.36 369	99.06 281	93.49 416	97.36 369	97.78 375	95.75 276	99.49 395	93.44 396	98.77 374	98.52 385

viewmambaseed2359dif		98.19 224	98.26 203	97.99 302	99.02 272	95.03 332	96.59 355	99.53 112	96.21 344	99.00 188	98.99 208	97.62 158	99.61 351	97.62 189	99.72 184	99.33 246

GDP-MVS		97.50 283	97.11 302	98.67 209	99.02 272	96.85 252	98.16 172	99.71 47	98.32 177	98.52 277	98.54 309	83.39 425	99.95 26	98.79 100	99.56 257	99.19 289

ZD-MVS					99.01 274	98.84 85		99.07 280	94.10 406	98.05 317	98.12 352	96.36 247	99.86 142	92.70 412	99.19 334

CDPH-MVS		97.26 305	96.66 332	99.07 134	99.00 275	98.15 138	96.03 389	99.01 296	91.21 442	97.79 336	97.85 373	96.89 213	99.69 304	92.75 410	99.38 301	99.39 215

diffmvs		98.22 219	98.24 207	98.17 287	99.00 275	95.44 316	96.38 368	99.58 85	97.79 229	98.53 275	98.50 318	96.76 225	99.74 277	97.95 164	99.64 225	99.34 240
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WR-MVS		98.40 190	98.19 214	99.03 144	99.00 275	97.65 196	96.85 339	98.94 301	98.57 160	98.89 216	98.50 318	95.60 280	99.85 155	97.54 196	99.85 105	99.59 106

plane_prior6					98.99 278	97.70 194						94.90 298

xiu_mvs_v1_base_debu		97.86 257	98.17 216	96.92 378	98.98 279	93.91 374	96.45 362	99.17 263	97.85 224	98.41 286	97.14 407	98.47 72	99.92 64	98.02 156	99.05 348	96.92 449

xiu_mvs_v1_base		97.86 257	98.17 216	96.92 378	98.98 279	93.91 374	96.45 362	99.17 263	97.85 224	98.41 286	97.14 407	98.47 72	99.92 64	98.02 156	99.05 348	96.92 449

xiu_mvs_v1_base_debi		97.86 257	98.17 216	96.92 378	98.98 279	93.91 374	96.45 362	99.17 263	97.85 224	98.41 286	97.14 407	98.47 72	99.92 64	98.02 156	99.05 348	96.92 449

MVP-Stereo		98.08 235	97.92 247	98.57 229	98.96 282	96.79 255	97.90 222	99.18 259	96.41 337	98.46 281	98.95 222	95.93 271	99.60 354	96.51 290	98.98 362	99.31 253
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 190	98.68 130	97.54 345	98.96 282	97.99 158	97.88 224	99.36 186	98.20 193	99.63 66	99.04 188	98.76 45	95.33 472	96.56 284	99.74 173	99.31 253
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
新几何1				98.91 166	98.94 284	97.76 188		98.76 338	87.58 459	96.75 397	98.10 354	94.80 305	99.78 252	92.73 411	99.00 357	99.20 284

USDC		97.41 294	97.40 283	97.44 354	98.94 284	93.67 384	95.17 425	99.53 112	94.03 408	98.97 195	99.10 171	95.29 289	99.34 422	95.84 328	99.73 176	99.30 256

tfpn200view9		94.03 401	93.44 404	95.78 414	98.93 286	91.44 421	97.60 271	94.29 447	97.94 216	97.10 375	94.31 456	79.67 439	99.62 344	83.05 461	98.08 411	96.29 456

testdata				98.09 291	98.93 286	95.40 318		98.80 332	90.08 450	97.45 362	98.37 332	95.26 290	99.70 300	93.58 392	98.95 365	99.17 296

thres400		94.14 399	93.44 404	96.24 402	98.93 286	91.44 421	97.60 271	94.29 447	97.94 216	97.10 375	94.31 456	79.67 439	99.62 344	83.05 461	98.08 411	97.66 437

TAPA-MVS	96.21 11	96.63 340	95.95 351	98.65 211	98.93 286	98.09 145	96.93 335	99.28 231	83.58 465	98.13 308	97.78 375	96.13 255	99.40 413	93.52 393	99.29 316	98.45 390
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 290	96.93 249	95.54 412	98.78 335	85.72 462	96.86 392	98.11 353	94.43 312			99.10 347	99.23 274

PVSNet_BlendedMVS		97.55 282	97.53 276	97.60 337	98.92 290	93.77 381	96.64 351	99.43 161	94.49 394	97.62 345	99.18 149	96.82 218	99.67 317	94.73 356	99.93 55	99.36 233

PVSNet_Blended		96.88 330	96.68 329	97.47 352	98.92 290	93.77 381	94.71 436	99.43 161	90.98 444	97.62 345	97.36 401	96.82 218	99.67 317	94.73 356	99.56 257	98.98 323

MSDG		97.71 270	97.52 277	98.28 274	98.91 293	96.82 253	94.42 446	99.37 182	97.65 238	98.37 291	98.29 341	97.40 181	99.33 424	94.09 378	99.22 327	98.68 374

Anonymous202405211		97.90 250	97.50 278	99.08 132	98.90 294	98.25 128	98.53 125	96.16 424	98.87 135	99.11 166	98.86 241	90.40 374	99.78 252	97.36 209	99.31 311	99.19 289

原ACMM1				98.35 267	98.90 294	96.25 281		98.83 329	92.48 428	96.07 419	98.10 354	95.39 288	99.71 293	92.61 414	98.99 359	99.08 305

GBi-Net		98.65 149	98.47 168	99.17 114	98.90 294	98.24 129	99.20 48	99.44 155	98.59 156	98.95 201	99.55 57	94.14 320	99.86 142	97.77 178	99.69 203	99.41 205

test1		98.65 149	98.47 168	99.17 114	98.90 294	98.24 129	99.20 48	99.44 155	98.59 156	98.95 201	99.55 57	94.14 320	99.86 142	97.77 178	99.69 203	99.41 205

FMVSNet2		98.49 181	98.40 178	98.75 196	98.90 294	97.14 237	98.61 116	99.13 272	98.59 156	99.19 159	99.28 120	94.14 320	99.82 203	97.97 162	99.80 138	99.29 258

OMC-MVS		97.88 254	97.49 279	99.04 143	98.89 299	98.63 98	96.94 333	99.25 240	95.02 383	98.53 275	98.51 314	97.27 190	99.47 401	93.50 395	99.51 272	99.01 317

