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 14	100.00 1	99.85 29

Gipuma		99.03 77	99.16 59	98.64 202	99.94 2	98.51 108	99.32 26	99.75 41	99.58 37	98.60 243	99.62 40	98.22 93	99.51 370	97.70 174	99.73 167	97.89 403
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 29	99.31 40	99.53 38	99.91 3	98.98 71	99.63 7	99.58 72	99.44 50	99.78 38	99.76 15	96.39 224	99.92 62	99.44 52	99.92 66	99.68 67

pmmvs6		99.67 3	99.70 3	99.60 15	99.90 4	99.27 27	99.53 9	99.76 38	99.64 27	99.84 29	99.83 4	99.50 9	99.87 129	99.36 55	99.92 66	99.64 80

PS-MVSNAJss		99.46 17	99.49 16	99.35 76	99.90 4	98.15 135	99.20 48	99.65 60	99.48 42	99.92 8	99.71 22	98.07 107	99.96 14	99.53 45	100.00 1	99.93 11

testf1		99.25 40	99.16 59	99.51 48	99.89 6	99.63 4	98.71 104	99.69 49	98.90 124	99.43 98	99.35 100	98.86 33	99.67 302	97.81 165	99.81 120	99.24 253

APD_test2		99.25 40	99.16 59	99.51 48	99.89 6	99.63 4	98.71 104	99.69 49	98.90 124	99.43 98	99.35 100	98.86 33	99.67 302	97.81 165	99.81 120	99.24 253

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 19	99.94 41	99.31 59	100.00 1	99.82 34

anonymousdsp		99.51 14	99.47 21	99.62 9	99.88 9	99.08 69	99.34 23	99.69 49	98.93 122	99.65 61	99.72 21	98.93 31	99.95 26	99.11 75	100.00 1	99.82 34

v7n		99.53 12	99.57 13	99.41 66	99.88 9	98.54 106	99.45 14	99.61 68	99.66 24	99.68 55	99.66 32	98.44 73	99.95 26	99.73 25	99.96 27	99.75 56

mvs_tets		99.63 6	99.67 6	99.49 54	99.88 9	98.61 98	99.34 23	99.71 45	99.27 71	99.90 13	99.74 18	99.68 4	99.97 7	99.55 40	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	98.08 181	99.95 1	99.45 48	99.98 2	99.75 16	99.80 1	99.97 7	99.82 10	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 58	99.09 102	99.89 17	99.68 25	99.53 7	99.97 7	99.50 48	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 86	99.11 92	99.70 49	99.73 20	99.00 26	99.97 7	99.26 63	99.98 12	99.89 16

MIMVSNet1		99.38 28	99.32 38	99.55 28	99.86 14	99.19 42	99.41 17	99.59 70	99.59 35	99.71 47	99.57 49	97.12 181	99.90 78	99.21 68	99.87 94	99.54 133

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 35	99.63 29	99.78 38	99.67 30	99.48 10	99.81 212	99.30 60	99.97 20	99.77 47
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 72	99.90 3	99.86 23	99.78 13	99.58 6	99.95 26	99.00 85	99.95 37	99.78 44

SixPastTwentyTwo		98.75 118	98.62 129	99.16 114	99.83 18	97.96 162	99.28 40	98.20 350	99.37 58	99.70 49	99.65 36	92.65 329	99.93 52	99.04 82	99.84 105	99.60 96

sc_t1		99.62 7	99.66 8	99.53 38	99.82 19	99.09 68	99.50 11	99.63 63	99.88 4	99.86 23	99.80 11	99.03 23	99.89 93	99.48 50	99.93 53	99.60 96

Baseline_NR-MVSNet		98.98 85	98.86 97	99.36 70	99.82 19	98.55 103	97.47 278	99.57 79	99.37 58	99.21 146	99.61 43	96.76 206	99.83 186	98.06 146	99.83 112	99.71 59

pm-mvs1		99.44 19	99.48 18	99.33 85	99.80 21	98.63 95	99.29 36	99.63 63	99.30 68	99.65 61	99.60 45	99.16 21	99.82 196	99.07 78	99.83 112	99.56 122

TransMVSNet (Re)		99.44 19	99.47 21	99.36 70	99.80 21	98.58 101	99.27 42	99.57 79	99.39 56	99.75 43	99.62 40	99.17 19	99.83 186	99.06 80	99.62 217	99.66 74

K. test v3		98.00 223	97.66 248	99.03 141	99.79 23	97.56 198	99.19 52	92.47 436	99.62 32	99.52 80	99.66 32	89.61 360	99.96 14	99.25 65	99.81 120	99.56 122

test_fmvsmconf0.1_n		99.49 15	99.54 14	99.34 79	99.78 24	98.11 139	97.77 233	99.90 11	99.33 63	99.97 3	99.66 32	99.71 3	99.96 14	99.79 17	99.99 5	99.96 8

APD_test1		98.83 104	98.66 123	99.34 79	99.78 24	99.47 9	98.42 144	99.45 129	98.28 175	98.98 176	99.19 140	97.76 133	99.58 345	96.57 259	99.55 244	98.97 305

test_vis3_rt		99.14 59	99.17 57	99.07 131	99.78 24	98.38 115	98.92 82	99.94 2	97.80 214	99.91 12	99.67 30	97.15 180	98.91 429	99.76 21	99.56 240	99.92 12

EGC-MVSNET		85.24 416	80.54 419	99.34 79	99.77 27	99.20 39	99.08 61	99.29 207	12.08 454	20.84 455	99.42 87	97.55 151	99.85 150	97.08 211	99.72 175	98.96 307

Anonymous20240521		98.69 129	98.87 94	98.16 271	99.77 27	95.11 312	99.08 61	99.44 135	99.34 62	99.33 121	99.55 57	94.10 304	99.94 41	99.25 65	99.96 27	99.42 192

FC-MVSNet-test		99.27 37	99.25 50	99.34 79	99.77 27	98.37 117	99.30 35	99.57 79	99.61 34	99.40 107	99.50 67	97.12 181	99.85 150	99.02 84	99.94 48	99.80 39

test_vis1_n		98.31 190	98.50 146	97.73 304	99.76 30	94.17 339	98.68 107	99.91 9	96.31 322	99.79 37	99.57 49	92.85 325	99.42 390	99.79 17	99.84 105	99.60 96

test_fmvs3		99.12 66	99.41 25	98.25 262	99.76 30	95.07 313	99.05 67	99.94 2	97.78 217	99.82 32	99.84 3	98.56 64	99.71 282	99.96 1	99.96 27	99.97 4

XXY-MVS		99.14 59	99.15 64	99.10 124	99.76 30	97.74 187	98.85 92	99.62 65	98.48 159	99.37 112	99.49 73	98.75 44	99.86 137	98.20 136	99.80 131	99.71 59

TDRefinement		99.42 24	99.38 28	99.55 28	99.76 30	99.33 21	99.68 6	99.71 45	99.38 57	99.53 78	99.61 43	98.64 54	99.80 220	98.24 132	99.84 105	99.52 145

fmvsm_s_conf0.1_n_a		99.17 51	99.30 43	98.80 175	99.75 34	96.59 254	97.97 207	99.86 16	98.22 178	99.88 20	99.71 22	98.59 60	99.84 168	99.73 25	99.98 12	99.98 3

tt0805		98.69 129	98.62 129	98.90 165	99.75 34	99.30 22	99.15 56	96.97 387	98.86 129	98.87 206	97.62 365	98.63 56	98.96 426	99.41 54	98.29 378	98.45 369

test_vis1_n_1920		98.40 175	98.92 89	96.81 364	99.74 36	90.76 415	98.15 170	99.91 9	98.33 166	99.89 17	99.55 57	95.07 275	99.88 110	99.76 21	99.93 53	99.79 41

FOURS1					99.73 37	99.67 3	99.43 15	99.54 94	99.43 52	99.26 138

PEN-MVS		99.41 25	99.34 35	99.62 9	99.73 37	99.14 57	99.29 36	99.54 94	99.62 32	99.56 69	99.42 87	98.16 101	99.96 14	98.78 99	99.93 53	99.77 47

lessismore_v0				98.97 152	99.73 37	97.53 200		86.71 451		99.37 112	99.52 66	89.93 356	99.92 62	98.99 86	99.72 175	99.44 185

SteuartSystems-ACMMP		98.79 111	98.54 141	99.54 31	99.73 37	99.16 48	98.23 160	99.31 191	97.92 205	98.90 196	98.90 219	98.00 113	99.88 110	96.15 291	99.72 175	99.58 111
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 209	98.15 201	98.22 265	99.73 37	95.15 309	97.36 286	99.68 54	94.45 377	98.99 175	99.27 118	96.87 195	99.94 41	97.13 208	99.91 75	99.57 116

Vis-MVSNet		99.34 30	99.36 32	99.27 95	99.73 37	98.26 124	99.17 53	99.78 35	99.11 92	99.27 134	99.48 74	98.82 36	99.95 26	98.94 89	99.93 53	99.59 103
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 20	99.82 5	99.02 25	99.90 78	99.54 41	99.95 37	99.61 94

SSC-MVS		98.71 122	98.74 107	98.62 208	99.72 43	96.08 274	98.74 97	98.64 330	99.74 13	99.67 57	99.24 130	94.57 290	99.95 26	99.11 75	99.24 302	99.82 34

test_f		98.67 137	98.87 94	98.05 280	99.72 43	95.59 288	98.51 128	99.81 30	96.30 324	99.78 38	99.82 5	96.14 234	98.63 436	99.82 10	99.93 53	99.95 9

ACMH	96.65 7	99.25 40	99.24 51	99.26 97	99.72 43	98.38 115	99.07 64	99.55 90	98.30 170	99.65 61	99.45 83	99.22 16	99.76 256	98.44 123	99.77 148	99.64 80
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 17	99.82 5	98.75 44	99.90 78	99.54 41	99.95 37	99.59 103

fmvsm_s_conf0.1_n		99.16 55	99.33 36	98.64 202	99.71 47	96.10 269	97.87 219	99.85 18	98.56 155	99.90 13	99.68 25	98.69 50	99.85 150	99.72 27	99.98 12	99.97 4

PS-CasMVS		99.40 26	99.33 36	99.62 9	99.71 47	99.10 65	99.29 36	99.53 97	99.53 39	99.46 93	99.41 91	98.23 90	99.95 26	98.89 93	99.95 37	99.81 37

DTE-MVSNet		99.43 23	99.35 33	99.66 7	99.71 47	99.30 22	99.31 30	99.51 101	99.64 27	99.56 69	99.46 79	98.23 90	99.97 7	98.78 99	99.93 53	99.72 58

WR-MVS_H		99.33 31	99.22 52	99.65 8	99.71 47	99.24 30	99.32 26	99.55 90	99.46 47	99.50 86	99.34 104	97.30 170	99.93 52	98.90 91	99.93 53	99.77 47

HPM-MVS_fast		99.01 79	98.82 100	99.57 21	99.71 47	99.35 17	99.00 72	99.50 104	97.33 260	98.94 191	98.86 229	98.75 44	99.82 196	97.53 184	99.71 180	99.56 122

ACMH+	96.62 9	99.08 73	99.00 82	99.33 85	99.71 47	98.83 83	98.60 114	99.58 72	99.11 92	99.53 78	99.18 144	98.81 37	99.67 302	96.71 248	99.77 148	99.50 151

PMVS	91.26 20	97.86 237	97.94 225	97.65 310	99.71 47	97.94 164	98.52 123	98.68 326	98.99 114	97.52 334	99.35 100	97.41 164	98.18 442	91.59 405	99.67 201	96.82 431
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
KinetiMVS		99.03 77	99.02 78	99.03 141	99.70 55	97.48 203	98.43 141	99.29 207	99.70 16	99.60 68	99.07 171	96.13 235	99.94 41	99.42 53	99.87 94	99.68 67

