High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

LCM-MVSNet		99.93 1	99.92 1	99.94 1	99.99 1	99.97 1	99.90 1	99.89 13	99.98 1	99.99 1	99.96 1	99.77 2	100.00 1	99.81 15	100.00 1	99.85 29

Gipuma		99.03 78	99.16 60	98.64 204	99.94 2	98.51 108	99.32 26	99.75 42	99.58 37	98.60 251	99.62 40	98.22 99	99.51 378	97.70 178	99.73 169	97.89 411
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 38	99.91 3	98.98 71	99.63 7	99.58 76	99.44 51	99.78 39	99.76 15	96.39 232	99.92 63	99.44 53	99.92 67	99.68 68

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

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

testf1		99.25 41	99.16 60	99.51 48	99.89 6	99.63 4	98.71 104	99.69 50	98.90 128	99.43 99	99.35 100	98.86 34	99.67 308	97.81 167	99.81 121	99.24 259

APD_test2		99.25 41	99.16 60	99.51 48	99.89 6	99.63 4	98.71 104	99.69 50	98.90 128	99.43 99	99.35 100	98.86 34	99.67 308	97.81 167	99.81 121	99.24 259

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

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

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

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

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

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

test_djsdf		99.52 13	99.51 15	99.53 38	99.86 14	98.74 88	99.39 20	99.56 90	99.11 93	99.70 50	99.73 20	99.00 27	99.97 7	99.26 64	99.98 12	99.89 16

MIMVSNet1		99.38 28	99.32 39	99.55 28	99.86 14	99.19 42	99.41 17	99.59 74	99.59 35	99.71 48	99.57 49	97.12 189	99.90 79	99.21 69	99.87 95	99.54 134

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 26	99.85 16	99.11 64	99.90 1	99.78 36	99.63 29	99.78 39	99.67 30	99.48 10	99.81 216	99.30 61	99.97 21	99.77 48
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 17	99.34 20	99.69 5	99.58 76	99.90 3	99.86 24	99.78 13	99.58 6	99.95 26	99.00 86	99.95 38	99.78 45

SixPastTwentyTwo		98.75 122	98.62 134	99.16 114	99.83 18	97.96 162	99.28 40	98.20 358	99.37 59	99.70 50	99.65 36	92.65 337	99.93 52	99.04 83	99.84 106	99.60 97

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

Baseline_NR-MVSNet		98.98 86	98.86 101	99.36 70	99.82 19	98.55 103	97.47 282	99.57 83	99.37 59	99.21 150	99.61 43	96.76 214	99.83 190	98.06 147	99.83 113	99.71 60

pm-mvs1		99.44 19	99.48 18	99.33 85	99.80 21	98.63 95	99.29 36	99.63 65	99.30 69	99.65 62	99.60 45	99.16 22	99.82 200	99.07 79	99.83 113	99.56 123

TransMVSNet (Re)		99.44 19	99.47 21	99.36 70	99.80 21	98.58 101	99.27 42	99.57 83	99.39 57	99.75 44	99.62 40	99.17 20	99.83 190	99.06 81	99.62 223	99.66 75

K. test v3		98.00 231	97.66 256	99.03 141	99.79 23	97.56 198	99.19 52	92.47 444	99.62 32	99.52 81	99.66 32	89.61 368	99.96 14	99.25 66	99.81 121	99.56 123

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

APD_test1		98.83 106	98.66 127	99.34 79	99.78 24	99.47 9	98.42 144	99.45 135	98.28 179	98.98 183	99.19 141	97.76 140	99.58 353	96.57 267	99.55 250	98.97 313

test_vis3_rt		99.14 60	99.17 58	99.07 131	99.78 24	98.38 115	98.92 82	99.94 2	97.80 220	99.91 12	99.67 30	97.15 188	98.91 437	99.76 22	99.56 246	99.92 12

EGC-MVSNET		85.24 424	80.54 427	99.34 79	99.77 27	99.20 39	99.08 61	99.29 215	12.08 462	20.84 463	99.42 87	97.55 159	99.85 154	97.08 219	99.72 177	98.96 315

Anonymous20240521		98.69 133	98.87 98	98.16 276	99.77 27	95.11 317	99.08 61	99.44 143	99.34 63	99.33 122	99.55 57	94.10 312	99.94 41	99.25 66	99.96 28	99.42 193

FC-MVSNet-test		99.27 38	99.25 51	99.34 79	99.77 27	98.37 117	99.30 35	99.57 83	99.61 34	99.40 108	99.50 67	97.12 189	99.85 154	99.02 85	99.94 49	99.80 40

test_vis1_n		98.31 196	98.50 152	97.73 310	99.76 30	94.17 345	98.68 107	99.91 9	96.31 329	99.79 38	99.57 49	92.85 333	99.42 398	99.79 18	99.84 106	99.60 97

test_fmvs3		99.12 67	99.41 26	98.25 267	99.76 30	95.07 318	99.05 67	99.94 2	97.78 223	99.82 33	99.84 3	98.56 68	99.71 286	99.96 1	99.96 28	99.97 4

XXY-MVS		99.14 60	99.15 65	99.10 124	99.76 30	97.74 187	98.85 92	99.62 67	98.48 163	99.37 113	99.49 73	98.75 46	99.86 141	98.20 137	99.80 132	99.71 60

TDRefinement		99.42 24	99.38 29	99.55 28	99.76 30	99.33 21	99.68 6	99.71 46	99.38 58	99.53 79	99.61 43	98.64 56	99.80 224	98.24 133	99.84 106	99.52 146

fmvsm_s_conf0.1_n_a		99.17 52	99.30 44	98.80 176	99.75 34	96.59 256	97.97 211	99.86 16	98.22 182	99.88 21	99.71 22	98.59 62	99.84 172	99.73 26	99.98 12	99.98 3

tt0805		98.69 133	98.62 134	98.90 166	99.75 34	99.30 22	99.15 56	96.97 395	98.86 133	98.87 214	97.62 373	98.63 58	98.96 434	99.41 55	98.29 386	98.45 377

test_vis1_n_1920		98.40 180	98.92 91	96.81 372	99.74 36	90.76 423	98.15 170	99.91 9	98.33 170	99.89 18	99.55 57	95.07 283	99.88 113	99.76 22	99.93 54	99.79 42

FOURS1					99.73 37	99.67 3	99.43 15	99.54 99	99.43 53	99.26 139

PEN-MVS		99.41 25	99.34 36	99.62 9	99.73 37	99.14 57	99.29 36	99.54 99	99.62 32	99.56 70	99.42 87	98.16 107	99.96 14	98.78 100	99.93 54	99.77 48

lessismore_v0				98.97 153	99.73 37	97.53 200		86.71 459		99.37 113	99.52 66	89.93 364	99.92 63	98.99 87	99.72 177	99.44 186

SteuartSystems-ACMMP		98.79 115	98.54 146	99.54 31	99.73 37	99.16 48	98.23 160	99.31 199	97.92 211	98.90 204	98.90 223	98.00 119	99.88 113	96.15 299	99.72 177	99.58 112
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 217	98.15 209	98.22 270	99.73 37	95.15 314	97.36 292	99.68 55	94.45 385	98.99 182	99.27 119	96.87 203	99.94 41	97.13 216	99.91 76	99.57 117

Vis-MVSNet		99.34 30	99.36 33	99.27 95	99.73 37	98.26 124	99.17 53	99.78 36	99.11 93	99.27 135	99.48 74	98.82 37	99.95 26	98.94 90	99.93 54	99.59 104
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
tt0320-xc		99.64 5	99.68 5	99.50 53	99.72 43	98.98 71	99.51 10	99.85 18	99.86 6	99.88 21	99.82 5	99.02 26	99.90 79	99.54 42	99.95 38	99.61 95

SSC-MVS		98.71 126	98.74 111	98.62 210	99.72 43	96.08 279	98.74 97	98.64 338	99.74 13	99.67 58	99.24 131	94.57 298	99.95 26	99.11 76	99.24 310	99.82 35

test_f		98.67 141	98.87 98	98.05 285	99.72 43	95.59 293	98.51 128	99.81 31	96.30 331	99.78 39	99.82 5	96.14 242	98.63 444	99.82 11	99.93 54	99.95 9

ACMH	96.65 7	99.25 41	99.24 52	99.26 97	99.72 43	98.38 115	99.07 64	99.55 94	98.30 174	99.65 62	99.45 83	99.22 17	99.76 260	98.44 124	99.77 149	99.64 81
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0320		99.61 8	99.65 9	99.48 56	99.71 47	98.94 78	99.54 8	99.83 25	99.87 5	99.89 18	99.82 5	98.75 46	99.90 79	99.54 42	99.95 38	99.59 104

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

PS-CasMVS		99.40 26	99.33 37	99.62 9	99.71 47	99.10 65	99.29 36	99.53 102	99.53 40	99.46 94	99.41 91	98.23 96	99.95 26	98.89 94	99.95 38	99.81 38

DTE-MVSNet		99.43 23	99.35 34	99.66 7	99.71 47	99.30 22	99.31 30	99.51 107	99.64 27	99.56 70	99.46 79	98.23 96	99.97 7	98.78 100	99.93 54	99.72 59

WR-MVS_H		99.33 31	99.22 53	99.65 8	99.71 47	99.24 30	99.32 26	99.55 94	99.46 48	99.50 87	99.34 104	97.30 178	99.93 52	98.90 92	99.93 54	99.77 48

HPM-MVS_fast		99.01 80	98.82 104	99.57 21	99.71 47	99.35 17	99.00 72	99.50 110	97.33 267	98.94 199	98.86 233	98.75 46	99.82 200	97.53 190	99.71 186	99.56 123

ACMH+	96.62 9	99.08 74	99.00 83	99.33 85	99.71 47	98.83 83	98.60 114	99.58 76	99.11 93	99.53 79	99.18 145	98.81 38	99.67 308	96.71 256	99.77 149	99.50 152

PMVS	91.26 20	97.86 245	97.94 233	97.65 317	99.71 47	97.94 164	98.52 123	98.68 334	98.99 116	97.52 342	99.35 100	97.41 172	98.18 450	91.59 413	99.67 207	96.82 439
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
KinetiMVS		99.03 78	99.02 79	99.03 141	99.70 55	97.48 203	98.43 141	99.29 215	99.70 16	99.60 69	99.07 172	96.13 243	99.94 41	99.42 54	99.87 95	99.68 68

FIs		99.14 60	99.09 73	99.29 91	99.70 55	98.28 123	99.13 58	99.52 106	99.48 43	99.24 144	99.41 91	96.79 211	99.82 200	98.69 110	99.88 91	99.76 53

VPNet		98.87 100	98.83 103	99.01 145	99.70 55	97.62 196	98.43 141	99.35 180	99.47 46	99.28 133	99.05 180	96.72 217	99.82 200	98.09 144	99.36 290	99.59 104

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

test_cas_vis1_n_1920		98.33 193	98.68 124	97.27 348	99.69 58	92.29 397	98.03 192	99.85 18	97.62 232	99.96 4	99.62 40	93.98 313	99.74 272	99.52 48	99.86 101	99.79 42

MP-MVS-pluss		98.57 156	98.23 197	99.60 15	99.69 58	99.35 17	97.16 311	99.38 166	94.87 375	98.97 187	98.99 200	98.01 118	99.88 113	97.29 204	99.70 193	99.58 112
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 46	99.32 39	98.96 154	99.68 61	97.35 211	98.84 94	99.48 119	99.69 18	99.63 65	99.68 25	99.03 24	99.96 14	97.97 156	99.92 67	99.57 117

sd_testset		99.28 37	99.31 41	99.19 108	99.68 61	98.06 151	99.41 17	99.30 207	99.69 18	99.63 65	99.68 25	99.25 16	99.96 14	97.25 207	99.92 67	99.57 117

test_fmvs1_n		98.09 222	98.28 188	97.52 334	99.68 61	93.47 376	98.63 110	99.93 5	95.41 363	99.68 56	99.64 37	91.88 347	99.48 385	99.82 11	99.87 95	99.62 87

CHOSEN 1792x2688		97.49 274	97.14 289	98.54 232	99.68 61	96.09 277	96.50 346	99.62 67	91.58 423	98.84 217	98.97 207	92.36 339	99.88 113	96.76 249	99.95 38	99.67 73

tfpnnormal		98.90 96	98.90 93	98.91 163	99.67 65	97.82 179	99.00 72	99.44 143	99.45 49	99.51 86	99.24 131	98.20 102	99.86 141	95.92 308	99.69 196	99.04 300

MTAPA		98.88 99	98.64 130	99.61 13	99.67 65	99.36 16	98.43 141	99.20 239	98.83 137	98.89 206	98.90 223	96.98 199	99.92 63	97.16 211	99.70 193	99.56 123

test_fmvsmvis_n_1920		99.26 40	99.49 16	98.54 232	99.66 67	96.97 236	98.00 199	99.85 18	99.24 74	99.92 8	99.50 67	99.39 12	99.95 26	99.89 3	99.98 12	98.71 354

mvs5depth		99.30 34	99.59 12	98.44 246	99.65 68	95.35 306	99.82 3	99.94 2	99.83 7	99.42 103	99.94 2	98.13 110	99.96 14	99.63 34	99.96 28	100.00 1