VortexMVS		97.98 247	98.31 195	97.02 372	98.88 300	91.45 420	98.03 196	99.47 139	98.65 147	99.55 76	99.47 77	91.49 363	99.81 220	99.32 60	99.91 77	99.80 41

MVSFormer		98.26 214	98.43 174	97.77 314	98.88 300	93.89 377	99.39 20	99.56 99	99.11 97	98.16 304	98.13 350	93.81 328	99.97 7	99.26 65	99.57 254	99.43 199

lupinMVS		97.06 320	96.86 316	97.65 330	98.88 300	93.89 377	95.48 416	97.97 379	93.53 414	98.16 304	97.58 387	93.81 328	99.91 73	96.77 259	99.57 254	99.17 296

dmvs_re		95.98 362	95.39 372	97.74 320	98.86 303	97.45 209	98.37 151	95.69 436	97.95 214	96.56 403	95.95 428	90.70 371	97.68 466	88.32 449	96.13 453	98.11 412

DELS-MVS		98.27 212	98.20 210	98.48 250	98.86 303	96.70 261	95.60 411	99.20 251	97.73 232	98.45 282	98.71 275	97.50 173	99.82 203	98.21 141	99.59 245	98.93 334
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
TinyColmap		97.89 252	97.98 238	97.60 337	98.86 303	94.35 352	96.21 378	99.44 155	97.45 266	99.06 173	98.88 238	97.99 126	99.28 432	94.38 371	99.58 250	99.18 292

LCM-MVSNet-Re		98.64 151	98.48 166	99.11 125	98.85 306	98.51 111	98.49 136	99.83 25	98.37 171	99.69 55	99.46 79	98.21 105	99.92 64	94.13 377	99.30 314	98.91 338

pmmvs4		97.58 280	97.28 291	98.51 245	98.84 307	96.93 249	95.40 420	98.52 357	93.60 413	98.61 260	98.65 293	95.10 294	99.60 354	96.97 240	99.79 144	98.99 322

NP-MVS					98.84 307	97.39 213					96.84 410

sss		97.21 310	96.93 310	98.06 296	98.83 309	95.22 325	96.75 345	98.48 359	94.49 394	97.27 371	97.90 370	92.77 346	99.80 228	96.57 280	99.32 309	99.16 299

PVSNet	93.40 17	95.67 371	95.70 357	95.57 419	98.83 309	88.57 446	92.50 463	97.72 384	92.69 426	96.49 411	96.44 420	93.72 331	99.43 409	93.61 390	99.28 317	98.71 367

MVE	83.40 22	92.50 424	91.92 426	94.25 435	98.83 309	91.64 417	92.71 462	83.52 475	95.92 358	86.46 473	95.46 441	95.20 291	95.40 471	80.51 466	98.64 386	95.73 464
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 405	93.91 397	93.39 447	98.82 312	81.72 474	97.76 244	95.28 438	98.60 155	96.54 404	96.66 414	65.85 469	99.62 344	96.65 273	98.99 359	98.82 348

ambc				98.24 279	98.82 312	95.97 292	98.62 115	99.00 298		99.27 141	99.21 142	96.99 207	99.50 392	96.55 287	99.50 280	99.26 268

旧先验1					98.82 312	97.45 209		98.76 338			98.34 336	95.50 285			99.01 356	99.23 274

test_vis1_rt		97.75 267	97.72 262	97.83 309	98.81 315	96.35 278	97.30 308	99.69 54	94.61 392	97.87 329	98.05 359	96.26 251	98.32 460	98.74 106	98.18 403	98.82 348

WTY-MVS		96.67 338	96.27 348	97.87 307	98.81 315	94.61 346	96.77 343	97.92 381	94.94 386	97.12 374	97.74 378	91.11 367	99.82 203	93.89 383	98.15 407	99.18 292

3Dnovator+	97.89 3	98.69 139	98.51 157	99.24 105	98.81 315	98.40 116	99.02 69	99.19 255	98.99 120	98.07 314	99.28 120	97.11 200	99.84 173	96.84 254	99.32 309	99.47 184

QAPM		97.31 301	96.81 322	98.82 177	98.80 318	97.49 204	99.06 65	99.19 255	90.22 448	97.69 342	99.16 155	96.91 212	99.90 80	90.89 439	99.41 296	99.07 307

VNet		98.42 187	98.30 196	98.79 184	98.79 319	97.29 220	98.23 163	98.66 348	99.31 68	98.85 225	98.80 258	94.80 305	99.78 252	98.13 146	99.13 342	99.31 253

DPM-MVS		96.32 350	95.59 363	98.51 245	98.76 320	97.21 228	94.54 445	98.26 368	91.94 433	96.37 412	97.25 403	93.06 340	99.43 409	91.42 429	98.74 375	98.89 340

3Dnovator	98.27 2	98.81 116	98.73 118	99.05 141	98.76 320	97.81 185	99.25 43	99.30 219	98.57 160	98.55 272	99.33 110	97.95 129	99.90 80	97.16 221	99.67 214	99.44 195

PLC	94.65 16	96.51 343	95.73 356	98.85 173	98.75 322	97.91 170	96.42 366	99.06 281	90.94 445	95.59 425	97.38 399	94.41 313	99.59 358	90.93 437	98.04 416	99.05 309
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 332	96.75 325	97.08 369	98.74 323	93.33 390	96.71 347	98.26 368	96.72 322	98.44 283	97.37 400	95.20 291	99.47 401	91.89 419	97.43 430	98.44 393

hse-mvs2		97.46 288	97.07 303	98.64 213	98.73 324	97.33 216	97.45 291	97.64 391	99.11 97	98.58 266	97.98 364	88.65 389	99.79 241	98.11 147	97.39 432	98.81 353

CDS-MVSNet		97.69 271	97.35 288	98.69 206	98.73 324	97.02 242	96.92 337	98.75 341	95.89 359	98.59 264	98.67 288	92.08 357	99.74 277	96.72 265	99.81 127	99.32 249
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SD_0403		96.28 352	95.83 353	97.64 333	98.72 326	94.30 353	98.87 88	98.77 336	97.80 227	96.53 405	98.02 361	97.34 185	99.47 401	76.93 470	99.48 283	99.16 299

EIA-MVS		98.00 243	97.74 259	98.80 181	98.72 326	98.09 145	98.05 192	99.60 77	97.39 270	96.63 400	95.55 436	97.68 150	99.80 228	96.73 264	99.27 318	98.52 385