FIs		99.14 59	99.09 72	99.29 91	99.70 55	98.28 123	99.13 58	99.52 100	99.48 42	99.24 143	99.41 91	96.79 203	99.82 196	98.69 109	99.88 90	99.76 52

VPNet		98.87 99	98.83 99	99.01 145	99.70 55	97.62 196	98.43 141	99.35 172	99.47 45	99.28 132	99.05 179	96.72 209	99.82 196	98.09 143	99.36 282	99.59 103

fmvsm_s_conf0.1_n_2		99.20 49	99.38 28	98.65 200	99.69 58	96.08 274	97.49 275	99.90 11	99.53 39	99.88 20	99.64 37	98.51 67	99.90 78	99.83 9	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 187	98.68 120	97.27 340	99.69 58	92.29 389	98.03 190	99.85 18	97.62 226	99.96 4	99.62 40	93.98 305	99.74 268	99.52 47	99.86 100	99.79 41

MP-MVS-pluss		98.57 151	98.23 189	99.60 15	99.69 58	99.35 17	97.16 305	99.38 158	94.87 367	98.97 180	98.99 198	98.01 112	99.88 110	97.29 196	99.70 187	99.58 111
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 45	99.32 38	98.96 153	99.68 61	97.35 211	98.84 94	99.48 113	99.69 18	99.63 64	99.68 25	99.03 23	99.96 14	97.97 155	99.92 66	99.57 116

sd_testset		99.28 36	99.31 40	99.19 108	99.68 61	98.06 151	99.41 17	99.30 199	99.69 18	99.63 64	99.68 25	99.25 15	99.96 14	97.25 199	99.92 66	99.57 116

test_fmvs1_n		98.09 214	98.28 181	97.52 326	99.68 61	93.47 368	98.63 110	99.93 5	95.41 355	99.68 55	99.64 37	91.88 339	99.48 377	99.82 10	99.87 94	99.62 86

CHOSEN 1792x2688		97.49 266	97.14 281	98.54 227	99.68 61	96.09 272	96.50 339	99.62 65	91.58 415	98.84 209	98.97 204	92.36 331	99.88 110	96.76 241	99.95 37	99.67 72

tfpnnormal		98.90 95	98.90 91	98.91 162	99.67 65	97.82 179	99.00 72	99.44 135	99.45 48	99.51 85	99.24 130	98.20 96	99.86 137	95.92 300	99.69 190	99.04 292

MTAPA		98.88 98	98.64 126	99.61 13	99.67 65	99.36 16	98.43 141	99.20 231	98.83 133	98.89 198	98.90 219	96.98 191	99.92 62	97.16 203	99.70 187	99.56 122

test_fmvsmvis_n_1920		99.26 39	99.49 16	98.54 227	99.66 67	96.97 234	98.00 197	99.85 18	99.24 73	99.92 8	99.50 67	99.39 12	99.95 26	99.89 3	99.98 12	98.71 346

mvs5depth		99.30 33	99.59 12	98.44 241	99.65 68	95.35 301	99.82 3	99.94 2	99.83 7	99.42 102	99.94 2	98.13 104	99.96 14	99.63 33	99.96 27	100.00 1

fmvsm_l_conf0.5_n_a		99.19 50	99.27 46	98.94 156	99.65 68	97.05 230	97.80 228	99.76 38	98.70 138	99.78 38	99.11 163	98.79 41	99.95 26	99.85 5	99.96 27	99.83 31

WB-MVS		98.52 164	98.55 139	98.43 242	99.65 68	95.59 288	98.52 123	98.77 315	99.65 26	99.52 80	99.00 197	94.34 296	99.93 52	98.65 111	98.83 350	99.76 52

CP-MVSNet		99.21 47	99.09 72	99.56 26	99.65 68	98.96 77	99.13 58	99.34 178	99.42 53	99.33 121	99.26 123	97.01 189	99.94 41	98.74 104	99.93 53	99.79 41

HPM-MVS		98.79 111	98.53 142	99.59 19	99.65 68	99.29 24	99.16 54	99.43 141	96.74 304	98.61 241	98.38 310	98.62 57	99.87 129	96.47 271	99.67 201	99.59 103
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 146	98.36 170	99.42 64	99.65 68	99.42 11	98.55 119	99.57 79	97.72 220	98.90 196	99.26 123	96.12 237	99.52 365	95.72 311	99.71 180	99.32 234

NormalMVS		98.26 197	97.97 222	99.15 117	99.64 74	97.83 174	98.28 154	99.43 141	99.24 73	98.80 216	98.85 232	89.76 358	99.94 41	98.04 148	99.67 201	99.68 67

lecture		99.25 40	99.12 67	99.62 9	99.64 74	99.40 12	98.89 87	99.51 101	99.19 84	99.37 112	99.25 128	98.36 77	99.88 110	98.23 134	99.67 201	99.59 103

fmvsm_l_conf0.5_n		99.21 47	99.28 45	99.02 144	99.64 74	97.28 215	97.82 224	99.76 38	98.73 135	99.82 32	99.09 170	98.81 37	99.95 26	99.86 4	99.96 27	99.83 31

test_fmvsmconf_n		99.44 19	99.48 18	99.31 90	99.64 74	98.10 141	97.68 245	99.84 22	99.29 69	99.92 8	99.57 49	99.60 5	99.96 14	99.74 24	99.98 12	99.89 16

TSAR-MVS + MP.		98.63 143	98.49 150	99.06 137	99.64 74	97.90 168	98.51 128	98.94 280	96.96 291	99.24 143	98.89 225	97.83 126	99.81 212	96.88 231	99.49 264	99.48 167
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 107	98.72 111	99.12 120	99.64 74	98.54 106	97.98 203	99.68 54	97.62 226	99.34 119	99.18 144	97.54 152	99.77 250	97.79 167	99.74 164	99.04 292

Elysia		99.15 56	99.14 65	99.18 109	99.63 80	97.92 165	98.50 130	99.43 141	99.67 21	99.70 49	99.13 159	96.66 212	99.98 4	99.54 41	99.96 27	99.64 80

StellarMVS		99.15 56	99.14 65	99.18 109	99.63 80	97.92 165	98.50 130	99.43 141	99.67 21	99.70 49	99.13 159	96.66 212	99.98 4	99.54 41	99.96 27	99.64 80

KD-MVS_self_test		99.25 40	99.18 56	99.44 63	99.63 80	99.06 70	98.69 106	99.54 94	99.31 66	99.62 67	99.53 63	97.36 167	99.86 137	99.24 67	99.71 180	99.39 205

EU-MVSNet		97.66 254	98.50 146	95.13 406	99.63 80	85.84 437	98.35 150	98.21 349	98.23 177	99.54 74	99.46 79	95.02 276	99.68 299	98.24 132	99.87 94	99.87 21

HyFIR lowres test		97.19 292	96.60 316	98.96 153	99.62 84	97.28 215	95.17 403	99.50 104	94.21 382	99.01 173	98.32 318	86.61 378	99.99 2	97.10 210	99.84 105	99.60 96

fmvsm_l_conf0.5_n_3		99.45 18	99.48 18	99.34 79	99.59 85	98.21 132	97.82 224	99.84 22	99.41 55	99.92 8	99.41 91	99.51 8	99.95 26	99.84 8	99.97 20	99.87 21

mmtdpeth		99.30 33	99.42 24	98.92 161	99.58 86	96.89 241	99.48 13	99.92 7	99.92 2	98.26 278	99.80 11	98.33 83	99.91 71	99.56 38	99.95 37	99.97 4

ACMMP_NAP		98.75 118	98.48 151	99.57 21	99.58 86	99.29 24	97.82 224	99.25 220	96.94 293	98.78 218	99.12 162	98.02 111	99.84 168	97.13 208	99.67 201	99.59 103

nrg030		99.40 26	99.35 33	99.54 31	99.58 86	99.13 60	98.98 75	99.48 113	99.68 20	99.46 93	99.26 123	98.62 57	99.73 274	99.17 72	99.92 66	99.76 52

VDDNet		98.21 204	97.95 223	99.01 145	99.58 86	97.74 187	99.01 70	97.29 378	99.67 21	98.97 180	99.50 67	90.45 353	99.80 220	97.88 161	99.20 310	99.48 167

COLMAP_ROB	96.50 10	98.99 82	98.85 98	99.41 66	99.58 86	99.10 65	98.74 97	99.56 86	99.09 102	99.33 121	99.19 140	98.40 75	99.72 281	95.98 298	99.76 160	99.42 192
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 91	97.73 189	97.93 208	99.83 25	99.22 76	99.93 6	99.30 112	99.42 11	99.96 14	99.85 5	99.99 5	99.29 243

ZNCC-MVS		98.68 134	98.40 163	99.54 31	99.57 91	99.21 33	98.46 138	99.29 207	97.28 266	98.11 290	98.39 308	98.00 113	99.87 129	96.86 234	99.64 211	99.55 129

MSP-MVS		98.40 175	98.00 217	99.61 13	99.57 91	99.25 29	98.57 117	99.35 172	97.55 237	99.31 129	97.71 358	94.61 289	99.88 110	96.14 292	99.19 313	99.70 64
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		98.32 188	98.39 166	98.13 272	99.57 91	95.54 291	97.78 230	99.49 111	97.37 257	99.19 148	97.65 362	98.96 28	99.49 374	96.50 270	98.99 338	99.34 227

MP-MVS		98.46 169	98.09 206	99.54 31	99.57 91	99.22 32	98.50 130	99.19 235	97.61 229	97.58 328	98.66 271	97.40 165	99.88 110	94.72 337	99.60 224	99.54 133
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 122	98.46 155	99.47 60	99.57 91	98.97 73	98.23 160	99.48 113	96.60 309	99.10 158	99.06 172	98.71 48	99.83 186	95.58 318	99.78 142	99.62 86

LGP-MVS_train				99.47 60	99.57 91	98.97 73		99.48 113	96.60 309	99.10 158	99.06 172	98.71 48	99.83 186	95.58 318	99.78 142	99.62 86

IS-MVSNet		98.19 206	97.90 230	99.08 129	99.57 91	97.97 159	99.31 30	98.32 345	99.01 113	98.98 176	99.03 183	91.59 341	99.79 233	95.49 320	99.80 131	99.48 167

dcpmvs_2		98.78 113	99.11 68	97.78 294	99.56 99	93.67 363	99.06 65	99.86 16	99.50 41	99.66 58	99.26 123	97.21 178	99.99 2	98.00 153	99.91 75	99.68 67

test_0402		98.76 117	98.71 114	98.93 158	99.56 99	98.14 137	98.45 140	99.34 178	99.28 70	98.95 184	98.91 216	98.34 82	99.79 233	95.63 315	99.91 75	98.86 324

EPP-MVSNet		98.30 191	98.04 213	99.07 131	99.56 99	97.83 174	99.29 36	98.07 356	99.03 111	98.59 245	99.13 159	92.16 335	99.90 78	96.87 232	99.68 195	99.49 156

ACMMP		98.75 118	98.50 146	99.52 44	99.56 99	99.16 48	98.87 88	99.37 162	97.16 281	98.82 213	99.01 194	97.71 136	99.87 129	96.29 283	99.69 190	99.54 133
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 68	99.20 55	98.78 181	99.55 103	96.59 254	97.79 229	99.82 29	98.21 179	99.81 35	99.53 63	98.46 71	99.84 168	99.70 30	99.97 20	99.90 15

fmvsm_s_conf0.5_n		99.09 69	99.26 48	98.61 211	99.55 103	96.09 272	97.74 239	99.81 30	98.55 156	99.85 26	99.55 57	98.60 59	99.84 168	99.69 32	99.98 12	99.89 16