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

WB-MVS		98.52 169	98.55 144	98.43 247	99.65 68	95.59 293	98.52 123	98.77 323	99.65 26	99.52 81	99.00 199	94.34 304	99.93 52	98.65 112	98.83 358	99.76 53

CP-MVSNet		99.21 48	99.09 73	99.56 26	99.65 68	98.96 77	99.13 58	99.34 186	99.42 54	99.33 122	99.26 124	97.01 197	99.94 41	98.74 105	99.93 54	99.79 42

HPM-MVS		98.79 115	98.53 148	99.59 19	99.65 68	99.29 24	99.16 54	99.43 149	96.74 311	98.61 249	98.38 318	98.62 59	99.87 132	96.47 279	99.67 207	99.59 104
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 150	98.36 177	99.42 64	99.65 68	99.42 11	98.55 119	99.57 83	97.72 226	98.90 204	99.26 124	96.12 245	99.52 373	95.72 319	99.71 186	99.32 237

NormalMVS		98.26 203	97.97 230	99.15 117	99.64 74	97.83 174	98.28 154	99.43 149	99.24 74	98.80 224	98.85 236	89.76 366	99.94 41	98.04 149	99.67 207	99.68 68

lecture		99.25 41	99.12 68	99.62 9	99.64 74	99.40 12	98.89 87	99.51 107	99.19 85	99.37 113	99.25 129	98.36 81	99.88 113	98.23 135	99.67 207	99.59 104

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

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

TSAR-MVS + MP.		98.63 147	98.49 156	99.06 137	99.64 74	97.90 168	98.51 128	98.94 288	96.96 298	99.24 144	98.89 229	97.83 132	99.81 216	96.88 239	99.49 270	99.48 168
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 109	98.72 115	99.12 120	99.64 74	98.54 106	97.98 207	99.68 55	97.62 232	99.34 120	99.18 145	97.54 160	99.77 254	97.79 169	99.74 166	99.04 300

Elysia		99.15 57	99.14 66	99.18 109	99.63 80	97.92 165	98.50 130	99.43 149	99.67 21	99.70 50	99.13 160	96.66 220	99.98 4	99.54 42	99.96 28	99.64 81

StellarMVS		99.15 57	99.14 66	99.18 109	99.63 80	97.92 165	98.50 130	99.43 149	99.67 21	99.70 50	99.13 160	96.66 220	99.98 4	99.54 42	99.96 28	99.64 81

KD-MVS_self_test		99.25 41	99.18 57	99.44 63	99.63 80	99.06 70	98.69 106	99.54 99	99.31 67	99.62 68	99.53 63	97.36 175	99.86 141	99.24 68	99.71 186	99.39 206

EU-MVSNet		97.66 262	98.50 152	95.13 414	99.63 80	85.84 445	98.35 150	98.21 357	98.23 181	99.54 75	99.46 79	95.02 284	99.68 304	98.24 133	99.87 95	99.87 21

HyFIR lowres test		97.19 300	96.60 324	98.96 154	99.62 84	97.28 215	95.17 411	99.50 110	94.21 390	99.01 179	98.32 326	86.61 386	99.99 2	97.10 218	99.84 106	99.60 97

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

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

mmtdpeth		99.30 34	99.42 25	98.92 162	99.58 87	96.89 243	99.48 13	99.92 7	99.92 2	98.26 286	99.80 11	98.33 87	99.91 72	99.56 39	99.95 38	99.97 4

ACMMP_NAP		98.75 122	98.48 157	99.57 21	99.58 87	99.29 24	97.82 228	99.25 228	96.94 300	98.78 226	99.12 163	98.02 117	99.84 172	97.13 216	99.67 207	99.59 104

nrg030		99.40 26	99.35 34	99.54 31	99.58 87	99.13 60	98.98 75	99.48 119	99.68 20	99.46 94	99.26 124	98.62 59	99.73 278	99.17 73	99.92 67	99.76 53

VDDNet		98.21 210	97.95 231	99.01 145	99.58 87	97.74 187	99.01 70	97.29 386	99.67 21	98.97 187	99.50 67	90.45 361	99.80 224	97.88 162	99.20 318	99.48 168

COLMAP_ROB	96.50 10	98.99 83	98.85 102	99.41 66	99.58 87	99.10 65	98.74 97	99.56 90	99.09 103	99.33 122	99.19 141	98.40 79	99.72 285	95.98 306	99.76 162	99.42 193
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	98.99 147	99.57 92	97.73 189	97.93 212	99.83 25	99.22 77	99.93 6	99.30 113	99.42 11	99.96 14	99.85 5	99.99 5	99.29 246

ZNCC-MVS		98.68 138	98.40 169	99.54 31	99.57 92	99.21 33	98.46 138	99.29 215	97.28 273	98.11 298	98.39 316	98.00 119	99.87 132	96.86 242	99.64 217	99.55 130

MSP-MVS		98.40 180	98.00 225	99.61 13	99.57 92	99.25 29	98.57 117	99.35 180	97.55 243	99.31 130	97.71 366	94.61 297	99.88 113	96.14 300	99.19 321	99.70 65
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
testgi		98.32 194	98.39 172	98.13 277	99.57 92	95.54 296	97.78 234	99.49 117	97.37 264	99.19 152	97.65 370	98.96 29	99.49 382	96.50 278	98.99 346	99.34 229

MP-MVS		98.46 174	98.09 214	99.54 31	99.57 92	99.22 32	98.50 130	99.19 243	97.61 235	97.58 336	98.66 279	97.40 173	99.88 113	94.72 345	99.60 230	99.54 134
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 126	98.46 161	99.47 60	99.57 92	98.97 73	98.23 160	99.48 119	96.60 316	99.10 162	99.06 173	98.71 50	99.83 190	95.58 326	99.78 143	99.62 87

LGP-MVS_train				99.47 60	99.57 92	98.97 73		99.48 119	96.60 316	99.10 162	99.06 173	98.71 50	99.83 190	95.58 326	99.78 143	99.62 87

IS-MVSNet		98.19 213	97.90 238	99.08 129	99.57 92	97.97 159	99.31 30	98.32 353	99.01 115	98.98 183	99.03 184	91.59 349	99.79 237	95.49 328	99.80 132	99.48 168

dcpmvs_2		98.78 117	99.11 69	97.78 300	99.56 100	93.67 371	99.06 65	99.86 16	99.50 42	99.66 59	99.26 124	97.21 186	99.99 2	98.00 154	99.91 76	99.68 68

test_0402		98.76 121	98.71 118	98.93 159	99.56 100	98.14 137	98.45 140	99.34 186	99.28 71	98.95 192	98.91 220	98.34 86	99.79 237	95.63 323	99.91 76	98.86 332

EPP-MVSNet		98.30 197	98.04 221	99.07 131	99.56 100	97.83 174	99.29 36	98.07 364	99.03 113	98.59 253	99.13 160	92.16 343	99.90 79	96.87 240	99.68 201	99.49 157

ACMMP		98.75 122	98.50 152	99.52 44	99.56 100	99.16 48	98.87 88	99.37 170	97.16 288	98.82 221	99.01 196	97.71 143	99.87 132	96.29 291	99.69 196	99.54 134
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
fmvsm_s_conf0.5_n_a		99.10 69	99.20 56	98.78 182	99.55 104	96.59 256	97.79 233	99.82 30	98.21 183	99.81 36	99.53 63	98.46 75	99.84 172	99.70 31	99.97 21	99.90 15

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

FMVSNet1		99.17 52	99.17 58	99.17 111	99.55 104	98.24 126	99.20 48	99.44 143	99.21 79	99.43 99	99.55 57	97.82 135	99.86 141	98.42 126	99.89 89	99.41 196

Vis-MVSNet (Re-imp)		97.46 276	97.16 286	98.34 259	99.55 104	96.10 274	98.94 80	98.44 347	98.32 172	98.16 292	98.62 288	88.76 373	99.73 278	93.88 371	99.79 138	99.18 279

ACMM	96.08 12	98.91 94	98.73 113	99.48 56	99.55 104	99.14 57	98.07 185	99.37 170	97.62 232	99.04 175	98.96 210	98.84 36	99.79 237	97.43 198	99.65 215	99.49 157
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 130	98.97 87	97.89 293	99.54 109	94.05 348	98.55 119	99.92 7	96.78 309	99.72 46	99.78 13	96.60 224	99.67 308	99.91 2	99.90 83	99.94 10

mPP-MVS		98.64 145	98.34 180	99.54 31	99.54 109	99.17 44	98.63 110	99.24 233	97.47 251	98.09 300	98.68 274	97.62 152	99.89 95	96.22 294	99.62 223	99.57 117

XVG-ACMP-BASELINE		98.56 157	98.34 180	99.22 105	99.54 109	98.59 100	97.71 246	99.46 131	97.25 276	98.98 183	98.99 200	97.54 160	99.84 172	95.88 309	99.74 166	99.23 261

region2R		98.69 133	98.40 169	99.54 31	99.53 112	99.17 44	98.52 123	99.31 199	97.46 256	98.44 271	98.51 302	97.83 132	99.88 113	96.46 280	99.58 239	99.58 112

PGM-MVS		98.66 142	98.37 176	99.55 28	99.53 112	99.18 43	98.23 160	99.49 117	97.01 297	98.69 237	98.88 230	98.00 119	99.89 95	95.87 312	99.59 234	99.58 112

Patchmatch-RL test		97.26 293	97.02 294	97.99 289	99.52 114	95.53 297	96.13 371	99.71 46	97.47 251	99.27 135	99.16 151	84.30 407	99.62 333	97.89 159	99.77 149	98.81 340

ACMMPR		98.70 130	98.42 167	99.54 31	99.52 114	99.14 57	98.52 123	99.31 199	97.47 251	98.56 258	98.54 297	97.75 141	99.88 113	96.57 267	99.59 234	99.58 112

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

AstraMVS		98.16 219	98.07 219	98.41 249	99.51 116	95.86 286	98.00 199	95.14 427	98.97 119	99.43 99	99.24 131	93.25 321	99.84 172	99.21 69	99.87 95	99.54 134

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

GST-MVS		98.61 151	98.30 186	99.52 44	99.51 116	99.20 39	98.26 158	99.25 228	97.44 259	98.67 240	98.39 316	97.68 144	99.85 154	96.00 304	99.51 261	99.52 146

Anonymous20231206		98.21 210	98.21 198	98.20 271	99.51 116	95.43 304	98.13 172	99.32 194	96.16 335	98.93 200	98.82 246	96.00 250	99.83 190	97.32 203	99.73 169	99.36 223

ACMP	95.32 15	98.41 178	98.09 214	99.36 70	99.51 116	98.79 86	97.68 249	99.38 166	95.76 350	98.81 223	98.82 246	98.36 81	99.82 200	94.75 342	99.77 149	99.48 168
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LuminaMVS		98.39 186	98.20 199	98.98 151	99.50 122	97.49 201	97.78 234	97.69 373	98.75 138	99.49 88	99.25 129	92.30 341	99.94 41	99.14 74	99.88 91	99.50 152

DVP-MVS		98.77 120	98.52 149	99.52 44	99.50 122	99.21 33	98.02 195	98.84 312	97.97 205	99.08 164	99.02 185	97.61 154	99.88 113	96.99 226	99.63 220	99.48 168
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				99.60 15	99.50 122	99.23 31	98.02 195	99.32 194					99.88 113	96.99 226	99.63 220	99.68 68

test0726					99.50 122	99.21 33	98.17 168	99.35 180	97.97 205	99.26 139	99.06 173	97.61 154

AllTest		98.44 176	98.20 199	99.16 114	99.50 122	98.55 103	98.25 159	99.58 76	96.80 307	98.88 210	99.06 173	97.65 147	99.57 355	94.45 352	99.61 228	99.37 216

TestCases				99.16 114	99.50 122	98.55 103		99.58 76	96.80 307	98.88 210	99.06 173	97.65 147	99.57 355	94.45 352	99.61 228	99.37 216

XVG-OURS		98.53 165	98.34 180	99.11 122	99.50 122	98.82 85	95.97 377	99.50 110	97.30 271	99.05 173	98.98 205	99.35 14	99.32 412	95.72 319	99.68 201	99.18 279

EG-PatchMatch MVS		98.99 83	99.01 81	98.94 157	99.50 122	97.47 204	98.04 190	99.59 74	98.15 198	99.40 108	99.36 99	98.58 67	99.76 260	98.78 100	99.68 201	99.59 104

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

SED-MVS		98.91 94	98.72 115	99.49 54	99.49 130	99.17 44	98.10 179	99.31 199	98.03 201	99.66 59	99.02 185	98.36 81	99.88 113	96.91 232	99.62 223	99.41 196

IU-MVS					99.49 130	99.15 52		98.87 303	92.97 408	99.41 105				96.76 249	99.62 223	99.66 75

test_241102_ONE					99.49 130	99.17 44		99.31 199	97.98 204	99.66 59	98.90 223	98.36 81	99.48 385

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

HFP-MVS		98.71 126	98.44 164	99.51 48	99.49 130	99.16 48	98.52 123	99.31 199	97.47 251	98.58 255	98.50 306	97.97 123	99.85 154	96.57 267	99.59 234	99.53 143

VPA-MVSNet		99.30 34	99.30 44	99.28 92	99.49 130	98.36 120	99.00 72	99.45 135	99.63 29	99.52 81	99.44 84	98.25 94	99.88 113	99.09 78	99.84 106	99.62 87