LFMVS		97.20 311	96.72 326	98.64 213	98.72 326	96.95 247	98.93 81	94.14 451	99.74 13	98.78 237	99.01 202	84.45 416	99.73 284	97.44 205	99.27 318	99.25 269

new_pmnet		96.99 327	96.76 324	97.67 326	98.72 326	94.89 335	95.95 395	98.20 371	92.62 427	98.55 272	98.54 309	94.88 301	99.52 386	93.96 381	99.44 294	98.59 382

Fast-Effi-MVS+		97.67 273	97.38 285	98.57 229	98.71 330	97.43 211	97.23 314	99.45 147	94.82 389	96.13 416	96.51 416	98.52 70	99.91 73	96.19 309	98.83 371	98.37 402

TEST9					98.71 330	98.08 149	95.96 393	99.03 290	91.40 439	95.85 422	97.53 389	96.52 238	99.76 264

train_agg		97.10 317	96.45 342	99.07 134	98.71 330	98.08 149	95.96 393	99.03 290	91.64 434	95.85 422	97.53 389	96.47 240	99.76 264	93.67 389	99.16 337	99.36 233

TSAR-MVS + GP.		98.18 226	97.98 238	98.77 192	98.71 330	97.88 172	96.32 372	98.66 348	96.33 339	99.23 153	98.51 314	97.48 177	99.40 413	97.16 221	99.46 285	99.02 316

FA-MVS(test-final)		96.99 327	96.82 320	97.50 349	98.70 334	94.78 338	99.34 23	96.99 407	95.07 382	98.48 280	99.33 110	88.41 392	99.65 335	96.13 315	98.92 368	98.07 415

AUN-MVS		96.24 356	95.45 368	98.60 224	98.70 334	97.22 226	97.38 298	97.65 389	95.95 357	95.53 432	97.96 368	82.11 433	99.79 241	96.31 302	97.44 429	98.80 358

our_test_3		97.39 296	97.73 261	96.34 397	98.70 334	89.78 442	94.61 442	98.97 300	96.50 330	99.04 183	98.85 244	95.98 267	99.84 173	97.26 215	99.67 214	99.41 205

ppachtmachnet_test		97.50 283	97.74 259	96.78 387	98.70 334	91.23 429	94.55 444	99.05 285	96.36 338	99.21 157	98.79 260	96.39 243	99.78 252	96.74 262	99.82 121	99.34 240

PCF-MVS	92.86 18	94.36 393	93.00 411	98.42 257	98.70 334	97.56 201	93.16 461	99.11 275	79.59 469	97.55 352	97.43 396	92.19 354	99.73 284	79.85 467	99.45 287	97.97 421
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 249	98.02 234	97.58 339	98.69 339	94.10 360	98.13 175	98.90 310	97.95 214	97.32 370	99.58 47	95.95 270	98.75 455	96.41 296	99.22 327	99.87 21

ETV-MVS		98.03 239	97.86 253	98.56 234	98.69 339	98.07 151	97.51 283	99.50 121	98.10 206	97.50 357	95.51 437	98.41 78	99.88 114	96.27 305	99.24 323	97.71 436

test_prior				98.95 159	98.69 339	97.95 166		99.03 290					99.59 358			99.30 256

mvsmamba		97.57 281	97.26 292	98.51 245	98.69 339	96.73 260	98.74 97	97.25 400	97.03 304	97.88 328	99.23 140	90.95 368	99.87 133	96.61 276	99.00 357	98.91 338

agg_prior					98.68 343	97.99 158		99.01 296		95.59 425			99.77 258

test_8					98.67 344	98.01 157	95.91 399	99.02 293	91.64 434	95.79 424	97.50 392	96.47 240	99.76 264

HQP-NCC					98.67 344		96.29 374		96.05 350	95.55 428

ACMP_Plane					98.67 344		96.29 374		96.05 350	95.55 428

CNVR-MVS		98.17 228	97.87 252	99.07 134	98.67 344	98.24 129	97.01 329	98.93 304	97.25 284	97.62 345	98.34 336	97.27 190	99.57 367	96.42 295	99.33 307	99.39 215

HQP-MVS		97.00 326	96.49 341	98.55 236	98.67 344	96.79 255	96.29 374	99.04 288	96.05 350	95.55 428	96.84 410	93.84 326	99.54 380	92.82 407	99.26 321	99.32 249

MM		98.22 219	97.99 237	98.91 166	98.66 349	96.97 244	97.89 223	94.44 445	99.54 40	98.95 201	99.14 162	93.50 332	99.92 64	99.80 17	99.96 28	99.85 29

test_fmvs1		97.72 269	97.94 244	97.07 371	98.66 349	92.39 407	97.68 255	99.81 31	95.20 381	99.54 78	99.44 84	91.56 362	99.41 412	99.78 21	99.77 155	99.40 214

balanced_conf03		98.63 153	98.72 120	98.38 262	98.66 349	96.68 263	98.90 83	99.42 167	98.99 120	98.97 195	99.19 145	95.81 275	99.85 155	98.77 104	99.77 155	98.60 379

thres200		93.72 407	93.14 409	95.46 423	98.66 349	91.29 425	96.61 353	94.63 444	97.39 270	96.83 393	93.71 459	79.88 436	99.56 370	82.40 464	98.13 408	95.54 465

wuyk23d		96.06 358	97.62 272	91.38 452	98.65 353	98.57 105	98.85 92	96.95 410	96.86 315	99.90 14	99.16 155	99.18 19	98.40 459	89.23 447	99.77 155	77.18 472

NCCC		97.86 257	97.47 282	99.05 141	98.61 354	98.07 151	96.98 331	98.90 310	97.63 239	97.04 379	97.93 369	95.99 266	99.66 328	95.31 344	98.82 373	99.43 199

DeepC-MVS_fast	96.85 6	98.30 208	98.15 220	98.75 196	98.61 354	97.23 224	97.76 244	99.09 278	97.31 278	98.75 243	98.66 291	97.56 164	99.64 338	96.10 316	99.55 261	99.39 215
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 409	92.09 420	97.75 318	98.60 356	94.40 350	97.32 306	95.26 439	97.56 249	96.79 396	95.50 438	53.57 477	99.77 258	95.26 345	98.97 363	99.08 305

thisisatest0515		94.12 400	93.16 408	96.97 376	98.60 356	92.90 397	93.77 457	90.61 464	94.10 406	96.91 386	95.87 431	74.99 451	99.80 228	94.52 362	99.12 345	98.20 408