FMVSNet1		99.17 51	99.17 57	99.17 111	99.55 103	98.24 126	99.20 48	99.44 135	99.21 78	99.43 98	99.55 57	97.82 129	99.86 137	98.42 125	99.89 88	99.41 195

Vis-MVSNet (Re-imp)		97.46 268	97.16 278	98.34 254	99.55 103	96.10 269	98.94 80	98.44 339	98.32 168	98.16 284	98.62 280	88.76 365	99.73 274	93.88 363	99.79 137	99.18 271

ACMM	96.08 12	98.91 93	98.73 109	99.48 56	99.55 103	99.14 57	98.07 184	99.37 162	97.62 226	99.04 169	98.96 207	98.84 35	99.79 233	97.43 190	99.65 209	99.49 156
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 126	98.97 86	97.89 287	99.54 108	94.05 342	98.55 119	99.92 7	96.78 302	99.72 45	99.78 13	96.60 216	99.67 302	99.91 2	99.90 82	99.94 10

mPP-MVS		98.64 141	98.34 173	99.54 31	99.54 108	99.17 44	98.63 110	99.24 225	97.47 244	98.09 292	98.68 266	97.62 145	99.89 93	96.22 286	99.62 217	99.57 116

XVG-ACMP-BASELINE		98.56 152	98.34 173	99.22 105	99.54 108	98.59 100	97.71 242	99.46 125	97.25 269	98.98 176	98.99 198	97.54 152	99.84 168	95.88 301	99.74 164	99.23 255

region2R		98.69 129	98.40 163	99.54 31	99.53 111	99.17 44	98.52 123	99.31 191	97.46 249	98.44 263	98.51 294	97.83 126	99.88 110	96.46 272	99.58 233	99.58 111

PGM-MVS		98.66 138	98.37 169	99.55 28	99.53 111	99.18 43	98.23 160	99.49 111	97.01 290	98.69 229	98.88 226	98.00 113	99.89 93	95.87 304	99.59 228	99.58 111

Patchmatch-RL test		97.26 285	97.02 286	97.99 284	99.52 113	95.53 292	96.13 364	99.71 45	97.47 244	99.27 134	99.16 150	84.30 399	99.62 327	97.89 158	99.77 148	98.81 332

ACMMPR		98.70 126	98.42 161	99.54 31	99.52 113	99.14 57	98.52 123	99.31 191	97.47 244	98.56 250	98.54 289	97.75 134	99.88 110	96.57 259	99.59 228	99.58 111

fmvsm_s_conf0.5_n_9		99.17 51	99.38 28	98.53 229	99.51 115	95.82 284	97.62 256	99.78 35	99.72 15	99.90 13	99.48 74	98.66 52	99.89 93	99.85 5	99.93 53	99.89 16

AstraMVS		98.16 211	98.07 211	98.41 244	99.51 115	95.86 281	98.00 197	95.14 419	98.97 117	99.43 98	99.24 130	93.25 313	99.84 168	99.21 68	99.87 94	99.54 133

fmvsm_s_conf0.5_n_8		99.13 63	99.26 48	98.74 192	99.51 115	96.44 261	97.65 251	99.65 60	99.66 24	99.78 38	99.48 74	97.92 120	99.93 52	99.72 27	99.95 37	99.87 21

GST-MVS		98.61 147	98.30 179	99.52 44	99.51 115	99.20 39	98.26 158	99.25 220	97.44 252	98.67 232	98.39 308	97.68 137	99.85 150	96.00 296	99.51 255	99.52 145

Anonymous20231206		98.21 204	98.21 190	98.20 266	99.51 115	95.43 299	98.13 172	99.32 186	96.16 327	98.93 192	98.82 240	96.00 242	99.83 186	97.32 195	99.73 167	99.36 221

ACMP	95.32 15	98.41 173	98.09 206	99.36 70	99.51 115	98.79 86	97.68 245	99.38 158	95.76 342	98.81 215	98.82 240	98.36 77	99.82 196	94.75 334	99.77 148	99.48 167
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LuminaMVS		98.39 181	98.20 191	98.98 151	99.50 121	97.49 201	97.78 230	97.69 365	98.75 134	99.49 87	99.25 128	92.30 333	99.94 41	99.14 73	99.88 90	99.50 151

DVP-MVS		98.77 116	98.52 143	99.52 44	99.50 121	99.21 33	98.02 193	98.84 304	97.97 199	99.08 160	99.02 184	97.61 146	99.88 110	96.99 218	99.63 214	99.48 167
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	99.50 121	99.23 31	98.02 193	99.32 186					99.88 110	96.99 218	99.63 214	99.68 67

test0726					99.50 121	99.21 33	98.17 168	99.35 172	97.97 199	99.26 138	99.06 172	97.61 146

AllTest		98.44 171	98.20 191	99.16 114	99.50 121	98.55 103	98.25 159	99.58 72	96.80 300	98.88 202	99.06 172	97.65 140	99.57 347	94.45 344	99.61 222	99.37 214

TestCases				99.16 114	99.50 121	98.55 103		99.58 72	96.80 300	98.88 202	99.06 172	97.65 140	99.57 347	94.45 344	99.61 222	99.37 214

XVG-OURS		98.53 160	98.34 173	99.11 122	99.50 121	98.82 85	95.97 370	99.50 104	97.30 264	99.05 167	98.98 202	99.35 13	99.32 404	95.72 311	99.68 195	99.18 271

EG-PatchMatch MVS		98.99 82	99.01 80	98.94 156	99.50 121	97.47 204	98.04 189	99.59 70	98.15 192	99.40 107	99.36 99	98.58 63	99.76 256	98.78 99	99.68 195	99.59 103

fmvsm_s_conf0.5_n_2		99.14 59	99.31 40	98.63 206	99.49 129	96.08 274	97.38 283	99.81 30	99.48 42	99.84 29	99.57 49	98.46 71	99.89 93	99.82 10	99.97 20	99.91 13

SED-MVS		98.91 93	98.72 111	99.49 54	99.49 129	99.17 44	98.10 179	99.31 191	98.03 195	99.66 58	99.02 184	98.36 77	99.88 110	96.91 224	99.62 217	99.41 195

IU-MVS					99.49 129	99.15 52		98.87 295	92.97 400	99.41 104				96.76 241	99.62 217	99.66 74

test_241102_ONE					99.49 129	99.17 44		99.31 191	97.98 198	99.66 58	98.90 219	98.36 77	99.48 377

UA-Net		99.47 16	99.40 26	99.70 2	99.49 129	99.29 24	99.80 4	99.72 43	99.82 8	99.04 169	99.81 8	98.05 110	99.96 14	98.85 95	99.99 5	99.86 27

HFP-MVS		98.71 122	98.44 158	99.51 48	99.49 129	99.16 48	98.52 123	99.31 191	97.47 244	98.58 247	98.50 298	97.97 117	99.85 150	96.57 259	99.59 228	99.53 142

VPA-MVSNet		99.30 33	99.30 43	99.28 92	99.49 129	98.36 120	99.00 72	99.45 129	99.63 29	99.52 80	99.44 84	98.25 88	99.88 110	99.09 77	99.84 105	99.62 86

XVG-OURS-SEG-HR		98.49 166	98.28 181	99.14 118	99.49 129	98.83 83	96.54 335	99.48 113	97.32 262	99.11 155	98.61 282	99.33 14	99.30 407	96.23 285	98.38 374	99.28 245

114514_t		96.50 325	95.77 334	98.69 196	99.48 137	97.43 208	97.84 223	99.55 90	81.42 447	96.51 387	98.58 286	95.53 262	99.67 302	93.41 376	99.58 233	98.98 302

IterMVS-LS		98.55 156	98.70 117	98.09 273	99.48 137	94.73 322	97.22 300	99.39 156	98.97 117	99.38 110	99.31 111	96.00 242	99.93 52	98.58 114	99.97 20	99.60 96
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 75	99.10 70	98.99 147	99.47 139	97.22 220	97.40 281	99.83 25	97.61 229	99.85 26	99.30 112	98.80 39	99.95 26	99.71 29	99.90 82	99.78 44

v8		99.01 79	99.16 59	98.57 218	99.47 139	96.31 266	98.90 83	99.47 121	99.03 111	99.52 80	99.57 49	96.93 192	99.81 212	99.60 34	99.98 12	99.60 96

SSC-MVS3.2		98.53 160	98.79 103	97.74 301	99.46 141	93.62 366	96.45 341	99.34 178	99.33 63	98.93 192	98.70 262	97.90 121	99.90 78	99.12 74	99.92 66	99.69 66

fmvsm_s_conf0.5_n_3		99.22 46	99.37 31	98.78 181	99.46 141	96.58 257	97.65 251	99.72 43	99.47 45	99.86 23	99.50 67	98.94 29	99.89 93	99.75 23	99.97 20	99.86 27

XVS		98.72 121	98.45 156	99.53 38	99.46 141	99.21 33	98.65 108	99.34 178	98.62 145	97.54 332	98.63 278	97.50 158	99.83 186	96.79 237	99.53 250	99.56 122

X-MVStestdata		94.32 374	92.59 393	99.53 38	99.46 141	99.21 33	98.65 108	99.34 178	98.62 145	97.54 332	45.85 452	97.50 158	99.83 186	96.79 237	99.53 250	99.56 122

test20.03		98.78 113	98.77 106	98.78 181	99.46 141	97.20 223	97.78 230	99.24 225	99.04 110	99.41 104	98.90 219	97.65 140	99.76 256	97.70 174	99.79 137	99.39 205

guyue		98.01 222	97.93 227	98.26 261	99.45 146	95.48 295	98.08 181	96.24 402	98.89 126	99.34 119	99.14 157	91.32 345	99.82 196	99.07 78	99.83 112	99.48 167

CSCG		98.68 134	98.50 146	99.20 106	99.45 146	98.63 95	98.56 118	99.57 79	97.87 209	98.85 207	98.04 339	97.66 139	99.84 168	96.72 246	99.81 120	99.13 281

GeoE		99.05 76	98.99 84	99.25 100	99.44 148	98.35 121	98.73 101	99.56 86	98.42 162	98.91 195	98.81 242	98.94 29	99.91 71	98.35 127	99.73 167	99.49 156

v148		98.45 170	98.60 134	98.00 283	99.44 148	94.98 314	97.44 280	99.06 261	98.30 170	99.32 127	98.97 204	96.65 214	99.62 327	98.37 126	99.85 101	99.39 205

v10		98.97 86	99.11 68	98.55 224	99.44 148	96.21 268	98.90 83	99.55 90	98.73 135	99.48 88	99.60 45	96.63 215	99.83 186	99.70 30	99.99 5	99.61 94

V42		98.78 113	98.78 105	98.76 186	99.44 148	97.04 231	98.27 157	99.19 235	97.87 209	99.25 142	99.16 150	96.84 196	99.78 244	99.21 68	99.84 105	99.46 177

MDA-MVSNet-bldmvs		97.94 228	97.91 229	98.06 278	99.44 148	94.96 315	96.63 333	99.15 251	98.35 164	98.83 210	99.11 163	94.31 297	99.85 150	96.60 256	98.72 356	99.37 214

casdiffmvs_mvg		99.12 66	99.16 59	98.99 147	99.43 153	97.73 189	98.00 197	99.62 65	99.22 76	99.55 72	99.22 136	98.93 31	99.75 263	98.66 110	99.81 120	99.50 151
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 95	99.01 80	98.57 218	99.42 154	96.59 254	98.13 172	99.66 58	99.09 102	99.30 130	99.02 184	98.79 41	99.89 93	97.87 163	99.80 131	99.23 255

test1111		96.49 326	96.82 300	95.52 399	99.42 154	87.08 434	99.22 45	87.14 450	99.11 92	99.46 93	99.58 47	88.69 366	99.86 137	98.80 97	99.95 37	99.62 86

v2v482		98.56 152	98.62 129	98.37 251	99.42 154	95.81 285	97.58 264	99.16 246	97.90 207	99.28 132	99.01 194	95.98 247	99.79 233	99.33 57	99.90 82	99.51 148