XVG-OURS-SEG-HR		98.49 171	98.28 188	99.14 118	99.49 130	98.83 83	96.54 342	99.48 119	97.32 269	99.11 159	98.61 290	99.33 15	99.30 415	96.23 293	98.38 382	99.28 248

114514_t		96.50 333	95.77 342	98.69 198	99.48 138	97.43 208	97.84 227	99.55 94	81.42 455	96.51 395	98.58 294	95.53 270	99.67 308	93.41 384	99.58 239	98.98 310

IterMVS-LS		98.55 161	98.70 121	98.09 278	99.48 138	94.73 328	97.22 306	99.39 164	98.97 119	99.38 111	99.31 112	96.00 250	99.93 52	98.58 115	99.97 21	99.60 97
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
fmvsm_s_conf0.5_n_5		99.07 76	99.10 71	98.99 147	99.47 140	97.22 220	97.40 287	99.83 25	97.61 235	99.85 27	99.30 113	98.80 40	99.95 26	99.71 30	99.90 83	99.78 45

v8		99.01 80	99.16 60	98.57 220	99.47 140	96.31 271	98.90 83	99.47 127	99.03 113	99.52 81	99.57 49	96.93 200	99.81 216	99.60 35	99.98 12	99.60 97

SSC-MVS3.2		98.53 165	98.79 107	97.74 307	99.46 142	93.62 374	96.45 348	99.34 186	99.33 64	98.93 200	98.70 270	97.90 127	99.90 79	99.12 75	99.92 67	99.69 67

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

XVS		98.72 125	98.45 162	99.53 38	99.46 142	99.21 33	98.65 108	99.34 186	98.62 149	97.54 340	98.63 286	97.50 166	99.83 190	96.79 245	99.53 256	99.56 123

X-MVStestdata		94.32 382	92.59 401	99.53 38	99.46 142	99.21 33	98.65 108	99.34 186	98.62 149	97.54 340	45.85 460	97.50 166	99.83 190	96.79 245	99.53 256	99.56 123

test20.03		98.78 117	98.77 110	98.78 182	99.46 142	97.20 223	97.78 234	99.24 233	99.04 112	99.41 105	98.90 223	97.65 147	99.76 260	97.70 178	99.79 138	99.39 206

guyue		98.01 230	97.93 235	98.26 266	99.45 147	95.48 300	98.08 182	96.24 410	98.89 130	99.34 120	99.14 158	91.32 353	99.82 200	99.07 79	99.83 113	99.48 168

CSCG		98.68 138	98.50 152	99.20 106	99.45 147	98.63 95	98.56 118	99.57 83	97.87 215	98.85 215	98.04 347	97.66 146	99.84 172	96.72 254	99.81 121	99.13 289

GeoE		99.05 77	98.99 85	99.25 100	99.44 149	98.35 121	98.73 101	99.56 90	98.42 166	98.91 203	98.81 248	98.94 30	99.91 72	98.35 128	99.73 169	99.49 157

v148		98.45 175	98.60 139	98.00 288	99.44 149	94.98 320	97.44 285	99.06 269	98.30 174	99.32 128	98.97 207	96.65 222	99.62 333	98.37 127	99.85 102	99.39 206

v10		98.97 87	99.11 69	98.55 227	99.44 149	96.21 273	98.90 83	99.55 94	98.73 139	99.48 89	99.60 45	96.63 223	99.83 190	99.70 31	99.99 5	99.61 95

V42		98.78 117	98.78 109	98.76 187	99.44 149	97.04 233	98.27 157	99.19 243	97.87 215	99.25 143	99.16 151	96.84 204	99.78 248	99.21 69	99.84 106	99.46 178

MDA-MVSNet-bldmvs		97.94 236	97.91 237	98.06 283	99.44 149	94.96 321	96.63 339	99.15 259	98.35 168	98.83 218	99.11 164	94.31 305	99.85 154	96.60 264	98.72 364	99.37 216

casdiffmvs_mvg		99.12 67	99.16 60	98.99 147	99.43 154	97.73 189	98.00 199	99.62 67	99.22 77	99.55 73	99.22 137	98.93 32	99.75 267	98.66 111	99.81 121	99.50 152
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
mamba_0404		98.90 96	99.01 81	98.57 220	99.42 155	96.59 256	98.13 172	99.66 59	99.09 103	99.30 131	99.02 185	98.79 42	99.89 95	97.87 164	99.80 132	99.23 261

test1111		96.49 334	96.82 308	95.52 407	99.42 155	87.08 442	99.22 45	87.14 458	99.11 93	99.46 94	99.58 47	88.69 374	99.86 141	98.80 98	99.95 38	99.62 87

v2v482		98.56 157	98.62 134	98.37 256	99.42 155	95.81 290	97.58 268	99.16 254	97.90 213	99.28 133	99.01 196	95.98 255	99.79 237	99.33 58	99.90 83	99.51 149

OPM-MVS		98.56 157	98.32 184	99.25 100	99.41 158	98.73 91	97.13 313	99.18 247	97.10 291	98.75 232	98.92 218	98.18 103	99.65 324	96.68 258	99.56 246	99.37 216
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 224	98.08 217	98.04 286	99.41 158	94.59 334	94.59 429	99.40 162	97.50 248	98.82 221	98.83 243	96.83 206	99.84 172	97.50 192	99.81 121	99.71 60

test_one_0601					99.39 160	99.20 39		99.31 199	98.49 162	98.66 242	99.02 185	97.64 150

mvsany_test3		98.87 100	98.92 91	98.74 193	99.38 161	96.94 240	98.58 116	99.10 264	96.49 321	99.96 4	99.81 8	98.18 103	99.45 393	98.97 88	99.79 138	99.83 32

patch_mono-2		98.51 170	98.63 132	98.17 274	99.38 161	94.78 325	97.36 292	99.69 50	98.16 193	98.49 267	99.29 116	97.06 192	99.97 7	98.29 132	99.91 76	99.76 53

test2506		92.39 413	91.89 415	93.89 428	99.38 161	82.28 459	99.32 26	66.03 466	99.08 107	98.77 229	99.57 49	66.26 454	99.84 172	98.71 108	99.95 38	99.54 134

ECVR-MVS		96.42 336	96.61 322	95.85 399	99.38 161	88.18 437	99.22 45	86.00 460	99.08 107	99.36 116	99.57 49	88.47 379	99.82 200	98.52 121	99.95 38	99.54 134

casdiffmvs		98.95 90	99.00 83	98.81 174	99.38 161	97.33 212	97.82 228	99.57 83	99.17 89	99.35 118	99.17 149	98.35 85	99.69 295	98.46 123	99.73 169	99.41 196
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 89	99.02 79	98.76 187	99.38 161	97.26 217	98.49 133	99.50 110	98.86 133	99.19 152	99.06 173	98.23 96	99.69 295	98.71 108	99.76 162	99.33 234

TranMVSNet+NR-MVSNet		99.17 52	99.07 76	99.46 62	99.37 167	98.87 81	98.39 146	99.42 155	99.42 54	99.36 116	99.06 173	98.38 80	99.95 26	98.34 129	99.90 83	99.57 117

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

tttt0517		95.64 361	94.98 371	97.64 320	99.36 168	93.81 366	98.72 102	90.47 452	98.08 200	98.67 240	98.34 323	73.88 440	99.92 63	97.77 171	99.51 261	99.20 271

test_part2					99.36 168	99.10 65				99.05 173

v1144		98.60 152	98.66 127	98.41 249	99.36 168	95.90 284	97.58 268	99.34 186	97.51 247	99.27 135	99.15 155	96.34 237	99.80 224	99.47 52	99.93 54	99.51 149

CP-MVS		98.70 130	98.42 167	99.52 44	99.36 168	99.12 62	98.72 102	99.36 174	97.54 245	98.30 280	98.40 315	97.86 131	99.89 95	96.53 276	99.72 177	99.56 123

Test_1112_low_res		96.99 315	96.55 326	98.31 262	99.35 173	95.47 302	95.84 389	99.53 102	91.51 425	96.80 382	98.48 309	91.36 352	99.83 190	96.58 265	99.53 256	99.62 87

DeepC-MVS	97.60 4	98.97 87	98.93 90	99.10 124	99.35 173	97.98 158	98.01 198	99.46 131	97.56 241	99.54 75	99.50 67	98.97 28	99.84 172	98.06 147	99.92 67	99.49 157
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 292	96.86 304	98.58 217	99.34 175	96.32 270	96.75 332	99.58 76	93.14 406	96.89 377	97.48 380	92.11 344	99.86 141	96.91 232	99.54 252	99.57 117

reproduce_model		99.15 57	98.97 87	99.67 4	99.33 176	99.44 10	98.15 170	99.47 127	99.12 92	99.52 81	99.32 111	98.31 88	99.90 79	97.78 170	99.73 169	99.66 75

MVSMamba_PlusPlus		98.83 106	98.98 86	98.36 257	99.32 177	96.58 259	98.90 83	99.41 159	99.75 11	98.72 235	99.50 67	96.17 241	99.94 41	99.27 63	99.78 143	98.57 370

fmvsm_s_conf0.5_n_4		99.01 80	99.22 53	98.38 253	99.31 178	95.48 300	97.56 270	99.73 43	98.87 131	99.75 44	99.27 119	98.80 40	99.86 141	99.80 16	99.90 83	99.81 38

SF-MVS		98.53 165	98.27 191	99.32 87	99.31 178	98.75 87	98.19 164	99.41 159	96.77 310	98.83 218	98.90 223	97.80 137	99.82 200	95.68 322	99.52 259	99.38 214

CPTT-MVS		97.84 251	97.36 275	99.27 95	99.31 178	98.46 111	98.29 153	99.27 222	94.90 374	97.83 320	98.37 319	94.90 286	99.84 172	93.85 373	99.54 252	99.51 149

UnsupCasMVSNet_eth		97.89 240	97.60 261	98.75 189	99.31 178	97.17 227	97.62 260	99.35 180	98.72 141	98.76 231	98.68 274	92.57 338	99.74 272	97.76 175	95.60 444	99.34 229

fmvsm_s_conf0.5_n_7		98.83 106	99.04 78	98.20 271	99.30 182	94.83 323	97.23 302	99.36 174	98.64 144	99.84 30	99.43 86	98.10 112	99.91 72	99.56 39	99.96 28	99.87 21

pmmvs-eth3d		98.47 173	98.34 180	98.86 168	99.30 182	97.76 185	97.16 311	99.28 219	95.54 356	99.42 103	99.19 141	97.27 181	99.63 330	97.89 159	99.97 21	99.20 271

mamv4		99.44 19	99.39 28	99.58 20	99.30 182	99.74 2	99.04 68	99.81 31	99.77 10	99.82 33	99.57 49	97.82 135	99.98 4	99.53 46	99.89 89	99.01 304

SymmetryMVS		98.05 226	97.71 251	99.09 128	99.29 185	97.83 174	98.28 154	97.64 378	99.24 74	98.80 224	98.85 236	89.76 366	99.94 41	98.04 149	99.50 268	99.49 157

Anonymous20231211		99.27 38	99.27 47	99.26 97	99.29 185	98.18 133	99.49 12	99.51 107	99.70 16	99.80 37	99.68 25	96.84 204	99.83 190	99.21 69	99.91 76	99.77 48

viewmanbaseed2359cas		98.58 155	98.54 146	98.70 197	99.28 187	97.13 231	97.47 282	99.55 94	97.55 243	98.96 191	98.92 218	97.77 139	99.59 346	97.59 186	99.77 149	99.39 206

UnsupCasMVSNet_bld		97.30 290	96.92 300	98.45 244	99.28 187	96.78 250	96.20 365	99.27 222	95.42 360	98.28 284	98.30 327	93.16 324	99.71 286	94.99 336	97.37 420	98.87 331

EC-MVSNet		99.09 70	99.05 77	99.20 106	99.28 187	98.93 79	99.24 44	99.84 22	99.08 107	98.12 297	98.37 319	98.72 49	99.90 79	99.05 82	99.77 149	98.77 348

mamba_0408		98.80 113	98.88 96	98.55 227	99.27 190	96.50 262	98.00 199	99.60 71	98.93 124	99.22 147	98.84 241	98.59 62	99.89 95	97.74 176	99.72 177	99.27 249

mamba_test_0407_2		98.80 113	98.88 96	98.56 225	99.27 190	96.50 262	98.00 199	99.60 71	98.93 124	99.22 147	98.84 241	98.59 62	99.90 79	97.74 176	99.72 177	99.27 249

mamba_test_0407		98.86 103	98.96 89	98.55 227	99.27 190	96.50 262	98.04 190	99.66 59	99.09 103	99.22 147	99.02 185	98.79 42	99.87 132	97.87 164	99.72 177	99.27 249

reproduce-ours		99.09 70	98.90 93	99.67 4	99.27 190	99.49 6	98.00 199	99.42 155	99.05 110	99.48 89	99.27 119	98.29 90	99.89 95	97.61 183	99.71 186	99.62 87

our_new_method		99.09 70	98.90 93	99.67 4	99.27 190	99.49 6	98.00 199	99.42 155	99.05 110	99.48 89	99.27 119	98.29 90	99.89 95	97.61 183	99.71 186	99.62 87