GA-MVS		95.86 365	95.32 375	97.49 350	98.60 356	94.15 359	93.83 456	97.93 380	95.49 371	96.68 398	97.42 397	83.21 426	99.30 428	96.22 307	98.55 392	99.01 317

dmvs_testset		92.94 419	92.21 419	95.13 427	98.59 359	90.99 432	97.65 261	92.09 460	96.95 307	94.00 452	93.55 460	92.34 352	96.97 469	72.20 471	92.52 467	97.43 444

OPU-MVS				98.82 177	98.59 359	98.30 125	98.10 182				98.52 313	98.18 107	98.75 455	94.62 359	99.48 283	99.41 205

MSLP-MVS++		98.02 240	98.14 222	97.64 333	98.58 361	95.19 326	97.48 287	99.23 247	97.47 259	97.90 326	98.62 300	97.04 202	98.81 453	97.55 194	99.41 296	98.94 333

test12				98.93 162	98.58 361	97.83 177		98.66 348		96.53 405		95.51 284	99.69 304		99.13 342	99.27 262

CL-MVSNet_self_test		97.44 291	97.22 295	98.08 294	98.57 363	95.78 300	94.30 449	98.79 333	96.58 328	98.60 262	98.19 348	94.74 308	99.64 338	96.41 296	98.84 370	98.82 348

PS-MVSNAJ		97.08 319	97.39 284	96.16 408	98.56 364	92.46 405	95.24 424	98.85 324	97.25 284	97.49 358	95.99 427	98.07 117	99.90 80	96.37 298	98.67 385	96.12 461

CNLPA		97.17 314	96.71 327	98.55 236	98.56 364	98.05 155	96.33 371	98.93 304	96.91 312	97.06 378	97.39 398	94.38 315	99.45 406	91.66 423	99.18 336	98.14 411

xiu_mvs_v2_base		97.16 315	97.49 279	96.17 406	98.54 366	92.46 405	95.45 417	98.84 325	97.25 284	97.48 359	96.49 417	98.31 89	99.90 80	96.34 301	98.68 384	96.15 460

alignmvs		97.35 298	96.88 315	98.78 187	98.54 366	98.09 145	97.71 251	97.69 386	99.20 82	97.59 348	95.90 430	88.12 394	99.55 374	98.18 143	98.96 364	98.70 370

FE-MVS		95.66 372	94.95 385	97.77 314	98.53 368	95.28 322	99.40 19	96.09 427	93.11 420	97.96 323	99.26 128	79.10 443	99.77 258	92.40 416	98.71 379	98.27 406

Effi-MVS+		98.02 240	97.82 255	98.62 219	98.53 368	97.19 230	97.33 305	99.68 59	97.30 279	96.68 398	97.46 395	98.56 68	99.80 228	96.63 274	98.20 402	98.86 345

baseline1		95.96 363	95.44 369	97.52 347	98.51 370	93.99 371	98.39 149	96.09 427	98.21 189	98.40 290	97.76 377	86.88 396	99.63 341	95.42 342	89.27 470	98.95 329

MVS_Test		98.18 226	98.36 186	97.67 326	98.48 371	94.73 341	98.18 168	99.02 293	97.69 235	98.04 318	99.11 168	97.22 194	99.56 370	98.57 118	98.90 369	98.71 367

MGCFI-Net		98.34 200	98.28 199	98.51 245	98.47 372	97.59 200	98.96 77	99.48 130	99.18 90	97.40 365	95.50 438	98.66 54	99.50 392	98.18 143	98.71 379	98.44 393

BH-RMVSNet		96.83 332	96.58 337	97.58 339	98.47 372	94.05 361	96.67 349	97.36 395	96.70 324	97.87 329	97.98 364	95.14 293	99.44 408	90.47 442	98.58 391	99.25 269

sasdasda		98.34 200	98.26 203	98.58 226	98.46 374	97.82 182	98.96 77	99.46 143	99.19 87	97.46 360	95.46 441	98.59 62	99.46 404	98.08 150	98.71 379	98.46 387

canonicalmvs		98.34 200	98.26 203	98.58 226	98.46 374	97.82 182	98.96 77	99.46 143	99.19 87	97.46 360	95.46 441	98.59 62	99.46 404	98.08 150	98.71 379	98.46 387

MVS-HIRNet		94.32 394	95.62 360	90.42 453	98.46 374	75.36 477	96.29 374	89.13 468	95.25 378	95.38 434	99.75 16	92.88 343	99.19 438	94.07 379	99.39 298	96.72 454

PHI-MVS		98.29 211	97.95 242	99.34 82	98.44 377	99.16 49	98.12 179	99.38 178	96.01 354	98.06 315	98.43 326	97.80 143	99.67 317	95.69 334	99.58 250	99.20 284

DVP-MVS++		98.90 98	98.70 127	99.51 49	98.43 378	99.15 53	99.43 15	99.32 206	98.17 196	99.26 145	99.02 191	98.18 107	99.88 114	97.07 230	99.45 287	99.49 165

MSC_two_6792asdad				99.32 90	98.43 378	98.37 120		98.86 321					99.89 96	97.14 224	99.60 241	99.71 62

No_MVS				99.32 90	98.43 378	98.37 120		98.86 321					99.89 96	97.14 224	99.60 241	99.71 62

Fast-Effi-MVS+-dtu		98.27 212	98.09 225	98.81 179	98.43 378	98.11 142	97.61 270	99.50 121	98.64 148	97.39 367	97.52 391	98.12 115	99.95 26	96.90 248	98.71 379	98.38 400

OpenMVS_ROB	95.38 14	95.84 367	95.18 380	97.81 311	98.41 382	97.15 236	97.37 302	98.62 352	83.86 464	98.65 254	98.37 332	94.29 318	99.68 313	88.41 448	98.62 389	96.60 455

DeepPCF-MVS	96.93 5	98.32 205	98.01 235	99.23 107	98.39 383	98.97 74	95.03 429	99.18 259	96.88 313	99.33 127	98.78 262	98.16 111	99.28 432	96.74 262	99.62 234	99.44 195

Patchmatch-test		96.55 342	96.34 344	97.17 366	98.35 384	93.06 393	98.40 148	97.79 382	97.33 275	98.41 286	98.67 288	83.68 424	99.69 304	95.16 347	99.31 311	98.77 361

AdaColmap		97.14 316	96.71 327	98.46 252	98.34 385	97.80 186	96.95 332	98.93 304	95.58 368	96.92 384	97.66 382	95.87 273	99.53 382	90.97 436	99.14 340	98.04 416

OpenMVS	96.65 7	97.09 318	96.68 329	98.32 269	98.32 386	97.16 235	98.86 91	99.37 182	89.48 452	96.29 414	99.15 159	96.56 236	99.90 80	92.90 404	99.20 331	97.89 424