OPM-MVS		98.56 152	98.32 177	99.25 100	99.41 157	98.73 91	97.13 307	99.18 239	97.10 284	98.75 224	98.92 215	98.18 97	99.65 318	96.68 250	99.56 240	99.37 214
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 216	98.08 209	98.04 281	99.41 157	94.59 328	94.59 421	99.40 154	97.50 241	98.82 213	98.83 237	96.83 198	99.84 168	97.50 186	99.81 120	99.71 59

test_one_0601					99.39 159	99.20 39		99.31 191	98.49 158	98.66 234	99.02 184	97.64 143

mvsany_test3		98.87 99	98.92 89	98.74 192	99.38 160	96.94 238	98.58 116	99.10 256	96.49 314	99.96 4	99.81 8	98.18 97	99.45 385	98.97 87	99.79 137	99.83 31

patch_mono-2		98.51 165	98.63 127	98.17 269	99.38 160	94.78 319	97.36 286	99.69 49	98.16 189	98.49 259	99.29 115	97.06 184	99.97 7	98.29 131	99.91 75	99.76 52

test2506		92.39 405	91.89 407	93.89 420	99.38 160	82.28 451	99.32 26	66.03 458	99.08 105	98.77 221	99.57 49	66.26 446	99.84 168	98.71 107	99.95 37	99.54 133

ECVR-MVS		96.42 328	96.61 314	95.85 391	99.38 160	88.18 429	99.22 45	86.00 452	99.08 105	99.36 115	99.57 49	88.47 371	99.82 196	98.52 120	99.95 37	99.54 133

casdiffmvs		98.95 89	99.00 82	98.81 173	99.38 160	97.33 212	97.82 224	99.57 79	99.17 88	99.35 117	99.17 148	98.35 81	99.69 290	98.46 122	99.73 167	99.41 195
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 88	99.02 78	98.76 186	99.38 160	97.26 217	98.49 133	99.50 104	98.86 129	99.19 148	99.06 172	98.23 90	99.69 290	98.71 107	99.76 160	99.33 232

TranMVSNet+NR-MVSNet		99.17 51	99.07 75	99.46 62	99.37 166	98.87 81	98.39 146	99.42 147	99.42 53	99.36 115	99.06 172	98.38 76	99.95 26	98.34 128	99.90 82	99.57 116

fmvsm_s_conf0.5_n_6		99.08 73	99.21 54	98.69 196	99.36 167	96.51 259	97.62 256	99.68 54	98.43 161	99.85 26	99.10 166	99.12 22	99.88 110	99.77 20	99.92 66	99.67 72

tttt0517		95.64 353	94.98 363	97.64 312	99.36 167	93.81 358	98.72 102	90.47 444	98.08 194	98.67 232	98.34 315	73.88 432	99.92 62	97.77 169	99.51 255	99.20 263

test_part2					99.36 167	99.10 65				99.05 167

v1144		98.60 148	98.66 123	98.41 244	99.36 167	95.90 279	97.58 264	99.34 178	97.51 240	99.27 134	99.15 154	96.34 229	99.80 220	99.47 51	99.93 53	99.51 148

CP-MVS		98.70 126	98.42 161	99.52 44	99.36 167	99.12 62	98.72 102	99.36 166	97.54 238	98.30 272	98.40 307	97.86 125	99.89 93	96.53 268	99.72 175	99.56 122

Test_1112_low_res		96.99 307	96.55 318	98.31 257	99.35 172	95.47 297	95.84 382	99.53 97	91.51 417	96.80 374	98.48 301	91.36 344	99.83 186	96.58 257	99.53 250	99.62 86

DeepC-MVS	97.60 4	98.97 86	98.93 88	99.10 124	99.35 172	97.98 158	98.01 196	99.46 125	97.56 235	99.54 74	99.50 67	98.97 27	99.84 168	98.06 146	99.92 66	99.49 156
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 284	96.86 296	98.58 215	99.34 174	96.32 265	96.75 326	99.58 72	93.14 398	96.89 369	97.48 372	92.11 336	99.86 137	96.91 224	99.54 246	99.57 116

reproduce_model		99.15 56	98.97 86	99.67 4	99.33 175	99.44 10	98.15 170	99.47 121	99.12 91	99.52 80	99.32 110	98.31 84	99.90 78	97.78 168	99.73 167	99.66 74

MVSMamba_PlusPlus		98.83 104	98.98 85	98.36 252	99.32 176	96.58 257	98.90 83	99.41 151	99.75 11	98.72 227	99.50 67	96.17 233	99.94 41	99.27 62	99.78 142	98.57 362

fmvsm_s_conf0.5_n_4		99.01 79	99.22 52	98.38 248	99.31 177	95.48 295	97.56 266	99.73 42	98.87 127	99.75 43	99.27 118	98.80 39	99.86 137	99.80 15	99.90 82	99.81 37

SF-MVS		98.53 160	98.27 184	99.32 87	99.31 177	98.75 87	98.19 164	99.41 151	96.77 303	98.83 210	98.90 219	97.80 131	99.82 196	95.68 314	99.52 253	99.38 212

CPTT-MVS		97.84 243	97.36 267	99.27 95	99.31 177	98.46 111	98.29 153	99.27 214	94.90 366	97.83 312	98.37 311	94.90 278	99.84 168	93.85 365	99.54 246	99.51 148

UnsupCasMVSNet_eth		97.89 232	97.60 253	98.75 188	99.31 177	97.17 226	97.62 256	99.35 172	98.72 137	98.76 223	98.68 266	92.57 330	99.74 268	97.76 173	95.60 436	99.34 227

fmvsm_s_conf0.5_n_7		98.83 104	99.04 77	98.20 266	99.30 181	94.83 317	97.23 296	99.36 166	98.64 140	99.84 29	99.43 86	98.10 106	99.91 71	99.56 38	99.96 27	99.87 21

pmmvs-eth3d		98.47 168	98.34 173	98.86 167	99.30 181	97.76 185	97.16 305	99.28 211	95.54 348	99.42 102	99.19 140	97.27 173	99.63 324	97.89 158	99.97 20	99.20 263

mamv4		99.44 19	99.39 27	99.58 20	99.30 181	99.74 2	99.04 68	99.81 30	99.77 10	99.82 32	99.57 49	97.82 129	99.98 4	99.53 45	99.89 88	99.01 296

SymmetryMVS		98.05 218	97.71 243	99.09 128	99.29 184	97.83 174	98.28 154	97.64 370	99.24 73	98.80 216	98.85 232	89.76 358	99.94 41	98.04 148	99.50 262	99.49 156

Anonymous20231211		99.27 37	99.27 46	99.26 97	99.29 184	98.18 133	99.49 12	99.51 101	99.70 16	99.80 36	99.68 25	96.84 196	99.83 186	99.21 68	99.91 75	99.77 47

UnsupCasMVSNet_bld		97.30 282	96.92 292	98.45 239	99.28 186	96.78 248	96.20 358	99.27 214	95.42 352	98.28 276	98.30 319	93.16 316	99.71 282	94.99 328	97.37 412	98.87 323

EC-MVSNet		99.09 69	99.05 76	99.20 106	99.28 186	98.93 79	99.24 44	99.84 22	99.08 105	98.12 289	98.37 311	98.72 47	99.90 78	99.05 81	99.77 148	98.77 340

reproduce-ours		99.09 69	98.90 91	99.67 4	99.27 188	99.49 6	98.00 197	99.42 147	99.05 108	99.48 88	99.27 118	98.29 86	99.89 93	97.61 178	99.71 180	99.62 86

our_new_method		99.09 69	98.90 91	99.67 4	99.27 188	99.49 6	98.00 197	99.42 147	99.05 108	99.48 88	99.27 118	98.29 86	99.89 93	97.61 178	99.71 180	99.62 86

DPE-MVS		98.59 150	98.26 185	99.57 21	99.27 188	99.15 52	97.01 310	99.39 156	97.67 222	99.44 97	98.99 198	97.53 154	99.89 93	95.40 322	99.68 195	99.66 74
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 242	98.18 196	96.87 360	99.27 188	91.16 409	95.53 391	99.25 220	99.10 99	99.41 104	99.35 100	93.10 318	99.96 14	98.65 111	99.94 48	99.49 156

v1192		98.60 148	98.66 123	98.41 244	99.27 188	95.88 280	97.52 271	99.36 166	97.41 253	99.33 121	99.20 139	96.37 227	99.82 196	99.57 36	99.92 66	99.55 129

N_pmnet		97.63 256	97.17 277	98.99 147	99.27 188	97.86 171	95.98 369	93.41 433	95.25 357	99.47 92	98.90 219	95.63 259	99.85 150	96.91 224	99.73 167	99.27 246

FPMVS		93.44 391	92.23 398	97.08 348	99.25 194	97.86 171	95.61 388	97.16 382	92.90 402	93.76 435	98.65 273	75.94 430	95.66 449	79.30 447	97.49 405	97.73 413

new-patchmatchnet		98.35 182	98.74 107	97.18 343	99.24 195	92.23 391	96.42 345	99.48 113	98.30 170	99.69 53	99.53 63	97.44 163	99.82 196	98.84 96	99.77 148	99.49 156

MCST-MVS		98.00 223	97.63 251	99.10 124	99.24 195	98.17 134	96.89 319	98.73 323	95.66 343	97.92 303	97.70 360	97.17 179	99.66 313	96.18 290	99.23 305	99.47 175

UniMVSNet (Re)		98.87 99	98.71 114	99.35 76	99.24 195	98.73 91	97.73 241	99.38 158	98.93 122	99.12 154	98.73 254	96.77 204	99.86 137	98.63 113	99.80 131	99.46 177

jason		97.45 270	97.35 268	97.76 298	99.24 195	93.93 352	95.86 379	98.42 341	94.24 381	98.50 258	98.13 329	94.82 282	99.91 71	97.22 200	99.73 167	99.43 189
jason: jason.
IterMVS		97.73 248	98.11 205	96.57 370	99.24 195	90.28 418	95.52 393	99.21 229	98.86 129	99.33 121	99.33 106	93.11 317	99.94 41	98.49 121	99.94 48	99.48 167
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 156	98.62 129	98.32 255	99.22 200	95.58 290	97.51 273	99.45 129	97.16 281	99.45 96	99.24 130	96.12 237	99.85 150	99.60 34	99.88 90	99.55 129

ITE_SJBPF				98.87 166	99.22 200	98.48 110		99.35 172	97.50 241	98.28 276	98.60 284	97.64 143	99.35 400	93.86 364	99.27 297	98.79 338

h-mvs33		97.77 246	97.33 270	99.10 124	99.21 202	97.84 173	98.35 150	98.57 333	99.11 92	98.58 247	99.02 184	88.65 369	99.96 14	98.11 141	96.34 428	99.49 156

v144192		98.54 158	98.57 137	98.45 239	99.21 202	95.98 277	97.63 255	99.36 166	97.15 283	99.32 127	99.18 144	95.84 254	99.84 168	99.50 48	99.91 75	99.54 133

APDe-MVS		98.99 82	98.79 103	99.60 15	99.21 202	99.15 52	98.87 88	99.48 113	97.57 233	99.35 117	99.24 130	97.83 126	99.89 93	97.88 161	99.70 187	99.75 56
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 91	98.81 102	99.28 92	99.21 202	98.45 112	98.46 138	99.33 184	99.63 29	99.48 88	99.15 154	97.23 176	99.75 263	97.17 202	99.66 208	99.63 85