DPE-MVS		98.59 154	98.26 192	99.57 21	99.27 190	99.15 52	97.01 316	99.39 164	97.67 228	99.44 98	98.99 200	97.53 162	99.89 95	95.40 330	99.68 201	99.66 75
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 250	98.18 204	96.87 368	99.27 190	91.16 417	95.53 399	99.25 228	99.10 100	99.41 105	99.35 100	93.10 326	99.96 14	98.65 112	99.94 49	99.49 157

v1192		98.60 152	98.66 127	98.41 249	99.27 190	95.88 285	97.52 275	99.36 174	97.41 260	99.33 122	99.20 140	96.37 235	99.82 200	99.57 37	99.92 67	99.55 130

N_pmnet		97.63 264	97.17 285	98.99 147	99.27 190	97.86 171	95.98 376	93.41 441	95.25 365	99.47 93	98.90 223	95.63 267	99.85 154	96.91 232	99.73 169	99.27 249

FPMVS		93.44 399	92.23 406	97.08 356	99.25 199	97.86 171	95.61 396	97.16 390	92.90 410	93.76 443	98.65 281	75.94 438	95.66 457	79.30 455	97.49 413	97.73 421

new-patchmatchnet		98.35 188	98.74 111	97.18 351	99.24 200	92.23 399	96.42 352	99.48 119	98.30 174	99.69 54	99.53 63	97.44 171	99.82 200	98.84 97	99.77 149	99.49 157

MCST-MVS		98.00 231	97.63 259	99.10 124	99.24 200	98.17 134	96.89 325	98.73 331	95.66 351	97.92 311	97.70 368	97.17 187	99.66 319	96.18 298	99.23 313	99.47 176

UniMVSNet (Re)		98.87 100	98.71 118	99.35 76	99.24 200	98.73 91	97.73 245	99.38 166	98.93 124	99.12 158	98.73 260	96.77 212	99.86 141	98.63 114	99.80 132	99.46 178

jason		97.45 278	97.35 276	97.76 304	99.24 200	93.93 360	95.86 386	98.42 349	94.24 389	98.50 266	98.13 337	94.82 290	99.91 72	97.22 208	99.73 169	99.43 190
jason: jason.
IterMVS		97.73 256	98.11 213	96.57 378	99.24 200	90.28 426	95.52 401	99.21 237	98.86 133	99.33 122	99.33 107	93.11 325	99.94 41	98.49 122	99.94 49	99.48 168
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 161	98.62 134	98.32 260	99.22 205	95.58 295	97.51 277	99.45 135	97.16 288	99.45 97	99.24 131	96.12 245	99.85 154	99.60 35	99.88 91	99.55 130

ITE_SJBPF				98.87 167	99.22 205	98.48 110		99.35 180	97.50 248	98.28 284	98.60 292	97.64 150	99.35 408	93.86 372	99.27 305	98.79 346

h-mvs33		97.77 254	97.33 278	99.10 124	99.21 207	97.84 173	98.35 150	98.57 341	99.11 93	98.58 255	99.02 185	88.65 377	99.96 14	98.11 142	96.34 436	99.49 157

v144192		98.54 163	98.57 142	98.45 244	99.21 207	95.98 282	97.63 259	99.36 174	97.15 290	99.32 128	99.18 145	95.84 262	99.84 172	99.50 49	99.91 76	99.54 134

APDe-MVS		98.99 83	98.79 107	99.60 15	99.21 207	99.15 52	98.87 88	99.48 119	97.57 239	99.35 118	99.24 131	97.83 132	99.89 95	97.88 162	99.70 193	99.75 57
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 92	98.81 106	99.28 92	99.21 207	98.45 112	98.46 138	99.33 192	99.63 29	99.48 89	99.15 155	97.23 184	99.75 267	97.17 210	99.66 214	99.63 86

SR-MVS-dyc-post		98.81 111	98.55 144	99.57 21	99.20 211	99.38 13	98.48 136	99.30 207	98.64 144	98.95 192	98.96 210	97.49 169	99.86 141	96.56 271	99.39 286	99.45 182

RE-MVS-def			98.58 141		99.20 211	99.38 13	98.48 136	99.30 207	98.64 144	98.95 192	98.96 210	97.75 141		96.56 271	99.39 286	99.45 182

v1921920		98.54 163	98.60 139	98.38 253	99.20 211	95.76 292	97.56 270	99.36 174	97.23 282	99.38 111	99.17 149	96.02 248	99.84 172	99.57 37	99.90 83	99.54 134

thisisatest0530		95.27 368	94.45 379	97.74 307	99.19 214	94.37 338	97.86 224	90.20 453	97.17 287	98.22 287	97.65 370	73.53 441	99.90 79	96.90 237	99.35 292	98.95 316

Anonymous20240529		98.93 92	98.87 98	99.12 120	99.19 214	98.22 131	99.01 70	98.99 286	99.25 73	99.54 75	99.37 95	97.04 193	99.80 224	97.89 159	99.52 259	99.35 227

APD-MVS_3200maxsize		98.84 105	98.61 138	99.53 38	99.19 214	99.27 27	98.49 133	99.33 192	98.64 144	99.03 178	98.98 205	97.89 129	99.85 154	96.54 275	99.42 283	99.46 178

HQP_MVS		97.99 234	97.67 253	98.93 159	99.19 214	97.65 193	97.77 237	99.27 222	98.20 187	97.79 323	97.98 351	94.90 286	99.70 291	94.42 354	99.51 261	99.45 182

plane_prior7					99.19 214	97.87 170

ab-mvs		98.41 178	98.36 177	98.59 216	99.19 214	97.23 218	99.32 26	98.81 317	97.66 229	98.62 247	99.40 94	96.82 207	99.80 224	95.88 309	99.51 261	98.75 351

F-COLMAP		97.30 290	96.68 317	99.14 118	99.19 214	98.39 114	97.27 301	99.30 207	92.93 409	96.62 388	98.00 349	95.73 265	99.68 304	92.62 400	98.46 381	99.35 227

SR-MVS		98.71 126	98.43 165	99.57 21	99.18 221	99.35 17	98.36 149	99.29 215	98.29 177	98.88 210	98.85 236	97.53 162	99.87 132	96.14 300	99.31 298	99.48 168

UniMVSNet_NR-MVSNet		98.86 103	98.68 124	99.40 68	99.17 222	98.74 88	97.68 249	99.40 162	99.14 91	99.06 166	98.59 293	96.71 218	99.93 52	98.57 117	99.77 149	99.53 143

LF4IMVS		97.90 238	97.69 252	98.52 235	99.17 222	97.66 192	97.19 310	99.47 127	96.31 329	97.85 319	98.20 334	96.71 218	99.52 373	94.62 346	99.72 177	98.38 387

SMA-MVS		98.40 180	98.03 222	99.51 48	99.16 224	99.21 33	98.05 188	99.22 236	94.16 391	98.98 183	99.10 167	97.52 164	99.79 237	96.45 281	99.64 217	99.53 143
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
DU-MVS		98.82 109	98.63 132	99.39 69	99.16 224	98.74 88	97.54 273	99.25 228	98.84 136	99.06 166	98.76 257	96.76 214	99.93 52	98.57 117	99.77 149	99.50 152

NR-MVSNet		98.95 90	98.82 104	99.36 70	99.16 224	98.72 93	99.22 45	99.20 239	99.10 100	99.72 46	98.76 257	96.38 234	99.86 141	98.00 154	99.82 117	99.50 152

MVS_111021_LR		98.30 197	98.12 212	98.83 171	99.16 224	98.03 153	96.09 373	99.30 207	97.58 238	98.10 299	98.24 330	98.25 94	99.34 409	96.69 257	99.65 215	99.12 290

DSMNet-mixed		97.42 281	97.60 261	96.87 368	99.15 228	91.46 406	98.54 121	99.12 261	92.87 411	97.58 336	99.63 39	96.21 240	99.90 79	95.74 318	99.54 252	99.27 249

D2MVS		97.84 251	97.84 242	97.83 296	99.14 229	94.74 327	96.94 320	98.88 301	95.84 348	98.89 206	98.96 210	94.40 302	99.69 295	97.55 187	99.95 38	99.05 296

pmmvs5		97.64 263	97.49 267	98.08 281	99.14 229	95.12 316	96.70 335	99.05 272	93.77 398	98.62 247	98.83 243	93.23 322	99.75 267	98.33 131	99.76 162	99.36 223

SPE-MVS-test		99.13 64	99.09 73	99.26 97	99.13 231	98.97 73	99.31 30	99.88 14	99.44 51	98.16 292	98.51 302	98.64 56	99.93 52	98.91 91	99.85 102	98.88 330

VDD-MVS		98.56 157	98.39 172	99.07 131	99.13 231	98.07 148	98.59 115	97.01 393	99.59 35	99.11 159	99.27 119	94.82 290	99.79 237	98.34 129	99.63 220	99.34 229

save fliter					99.11 233	97.97 159	96.53 344	99.02 280	98.24 180

APD-MVS		98.10 220	97.67 253	99.42 64	99.11 233	98.93 79	97.76 240	99.28 219	94.97 372	98.72 235	98.77 255	97.04 193	99.85 154	93.79 374	99.54 252	99.49 157
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 133	98.71 118	98.62 210	99.10 235	96.37 268	97.23 302	98.87 303	99.20 81	99.19 152	98.99 200	97.30 178	99.85 154	98.77 103	99.79 138	99.65 80

EI-MVSNet		98.40 180	98.51 150	98.04 286	99.10 235	94.73 328	97.20 307	98.87 303	98.97 119	99.06 166	99.02 185	96.00 250	99.80 224	98.58 115	99.82 117	99.60 97

CVMVSNet		96.25 342	97.21 284	93.38 435	99.10 235	80.56 463	97.20 307	98.19 360	96.94 300	99.00 180	99.02 185	89.50 370	99.80 224	96.36 287	99.59 234	99.78 45

EI-MVSNet-Vis-set		98.68 138	98.70 121	98.63 208	99.09 238	96.40 267	97.23 302	98.86 308	99.20 81	99.18 156	98.97 207	97.29 180	99.85 154	98.72 107	99.78 143	99.64 81

HPM-MVS++		98.10 220	97.64 258	99.48 56	99.09 238	99.13 60	97.52 275	98.75 328	97.46 256	96.90 376	97.83 361	96.01 249	99.84 172	95.82 316	99.35 292	99.46 178

DP-MVS Recon		97.33 288	96.92 300	98.57 220	99.09 238	97.99 155	96.79 328	99.35 180	93.18 405	97.71 327	98.07 345	95.00 285	99.31 413	93.97 367	99.13 329	98.42 384

MVS_111021_HR		98.25 206	98.08 217	98.75 189	99.09 238	97.46 205	95.97 377	99.27 222	97.60 237	97.99 309	98.25 329	98.15 109	99.38 404	96.87 240	99.57 243	99.42 193

BP-MVS1		97.40 283	96.97 296	98.71 196	99.07 242	96.81 246	98.34 152	97.18 388	98.58 155	98.17 289	98.61 290	84.01 409	99.94 41	98.97 88	99.78 143	99.37 216

9.14			97.78 244		99.07 242		97.53 274	99.32 194	95.53 357	98.54 262	98.70 270	97.58 156	99.76 260	94.32 359	99.46 273

PAPM_NR		96.82 322	96.32 333	98.30 263	99.07 242	96.69 254	97.48 280	98.76 325	95.81 349	96.61 389	96.47 406	94.12 311	99.17 426	90.82 427	97.78 407	99.06 295

TAMVS		98.24 207	98.05 220	98.80 176	99.07 242	97.18 225	97.88 220	98.81 317	96.66 315	99.17 157	99.21 138	94.81 292	99.77 254	96.96 230	99.88 91	99.44 186

CLD-MVS		97.49 274	97.16 286	98.48 241	99.07 242	97.03 234	94.71 422	99.21 237	94.46 383	98.06 302	97.16 392	97.57 157	99.48 385	94.46 351	99.78 143	98.95 316
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 64	99.10 71	99.24 102	99.06 247	99.15 52	99.36 22	99.88 14	99.36 62	98.21 288	98.46 310	98.68 53	99.93 52	99.03 84	99.85 102	98.64 363

thres100view900		94.19 385	93.67 390	95.75 402	99.06 247	91.35 410	98.03 192	94.24 436	98.33 170	97.40 352	94.98 436	79.84 425	99.62 333	83.05 448	98.08 398	96.29 443

thres600view7		94.45 380	93.83 387	96.29 386	99.06 247	91.53 405	97.99 206	94.24 436	98.34 169	97.44 350	95.01 434	79.84 425	99.67 308	84.33 446	98.23 387	97.66 424

plane_prior1					99.05 250

YYNet1		97.60 265	97.67 253	97.39 344	99.04 251	93.04 383	95.27 408	98.38 352	97.25 276	98.92 202	98.95 214	95.48 274	99.73 278	96.99 226	98.74 362	99.41 196

MDA-MVSNet_test_wron		97.60 265	97.66 256	97.41 343	99.04 251	93.09 379	95.27 408	98.42 349	97.26 275	98.88 210	98.95 214	95.43 275	99.73 278	97.02 223	98.72 364	99.41 196