MG-MVS		96.77 335	96.61 334	97.26 362	98.31 387	93.06 393	95.93 396	98.12 376	96.45 336	97.92 324	98.73 272	93.77 330	99.39 415	91.19 434	99.04 351	99.33 246

test_yl		96.69 336	96.29 346	97.90 304	98.28 388	95.24 323	97.29 309	97.36 395	98.21 189	98.17 301	97.86 371	86.27 400	99.55 374	94.87 353	98.32 396	98.89 340

DCV-MVSNet		96.69 336	96.29 346	97.90 304	98.28 388	95.24 323	97.29 309	97.36 395	98.21 189	98.17 301	97.86 371	86.27 400	99.55 374	94.87 353	98.32 396	98.89 340

CHOSEN 280x420		95.51 377	95.47 366	95.65 418	98.25 390	88.27 449	93.25 460	98.88 314	93.53 414	94.65 443	97.15 406	86.17 402	99.93 53	97.41 207	99.93 55	98.73 366

SCA		96.41 349	96.66 332	95.67 416	98.24 391	88.35 448	95.85 402	96.88 413	96.11 348	97.67 343	98.67 288	93.10 338	99.85 155	94.16 373	99.22 327	98.81 353

DeepMVS_CX				93.44 446	98.24 391	94.21 356		94.34 446	64.28 472	91.34 466	94.87 453	89.45 383	92.77 473	77.54 469	93.14 466	93.35 468

MS-PatchMatch		97.68 272	97.75 258	97.45 353	98.23 393	93.78 380	97.29 309	98.84 325	96.10 349	98.64 255	98.65 293	96.04 259	99.36 418	96.84 254	99.14 340	99.20 284

BH-w/o		95.13 383	94.89 387	95.86 411	98.20 394	91.31 424	95.65 409	97.37 394	93.64 412	96.52 407	95.70 434	93.04 341	99.02 444	88.10 450	95.82 456	97.24 447

mvs_anonymous		97.83 265	98.16 219	96.87 381	98.18 395	91.89 414	97.31 307	98.90 310	97.37 272	98.83 228	99.46 79	96.28 250	99.79 241	98.90 93	98.16 406	98.95 329

miper_lstm_enhance		97.18 313	97.16 298	97.25 363	98.16 396	92.85 398	95.15 427	99.31 211	97.25 284	98.74 245	98.78 262	90.07 375	99.78 252	97.19 219	99.80 138	99.11 304

RRT-MVS		97.88 254	97.98 238	97.61 336	98.15 397	93.77 381	98.97 76	99.64 69	99.16 92	98.69 248	99.42 88	91.60 360	99.89 96	97.63 188	98.52 393	99.16 299

ET-MVSNet_ETH3D		94.30 396	93.21 407	97.58 339	98.14 398	94.47 349	94.78 435	93.24 456	94.72 390	89.56 468	95.87 431	78.57 446	99.81 220	96.91 243	97.11 441	98.46 387

ADS-MVSNet2		95.43 378	94.98 383	96.76 388	98.14 398	91.74 415	97.92 219	97.76 383	90.23 446	96.51 408	98.91 228	85.61 407	99.85 155	92.88 405	96.90 442	98.69 371

ADS-MVSNet		95.24 381	94.93 386	96.18 405	98.14 398	90.10 441	97.92 219	97.32 398	90.23 446	96.51 408	98.91 228	85.61 407	99.74 277	92.88 405	96.90 442	98.69 371

c3_l		97.36 297	97.37 286	97.31 358	98.09 401	93.25 391	95.01 430	99.16 266	97.05 301	98.77 240	98.72 274	92.88 343	99.64 338	96.93 242	99.76 168	99.05 309

FMVSNet3		97.50 283	97.24 294	98.29 273	98.08 402	95.83 297	97.86 228	98.91 309	97.89 221	98.95 201	98.95 222	87.06 395	99.81 220	97.77 178	99.69 203	99.23 274

PAPM		91.88 433	90.34 436	96.51 392	98.06 403	92.56 403	92.44 464	97.17 402	86.35 460	90.38 467	96.01 426	86.61 398	99.21 437	70.65 473	95.43 458	97.75 433

Effi-MVS+-dtu		98.26 214	97.90 250	99.35 79	98.02 404	99.49 6	98.02 199	99.16 266	98.29 182	97.64 344	97.99 363	96.44 242	99.95 26	96.66 272	98.93 367	98.60 379

eth_miper_zixun_eth		97.23 309	97.25 293	97.17 366	98.00 405	92.77 400	94.71 436	99.18 259	97.27 282	98.56 270	98.74 271	91.89 358	99.69 304	97.06 232	99.81 127	99.05 309

HY-MVS	95.94 13	95.90 364	95.35 374	97.55 344	97.95 406	94.79 337	98.81 96	96.94 411	92.28 431	95.17 436	98.57 307	89.90 377	99.75 272	91.20 433	97.33 437	98.10 413

UGNet		98.53 174	98.45 171	98.79 184	97.94 407	96.96 246	99.08 61	98.54 355	99.10 104	96.82 394	99.47 77	96.55 237	99.84 173	98.56 121	99.94 49	99.55 134
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
MAR-MVS		96.47 347	95.70 357	98.79 184	97.92 408	99.12 63	98.28 157	98.60 353	92.16 432	95.54 431	96.17 424	94.77 307	99.52 386	89.62 445	98.23 400	97.72 435
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
MVSTER		96.86 331	96.55 338	97.79 312	97.91 409	94.21 356	97.56 276	98.87 316	97.49 258	99.06 173	99.05 186	80.72 434	99.80 228	98.44 127	99.82 121	99.37 226

API-MVS		97.04 322	96.91 314	97.42 355	97.88 410	98.23 133	98.18 168	98.50 358	97.57 247	97.39 367	96.75 412	96.77 223	99.15 441	90.16 443	99.02 355	94.88 466

myMVS_eth3d28		92.92 420	92.31 416	94.77 430	97.84 411	87.59 453	96.19 380	96.11 426	97.08 300	94.27 446	93.49 462	66.07 468	98.78 454	91.78 421	97.93 419	97.92 423

miper_ehance_all_eth		97.06 320	97.03 305	97.16 368	97.83 412	93.06 393	94.66 439	99.09 278	95.99 355	98.69 248	98.45 324	92.73 348	99.61 351	96.79 256	99.03 352	98.82 348

cl____		97.02 323	96.83 319	97.58 339	97.82 413	94.04 363	94.66 439	99.16 266	97.04 302	98.63 256	98.71 275	88.68 388	99.69 304	97.00 235	99.81 127	99.00 321