SR-MVS-dyc-post		98.81 109	98.55 139	99.57 21	99.20 206	99.38 13	98.48 136	99.30 199	98.64 140	98.95 184	98.96 207	97.49 161	99.86 137	96.56 263	99.39 278	99.45 181

RE-MVS-def			98.58 136		99.20 206	99.38 13	98.48 136	99.30 199	98.64 140	98.95 184	98.96 207	97.75 134		96.56 263	99.39 278	99.45 181

v1921920		98.54 158	98.60 134	98.38 248	99.20 206	95.76 287	97.56 266	99.36 166	97.23 275	99.38 110	99.17 148	96.02 240	99.84 168	99.57 36	99.90 82	99.54 133

thisisatest0530		95.27 360	94.45 371	97.74 301	99.19 209	94.37 332	97.86 220	90.20 445	97.17 280	98.22 279	97.65 362	73.53 433	99.90 78	96.90 229	99.35 284	98.95 308

Anonymous20240529		98.93 91	98.87 94	99.12 120	99.19 209	98.22 131	99.01 70	98.99 278	99.25 72	99.54 74	99.37 95	97.04 185	99.80 220	97.89 158	99.52 253	99.35 225

APD-MVS_3200maxsize		98.84 103	98.61 133	99.53 38	99.19 209	99.27 27	98.49 133	99.33 184	98.64 140	99.03 172	98.98 202	97.89 123	99.85 150	96.54 267	99.42 275	99.46 177

HQP_MVS		97.99 226	97.67 245	98.93 158	99.19 209	97.65 193	97.77 233	99.27 214	98.20 183	97.79 315	97.98 343	94.90 278	99.70 286	94.42 346	99.51 255	99.45 181

plane_prior7					99.19 209	97.87 170

ab-mvs		98.41 173	98.36 170	98.59 214	99.19 209	97.23 218	99.32 26	98.81 309	97.66 223	98.62 239	99.40 94	96.82 199	99.80 220	95.88 301	99.51 255	98.75 343

F-COLMAP		97.30 282	96.68 309	99.14 118	99.19 209	98.39 114	97.27 295	99.30 199	92.93 401	96.62 380	98.00 341	95.73 257	99.68 299	92.62 392	98.46 373	99.35 225

SR-MVS		98.71 122	98.43 159	99.57 21	99.18 216	99.35 17	98.36 149	99.29 207	98.29 173	98.88 202	98.85 232	97.53 154	99.87 129	96.14 292	99.31 290	99.48 167

UniMVSNet_NR-MVSNet		98.86 102	98.68 120	99.40 68	99.17 217	98.74 88	97.68 245	99.40 154	99.14 90	99.06 162	98.59 285	96.71 210	99.93 52	98.57 116	99.77 148	99.53 142

LF4IMVS		97.90 230	97.69 244	98.52 230	99.17 217	97.66 192	97.19 304	99.47 121	96.31 322	97.85 311	98.20 326	96.71 210	99.52 365	94.62 338	99.72 175	98.38 379

SMA-MVS		98.40 175	98.03 214	99.51 48	99.16 219	99.21 33	98.05 187	99.22 228	94.16 383	98.98 176	99.10 166	97.52 156	99.79 233	96.45 273	99.64 211	99.53 142
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		98.82 107	98.63 127	99.39 69	99.16 219	98.74 88	97.54 269	99.25 220	98.84 132	99.06 162	98.76 251	96.76 206	99.93 52	98.57 116	99.77 148	99.50 151

NR-MVSNet		98.95 89	98.82 100	99.36 70	99.16 219	98.72 93	99.22 45	99.20 231	99.10 99	99.72 45	98.76 251	96.38 226	99.86 137	98.00 153	99.82 116	99.50 151

MVS_111021_LR		98.30 191	98.12 204	98.83 170	99.16 219	98.03 153	96.09 366	99.30 199	97.58 232	98.10 291	98.24 322	98.25 88	99.34 401	96.69 249	99.65 209	99.12 282

DSMNet-mixed		97.42 273	97.60 253	96.87 360	99.15 223	91.46 398	98.54 121	99.12 253	92.87 403	97.58 328	99.63 39	96.21 232	99.90 78	95.74 310	99.54 246	99.27 246

D2MVS		97.84 243	97.84 234	97.83 290	99.14 224	94.74 321	96.94 314	98.88 293	95.84 340	98.89 198	98.96 207	94.40 294	99.69 290	97.55 181	99.95 37	99.05 288

pmmvs5		97.64 255	97.49 259	98.08 276	99.14 224	95.12 311	96.70 329	99.05 264	93.77 390	98.62 239	98.83 237	93.23 314	99.75 263	98.33 130	99.76 160	99.36 221

SPE-MVS-test		99.13 63	99.09 72	99.26 97	99.13 226	98.97 73	99.31 30	99.88 14	99.44 50	98.16 284	98.51 294	98.64 54	99.93 52	98.91 90	99.85 101	98.88 322

VDD-MVS		98.56 152	98.39 166	99.07 131	99.13 226	98.07 148	98.59 115	97.01 385	99.59 35	99.11 155	99.27 118	94.82 282	99.79 233	98.34 128	99.63 214	99.34 227

save fliter					99.11 228	97.97 159	96.53 337	99.02 272	98.24 176

APD-MVS		98.10 212	97.67 245	99.42 64	99.11 228	98.93 79	97.76 236	99.28 211	94.97 364	98.72 227	98.77 249	97.04 185	99.85 150	93.79 366	99.54 246	99.49 156
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 129	98.71 114	98.62 208	99.10 230	96.37 263	97.23 296	98.87 295	99.20 80	99.19 148	98.99 198	97.30 170	99.85 150	98.77 102	99.79 137	99.65 79

EI-MVSNet		98.40 175	98.51 144	98.04 281	99.10 230	94.73 322	97.20 301	98.87 295	98.97 117	99.06 162	99.02 184	96.00 242	99.80 220	98.58 114	99.82 116	99.60 96

CVMVSNet		96.25 334	97.21 276	93.38 427	99.10 230	80.56 455	97.20 301	98.19 352	96.94 293	99.00 174	99.02 184	89.50 362	99.80 220	96.36 279	99.59 228	99.78 44

EI-MVSNet-Vis-set		98.68 134	98.70 117	98.63 206	99.09 233	96.40 262	97.23 296	98.86 300	99.20 80	99.18 152	98.97 204	97.29 172	99.85 150	98.72 106	99.78 142	99.64 80

HPM-MVS++		98.10 212	97.64 250	99.48 56	99.09 233	99.13 60	97.52 271	98.75 320	97.46 249	96.90 368	97.83 353	96.01 241	99.84 168	95.82 308	99.35 284	99.46 177

DP-MVS Recon		97.33 280	96.92 292	98.57 218	99.09 233	97.99 155	96.79 322	99.35 172	93.18 397	97.71 319	98.07 337	95.00 277	99.31 405	93.97 359	99.13 321	98.42 376

MVS_111021_HR		98.25 200	98.08 209	98.75 188	99.09 233	97.46 205	95.97 370	99.27 214	97.60 231	97.99 301	98.25 321	98.15 103	99.38 396	96.87 232	99.57 237	99.42 192

BP-MVS1		97.40 275	96.97 288	98.71 195	99.07 237	96.81 244	98.34 152	97.18 380	98.58 151	98.17 281	98.61 282	84.01 401	99.94 41	98.97 87	99.78 142	99.37 214

9.14			97.78 236		99.07 237		97.53 270	99.32 186	95.53 349	98.54 254	98.70 262	97.58 148	99.76 256	94.32 351	99.46 267

PAPM_NR		96.82 314	96.32 325	98.30 258	99.07 237	96.69 252	97.48 276	98.76 317	95.81 341	96.61 381	96.47 398	94.12 303	99.17 418	90.82 419	97.78 399	99.06 287

TAMVS		98.24 201	98.05 212	98.80 175	99.07 237	97.18 225	97.88 216	98.81 309	96.66 308	99.17 153	99.21 137	94.81 284	99.77 250	96.96 222	99.88 90	99.44 185

CLD-MVS		97.49 266	97.16 278	98.48 236	99.07 237	97.03 232	94.71 414	99.21 229	94.46 375	98.06 294	97.16 384	97.57 149	99.48 377	94.46 343	99.78 142	98.95 308
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 63	99.10 70	99.24 102	99.06 242	99.15 52	99.36 22	99.88 14	99.36 61	98.21 280	98.46 302	98.68 51	99.93 52	99.03 83	99.85 101	98.64 355

thres100view900		94.19 377	93.67 382	95.75 394	99.06 242	91.35 402	98.03 190	94.24 428	98.33 166	97.40 344	94.98 428	79.84 417	99.62 327	83.05 440	98.08 390	96.29 435

thres600view7		94.45 372	93.83 379	96.29 378	99.06 242	91.53 397	97.99 202	94.24 428	98.34 165	97.44 342	95.01 426	79.84 417	99.67 302	84.33 438	98.23 379	97.66 416

plane_prior1					99.05 245

YYNet1		97.60 257	97.67 245	97.39 336	99.04 246	93.04 375	95.27 400	98.38 344	97.25 269	98.92 194	98.95 211	95.48 266	99.73 274	96.99 218	98.74 354	99.41 195

MDA-MVSNet_test_wron		97.60 257	97.66 248	97.41 335	99.04 246	93.09 371	95.27 400	98.42 341	97.26 268	98.88 202	98.95 211	95.43 267	99.73 274	97.02 215	98.72 356	99.41 195

MIMVSNet		96.62 321	96.25 329	97.71 305	99.04 246	94.66 325	99.16 54	96.92 391	97.23 275	97.87 308	99.10 166	86.11 384	99.65 318	91.65 403	99.21 309	98.82 327

ICG_test_0404		98.07 216	98.20 191	97.69 306	99.03 249	94.03 345	96.67 330	99.45 129	98.16 189	98.03 298	98.71 257	96.80 202	99.82 196	97.50 186	99.45 269	99.22 260

icg_test_0403		98.34 183	98.56 138	97.66 309	99.03 249	94.03 345	97.98 203	99.45 129	98.16 189	98.89 198	98.71 257	97.90 121	99.74 268	97.50 186	99.45 269	99.22 260

PatchMatch-RL		97.24 288	96.78 303	98.61 211	99.03 249	97.83 174	96.36 348	99.06 261	93.49 395	97.36 348	97.78 354	95.75 256	99.49 374	93.44 375	98.77 353	98.52 364

GDP-MVS		97.50 263	97.11 282	98.67 199	99.02 252	96.85 242	98.16 169	99.71 45	98.32 168	98.52 257	98.54 289	83.39 405	99.95 26	98.79 98	99.56 240	99.19 268

ZD-MVS					99.01 253	98.84 82		99.07 260	94.10 385	98.05 296	98.12 331	96.36 228	99.86 137	92.70 391	99.19 313

CDPH-MVS		97.26 285	96.66 312	99.07 131	99.00 254	98.15 135	96.03 368	99.01 275	91.21 421	97.79 315	97.85 352	96.89 194	99.69 290	92.75 389	99.38 281	99.39 205

diffmvs		98.22 202	98.24 188	98.17 269	99.00 254	95.44 298	96.38 347	99.58 72	97.79 216	98.53 255	98.50 298	96.76 206	99.74 268	97.95 157	99.64 211	99.34 227
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		98.40 175	98.19 195	99.03 141	99.00 254	97.65 193	96.85 320	98.94 280	98.57 152	98.89 198	98.50 298	95.60 260	99.85 150	97.54 183	99.85 101	99.59 103

plane_prior6					98.99 257	97.70 191						94.90 278

xiu_mvs_v1_base_debu		97.86 237	98.17 197	96.92 357	98.98 258	93.91 353	96.45 341	99.17 243	97.85 211	98.41 266	97.14 386	98.47 68	99.92 62	98.02 150	99.05 327	96.92 428

xiu_mvs_v1_base		97.86 237	98.17 197	96.92 357	98.98 258	93.91 353	96.45 341	99.17 243	97.85 211	98.41 266	97.14 386	98.47 68	99.92 62	98.02 150	99.05 327	96.92 428

xiu_mvs_v1_base_debi		97.86 237	98.17 197	96.92 357	98.98 258	93.91 353	96.45 341	99.17 243	97.85 211	98.41 266	97.14 386	98.47 68	99.92 62	98.02 150	99.05 327	96.92 428