MIMVSNet		96.62 329	96.25 337	97.71 311	99.04 251	94.66 331	99.16 54	96.92 399	97.23 282	97.87 316	99.10 167	86.11 392	99.65 324	91.65 411	99.21 317	98.82 335

icg_test_0407_2		98.20 212	98.38 174	97.65 317	99.03 254	94.03 351	95.78 391	99.45 135	98.16 193	99.06 166	98.71 263	98.27 92	99.68 304	97.50 192	99.45 275	99.22 266

icg_test_0407		98.39 186	98.64 130	97.66 315	99.03 254	94.03 351	98.10 179	99.45 135	98.16 193	99.06 166	98.71 263	98.27 92	99.71 286	97.50 192	99.45 275	99.22 266

ICG_test_0404		98.07 224	98.20 199	97.69 312	99.03 254	94.03 351	96.67 336	99.45 135	98.16 193	98.03 306	98.71 263	96.80 210	99.82 200	97.50 192	99.45 275	99.22 266

icg_test_0403		98.34 189	98.56 143	97.66 315	99.03 254	94.03 351	97.98 207	99.45 135	98.16 193	98.89 206	98.71 263	97.90 127	99.74 272	97.50 192	99.45 275	99.22 266

PatchMatch-RL		97.24 296	96.78 311	98.61 213	99.03 254	97.83 174	96.36 355	99.06 269	93.49 403	97.36 356	97.78 362	95.75 264	99.49 382	93.44 383	98.77 361	98.52 372

viewmambaseed2359dif		98.19 213	98.26 192	97.99 289	99.02 259	95.03 319	96.59 341	99.53 102	96.21 332	99.00 180	98.99 200	97.62 152	99.61 340	97.62 182	99.72 177	99.33 234

GDP-MVS		97.50 271	97.11 290	98.67 201	99.02 259	96.85 244	98.16 169	99.71 46	98.32 172	98.52 265	98.54 297	83.39 413	99.95 26	98.79 99	99.56 246	99.19 276

ZD-MVS					99.01 261	98.84 82		99.07 268	94.10 393	98.05 304	98.12 339	96.36 236	99.86 141	92.70 399	99.19 321

CDPH-MVS		97.26 293	96.66 320	99.07 131	99.00 262	98.15 135	96.03 375	99.01 283	91.21 429	97.79 323	97.85 360	96.89 202	99.69 295	92.75 397	99.38 289	99.39 206

diffmvs		98.22 208	98.24 196	98.17 274	99.00 262	95.44 303	96.38 354	99.58 76	97.79 222	98.53 263	98.50 306	96.76 214	99.74 272	97.95 158	99.64 217	99.34 229
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		98.40 180	98.19 203	99.03 141	99.00 262	97.65 193	96.85 326	98.94 288	98.57 156	98.89 206	98.50 306	95.60 268	99.85 154	97.54 189	99.85 102	99.59 104

plane_prior6					98.99 265	97.70 191						94.90 286

xiu_mvs_v1_base_debu		97.86 245	98.17 205	96.92 365	98.98 266	93.91 361	96.45 348	99.17 251	97.85 217	98.41 274	97.14 394	98.47 72	99.92 63	98.02 151	99.05 335	96.92 436

xiu_mvs_v1_base		97.86 245	98.17 205	96.92 365	98.98 266	93.91 361	96.45 348	99.17 251	97.85 217	98.41 274	97.14 394	98.47 72	99.92 63	98.02 151	99.05 335	96.92 436

xiu_mvs_v1_base_debi		97.86 245	98.17 205	96.92 365	98.98 266	93.91 361	96.45 348	99.17 251	97.85 217	98.41 274	97.14 394	98.47 72	99.92 63	98.02 151	99.05 335	96.92 436

MVP-Stereo		98.08 223	97.92 236	98.57 220	98.96 269	96.79 247	97.90 218	99.18 247	96.41 325	98.46 269	98.95 214	95.93 259	99.60 342	96.51 277	98.98 349	99.31 241
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 180	98.68 124	97.54 332	98.96 269	97.99 155	97.88 220	99.36 174	98.20 187	99.63 65	99.04 182	98.76 45	95.33 459	96.56 271	99.74 166	99.31 241
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				98.91 163	98.94 271	97.76 185		98.76 325	87.58 446	96.75 384	98.10 341	94.80 293	99.78 248	92.73 398	99.00 344	99.20 271

USDC		97.41 282	97.40 271	97.44 341	98.94 271	93.67 371	95.17 411	99.53 102	94.03 395	98.97 187	99.10 167	95.29 277	99.34 409	95.84 315	99.73 169	99.30 244

tfpn200view9		94.03 389	93.44 392	95.78 401	98.93 273	91.44 408	97.60 265	94.29 434	97.94 209	97.10 362	94.31 443	79.67 427	99.62 333	83.05 448	98.08 398	96.29 443

testdata				98.09 278	98.93 273	95.40 305		98.80 319	90.08 437	97.45 349	98.37 319	95.26 278	99.70 291	93.58 379	98.95 352	99.17 283

thres400		94.14 387	93.44 392	96.24 389	98.93 273	91.44 408	97.60 265	94.29 434	97.94 209	97.10 362	94.31 443	79.67 427	99.62 333	83.05 448	98.08 398	97.66 424

TAPA-MVS	96.21 11	96.63 328	95.95 339	98.65 202	98.93 273	98.09 142	96.93 322	99.28 219	83.58 452	98.13 296	97.78 362	96.13 243	99.40 400	93.52 380	99.29 303	98.45 377
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 277	96.93 241	95.54 398	98.78 322	85.72 449	96.86 379	98.11 340	94.43 300			99.10 334	99.23 261

PVSNet_BlendedMVS		97.55 270	97.53 264	97.60 324	98.92 277	93.77 368	96.64 338	99.43 149	94.49 381	97.62 332	99.18 145	96.82 207	99.67 308	94.73 343	99.93 54	99.36 223

PVSNet_Blended		96.88 318	96.68 317	97.47 339	98.92 277	93.77 368	94.71 422	99.43 149	90.98 431	97.62 332	97.36 388	96.82 207	99.67 308	94.73 343	99.56 246	98.98 310

MSDG		97.71 258	97.52 265	98.28 265	98.91 280	96.82 245	94.42 432	99.37 170	97.65 230	98.37 279	98.29 328	97.40 173	99.33 411	94.09 365	99.22 314	98.68 361

Anonymous202405211		97.90 238	97.50 266	99.08 129	98.90 281	98.25 125	98.53 122	96.16 411	98.87 131	99.11 159	98.86 233	90.40 362	99.78 248	97.36 201	99.31 298	99.19 276

原ACMM1				98.35 258	98.90 281	96.25 272		98.83 316	92.48 415	96.07 406	98.10 341	95.39 276	99.71 286	92.61 401	98.99 346	99.08 292

GBi-Net		98.65 143	98.47 159	99.17 111	98.90 281	98.24 126	99.20 48	99.44 143	98.59 152	98.95 192	99.55 57	94.14 308	99.86 141	97.77 171	99.69 196	99.41 196

test1		98.65 143	98.47 159	99.17 111	98.90 281	98.24 126	99.20 48	99.44 143	98.59 152	98.95 192	99.55 57	94.14 308	99.86 141	97.77 171	99.69 196	99.41 196

FMVSNet2		98.49 171	98.40 169	98.75 189	98.90 281	97.14 230	98.61 113	99.13 260	98.59 152	99.19 152	99.28 117	94.14 308	99.82 200	97.97 156	99.80 132	99.29 246

OMC-MVS		97.88 242	97.49 267	99.04 140	98.89 286	98.63 95	96.94 320	99.25 228	95.02 370	98.53 263	98.51 302	97.27 181	99.47 388	93.50 382	99.51 261	99.01 304

VortexMVS		97.98 235	98.31 185	97.02 359	98.88 287	91.45 407	98.03 192	99.47 127	98.65 143	99.55 73	99.47 77	91.49 351	99.81 216	99.32 59	99.91 76	99.80 40

MVSFormer		98.26 203	98.43 165	97.77 301	98.88 287	93.89 364	99.39 20	99.56 90	99.11 93	98.16 292	98.13 337	93.81 316	99.97 7	99.26 64	99.57 243	99.43 190

lupinMVS		97.06 308	96.86 304	97.65 317	98.88 287	93.89 364	95.48 402	97.97 366	93.53 401	98.16 292	97.58 374	93.81 316	99.91 72	96.77 248	99.57 243	99.17 283

dmvs_re		95.98 350	95.39 360	97.74 307	98.86 290	97.45 206	98.37 148	95.69 423	97.95 207	96.56 390	95.95 415	90.70 359	97.68 453	88.32 436	96.13 440	98.11 399

DELS-MVS		98.27 201	98.20 199	98.48 241	98.86 290	96.70 253	95.60 397	99.20 239	97.73 225	98.45 270	98.71 263	97.50 166	99.82 200	98.21 136	99.59 234	98.93 321
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		97.89 240	97.98 227	97.60 324	98.86 290	94.35 339	96.21 364	99.44 143	97.45 258	99.06 166	98.88 230	97.99 122	99.28 419	94.38 358	99.58 239	99.18 279

LCM-MVSNet-Re		98.64 145	98.48 157	99.11 122	98.85 293	98.51 108	98.49 133	99.83 25	98.37 167	99.69 54	99.46 79	98.21 101	99.92 63	94.13 364	99.30 301	98.91 325

pmmvs4		97.58 268	97.28 279	98.51 236	98.84 294	96.93 241	95.40 406	98.52 344	93.60 400	98.61 249	98.65 281	95.10 282	99.60 342	96.97 229	99.79 138	98.99 309

NP-MVS					98.84 294	97.39 210					96.84 397

sss		97.21 298	96.93 298	98.06 283	98.83 296	95.22 312	96.75 332	98.48 346	94.49 381	97.27 358	97.90 357	92.77 334	99.80 224	96.57 267	99.32 296	99.16 286

PVSNet	93.40 17	95.67 359	95.70 345	95.57 406	98.83 296	88.57 433	92.50 449	97.72 371	92.69 413	96.49 398	96.44 407	93.72 319	99.43 396	93.61 377	99.28 304	98.71 354

MVE	83.40 22	92.50 412	91.92 414	94.25 422	98.83 296	91.64 404	92.71 448	83.52 462	95.92 346	86.46 460	95.46 428	95.20 279	95.40 458	80.51 453	98.64 373	95.73 451
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 393	93.91 385	93.39 434	98.82 299	81.72 461	97.76 240	95.28 425	98.60 151	96.54 391	96.66 401	65.85 457	99.62 333	96.65 260	98.99 346	98.82 335

ambc				98.24 269	98.82 299	95.97 283	98.62 112	99.00 285		99.27 135	99.21 138	96.99 198	99.50 379	96.55 274	99.50 268	99.26 255

旧先验1					98.82 299	97.45 206		98.76 325			98.34 323	95.50 273			99.01 343	99.23 261

test_vis1_rt		97.75 255	97.72 250	97.83 296	98.81 302	96.35 269	97.30 297	99.69 50	94.61 379	97.87 316	98.05 346	96.26 239	98.32 447	98.74 105	98.18 390	98.82 335

WTY-MVS		96.67 326	96.27 336	97.87 294	98.81 302	94.61 333	96.77 330	97.92 368	94.94 373	97.12 361	97.74 365	91.11 355	99.82 200	93.89 370	98.15 394	99.18 279

3Dnovator+	97.89 3	98.69 133	98.51 150	99.24 102	98.81 302	98.40 113	99.02 69	99.19 243	98.99 116	98.07 301	99.28 117	97.11 191	99.84 172	96.84 243	99.32 296	99.47 176

QAPM		97.31 289	96.81 310	98.82 172	98.80 305	97.49 201	99.06 65	99.19 243	90.22 435	97.69 329	99.16 151	96.91 201	99.90 79	90.89 426	99.41 284	99.07 294

VNet		98.42 177	98.30 186	98.79 179	98.79 306	97.29 214	98.23 160	98.66 335	99.31 67	98.85 215	98.80 249	94.80 293	99.78 248	98.13 141	99.13 329	99.31 241

DPM-MVS		96.32 338	95.59 351	98.51 236	98.76 307	97.21 222	94.54 431	98.26 355	91.94 420	96.37 399	97.25 390	93.06 328	99.43 396	91.42 416	98.74 362	98.89 327

3Dnovator	98.27 2	98.81 111	98.73 113	99.05 138	98.76 307	97.81 182	99.25 43	99.30 207	98.57 156	98.55 260	99.33 107	97.95 124	99.90 79	97.16 211	99.67 207	99.44 186

PLC	94.65 16	96.51 331	95.73 344	98.85 169	98.75 309	97.91 167	96.42 352	99.06 269	90.94 432	95.59 412	97.38 386	94.41 301	99.59 346	90.93 424	98.04 403	99.05 296
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 320	96.75 313	97.08 356	98.74 310	93.33 377	96.71 334	98.26 355	96.72 312	98.44 271	97.37 387	95.20 279	99.47 388	91.89 406	97.43 417	98.44 380

hse-mvs2		97.46 276	97.07 291	98.64 204	98.73 311	97.33 212	97.45 284	97.64 378	99.11 93	98.58 255	97.98 351	88.65 377	99.79 237	98.11 142	97.39 419	98.81 340