DIV-MVS_self_test		97.02 323	96.84 318	97.58 339	97.82 413	94.03 364	94.66 439	99.16 266	97.04 302	98.63 256	98.71 275	88.69 386	99.69 304	97.00 235	99.81 127	99.01 317

CANet		97.87 256	97.76 257	98.19 286	97.75 415	95.51 308	96.76 344	99.05 285	97.74 231	96.93 383	98.21 346	95.59 281	99.89 96	97.86 173	99.93 55	99.19 289

UBG		93.25 414	92.32 415	96.04 410	97.72 416	90.16 440	95.92 398	95.91 431	96.03 353	93.95 454	93.04 465	69.60 458	99.52 386	90.72 441	97.98 417	98.45 390

mvsany_test1		97.60 277	97.54 275	97.77 314	97.72 416	95.35 319	95.36 421	97.13 404	94.13 405	99.71 49	99.33 110	97.93 130	99.30 428	97.60 192	98.94 366	98.67 375

PVSNet_0	89.98 21	91.15 434	90.30 437	93.70 443	97.72 416	84.34 467	90.24 467	97.42 393	90.20 449	93.79 455	93.09 464	90.90 370	98.89 452	86.57 456	72.76 473	97.87 426

CR-MVSNet		96.28 352	95.95 351	97.28 360	97.71 419	94.22 354	98.11 180	98.92 307	92.31 430	96.91 386	99.37 98	85.44 410	99.81 220	97.39 208	97.36 435	97.81 429

RPMNet		97.02 323	96.93 310	97.30 359	97.71 419	94.22 354	98.11 180	99.30 219	99.37 60	96.91 386	99.34 107	86.72 397	99.87 133	97.53 197	97.36 435	97.81 429

ETVMVS		92.60 423	91.08 432	97.18 364	97.70 421	93.65 386	96.54 356	95.70 434	96.51 329	94.68 442	92.39 468	61.80 474	99.50 392	86.97 453	97.41 431	98.40 398

pmmvs3		95.03 385	94.40 392	96.93 377	97.70 421	92.53 404	95.08 428	97.71 385	88.57 456	97.71 340	98.08 357	79.39 441	99.82 203	96.19 309	99.11 346	98.43 395

baseline2		93.73 406	92.83 412	96.42 395	97.70 421	91.28 426	96.84 340	89.77 467	93.96 410	92.44 462	95.93 429	79.14 442	99.77 258	92.94 403	96.76 446	98.21 407

WBMVS		95.18 382	94.78 388	96.37 396	97.68 424	89.74 443	95.80 404	98.73 344	97.54 253	98.30 292	98.44 325	70.06 456	99.82 203	96.62 275	99.87 96	99.54 140

tpm		94.67 390	94.34 394	95.66 417	97.68 424	88.42 447	97.88 224	94.90 441	94.46 396	96.03 421	98.56 308	78.66 444	99.79 241	95.88 322	95.01 460	98.78 360

CANet_DTU		97.26 305	97.06 304	97.84 308	97.57 426	94.65 345	96.19 380	98.79 333	97.23 290	95.14 437	98.24 343	93.22 335	99.84 173	97.34 210	99.84 110	99.04 313

testing11		93.08 417	92.02 422	96.26 401	97.56 427	90.83 435	96.32 372	95.70 434	96.47 333	92.66 461	93.73 458	64.36 472	99.59 358	93.77 388	97.57 424	98.37 402

tpm2		93.09 416	92.58 414	94.62 432	97.56 427	86.53 456	97.66 259	95.79 433	86.15 461	94.07 451	98.23 345	75.95 449	99.53 382	90.91 438	96.86 445	97.81 429

testing91		93.32 412	92.27 417	96.47 394	97.54 429	91.25 427	96.17 384	96.76 415	97.18 294	93.65 457	93.50 461	65.11 471	99.63 341	93.04 402	97.45 428	98.53 384

TR-MVS		95.55 375	95.12 381	96.86 384	97.54 429	93.94 372	96.49 361	96.53 420	94.36 401	97.03 381	96.61 415	94.26 319	99.16 440	86.91 455	96.31 450	97.47 443

testing99		93.04 418	91.98 425	96.23 403	97.53 431	90.70 437	96.35 370	95.94 430	96.87 314	93.41 458	93.43 463	63.84 473	99.59 358	93.24 400	97.19 438	98.40 398

1314		95.74 369	95.60 361	96.17 406	97.53 431	92.75 401	98.07 189	98.31 367	91.22 441	94.25 447	96.68 413	95.53 282	99.03 443	91.64 425	97.18 439	96.74 453

CostFormer		93.97 402	93.78 400	94.51 433	97.53 431	85.83 459	97.98 211	95.96 429	89.29 454	94.99 439	98.63 298	78.63 445	99.62 344	94.54 361	96.50 447	98.09 414

FMVSNet5		96.01 360	95.20 379	98.41 258	97.53 431	96.10 283	98.74 97	99.50 121	97.22 293	98.03 319	99.04 188	69.80 457	99.88 114	97.27 214	99.71 193	99.25 269

PMMVS		96.51 343	95.98 350	98.09 291	97.53 431	95.84 296	94.92 432	98.84 325	91.58 436	96.05 420	95.58 435	95.68 278	99.66 328	95.59 338	98.09 410	98.76 363

reproduce_monomvs		95.00 387	95.25 376	94.22 436	97.51 436	83.34 468	97.86 228	98.44 360	98.51 165	99.29 137	99.30 116	67.68 462	99.56 370	98.89 95	99.81 127	99.77 49

PAPR		95.29 379	94.47 390	97.75 318	97.50 437	95.14 328	94.89 433	98.71 346	91.39 440	95.35 435	95.48 440	94.57 310	99.14 442	84.95 458	97.37 433	98.97 326

testing222		91.96 431	90.37 435	96.72 389	97.47 438	92.59 402	96.11 386	94.76 442	96.83 316	92.90 460	92.87 466	57.92 475	99.55 374	86.93 454	97.52 425	98.00 420

PatchT		96.65 339	96.35 343	97.54 345	97.40 439	95.32 321	97.98 211	96.64 417	99.33 65	96.89 390	99.42 88	84.32 418	99.81 220	97.69 187	97.49 426	97.48 442

tpm cat1		93.29 413	93.13 410	93.75 442	97.39 440	84.74 462	97.39 296	97.65 389	83.39 466	94.16 448	98.41 327	82.86 429	99.39 415	91.56 427	95.35 459	97.14 448