MVP-Stereo		98.08 215	97.92 228	98.57 218	98.96 261	96.79 245	97.90 214	99.18 239	96.41 318	98.46 261	98.95 211	95.93 251	99.60 335	96.51 269	98.98 341	99.31 238
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 175	98.68 120	97.54 324	98.96 261	97.99 155	97.88 216	99.36 166	98.20 183	99.63 64	99.04 181	98.76 43	95.33 451	96.56 263	99.74 164	99.31 238
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				98.91 162	98.94 263	97.76 185		98.76 317	87.58 438	96.75 376	98.10 333	94.80 285	99.78 244	92.73 390	99.00 336	99.20 263

USDC		97.41 274	97.40 263	97.44 333	98.94 263	93.67 363	95.17 403	99.53 97	94.03 387	98.97 180	99.10 166	95.29 269	99.34 401	95.84 307	99.73 167	99.30 241

tfpn200view9		94.03 381	93.44 384	95.78 393	98.93 265	91.44 400	97.60 261	94.29 426	97.94 203	97.10 354	94.31 435	79.67 419	99.62 327	83.05 440	98.08 390	96.29 435

testdata				98.09 273	98.93 265	95.40 300		98.80 311	90.08 429	97.45 341	98.37 311	95.26 270	99.70 286	93.58 371	98.95 344	99.17 275

thres400		94.14 379	93.44 384	96.24 381	98.93 265	91.44 400	97.60 261	94.29 426	97.94 203	97.10 354	94.31 435	79.67 419	99.62 327	83.05 440	98.08 390	97.66 416

TAPA-MVS	96.21 11	96.63 320	95.95 331	98.65 200	98.93 265	98.09 142	96.93 316	99.28 211	83.58 444	98.13 288	97.78 354	96.13 235	99.40 392	93.52 372	99.29 295	98.45 369
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 269	96.93 239	95.54 390	98.78 314	85.72 441	96.86 371	98.11 332	94.43 292			99.10 326	99.23 255

PVSNet_BlendedMVS		97.55 262	97.53 256	97.60 316	98.92 269	93.77 360	96.64 332	99.43 141	94.49 373	97.62 324	99.18 144	96.82 199	99.67 302	94.73 335	99.93 53	99.36 221

PVSNet_Blended		96.88 310	96.68 309	97.47 331	98.92 269	93.77 360	94.71 414	99.43 141	90.98 423	97.62 324	97.36 380	96.82 199	99.67 302	94.73 335	99.56 240	98.98 302

MSDG		97.71 250	97.52 257	98.28 260	98.91 272	96.82 243	94.42 424	99.37 162	97.65 224	98.37 271	98.29 320	97.40 165	99.33 403	94.09 357	99.22 306	98.68 353

Anonymous202405211		97.90 230	97.50 258	99.08 129	98.90 273	98.25 125	98.53 122	96.16 403	98.87 127	99.11 155	98.86 229	90.40 354	99.78 244	97.36 193	99.31 290	99.19 268

原ACMM1				98.35 253	98.90 273	96.25 267		98.83 308	92.48 407	96.07 398	98.10 333	95.39 268	99.71 282	92.61 393	98.99 338	99.08 284

GBi-Net		98.65 139	98.47 153	99.17 111	98.90 273	98.24 126	99.20 48	99.44 135	98.59 148	98.95 184	99.55 57	94.14 300	99.86 137	97.77 169	99.69 190	99.41 195

test1		98.65 139	98.47 153	99.17 111	98.90 273	98.24 126	99.20 48	99.44 135	98.59 148	98.95 184	99.55 57	94.14 300	99.86 137	97.77 169	99.69 190	99.41 195

FMVSNet2		98.49 166	98.40 163	98.75 188	98.90 273	97.14 229	98.61 113	99.13 252	98.59 148	99.19 148	99.28 116	94.14 300	99.82 196	97.97 155	99.80 131	99.29 243

OMC-MVS		97.88 234	97.49 259	99.04 140	98.89 278	98.63 95	96.94 314	99.25 220	95.02 362	98.53 255	98.51 294	97.27 173	99.47 380	93.50 374	99.51 255	99.01 296

VortexMVS		97.98 227	98.31 178	97.02 351	98.88 279	91.45 399	98.03 190	99.47 121	98.65 139	99.55 72	99.47 77	91.49 343	99.81 212	99.32 58	99.91 75	99.80 39

MVSFormer		98.26 197	98.43 159	97.77 295	98.88 279	93.89 356	99.39 20	99.56 86	99.11 92	98.16 284	98.13 329	93.81 308	99.97 7	99.26 63	99.57 237	99.43 189

lupinMVS		97.06 300	96.86 296	97.65 310	98.88 279	93.89 356	95.48 394	97.97 358	93.53 393	98.16 284	97.58 366	93.81 308	99.91 71	96.77 240	99.57 237	99.17 275

dmvs_re		95.98 342	95.39 352	97.74 301	98.86 282	97.45 206	98.37 148	95.69 415	97.95 201	96.56 382	95.95 407	90.70 351	97.68 445	88.32 428	96.13 432	98.11 391

DELS-MVS		98.27 195	98.20 191	98.48 236	98.86 282	96.70 251	95.60 389	99.20 231	97.73 219	98.45 262	98.71 257	97.50 158	99.82 196	98.21 135	99.59 228	98.93 313
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		97.89 232	97.98 219	97.60 316	98.86 282	94.35 333	96.21 357	99.44 135	97.45 251	99.06 162	98.88 226	97.99 116	99.28 411	94.38 350	99.58 233	99.18 271

LCM-MVSNet-Re		98.64 141	98.48 151	99.11 122	98.85 285	98.51 108	98.49 133	99.83 25	98.37 163	99.69 53	99.46 79	98.21 95	99.92 62	94.13 356	99.30 293	98.91 317

pmmvs4		97.58 260	97.28 271	98.51 231	98.84 286	96.93 239	95.40 398	98.52 336	93.60 392	98.61 241	98.65 273	95.10 274	99.60 335	96.97 221	99.79 137	98.99 301

NP-MVS					98.84 286	97.39 210					96.84 389

sss		97.21 290	96.93 290	98.06 278	98.83 288	95.22 307	96.75 326	98.48 338	94.49 373	97.27 350	97.90 349	92.77 326	99.80 220	96.57 259	99.32 288	99.16 278

PVSNet	93.40 17	95.67 351	95.70 337	95.57 398	98.83 288	88.57 425	92.50 441	97.72 363	92.69 405	96.49 390	96.44 399	93.72 311	99.43 388	93.61 369	99.28 296	98.71 346

MVE	83.40 22	92.50 404	91.92 406	94.25 414	98.83 288	91.64 396	92.71 440	83.52 454	95.92 338	86.46 452	95.46 420	95.20 271	95.40 450	80.51 445	98.64 365	95.73 443
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 385	93.91 377	93.39 426	98.82 291	81.72 453	97.76 236	95.28 417	98.60 147	96.54 383	96.66 393	65.85 449	99.62 327	96.65 252	98.99 338	98.82 327

ambc				98.24 264	98.82 291	95.97 278	98.62 112	99.00 277		99.27 134	99.21 137	96.99 190	99.50 371	96.55 266	99.50 262	99.26 249

旧先验1					98.82 291	97.45 206		98.76 317			98.34 315	95.50 265			99.01 335	99.23 255

test_vis1_rt		97.75 247	97.72 242	97.83 290	98.81 294	96.35 264	97.30 291	99.69 49	94.61 371	97.87 308	98.05 338	96.26 231	98.32 439	98.74 104	98.18 382	98.82 327

WTY-MVS		96.67 318	96.27 328	97.87 288	98.81 294	94.61 327	96.77 324	97.92 360	94.94 365	97.12 353	97.74 357	91.11 347	99.82 196	93.89 362	98.15 386	99.18 271

3Dnovator+	97.89 3	98.69 129	98.51 144	99.24 102	98.81 294	98.40 113	99.02 69	99.19 235	98.99 114	98.07 293	99.28 116	97.11 183	99.84 168	96.84 235	99.32 288	99.47 175

QAPM		97.31 281	96.81 302	98.82 171	98.80 297	97.49 201	99.06 65	99.19 235	90.22 427	97.69 321	99.16 150	96.91 193	99.90 78	90.89 418	99.41 276	99.07 286

VNet		98.42 172	98.30 179	98.79 178	98.79 298	97.29 214	98.23 160	98.66 327	99.31 66	98.85 207	98.80 243	94.80 285	99.78 244	98.13 140	99.13 321	99.31 238

DPM-MVS		96.32 330	95.59 343	98.51 231	98.76 299	97.21 222	94.54 423	98.26 347	91.94 412	96.37 391	97.25 382	93.06 320	99.43 388	91.42 408	98.74 354	98.89 319

3Dnovator	98.27 2	98.81 109	98.73 109	99.05 138	98.76 299	97.81 182	99.25 43	99.30 199	98.57 152	98.55 252	99.33 106	97.95 118	99.90 78	97.16 203	99.67 201	99.44 185

PLC	94.65 16	96.51 323	95.73 336	98.85 168	98.75 301	97.91 167	96.42 345	99.06 261	90.94 424	95.59 404	97.38 378	94.41 293	99.59 339	90.93 416	98.04 395	99.05 288
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 312	96.75 305	97.08 348	98.74 302	93.33 369	96.71 328	98.26 347	96.72 305	98.44 263	97.37 379	95.20 271	99.47 380	91.89 398	97.43 409	98.44 372

hse-mvs2		97.46 268	97.07 283	98.64 202	98.73 303	97.33 212	97.45 279	97.64 370	99.11 92	98.58 247	97.98 343	88.65 369	99.79 233	98.11 141	97.39 411	98.81 332

CDS-MVSNet		97.69 251	97.35 268	98.69 196	98.73 303	97.02 233	96.92 318	98.75 320	95.89 339	98.59 245	98.67 268	92.08 337	99.74 268	96.72 246	99.81 120	99.32 234
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SD_0403		96.28 332	95.83 333	97.64 312	98.72 305	94.30 334	98.87 88	98.77 315	97.80 214	96.53 384	98.02 340	97.34 168	99.47 380	76.93 449	99.48 265	99.16 278

EIA-MVS		98.00 223	97.74 239	98.80 175	98.72 305	98.09 142	98.05 187	99.60 69	97.39 255	96.63 379	95.55 415	97.68 137	99.80 220	96.73 245	99.27 297	98.52 364

LFMVS		97.20 291	96.72 306	98.64 202	98.72 305	96.95 237	98.93 81	94.14 430	99.74 13	98.78 218	99.01 194	84.45 396	99.73 274	97.44 189	99.27 297	99.25 250

new_pmnet		96.99 307	96.76 304	97.67 307	98.72 305	94.89 316	95.95 374	98.20 350	92.62 406	98.55 252	98.54 289	94.88 281	99.52 365	93.96 360	99.44 274	98.59 361

Fast-Effi-MVS+		97.67 253	97.38 265	98.57 218	98.71 309	97.43 208	97.23 296	99.45 129	94.82 368	96.13 395	96.51 395	98.52 66	99.91 71	96.19 288	98.83 350	98.37 381