CDS-MVSNet		97.69 259	97.35 276	98.69 198	98.73 311	97.02 235	96.92 324	98.75 328	95.89 347	98.59 253	98.67 276	92.08 345	99.74 272	96.72 254	99.81 121	99.32 237
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SD_0403		96.28 340	95.83 341	97.64 320	98.72 313	94.30 340	98.87 88	98.77 323	97.80 220	96.53 392	98.02 348	97.34 176	99.47 388	76.93 457	99.48 271	99.16 286

EIA-MVS		98.00 231	97.74 247	98.80 176	98.72 313	98.09 142	98.05 188	99.60 71	97.39 262	96.63 387	95.55 423	97.68 144	99.80 224	96.73 253	99.27 305	98.52 372

LFMVS		97.20 299	96.72 314	98.64 204	98.72 313	96.95 239	98.93 81	94.14 438	99.74 13	98.78 226	99.01 196	84.45 404	99.73 278	97.44 197	99.27 305	99.25 256

new_pmnet		96.99 315	96.76 312	97.67 313	98.72 313	94.89 322	95.95 381	98.20 358	92.62 414	98.55 260	98.54 297	94.88 289	99.52 373	93.96 368	99.44 282	98.59 369

Fast-Effi-MVS+		97.67 261	97.38 273	98.57 220	98.71 317	97.43 208	97.23 302	99.45 135	94.82 376	96.13 403	96.51 403	98.52 70	99.91 72	96.19 296	98.83 358	98.37 389

TEST9					98.71 317	98.08 146	95.96 379	99.03 277	91.40 426	95.85 409	97.53 376	96.52 227	99.76 260

train_agg		97.10 305	96.45 330	99.07 131	98.71 317	98.08 146	95.96 379	99.03 277	91.64 421	95.85 409	97.53 376	96.47 229	99.76 260	93.67 376	99.16 324	99.36 223

TSAR-MVS + GP.		98.18 215	97.98 227	98.77 186	98.71 317	97.88 169	96.32 358	98.66 335	96.33 327	99.23 146	98.51 302	97.48 170	99.40 400	97.16 211	99.46 273	99.02 303

FA-MVS(test-final)		96.99 315	96.82 308	97.50 336	98.70 321	94.78 325	99.34 23	96.99 394	95.07 369	98.48 268	99.33 107	88.41 380	99.65 324	96.13 302	98.92 355	98.07 402

AUN-MVS		96.24 344	95.45 356	98.60 215	98.70 321	97.22 220	97.38 289	97.65 376	95.95 345	95.53 419	97.96 355	82.11 421	99.79 237	96.31 289	97.44 416	98.80 345

our_test_3		97.39 284	97.73 249	96.34 384	98.70 321	89.78 429	94.61 428	98.97 287	96.50 320	99.04 175	98.85 236	95.98 255	99.84 172	97.26 206	99.67 207	99.41 196

ppachtmachnet_test		97.50 271	97.74 247	96.78 374	98.70 321	91.23 416	94.55 430	99.05 272	96.36 326	99.21 150	98.79 251	96.39 232	99.78 248	96.74 251	99.82 117	99.34 229

PCF-MVS	92.86 18	94.36 381	93.00 399	98.42 248	98.70 321	97.56 198	93.16 447	99.11 263	79.59 456	97.55 339	97.43 383	92.19 342	99.73 278	79.85 454	99.45 275	97.97 408
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 237	98.02 223	97.58 326	98.69 326	94.10 347	98.13 172	98.90 297	97.95 207	97.32 357	99.58 47	95.95 258	98.75 442	96.41 283	99.22 314	99.87 21

ETV-MVS		98.03 227	97.86 241	98.56 225	98.69 326	98.07 148	97.51 277	99.50 110	98.10 199	97.50 344	95.51 424	98.41 78	99.88 113	96.27 292	99.24 310	97.71 423

test_prior				98.95 156	98.69 326	97.95 163		99.03 277					99.59 346			99.30 244

mvsmamba		97.57 269	97.26 280	98.51 236	98.69 326	96.73 252	98.74 97	97.25 387	97.03 296	97.88 315	99.23 136	90.95 356	99.87 132	96.61 263	99.00 344	98.91 325

agg_prior					98.68 330	97.99 155		99.01 283		95.59 412			99.77 254

test_8					98.67 331	98.01 154	95.91 385	99.02 280	91.64 421	95.79 411	97.50 379	96.47 229	99.76 260

HQP-NCC					98.67 331		96.29 360		96.05 338	95.55 415

ACMP_Plane					98.67 331		96.29 360		96.05 338	95.55 415

CNVR-MVS		98.17 217	97.87 240	99.07 131	98.67 331	98.24 126	97.01 316	98.93 291	97.25 276	97.62 332	98.34 323	97.27 181	99.57 355	96.42 282	99.33 295	99.39 206

HQP-MVS		97.00 314	96.49 329	98.55 227	98.67 331	96.79 247	96.29 360	99.04 275	96.05 338	95.55 415	96.84 397	93.84 314	99.54 367	92.82 394	99.26 308	99.32 237

MM		98.22 208	97.99 226	98.91 163	98.66 336	96.97 236	97.89 219	94.44 432	99.54 39	98.95 192	99.14 158	93.50 320	99.92 63	99.80 16	99.96 28	99.85 29

test_fmvs1		97.72 257	97.94 233	97.07 358	98.66 336	92.39 394	97.68 249	99.81 31	95.20 368	99.54 75	99.44 84	91.56 350	99.41 399	99.78 20	99.77 149	99.40 205

balanced_conf03		98.63 147	98.72 115	98.38 253	98.66 336	96.68 255	98.90 83	99.42 155	98.99 116	98.97 187	99.19 141	95.81 263	99.85 154	98.77 103	99.77 149	98.60 366

thres200		93.72 395	93.14 397	95.46 410	98.66 336	91.29 412	96.61 340	94.63 431	97.39 262	96.83 380	93.71 446	79.88 424	99.56 358	82.40 451	98.13 395	95.54 452

wuyk23d		96.06 346	97.62 260	91.38 439	98.65 340	98.57 102	98.85 92	96.95 397	96.86 305	99.90 14	99.16 151	99.18 19	98.40 446	89.23 434	99.77 149	77.18 459

NCCC		97.86 245	97.47 270	99.05 138	98.61 341	98.07 148	96.98 318	98.90 297	97.63 231	97.04 366	97.93 356	95.99 254	99.66 319	95.31 331	98.82 360	99.43 190

DeepC-MVS_fast	96.85 6	98.30 197	98.15 209	98.75 189	98.61 341	97.23 218	97.76 240	99.09 266	97.31 270	98.75 232	98.66 279	97.56 158	99.64 327	96.10 303	99.55 250	99.39 206
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 397	92.09 408	97.75 305	98.60 343	94.40 337	97.32 295	95.26 426	97.56 241	96.79 383	95.50 425	53.57 465	99.77 254	95.26 332	98.97 350	99.08 292

thisisatest0515		94.12 388	93.16 396	96.97 363	98.60 343	92.90 384	93.77 443	90.61 451	94.10 393	96.91 373	95.87 418	74.99 439	99.80 224	94.52 349	99.12 332	98.20 395

GA-MVS		95.86 353	95.32 363	97.49 337	98.60 343	94.15 346	93.83 442	97.93 367	95.49 358	96.68 385	97.42 384	83.21 414	99.30 415	96.22 294	98.55 379	99.01 304

dmvs_testset		92.94 407	92.21 407	95.13 414	98.59 346	90.99 419	97.65 255	92.09 447	96.95 299	94.00 439	93.55 447	92.34 340	96.97 456	72.20 458	92.52 454	97.43 431

OPU-MVS				98.82 172	98.59 346	98.30 122	98.10 179				98.52 301	98.18 103	98.75 442	94.62 346	99.48 271	99.41 196

MSLP-MVS++		98.02 228	98.14 211	97.64 320	98.58 348	95.19 313	97.48 280	99.23 235	97.47 251	97.90 313	98.62 288	97.04 193	98.81 440	97.55 187	99.41 284	98.94 320

test12				98.93 159	98.58 348	97.83 174		98.66 335		96.53 392		95.51 272	99.69 295		99.13 329	99.27 249

CL-MVSNet_self_test		97.44 279	97.22 283	98.08 281	98.57 350	95.78 291	94.30 435	98.79 320	96.58 318	98.60 251	98.19 335	94.74 296	99.64 327	96.41 283	98.84 357	98.82 335

PS-MVSNAJ		97.08 307	97.39 272	96.16 395	98.56 351	92.46 392	95.24 410	98.85 311	97.25 276	97.49 345	95.99 414	98.07 113	99.90 79	96.37 285	98.67 372	96.12 448

CNLPA		97.17 302	96.71 315	98.55 227	98.56 351	98.05 152	96.33 357	98.93 291	96.91 302	97.06 365	97.39 385	94.38 303	99.45 393	91.66 410	99.18 323	98.14 398

xiu_mvs_v2_base		97.16 303	97.49 267	96.17 393	98.54 353	92.46 392	95.45 403	98.84 312	97.25 276	97.48 346	96.49 404	98.31 88	99.90 79	96.34 288	98.68 371	96.15 447

alignmvs		97.35 286	96.88 303	98.78 182	98.54 353	98.09 142	97.71 246	97.69 373	99.20 81	97.59 335	95.90 417	88.12 382	99.55 362	98.18 138	98.96 351	98.70 357

FE-MVS		95.66 360	94.95 373	97.77 301	98.53 355	95.28 309	99.40 19	96.09 414	93.11 407	97.96 310	99.26 124	79.10 431	99.77 254	92.40 403	98.71 366	98.27 393

Effi-MVS+		98.02 228	97.82 243	98.62 210	98.53 355	97.19 224	97.33 294	99.68 55	97.30 271	96.68 385	97.46 382	98.56 68	99.80 224	96.63 261	98.20 389	98.86 332

baseline1		95.96 351	95.44 357	97.52 334	98.51 357	93.99 358	98.39 146	96.09 414	98.21 183	98.40 278	97.76 364	86.88 384	99.63 330	95.42 329	89.27 457	98.95 316

MVS_Test		98.18 215	98.36 177	97.67 313	98.48 358	94.73 328	98.18 165	99.02 280	97.69 227	98.04 305	99.11 164	97.22 185	99.56 358	98.57 117	98.90 356	98.71 354

MGCFI-Net		98.34 189	98.28 188	98.51 236	98.47 359	97.59 197	98.96 77	99.48 119	99.18 88	97.40 352	95.50 425	98.66 54	99.50 379	98.18 138	98.71 366	98.44 380

BH-RMVSNet		96.83 320	96.58 325	97.58 326	98.47 359	94.05 348	96.67 336	97.36 382	96.70 314	97.87 316	97.98 351	95.14 281	99.44 395	90.47 429	98.58 378	99.25 256

sasdasda		98.34 189	98.26 192	98.58 217	98.46 361	97.82 179	98.96 77	99.46 131	99.19 85	97.46 347	95.46 428	98.59 62	99.46 391	98.08 145	98.71 366	98.46 374

canonicalmvs		98.34 189	98.26 192	98.58 217	98.46 361	97.82 179	98.96 77	99.46 131	99.19 85	97.46 347	95.46 428	98.59 62	99.46 391	98.08 145	98.71 366	98.46 374

MVS-HIRNet		94.32 382	95.62 348	90.42 440	98.46 361	75.36 464	96.29 360	89.13 455	95.25 365	95.38 421	99.75 16	92.88 331	99.19 425	94.07 366	99.39 286	96.72 441

PHI-MVS		98.29 200	97.95 231	99.34 79	98.44 364	99.16 48	98.12 176	99.38 166	96.01 342	98.06 302	98.43 313	97.80 137	99.67 308	95.69 321	99.58 239	99.20 271

DVP-MVS++		98.90 96	98.70 121	99.51 48	98.43 365	99.15 52	99.43 15	99.32 194	98.17 190	99.26 139	99.02 185	98.18 103	99.88 113	97.07 220	99.45 275	99.49 157

MSC_two_6792asdad				99.32 87	98.43 365	98.37 117		98.86 308					99.89 95	97.14 214	99.60 230	99.71 60

No_MVS				99.32 87	98.43 365	98.37 117		98.86 308					99.89 95	97.14 214	99.60 230	99.71 60

Fast-Effi-MVS+-dtu		98.27 201	98.09 214	98.81 174	98.43 365	98.11 139	97.61 264	99.50 110	98.64 144	97.39 354	97.52 378	98.12 111	99.95 26	96.90 237	98.71 366	98.38 387

OpenMVS_ROB	95.38 14	95.84 355	95.18 368	97.81 298	98.41 369	97.15 229	97.37 291	98.62 339	83.86 451	98.65 243	98.37 319	94.29 306	99.68 304	88.41 435	98.62 376	96.60 442

DeepPCF-MVS	96.93 5	98.32 194	98.01 224	99.23 104	98.39 370	98.97 73	95.03 415	99.18 247	96.88 303	99.33 122	98.78 253	98.16 107	99.28 419	96.74 251	99.62 223	99.44 186

Patchmatch-test		96.55 330	96.34 332	97.17 353	98.35 371	93.06 380	98.40 145	97.79 369	97.33 267	98.41 274	98.67 276	83.68 412	99.69 295	95.16 334	99.31 298	98.77 348

AdaColmap		97.14 304	96.71 315	98.46 243	98.34 372	97.80 183	96.95 319	98.93 291	95.58 355	96.92 371	97.66 369	95.87 261	99.53 369	90.97 423	99.14 327	98.04 403