PatchmatchNet		95.58 374	95.67 359	95.30 426	97.34 441	87.32 454	97.65 261	96.65 416	95.30 377	97.07 377	98.69 284	84.77 413	99.75 272	94.97 351	98.64 386	98.83 347
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 298	96.97 308	98.50 249	97.31 442	96.47 274	98.18 168	98.92 307	98.95 127	98.78 237	99.37 98	85.44 410	99.85 155	95.96 320	99.83 117	99.17 296

LS3D		98.63 153	98.38 183	99.36 73	97.25 443	99.38 13	99.12 60	99.32 206	99.21 80	98.44 283	98.88 238	97.31 186	99.80 228	96.58 278	99.34 306	98.92 335

IB-MVS	91.63 19	92.24 429	90.90 433	96.27 400	97.22 444	91.24 428	94.36 448	93.33 455	92.37 429	92.24 464	94.58 455	66.20 467	99.89 96	93.16 401	94.63 462	97.66 437
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
UWE-MVS		92.38 426	91.76 429	94.21 437	97.16 445	84.65 463	95.42 419	88.45 469	95.96 356	96.17 415	95.84 433	66.36 465	99.71 293	91.87 420	98.64 386	98.28 405

tpmrst		95.07 384	95.46 367	93.91 440	97.11 446	84.36 466	97.62 266	96.96 409	94.98 384	96.35 413	98.80 258	85.46 409	99.59 358	95.60 337	96.23 451	97.79 432

Syy-MVS		96.04 359	95.56 365	97.49 350	97.10 447	94.48 348	96.18 382	96.58 418	95.65 365	94.77 440	92.29 469	91.27 366	99.36 418	98.17 145	98.05 414	98.63 377

myMVS_eth3d		91.92 432	90.45 434	96.30 398	97.10 447	90.90 433	96.18 382	96.58 418	95.65 365	94.77 440	92.29 469	53.88 476	99.36 418	89.59 446	98.05 414	98.63 377

MDTV_nov1_ep13			95.22 378		97.06 449	83.20 469	97.74 248	96.16 424	94.37 400	96.99 382	98.83 251	83.95 422	99.53 382	93.90 382	97.95 418

MVS		93.19 415	92.09 420	96.50 393	96.91 450	94.03 364	98.07 189	98.06 378	68.01 471	94.56 445	96.48 418	95.96 269	99.30 428	83.84 460	96.89 444	96.17 458

E-PMN		94.17 398	94.37 393	93.58 444	96.86 451	85.71 460	90.11 469	97.07 405	98.17 196	97.82 335	97.19 404	84.62 415	98.94 448	89.77 444	97.68 423	96.09 462

JIA-IIPM		95.52 376	95.03 382	97.00 373	96.85 452	94.03 364	96.93 335	95.82 432	99.20 82	94.63 444	99.71 22	83.09 427	99.60 354	94.42 367	94.64 461	97.36 446

EMVS		93.83 404	94.02 396	93.23 449	96.83 453	84.96 461	89.77 470	96.32 422	97.92 218	97.43 364	96.36 423	86.17 402	98.93 449	87.68 451	97.73 422	95.81 463

cl22		95.79 368	95.39 372	96.98 375	96.77 454	92.79 399	94.40 447	98.53 356	94.59 393	97.89 327	98.17 349	82.82 430	99.24 434	96.37 298	99.03 352	98.92 335

WB-MVSnew		95.73 370	95.57 364	96.23 403	96.70 455	90.70 437	96.07 388	93.86 452	95.60 367	97.04 379	95.45 444	96.00 262	99.55 374	91.04 435	98.31 398	98.43 395

dp		93.47 410	93.59 403	93.13 450	96.64 456	81.62 475	97.66 259	96.42 421	92.80 425	96.11 417	98.64 296	78.55 447	99.59 358	93.31 398	92.18 469	98.16 410

MonoMVSNet		96.25 354	96.53 340	95.39 424	96.57 457	91.01 431	98.82 95	97.68 388	98.57 160	98.03 319	99.37 98	90.92 369	97.78 465	94.99 349	93.88 465	97.38 445

test-LLR		93.90 403	93.85 398	94.04 438	96.53 458	84.62 464	94.05 453	92.39 458	96.17 345	94.12 449	95.07 445	82.30 431	99.67 317	95.87 325	98.18 403	97.82 427

test-mter		92.33 428	91.76 429	94.04 438	96.53 458	84.62 464	94.05 453	92.39 458	94.00 409	94.12 449	95.07 445	65.63 470	99.67 317	95.87 325	98.18 403	97.82 427

TESTMET0.1,1		92.19 430	91.77 428	93.46 445	96.48 460	82.80 471	94.05 453	91.52 463	94.45 398	94.00 452	94.88 451	66.65 464	99.56 370	95.78 330	98.11 409	98.02 417

MGCNet		97.44 291	97.01 307	98.72 202	96.42 461	96.74 259	97.20 319	91.97 461	98.46 168	98.30 292	98.79 260	92.74 347	99.91 73	99.30 62	99.94 49	99.52 152

miper_enhance_ethall		96.01 360	95.74 355	96.81 385	96.41 462	92.27 411	93.69 458	98.89 313	91.14 443	98.30 292	97.35 402	90.58 372	99.58 365	96.31 302	99.03 352	98.60 379

tpmvs		95.02 386	95.25 376	94.33 434	96.39 463	85.87 457	98.08 185	96.83 414	95.46 372	95.51 433	98.69 284	85.91 405	99.53 382	94.16 373	96.23 451	97.58 440

CMPMVS	75.91 23	96.29 351	95.44 369	98.84 174	96.25 464	98.69 97	97.02 328	99.12 273	88.90 455	97.83 333	98.86 241	89.51 381	98.90 451	91.92 418	99.51 272	98.92 335
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 391	93.69 401	96.99 374	96.05 465	93.61 388	94.97 431	93.49 453	96.17 345	97.57 351	94.88 451	82.30 431	99.01 446	93.60 391	94.17 464	98.37 402

EPMVS		93.72 407	93.27 406	95.09 429	96.04 466	87.76 451	98.13 175	85.01 474	94.69 391	96.92 384	98.64 296	78.47 448	99.31 426	95.04 348	96.46 448	98.20 408

cascas		94.79 389	94.33 395	96.15 409	96.02 467	92.36 409	92.34 465	99.26 239	85.34 463	95.08 438	94.96 450	92.96 342	98.53 458	94.41 370	98.59 390	97.56 441