TEST9					98.71 309	98.08 146	95.96 372	99.03 269	91.40 418	95.85 401	97.53 368	96.52 219	99.76 256

train_agg		97.10 297	96.45 322	99.07 131	98.71 309	98.08 146	95.96 372	99.03 269	91.64 413	95.85 401	97.53 368	96.47 221	99.76 256	93.67 368	99.16 316	99.36 221

TSAR-MVS + GP.		98.18 207	97.98 219	98.77 185	98.71 309	97.88 169	96.32 351	98.66 327	96.33 320	99.23 145	98.51 294	97.48 162	99.40 392	97.16 203	99.46 267	99.02 295

FA-MVS(test-final)		96.99 307	96.82 300	97.50 328	98.70 313	94.78 319	99.34 23	96.99 386	95.07 361	98.48 260	99.33 106	88.41 372	99.65 318	96.13 294	98.92 347	98.07 394

AUN-MVS		96.24 336	95.45 348	98.60 213	98.70 313	97.22 220	97.38 283	97.65 368	95.95 337	95.53 411	97.96 347	82.11 413	99.79 233	96.31 281	97.44 408	98.80 337

our_test_3		97.39 276	97.73 241	96.34 376	98.70 313	89.78 421	94.61 420	98.97 279	96.50 313	99.04 169	98.85 232	95.98 247	99.84 168	97.26 198	99.67 201	99.41 195

ppachtmachnet_test		97.50 263	97.74 239	96.78 366	98.70 313	91.23 408	94.55 422	99.05 264	96.36 319	99.21 146	98.79 245	96.39 224	99.78 244	96.74 243	99.82 116	99.34 227

PCF-MVS	92.86 18	94.36 373	93.00 391	98.42 243	98.70 313	97.56 198	93.16 439	99.11 255	79.59 448	97.55 331	97.43 375	92.19 334	99.73 274	79.85 446	99.45 269	97.97 400
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 229	98.02 215	97.58 318	98.69 318	94.10 341	98.13 172	98.90 289	97.95 201	97.32 349	99.58 47	95.95 250	98.75 434	96.41 275	99.22 306	99.87 21

ETV-MVS		98.03 219	97.86 233	98.56 223	98.69 318	98.07 148	97.51 273	99.50 104	98.10 193	97.50 336	95.51 416	98.41 74	99.88 110	96.27 284	99.24 302	97.71 415

test_prior				98.95 155	98.69 318	97.95 163		99.03 269					99.59 339			99.30 241

mvsmamba		97.57 261	97.26 272	98.51 231	98.69 318	96.73 250	98.74 97	97.25 379	97.03 289	97.88 307	99.23 135	90.95 348	99.87 129	96.61 255	99.00 336	98.91 317

agg_prior					98.68 322	97.99 155		99.01 275		95.59 404			99.77 250

test_8					98.67 323	98.01 154	95.91 378	99.02 272	91.64 413	95.79 403	97.50 371	96.47 221	99.76 256

HQP-NCC					98.67 323		96.29 353		96.05 330	95.55 407

ACMP_Plane					98.67 323		96.29 353		96.05 330	95.55 407

CNVR-MVS		98.17 209	97.87 232	99.07 131	98.67 323	98.24 126	97.01 310	98.93 283	97.25 269	97.62 324	98.34 315	97.27 173	99.57 347	96.42 274	99.33 287	99.39 205

HQP-MVS		97.00 306	96.49 321	98.55 224	98.67 323	96.79 245	96.29 353	99.04 267	96.05 330	95.55 407	96.84 389	93.84 306	99.54 359	92.82 386	99.26 300	99.32 234

MM		98.22 202	97.99 218	98.91 162	98.66 328	96.97 234	97.89 215	94.44 424	99.54 38	98.95 184	99.14 157	93.50 312	99.92 62	99.80 15	99.96 27	99.85 29

test_fmvs1		97.72 249	97.94 225	97.07 350	98.66 328	92.39 386	97.68 245	99.81 30	95.20 360	99.54 74	99.44 84	91.56 342	99.41 391	99.78 19	99.77 148	99.40 204

balanced_conf03		98.63 143	98.72 111	98.38 248	98.66 328	96.68 253	98.90 83	99.42 147	98.99 114	98.97 180	99.19 140	95.81 255	99.85 150	98.77 102	99.77 148	98.60 358

thres200		93.72 387	93.14 389	95.46 402	98.66 328	91.29 404	96.61 334	94.63 423	97.39 255	96.83 372	93.71 438	79.88 416	99.56 350	82.40 443	98.13 387	95.54 444

wuyk23d		96.06 338	97.62 252	91.38 431	98.65 332	98.57 102	98.85 92	96.95 389	96.86 298	99.90 13	99.16 150	99.18 18	98.40 438	89.23 426	99.77 148	77.18 451

NCCC		97.86 237	97.47 262	99.05 138	98.61 333	98.07 148	96.98 312	98.90 289	97.63 225	97.04 358	97.93 348	95.99 246	99.66 313	95.31 323	98.82 352	99.43 189

DeepC-MVS_fast	96.85 6	98.30 191	98.15 201	98.75 188	98.61 333	97.23 218	97.76 236	99.09 258	97.31 263	98.75 224	98.66 271	97.56 150	99.64 321	96.10 295	99.55 244	99.39 205
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 389	92.09 400	97.75 299	98.60 335	94.40 331	97.32 289	95.26 418	97.56 235	96.79 375	95.50 417	53.57 457	99.77 250	95.26 324	98.97 342	99.08 284

thisisatest0515		94.12 380	93.16 388	96.97 355	98.60 335	92.90 376	93.77 435	90.61 443	94.10 385	96.91 365	95.87 410	74.99 431	99.80 220	94.52 341	99.12 324	98.20 387

GA-MVS		95.86 345	95.32 355	97.49 329	98.60 335	94.15 340	93.83 434	97.93 359	95.49 350	96.68 377	97.42 376	83.21 406	99.30 407	96.22 286	98.55 371	99.01 296

dmvs_testset		92.94 399	92.21 399	95.13 406	98.59 338	90.99 411	97.65 251	92.09 439	96.95 292	94.00 431	93.55 439	92.34 332	96.97 448	72.20 450	92.52 446	97.43 423

OPU-MVS				98.82 171	98.59 338	98.30 122	98.10 179				98.52 293	98.18 97	98.75 434	94.62 338	99.48 265	99.41 195

MSLP-MVS++		98.02 220	98.14 203	97.64 312	98.58 340	95.19 308	97.48 276	99.23 227	97.47 244	97.90 305	98.62 280	97.04 185	98.81 432	97.55 181	99.41 276	98.94 312

test12				98.93 158	98.58 340	97.83 174		98.66 327		96.53 384		95.51 264	99.69 290		99.13 321	99.27 246

CL-MVSNet_self_test		97.44 271	97.22 275	98.08 276	98.57 342	95.78 286	94.30 427	98.79 312	96.58 311	98.60 243	98.19 327	94.74 288	99.64 321	96.41 275	98.84 349	98.82 327

PS-MVSNAJ		97.08 299	97.39 264	96.16 387	98.56 343	92.46 384	95.24 402	98.85 303	97.25 269	97.49 337	95.99 406	98.07 107	99.90 78	96.37 277	98.67 364	96.12 440

CNLPA		97.17 294	96.71 307	98.55 224	98.56 343	98.05 152	96.33 350	98.93 283	96.91 295	97.06 357	97.39 377	94.38 295	99.45 385	91.66 402	99.18 315	98.14 390

xiu_mvs_v2_base		97.16 295	97.49 259	96.17 385	98.54 345	92.46 384	95.45 395	98.84 304	97.25 269	97.48 338	96.49 396	98.31 84	99.90 78	96.34 280	98.68 363	96.15 439

alignmvs		97.35 278	96.88 295	98.78 181	98.54 345	98.09 142	97.71 242	97.69 365	99.20 80	97.59 327	95.90 409	88.12 374	99.55 354	98.18 137	98.96 343	98.70 349

FE-MVS		95.66 352	94.95 365	97.77 295	98.53 347	95.28 304	99.40 19	96.09 406	93.11 399	97.96 302	99.26 123	79.10 423	99.77 250	92.40 395	98.71 358	98.27 385

Effi-MVS+		98.02 220	97.82 235	98.62 208	98.53 347	97.19 224	97.33 288	99.68 54	97.30 264	96.68 377	97.46 374	98.56 64	99.80 220	96.63 253	98.20 381	98.86 324

baseline1		95.96 343	95.44 349	97.52 326	98.51 349	93.99 350	98.39 146	96.09 406	98.21 179	98.40 270	97.76 356	86.88 376	99.63 324	95.42 321	89.27 449	98.95 308

MVS_Test		98.18 207	98.36 170	97.67 307	98.48 350	94.73 322	98.18 165	99.02 272	97.69 221	98.04 297	99.11 163	97.22 177	99.56 350	98.57 116	98.90 348	98.71 346

MGCFI-Net		98.34 183	98.28 181	98.51 231	98.47 351	97.59 197	98.96 77	99.48 113	99.18 87	97.40 344	95.50 417	98.66 52	99.50 371	98.18 137	98.71 358	98.44 372

BH-RMVSNet		96.83 312	96.58 317	97.58 318	98.47 351	94.05 342	96.67 330	97.36 374	96.70 307	97.87 308	97.98 343	95.14 273	99.44 387	90.47 421	98.58 370	99.25 250

sasdasda		98.34 183	98.26 185	98.58 215	98.46 353	97.82 179	98.96 77	99.46 125	99.19 84	97.46 339	95.46 420	98.59 60	99.46 383	98.08 144	98.71 358	98.46 366

canonicalmvs		98.34 183	98.26 185	98.58 215	98.46 353	97.82 179	98.96 77	99.46 125	99.19 84	97.46 339	95.46 420	98.59 60	99.46 383	98.08 144	98.71 358	98.46 366

MVS-HIRNet		94.32 374	95.62 340	90.42 432	98.46 353	75.36 456	96.29 353	89.13 447	95.25 357	95.38 413	99.75 16	92.88 323	99.19 417	94.07 358	99.39 278	96.72 433

PHI-MVS		98.29 194	97.95 223	99.34 79	98.44 356	99.16 48	98.12 176	99.38 158	96.01 334	98.06 294	98.43 305	97.80 131	99.67 302	95.69 313	99.58 233	99.20 263

DVP-MVS++		98.90 95	98.70 117	99.51 48	98.43 357	99.15 52	99.43 15	99.32 186	98.17 186	99.26 138	99.02 184	98.18 97	99.88 110	97.07 212	99.45 269	99.49 156

MSC_two_6792asdad				99.32 87	98.43 357	98.37 117		98.86 300					99.89 93	97.14 206	99.60 224	99.71 59

No_MVS				99.32 87	98.43 357	98.37 117		98.86 300					99.89 93	97.14 206	99.60 224	99.71 59

Fast-Effi-MVS+-dtu		98.27 195	98.09 206	98.81 173	98.43 357	98.11 139	97.61 260	99.50 104	98.64 140	97.39 346	97.52 370	98.12 105	99.95 26	96.90 229	98.71 358	98.38 379

OpenMVS_ROB	95.38 14	95.84 347	95.18 360	97.81 292	98.41 361	97.15 228	97.37 285	98.62 331	83.86 443	98.65 235	98.37 311	94.29 298	99.68 299	88.41 427	98.62 368	96.60 434

DeepPCF-MVS	96.93 5	98.32 188	98.01 216	99.23 104	98.39 362	98.97 73	95.03 407	99.18 239	96.88 296	99.33 121	98.78 247	98.16 101	99.28 411	96.74 243	99.62 217	99.44 185