OpenMVS	96.65 7	97.09 306	96.68 317	98.32 260	98.32 373	97.16 228	98.86 91	99.37 170	89.48 439	96.29 401	99.15 155	96.56 225	99.90 79	92.90 391	99.20 318	97.89 411

MG-MVS		96.77 323	96.61 322	97.26 349	98.31 374	93.06 380	95.93 382	98.12 363	96.45 324	97.92 311	98.73 260	93.77 318	99.39 402	91.19 421	99.04 338	99.33 234

test_yl		96.69 324	96.29 334	97.90 291	98.28 375	95.24 310	97.29 298	97.36 382	98.21 183	98.17 289	97.86 358	86.27 388	99.55 362	94.87 340	98.32 383	98.89 327

DCV-MVSNet		96.69 324	96.29 334	97.90 291	98.28 375	95.24 310	97.29 298	97.36 382	98.21 183	98.17 289	97.86 358	86.27 388	99.55 362	94.87 340	98.32 383	98.89 327

CHOSEN 280x420		95.51 365	95.47 354	95.65 405	98.25 377	88.27 436	93.25 446	98.88 301	93.53 401	94.65 430	97.15 393	86.17 390	99.93 52	97.41 199	99.93 54	98.73 353

SCA		96.41 337	96.66 320	95.67 403	98.24 378	88.35 435	95.85 388	96.88 400	96.11 336	97.67 330	98.67 276	93.10 326	99.85 154	94.16 360	99.22 314	98.81 340

DeepMVS_CX				93.44 433	98.24 378	94.21 343		94.34 433	64.28 459	91.34 453	94.87 440	89.45 371	92.77 460	77.54 456	93.14 453	93.35 455

MS-PatchMatch		97.68 260	97.75 246	97.45 340	98.23 380	93.78 367	97.29 298	98.84 312	96.10 337	98.64 244	98.65 281	96.04 247	99.36 405	96.84 243	99.14 327	99.20 271

BH-w/o		95.13 371	94.89 375	95.86 398	98.20 381	91.31 411	95.65 395	97.37 381	93.64 399	96.52 394	95.70 421	93.04 329	99.02 431	88.10 437	95.82 443	97.24 434

mvs_anonymous		97.83 253	98.16 208	96.87 368	98.18 382	91.89 401	97.31 296	98.90 297	97.37 264	98.83 218	99.46 79	96.28 238	99.79 237	98.90 92	98.16 393	98.95 316

miper_lstm_enhance		97.18 301	97.16 286	97.25 350	98.16 383	92.85 385	95.15 413	99.31 199	97.25 276	98.74 234	98.78 253	90.07 363	99.78 248	97.19 209	99.80 132	99.11 291

RRT-MVS		97.88 242	97.98 227	97.61 323	98.15 384	93.77 368	98.97 76	99.64 64	99.16 90	98.69 237	99.42 87	91.60 348	99.89 95	97.63 181	98.52 380	99.16 286

ET-MVSNet_ETH3D		94.30 384	93.21 395	97.58 326	98.14 385	94.47 336	94.78 421	93.24 443	94.72 377	89.56 455	95.87 418	78.57 434	99.81 216	96.91 232	97.11 428	98.46 374

ADS-MVSNet2		95.43 366	94.98 371	96.76 375	98.14 385	91.74 402	97.92 215	97.76 370	90.23 433	96.51 395	98.91 220	85.61 395	99.85 154	92.88 392	96.90 429	98.69 358

ADS-MVSNet		95.24 369	94.93 374	96.18 392	98.14 385	90.10 428	97.92 215	97.32 385	90.23 433	96.51 395	98.91 220	85.61 395	99.74 272	92.88 392	96.90 429	98.69 358

c3_l		97.36 285	97.37 274	97.31 345	98.09 388	93.25 378	95.01 416	99.16 254	97.05 293	98.77 229	98.72 262	92.88 331	99.64 327	96.93 231	99.76 162	99.05 296

FMVSNet3		97.50 271	97.24 282	98.29 264	98.08 389	95.83 288	97.86 224	98.91 296	97.89 214	98.95 192	98.95 214	87.06 383	99.81 216	97.77 171	99.69 196	99.23 261

PAPM		91.88 421	90.34 424	96.51 379	98.06 390	92.56 390	92.44 450	97.17 389	86.35 447	90.38 454	96.01 413	86.61 386	99.21 424	70.65 460	95.43 445	97.75 420

Effi-MVS+-dtu		98.26 203	97.90 238	99.35 76	98.02 391	99.49 6	98.02 195	99.16 254	98.29 177	97.64 331	97.99 350	96.44 231	99.95 26	96.66 259	98.93 354	98.60 366

eth_miper_zixun_eth		97.23 297	97.25 281	97.17 353	98.00 392	92.77 387	94.71 422	99.18 247	97.27 274	98.56 258	98.74 259	91.89 346	99.69 295	97.06 222	99.81 121	99.05 296

HY-MVS	95.94 13	95.90 352	95.35 362	97.55 331	97.95 393	94.79 324	98.81 96	96.94 398	92.28 418	95.17 423	98.57 295	89.90 365	99.75 267	91.20 420	97.33 424	98.10 400

UGNet		98.53 165	98.45 162	98.79 179	97.94 394	96.96 238	99.08 61	98.54 342	99.10 100	96.82 381	99.47 77	96.55 226	99.84 172	98.56 120	99.94 49	99.55 130
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
MAR-MVS		96.47 335	95.70 345	98.79 179	97.92 395	99.12 62	98.28 154	98.60 340	92.16 419	95.54 418	96.17 411	94.77 295	99.52 373	89.62 432	98.23 387	97.72 422
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		96.86 319	96.55 326	97.79 299	97.91 396	94.21 343	97.56 270	98.87 303	97.49 250	99.06 166	99.05 180	80.72 422	99.80 224	98.44 124	99.82 117	99.37 216

API-MVS		97.04 310	96.91 302	97.42 342	97.88 397	98.23 130	98.18 165	98.50 345	97.57 239	97.39 354	96.75 399	96.77 212	99.15 428	90.16 430	99.02 342	94.88 453

myMVS_eth3d28		92.92 408	92.31 404	94.77 417	97.84 398	87.59 440	96.19 366	96.11 413	97.08 292	94.27 433	93.49 449	66.07 456	98.78 441	91.78 408	97.93 406	97.92 410

miper_ehance_all_eth		97.06 308	97.03 293	97.16 355	97.83 399	93.06 380	94.66 425	99.09 266	95.99 343	98.69 237	98.45 311	92.73 336	99.61 340	96.79 245	99.03 339	98.82 335

cl____		97.02 311	96.83 307	97.58 326	97.82 400	94.04 350	94.66 425	99.16 254	97.04 294	98.63 245	98.71 263	88.68 376	99.69 295	97.00 224	99.81 121	99.00 308

DIV-MVS_self_test		97.02 311	96.84 306	97.58 326	97.82 400	94.03 351	94.66 425	99.16 254	97.04 294	98.63 245	98.71 263	88.69 374	99.69 295	97.00 224	99.81 121	99.01 304

CANet		97.87 244	97.76 245	98.19 273	97.75 402	95.51 298	96.76 331	99.05 272	97.74 224	96.93 370	98.21 333	95.59 269	99.89 95	97.86 166	99.93 54	99.19 276

UBG		93.25 402	92.32 403	96.04 397	97.72 403	90.16 427	95.92 384	95.91 418	96.03 341	93.95 441	93.04 452	69.60 446	99.52 373	90.72 428	97.98 404	98.45 377

mvsany_test1		97.60 265	97.54 263	97.77 301	97.72 403	95.35 306	95.36 407	97.13 391	94.13 392	99.71 48	99.33 107	97.93 125	99.30 415	97.60 185	98.94 353	98.67 362

PVSNet_0	89.98 21	91.15 422	90.30 425	93.70 430	97.72 403	84.34 454	90.24 453	97.42 380	90.20 436	93.79 442	93.09 451	90.90 358	98.89 439	86.57 443	72.76 460	97.87 413

CR-MVSNet		96.28 340	95.95 339	97.28 347	97.71 406	94.22 341	98.11 177	98.92 294	92.31 417	96.91 373	99.37 95	85.44 398	99.81 216	97.39 200	97.36 422	97.81 416

RPMNet		97.02 311	96.93 298	97.30 346	97.71 406	94.22 341	98.11 177	99.30 207	99.37 59	96.91 373	99.34 104	86.72 385	99.87 132	97.53 190	97.36 422	97.81 416

ETVMVS		92.60 411	91.08 420	97.18 351	97.70 408	93.65 373	96.54 342	95.70 421	96.51 319	94.68 429	92.39 455	61.80 462	99.50 379	86.97 440	97.41 418	98.40 385

pmmvs3		95.03 373	94.40 380	96.93 364	97.70 408	92.53 391	95.08 414	97.71 372	88.57 443	97.71 327	98.08 344	79.39 429	99.82 200	96.19 296	99.11 333	98.43 382

baseline2		93.73 394	92.83 400	96.42 382	97.70 408	91.28 413	96.84 327	89.77 454	93.96 397	92.44 449	95.93 416	79.14 430	99.77 254	92.94 390	96.76 433	98.21 394

WBMVS		95.18 370	94.78 376	96.37 383	97.68 411	89.74 430	95.80 390	98.73 331	97.54 245	98.30 280	98.44 312	70.06 444	99.82 200	96.62 262	99.87 95	99.54 134

tpm		94.67 378	94.34 382	95.66 404	97.68 411	88.42 434	97.88 220	94.90 428	94.46 383	96.03 408	98.56 296	78.66 432	99.79 237	95.88 309	95.01 447	98.78 347

CANet_DTU		97.26 293	97.06 292	97.84 295	97.57 413	94.65 332	96.19 366	98.79 320	97.23 282	95.14 424	98.24 330	93.22 323	99.84 172	97.34 202	99.84 106	99.04 300

testing11		93.08 405	92.02 410	96.26 388	97.56 414	90.83 422	96.32 358	95.70 421	96.47 323	92.66 448	93.73 445	64.36 460	99.59 346	93.77 375	97.57 411	98.37 389

tpm2		93.09 404	92.58 402	94.62 419	97.56 414	86.53 443	97.66 253	95.79 420	86.15 448	94.07 438	98.23 332	75.95 437	99.53 369	90.91 425	96.86 432	97.81 416

testing91		93.32 400	92.27 405	96.47 381	97.54 416	91.25 414	96.17 370	96.76 402	97.18 286	93.65 444	93.50 448	65.11 459	99.63 330	93.04 389	97.45 415	98.53 371

TR-MVS		95.55 363	95.12 369	96.86 371	97.54 416	93.94 359	96.49 347	96.53 407	94.36 388	97.03 368	96.61 402	94.26 307	99.16 427	86.91 442	96.31 437	97.47 430

testing99		93.04 406	91.98 413	96.23 390	97.53 418	90.70 424	96.35 356	95.94 417	96.87 304	93.41 445	93.43 450	63.84 461	99.59 346	93.24 387	97.19 425	98.40 385

1314		95.74 357	95.60 349	96.17 393	97.53 418	92.75 388	98.07 185	98.31 354	91.22 428	94.25 434	96.68 400	95.53 270	99.03 430	91.64 412	97.18 426	96.74 440

CostFormer		93.97 390	93.78 388	94.51 420	97.53 418	85.83 446	97.98 207	95.96 416	89.29 441	94.99 426	98.63 286	78.63 433	99.62 333	94.54 348	96.50 434	98.09 401

FMVSNet5		96.01 348	95.20 367	98.41 249	97.53 418	96.10 274	98.74 97	99.50 110	97.22 285	98.03 306	99.04 182	69.80 445	99.88 113	97.27 205	99.71 186	99.25 256

PMMVS		96.51 331	95.98 338	98.09 278	97.53 418	95.84 287	94.92 418	98.84 312	91.58 423	96.05 407	95.58 422	95.68 266	99.66 319	95.59 325	98.09 397	98.76 350

reproduce_monomvs		95.00 375	95.25 364	94.22 423	97.51 423	83.34 455	97.86 224	98.44 347	98.51 161	99.29 132	99.30 113	67.68 450	99.56 358	98.89 94	99.81 121	99.77 48

PAPR		95.29 367	94.47 378	97.75 305	97.50 424	95.14 315	94.89 419	98.71 333	91.39 427	95.35 422	95.48 427	94.57 298	99.14 429	84.95 445	97.37 420	98.97 313

testing222		91.96 419	90.37 423	96.72 376	97.47 425	92.59 389	96.11 372	94.76 429	96.83 306	92.90 447	92.87 453	57.92 463	99.55 362	86.93 441	97.52 412	98.00 407

PatchT		96.65 327	96.35 331	97.54 332	97.40 426	95.32 308	97.98 207	96.64 404	99.33 64	96.89 377	99.42 87	84.32 406	99.81 216	97.69 180	97.49 413	97.48 429

tpm cat1		93.29 401	93.13 398	93.75 429	97.39 427	84.74 449	97.39 288	97.65 376	83.39 453	94.16 435	98.41 314	82.86 417	99.39 402	91.56 414	95.35 446	97.14 435