MVStest1		95.86 365	95.60 361	96.63 390	95.87 468	91.70 416	97.93 216	98.94 301	98.03 208	99.56 73	99.66 32	71.83 454	98.26 461	99.35 58	99.24 323	99.91 13

gg-mvs-nofinetune		92.37 427	91.20 431	95.85 412	95.80 469	92.38 408	99.31 30	81.84 476	99.75 11	91.83 465	99.74 18	68.29 459	99.02 444	87.15 452	97.12 440	96.16 459

gm-plane-assit					94.83 470	81.97 473			88.07 458		94.99 448		99.60 354	91.76 422

GG-mvs-BLEND				94.76 431	94.54 471	92.13 413	99.31 30	80.47 477		88.73 471	91.01 471	67.59 463	98.16 464	82.30 465	94.53 463	93.98 467

UWE-MVS-28		90.22 435	89.28 438	93.02 451	94.50 472	82.87 470	96.52 359	87.51 470	95.21 380	92.36 463	96.04 425	71.57 455	98.25 462	72.04 472	97.77 421	97.94 422

EPNet_dtu		94.93 388	94.78 388	95.38 425	93.58 473	87.68 452	96.78 342	95.69 436	97.35 274	89.14 470	98.09 356	88.15 393	99.49 395	94.95 352	99.30 314	98.98 323
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 439	75.95 442	77.12 456	92.39 474	67.91 480	90.16 468	59.44 481	82.04 467	89.42 469	94.67 454	49.68 478	81.74 474	48.06 474	77.66 472	81.72 470

KD-MVS_2432*1600		92.87 421	91.99 423	95.51 421	91.37 475	89.27 444	94.07 451	98.14 374	95.42 373	97.25 372	96.44 420	67.86 460	99.24 434	91.28 431	96.08 454	98.02 417

miper_refine_blended		92.87 421	91.99 423	95.51 421	91.37 475	89.27 444	94.07 451	98.14 374	95.42 373	97.25 372	96.44 420	67.86 460	99.24 434	91.28 431	96.08 454	98.02 417

EPNet		96.14 357	95.44 369	98.25 277	90.76 477	95.50 311	97.92 219	94.65 443	98.97 123	92.98 459	98.85 244	89.12 384	99.87 133	95.99 318	99.68 208	99.39 215
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 440	68.95 443	70.34 457	87.68 478	65.00 481	91.11 466	59.90 480	69.02 470	74.46 475	88.89 472	48.58 479	68.03 476	28.61 475	72.33 474	77.99 471

test_method		79.78 437	79.50 440	80.62 454	80.21 479	45.76 482	70.82 471	98.41 364	31.08 474	80.89 474	97.71 379	84.85 412	97.37 467	91.51 428	80.03 471	98.75 364

tmp_tt		78.77 438	78.73 441	78.90 455	58.45 480	74.76 479	94.20 450	78.26 478	39.16 473	86.71 472	92.82 467	80.50 435	75.19 475	86.16 457	92.29 468	86.74 469

testmvs		17.12 442	20.53 445	6.87 459	12.05 481	4.20 484	93.62 459	6.73 482	4.62 477	10.41 477	24.33 474	8.28 481	3.56 478	9.69 477	15.07 475	12.86 474

test123		17.04 443	20.11 446	7.82 458	10.25 482	4.91 483	94.80 434	4.47 483	4.93 476	10.00 478	24.28 475	9.69 480	3.64 477	10.14 476	12.43 476	14.92 473

mmdepth		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

monomultidepth		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

test_blank		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

eth-test2					0.00 483

eth-test					0.00 483

uanet_test		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

DCPMVS		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

cdsmvs_eth3d_5k		24.66 441	32.88 444	0.00 460	0.00 483	0.00 485	0.00 472	99.10 276	0.00 478	0.00 479	97.58 387	99.21 18	0.00 479	0.00 478	0.00 477	0.00 475

pcd_1.5k_mvsjas		8.17 444	10.90 447	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	98.07 117	0.00 479	0.00 478	0.00 477	0.00 475

sosnet-low-res		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

sosnet		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

uncertanet		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

Regformer		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

ab-mvs-re		8.12 445	10.83 448	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	97.48 393	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

uanet		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

TestfortrainingZip							98.68 107

WAC-MVS						90.90 433								91.37 430

PC_three_1452									93.27 417	99.40 113	98.54 309	98.22 103	97.00 468	95.17 346	99.45 287	99.49 165

test_241102_TWO								99.30 219	98.03 208	99.26 145	99.02 191	97.51 172	99.88 114	96.91 243	99.60 241	99.66 77

test_0728_THIRD									98.17 196	99.08 171	99.02 191	97.89 134	99.88 114	97.07 230	99.71 193	99.70 67

GSMVS																98.81 353

sam_mvs1												84.74 414				98.81 353

sam_mvs												84.29 420

MTGPA								99.20 251

test_post1							97.59 273				20.48 477	83.07 428	99.66 328	94.16 373

test_post											21.25 476	83.86 423	99.70 300

patchmatchnet-post											98.77 264	84.37 417	99.85 155

MTMP							97.93 216	91.91 462

test9_res														93.28 399	99.15 339	99.38 224

agg_prior2														92.50 415	99.16 337	99.37 226

test_prior4						97.97 162	95.86 400

test_prior2							95.74 407		96.48 332	96.11 417	97.63 385	95.92 272		94.16 373	99.20 331

旧先验2							95.76 406		88.56 457	97.52 355			99.66 328	94.48 363

新几何2							95.93 396

无先验							95.74 407	98.74 343	89.38 453				99.73 284	92.38 417		99.22 279

原ACMM2							95.53 413

testdata2													99.79 241	92.80 409

segment_acmp												97.02 205

testdata1							95.44 418		96.32 340

plane_prior5								99.27 234					99.70 300	94.42 367	99.51 272	99.45 191

plane_prior4											97.98 364

plane_prior3						97.78 187			97.41 268	97.79 336

plane_prior2							97.77 241		98.20 193

plane_prior						97.65 196	97.07 327		96.72 322						99.36 302

n2								0.00 484

nn								0.00 484

door-mid								99.57 92

test11								98.87 316

door								99.41 171

HQP5-MVS						96.79 255

BP-MVS														92.82 407

HQP4-MVS										95.56 427			99.54 380			99.32 249

HQP3-MVS								99.04 288							99.26 321

HQP2-MVS												93.84 326

MDTV_nov1_ep13_2view						74.92 478	97.69 254		90.06 451	97.75 339		85.78 406		93.52 393		98.69 371

ACMMP++_ref															99.77 155

ACMMP++															99.68 208

Test By Simon												96.52 238

High-resolution multi-view benchmark