PatchmatchNet		95.58 362	95.67 347	95.30 413	97.34 428	87.32 441	97.65 255	96.65 403	95.30 364	97.07 364	98.69 272	84.77 401	99.75 267	94.97 338	98.64 373	98.83 334
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 286	96.97 296	98.50 240	97.31 429	96.47 265	98.18 165	98.92 294	98.95 123	98.78 226	99.37 95	85.44 398	99.85 154	95.96 307	99.83 113	99.17 283

LS3D		98.63 147	98.38 174	99.36 70	97.25 430	99.38 13	99.12 60	99.32 194	99.21 79	98.44 271	98.88 230	97.31 177	99.80 224	96.58 265	99.34 294	98.92 322

IB-MVS	91.63 19	92.24 417	90.90 421	96.27 387	97.22 431	91.24 415	94.36 434	93.33 442	92.37 416	92.24 451	94.58 442	66.20 455	99.89 95	93.16 388	94.63 449	97.66 424
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		92.38 414	91.76 417	94.21 424	97.16 432	84.65 450	95.42 405	88.45 456	95.96 344	96.17 402	95.84 420	66.36 453	99.71 286	91.87 407	98.64 373	98.28 392

tpmrst		95.07 372	95.46 355	93.91 427	97.11 433	84.36 453	97.62 260	96.96 396	94.98 371	96.35 400	98.80 249	85.46 397	99.59 346	95.60 324	96.23 438	97.79 419

Syy-MVS		96.04 347	95.56 353	97.49 337	97.10 434	94.48 335	96.18 368	96.58 405	95.65 352	94.77 427	92.29 456	91.27 354	99.36 405	98.17 140	98.05 401	98.63 364

myMVS_eth3d		91.92 420	90.45 422	96.30 385	97.10 434	90.90 420	96.18 368	96.58 405	95.65 352	94.77 427	92.29 456	53.88 464	99.36 405	89.59 433	98.05 401	98.63 364

MDTV_nov1_ep13			95.22 366		97.06 436	83.20 456	97.74 243	96.16 411	94.37 387	96.99 369	98.83 243	83.95 410	99.53 369	93.90 369	97.95 405

MVS		93.19 403	92.09 408	96.50 380	96.91 437	94.03 351	98.07 185	98.06 365	68.01 458	94.56 432	96.48 405	95.96 257	99.30 415	83.84 447	96.89 431	96.17 445

E-PMN		94.17 386	94.37 381	93.58 431	96.86 438	85.71 447	90.11 455	97.07 392	98.17 190	97.82 322	97.19 391	84.62 403	98.94 435	89.77 431	97.68 410	96.09 449

JIA-IIPM		95.52 364	95.03 370	97.00 360	96.85 439	94.03 351	96.93 322	95.82 419	99.20 81	94.63 431	99.71 22	83.09 415	99.60 342	94.42 354	94.64 448	97.36 433

EMVS		93.83 392	94.02 384	93.23 436	96.83 440	84.96 448	89.77 456	96.32 409	97.92 211	97.43 351	96.36 410	86.17 390	98.93 436	87.68 438	97.73 409	95.81 450

cl22		95.79 356	95.39 360	96.98 362	96.77 441	92.79 386	94.40 433	98.53 343	94.59 380	97.89 314	98.17 336	82.82 418	99.24 421	96.37 285	99.03 339	98.92 322

WB-MVSnew		95.73 358	95.57 352	96.23 390	96.70 442	90.70 424	96.07 374	93.86 439	95.60 354	97.04 366	95.45 431	96.00 250	99.55 362	91.04 422	98.31 385	98.43 382

dp		93.47 398	93.59 391	93.13 437	96.64 443	81.62 462	97.66 253	96.42 408	92.80 412	96.11 404	98.64 284	78.55 435	99.59 346	93.31 385	92.18 456	98.16 397

MonoMVSNet		96.25 342	96.53 328	95.39 411	96.57 444	91.01 418	98.82 95	97.68 375	98.57 156	98.03 306	99.37 95	90.92 357	97.78 452	94.99 336	93.88 452	97.38 432

test-LLR		93.90 391	93.85 386	94.04 425	96.53 445	84.62 451	94.05 439	92.39 445	96.17 333	94.12 436	95.07 432	82.30 419	99.67 308	95.87 312	98.18 390	97.82 414

test-mter		92.33 416	91.76 417	94.04 425	96.53 445	84.62 451	94.05 439	92.39 445	94.00 396	94.12 436	95.07 432	65.63 458	99.67 308	95.87 312	98.18 390	97.82 414

TESTMET0.1,1		92.19 418	91.77 416	93.46 432	96.48 447	82.80 458	94.05 439	91.52 450	94.45 385	94.00 439	94.88 438	66.65 452	99.56 358	95.78 317	98.11 396	98.02 404

MVS_0304		97.44 279	97.01 295	98.72 195	96.42 448	96.74 251	97.20 307	91.97 448	98.46 164	98.30 280	98.79 251	92.74 335	99.91 72	99.30 61	99.94 49	99.52 146

miper_enhance_ethall		96.01 348	95.74 343	96.81 372	96.41 449	92.27 398	93.69 444	98.89 300	91.14 430	98.30 280	97.35 389	90.58 360	99.58 353	96.31 289	99.03 339	98.60 366

tpmvs		95.02 374	95.25 364	94.33 421	96.39 450	85.87 444	98.08 182	96.83 401	95.46 359	95.51 420	98.69 272	85.91 393	99.53 369	94.16 360	96.23 438	97.58 427

CMPMVS	75.91 23	96.29 339	95.44 357	98.84 170	96.25 451	98.69 94	97.02 315	99.12 261	88.90 442	97.83 320	98.86 233	89.51 369	98.90 438	91.92 405	99.51 261	98.92 322
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 379	93.69 389	96.99 361	96.05 452	93.61 375	94.97 417	93.49 440	96.17 333	97.57 338	94.88 438	82.30 419	99.01 433	93.60 378	94.17 451	98.37 389

EPMVS		93.72 395	93.27 394	95.09 416	96.04 453	87.76 438	98.13 172	85.01 461	94.69 378	96.92 371	98.64 284	78.47 436	99.31 413	95.04 335	96.46 435	98.20 395

cascas		94.79 377	94.33 383	96.15 396	96.02 454	92.36 396	92.34 451	99.26 227	85.34 450	95.08 425	94.96 437	92.96 330	98.53 445	94.41 357	98.59 377	97.56 428

MVStest1		95.86 353	95.60 349	96.63 377	95.87 455	91.70 403	97.93 212	98.94 288	98.03 201	99.56 70	99.66 32	71.83 442	98.26 448	99.35 57	99.24 310	99.91 13

gg-mvs-nofinetune		92.37 415	91.20 419	95.85 399	95.80 456	92.38 395	99.31 30	81.84 463	99.75 11	91.83 452	99.74 18	68.29 447	99.02 431	87.15 439	97.12 427	96.16 446

gm-plane-assit					94.83 457	81.97 460			88.07 445		94.99 435		99.60 342	91.76 409

GG-mvs-BLEND				94.76 418	94.54 458	92.13 400	99.31 30	80.47 464		88.73 458	91.01 458	67.59 451	98.16 451	82.30 452	94.53 450	93.98 454

UWE-MVS-28		90.22 423	89.28 426	93.02 438	94.50 459	82.87 457	96.52 345	87.51 457	95.21 367	92.36 450	96.04 412	71.57 443	98.25 449	72.04 459	97.77 408	97.94 409

EPNet_dtu		94.93 376	94.78 376	95.38 412	93.58 460	87.68 439	96.78 329	95.69 423	97.35 266	89.14 457	98.09 343	88.15 381	99.49 382	94.95 339	99.30 301	98.98 310
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 427	75.95 430	77.12 443	92.39 461	67.91 467	90.16 454	59.44 468	82.04 454	89.42 456	94.67 441	49.68 466	81.74 461	48.06 461	77.66 459	81.72 457

KD-MVS_2432*1600		92.87 409	91.99 411	95.51 408	91.37 462	89.27 431	94.07 437	98.14 361	95.42 360	97.25 359	96.44 407	67.86 448	99.24 421	91.28 418	96.08 441	98.02 404

miper_refine_blended		92.87 409	91.99 411	95.51 408	91.37 462	89.27 431	94.07 437	98.14 361	95.42 360	97.25 359	96.44 407	67.86 448	99.24 421	91.28 418	96.08 441	98.02 404

EPNet		96.14 345	95.44 357	98.25 267	90.76 464	95.50 299	97.92 215	94.65 430	98.97 119	92.98 446	98.85 236	89.12 372	99.87 132	95.99 305	99.68 201	99.39 206
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 428	68.95 431	70.34 444	87.68 465	65.00 468	91.11 452	59.90 467	69.02 457	74.46 462	88.89 459	48.58 467	68.03 463	28.61 462	72.33 461	77.99 458

test_method		79.78 425	79.50 428	80.62 441	80.21 466	45.76 469	70.82 457	98.41 351	31.08 461	80.89 461	97.71 366	84.85 400	97.37 454	91.51 415	80.03 458	98.75 351

tmp_tt		78.77 426	78.73 429	78.90 442	58.45 467	74.76 466	94.20 436	78.26 465	39.16 460	86.71 459	92.82 454	80.50 423	75.19 462	86.16 444	92.29 455	86.74 456

testmvs		17.12 430	20.53 433	6.87 446	12.05 468	4.20 471	93.62 445	6.73 469	4.62 464	10.41 464	24.33 461	8.28 469	3.56 465	9.69 464	15.07 462	12.86 461

test123		17.04 431	20.11 434	7.82 445	10.25 469	4.91 470	94.80 420	4.47 470	4.93 463	10.00 465	24.28 462	9.69 468	3.64 464	10.14 463	12.43 463	14.92 460

mmdepth		0.00 434	0.00 437	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.00 465	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

monomultidepth		0.00 434	0.00 437	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.00 465	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

test_blank		0.00 434	0.00 437	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.00 465	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

eth-test2					0.00 470

eth-test					0.00 470

uanet_test		0.00 434	0.00 437	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.00 465	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

DCPMVS		0.00 434	0.00 437	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.00 465	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

cdsmvs_eth3d_5k		24.66 429	32.88 432	0.00 447	0.00 470	0.00 472	0.00 458	99.10 264	0.00 465	0.00 466	97.58 374	99.21 18	0.00 466	0.00 465	0.00 464	0.00 462

pcd_1.5k_mvsjas		8.17 432	10.90 435	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.00 465	98.07 113	0.00 466	0.00 465	0.00 464	0.00 462

sosnet-low-res		0.00 434	0.00 437	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.00 465	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

sosnet		0.00 434	0.00 437	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.00 465	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

uncertanet		0.00 434	0.00 437	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.00 465	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

Regformer		0.00 434	0.00 437	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.00 465	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

ab-mvs-re		8.12 433	10.83 436	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	97.48 380	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

uanet		0.00 434	0.00 437	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.00 465	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

WAC-MVS						90.90 420								91.37 417

PC_three_1452									93.27 404	99.40 108	98.54 297	98.22 99	97.00 455	95.17 333	99.45 275	99.49 157

test_241102_TWO								99.30 207	98.03 201	99.26 139	99.02 185	97.51 165	99.88 113	96.91 232	99.60 230	99.66 75

test_0728_THIRD									98.17 190	99.08 164	99.02 185	97.89 129	99.88 113	97.07 220	99.71 186	99.70 65

GSMVS																98.81 340

sam_mvs1												84.74 402				98.81 340

sam_mvs												84.29 408

MTGPA								99.20 239

test_post1							97.59 267				20.48 464	83.07 416	99.66 319	94.16 360

test_post											21.25 463	83.86 411	99.70 291

patchmatchnet-post											98.77 255	84.37 405	99.85 154

MTMP							97.93 212	91.91 449

test9_res														93.28 386	99.15 326	99.38 214

agg_prior2														92.50 402	99.16 324	99.37 216

test_prior4						97.97 159	95.86 386

test_prior2							95.74 393		96.48 322	96.11 404	97.63 372	95.92 260		94.16 360	99.20 318

旧先验2							95.76 392		88.56 444	97.52 342			99.66 319	94.48 350

新几何2							95.93 382

无先验							95.74 393	98.74 330	89.38 440				99.73 278	92.38 404		99.22 266

原ACMM2							95.53 399

testdata2													99.79 237	92.80 396

segment_acmp												97.02 196

testdata1							95.44 404		96.32 328

plane_prior5								99.27 222					99.70 291	94.42 354	99.51 261	99.45 182

plane_prior4											97.98 351

plane_prior3						97.78 184			97.41 260	97.79 323

plane_prior2							97.77 237		98.20 187

plane_prior						97.65 193	97.07 314		96.72 312						99.36 290

n2								0.00 471

nn								0.00 471

door-mid								99.57 83

test11								98.87 303

door								99.41 159

HQP5-MVS						96.79 247

BP-MVS														92.82 394

HQP4-MVS										95.56 414			99.54 367			99.32 237

HQP3-MVS								99.04 275							99.26 308

HQP2-MVS												93.84 314

MDTV_nov1_ep13_2view						74.92 465	97.69 248		90.06 438	97.75 326		85.78 394		93.52 380		98.69 358

ACMMP++_ref															99.77 149

ACMMP++															99.68 201

Test By Simon												96.52 227

High-resolution multi-view benchmark