Patchmatch-test		96.55 322	96.34 324	97.17 345	98.35 363	93.06 372	98.40 145	97.79 361	97.33 260	98.41 266	98.67 268	83.68 404	99.69 290	95.16 326	99.31 290	98.77 340

AdaColmap		97.14 296	96.71 307	98.46 238	98.34 364	97.80 183	96.95 313	98.93 283	95.58 347	96.92 363	97.66 361	95.87 253	99.53 361	90.97 415	99.14 319	98.04 395

OpenMVS	96.65 7	97.09 298	96.68 309	98.32 255	98.32 365	97.16 227	98.86 91	99.37 162	89.48 431	96.29 393	99.15 154	96.56 217	99.90 78	92.90 383	99.20 310	97.89 403

MG-MVS		96.77 315	96.61 314	97.26 341	98.31 366	93.06 372	95.93 375	98.12 355	96.45 317	97.92 303	98.73 254	93.77 310	99.39 394	91.19 413	99.04 330	99.33 232

test_yl		96.69 316	96.29 326	97.90 285	98.28 367	95.24 305	97.29 292	97.36 374	98.21 179	98.17 281	97.86 350	86.27 380	99.55 354	94.87 332	98.32 375	98.89 319

DCV-MVSNet		96.69 316	96.29 326	97.90 285	98.28 367	95.24 305	97.29 292	97.36 374	98.21 179	98.17 281	97.86 350	86.27 380	99.55 354	94.87 332	98.32 375	98.89 319

CHOSEN 280x420		95.51 357	95.47 346	95.65 397	98.25 369	88.27 428	93.25 438	98.88 293	93.53 393	94.65 422	97.15 385	86.17 382	99.93 52	97.41 191	99.93 53	98.73 345

SCA		96.41 329	96.66 312	95.67 395	98.24 370	88.35 427	95.85 381	96.88 392	96.11 328	97.67 322	98.67 268	93.10 318	99.85 150	94.16 352	99.22 306	98.81 332

DeepMVS_CX				93.44 425	98.24 370	94.21 337		94.34 425	64.28 451	91.34 445	94.87 432	89.45 363	92.77 452	77.54 448	93.14 445	93.35 447

MS-PatchMatch		97.68 252	97.75 238	97.45 332	98.23 372	93.78 359	97.29 292	98.84 304	96.10 329	98.64 236	98.65 273	96.04 239	99.36 397	96.84 235	99.14 319	99.20 263

BH-w/o		95.13 363	94.89 367	95.86 390	98.20 373	91.31 403	95.65 387	97.37 373	93.64 391	96.52 386	95.70 413	93.04 321	99.02 423	88.10 429	95.82 435	97.24 426

mvs_anonymous		97.83 245	98.16 200	96.87 360	98.18 374	91.89 393	97.31 290	98.90 289	97.37 257	98.83 210	99.46 79	96.28 230	99.79 233	98.90 91	98.16 385	98.95 308

miper_lstm_enhance		97.18 293	97.16 278	97.25 342	98.16 375	92.85 377	95.15 405	99.31 191	97.25 269	98.74 226	98.78 247	90.07 355	99.78 244	97.19 201	99.80 131	99.11 283

RRT-MVS		97.88 234	97.98 219	97.61 315	98.15 376	93.77 360	98.97 76	99.64 62	99.16 89	98.69 229	99.42 87	91.60 340	99.89 93	97.63 177	98.52 372	99.16 278

ET-MVSNet_ETH3D		94.30 376	93.21 387	97.58 318	98.14 377	94.47 330	94.78 413	93.24 435	94.72 369	89.56 447	95.87 410	78.57 426	99.81 212	96.91 224	97.11 420	98.46 366

ADS-MVSNet2		95.43 358	94.98 363	96.76 367	98.14 377	91.74 394	97.92 211	97.76 362	90.23 425	96.51 387	98.91 216	85.61 387	99.85 150	92.88 384	96.90 421	98.69 350

ADS-MVSNet		95.24 361	94.93 366	96.18 384	98.14 377	90.10 420	97.92 211	97.32 377	90.23 425	96.51 387	98.91 216	85.61 387	99.74 268	92.88 384	96.90 421	98.69 350

c3_l		97.36 277	97.37 266	97.31 337	98.09 380	93.25 370	95.01 408	99.16 246	97.05 286	98.77 221	98.72 256	92.88 323	99.64 321	96.93 223	99.76 160	99.05 288

FMVSNet3		97.50 263	97.24 274	98.29 259	98.08 381	95.83 283	97.86 220	98.91 288	97.89 208	98.95 184	98.95 211	87.06 375	99.81 212	97.77 169	99.69 190	99.23 255

PAPM		91.88 413	90.34 416	96.51 371	98.06 382	92.56 382	92.44 442	97.17 381	86.35 439	90.38 446	96.01 405	86.61 378	99.21 416	70.65 452	95.43 437	97.75 412

Effi-MVS+-dtu		98.26 197	97.90 230	99.35 76	98.02 383	99.49 6	98.02 193	99.16 246	98.29 173	97.64 323	97.99 342	96.44 223	99.95 26	96.66 251	98.93 346	98.60 358

eth_miper_zixun_eth		97.23 289	97.25 273	97.17 345	98.00 384	92.77 379	94.71 414	99.18 239	97.27 267	98.56 250	98.74 253	91.89 338	99.69 290	97.06 214	99.81 120	99.05 288

HY-MVS	95.94 13	95.90 344	95.35 354	97.55 323	97.95 385	94.79 318	98.81 96	96.94 390	92.28 410	95.17 415	98.57 287	89.90 357	99.75 263	91.20 412	97.33 416	98.10 392

UGNet		98.53 160	98.45 156	98.79 178	97.94 386	96.96 236	99.08 61	98.54 334	99.10 99	96.82 373	99.47 77	96.55 218	99.84 168	98.56 119	99.94 48	99.55 129
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		96.47 327	95.70 337	98.79 178	97.92 387	99.12 62	98.28 154	98.60 332	92.16 411	95.54 410	96.17 403	94.77 287	99.52 365	89.62 424	98.23 379	97.72 414
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		96.86 311	96.55 318	97.79 293	97.91 388	94.21 337	97.56 266	98.87 295	97.49 243	99.06 162	99.05 179	80.72 414	99.80 220	98.44 123	99.82 116	99.37 214

API-MVS		97.04 302	96.91 294	97.42 334	97.88 389	98.23 130	98.18 165	98.50 337	97.57 233	97.39 346	96.75 391	96.77 204	99.15 420	90.16 422	99.02 334	94.88 445

myMVS_eth3d28		92.92 400	92.31 396	94.77 409	97.84 390	87.59 432	96.19 359	96.11 405	97.08 285	94.27 425	93.49 441	66.07 448	98.78 433	91.78 400	97.93 398	97.92 402

miper_ehance_all_eth		97.06 300	97.03 285	97.16 347	97.83 391	93.06 372	94.66 417	99.09 258	95.99 335	98.69 229	98.45 303	92.73 328	99.61 334	96.79 237	99.03 331	98.82 327

cl____		97.02 303	96.83 299	97.58 318	97.82 392	94.04 344	94.66 417	99.16 246	97.04 287	98.63 237	98.71 257	88.68 368	99.69 290	97.00 216	99.81 120	99.00 300

DIV-MVS_self_test		97.02 303	96.84 298	97.58 318	97.82 392	94.03 345	94.66 417	99.16 246	97.04 287	98.63 237	98.71 257	88.69 366	99.69 290	97.00 216	99.81 120	99.01 296

CANet		97.87 236	97.76 237	98.19 268	97.75 394	95.51 293	96.76 325	99.05 264	97.74 218	96.93 362	98.21 325	95.59 261	99.89 93	97.86 164	99.93 53	99.19 268

UBG		93.25 394	92.32 395	96.04 389	97.72 395	90.16 419	95.92 377	95.91 410	96.03 333	93.95 433	93.04 444	69.60 438	99.52 365	90.72 420	97.98 396	98.45 369

mvsany_test1		97.60 257	97.54 255	97.77 295	97.72 395	95.35 301	95.36 399	97.13 383	94.13 384	99.71 47	99.33 106	97.93 119	99.30 407	97.60 180	98.94 345	98.67 354

PVSNet_0	89.98 21	91.15 414	90.30 417	93.70 422	97.72 395	84.34 446	90.24 445	97.42 372	90.20 428	93.79 434	93.09 443	90.90 350	98.89 431	86.57 435	72.76 452	97.87 405

CR-MVSNet		96.28 332	95.95 331	97.28 339	97.71 398	94.22 335	98.11 177	98.92 286	92.31 409	96.91 365	99.37 95	85.44 390	99.81 212	97.39 192	97.36 414	97.81 408

RPMNet		97.02 303	96.93 290	97.30 338	97.71 398	94.22 335	98.11 177	99.30 199	99.37 58	96.91 365	99.34 104	86.72 377	99.87 129	97.53 184	97.36 414	97.81 408

ETVMVS		92.60 403	91.08 412	97.18 343	97.70 400	93.65 365	96.54 335	95.70 413	96.51 312	94.68 421	92.39 447	61.80 454	99.50 371	86.97 432	97.41 410	98.40 377

pmmvs3		95.03 365	94.40 372	96.93 356	97.70 400	92.53 383	95.08 406	97.71 364	88.57 435	97.71 319	98.08 336	79.39 421	99.82 196	96.19 288	99.11 325	98.43 374

baseline2		93.73 386	92.83 392	96.42 374	97.70 400	91.28 405	96.84 321	89.77 446	93.96 389	92.44 441	95.93 408	79.14 422	99.77 250	92.94 382	96.76 425	98.21 386

WBMVS		95.18 362	94.78 368	96.37 375	97.68 403	89.74 422	95.80 383	98.73 323	97.54 238	98.30 272	98.44 304	70.06 436	99.82 196	96.62 254	99.87 94	99.54 133

tpm		94.67 370	94.34 374	95.66 396	97.68 403	88.42 426	97.88 216	94.90 420	94.46 375	96.03 400	98.56 288	78.66 424	99.79 233	95.88 301	95.01 439	98.78 339

CANet_DTU		97.26 285	97.06 284	97.84 289	97.57 405	94.65 326	96.19 359	98.79 312	97.23 275	95.14 416	98.24 322	93.22 315	99.84 168	97.34 194	99.84 105	99.04 292

testing11		93.08 397	92.02 402	96.26 380	97.56 406	90.83 414	96.32 351	95.70 413	96.47 316	92.66 440	93.73 437	64.36 452	99.59 339	93.77 367	97.57 403	98.37 381

tpm2		93.09 396	92.58 394	94.62 411	97.56 406	86.53 435	97.66 249	95.79 412	86.15 440	94.07 430	98.23 324	75.95 429	99.53 361	90.91 417	96.86 424	97.81 408

testing91		93.32 392	92.27 397	96.47 373	97.54 408	91.25 406	96.17 363	96.76 394	97.18 279	93.65 436	93.50 440	65.11 451	99.63 324	93.04 381	97.45 407	98.53 363

TR-MVS		95.55 355	95.12 361	96.86 363	97.54 408	93.94 351	96.49 340	96.53 399	94.36 380	97.03 360	96.61 394	94.26 299	99.16 419	86.91 434	96.31 429	97.47 422

testing99		93.04 398	91.98 405	96.23 382	97.53 410	90.70 416	96.35 349	95.94 409	96.87 297	93.41 437	93.43 442	63.84 453	99.59 339	93.24 379	97.19 417	98.40 377

1314		95.74 349	95.60 341	96.17 385	97.53 410	92.75 380	98.07 184	98.31 346	91.22 420	94.25 426	96.68 392	95.53 262	99.03 422	91.64 404	97.18 418	96.74 432

CostFormer		93.97 382	93.78 380	94.51 412	97.53 410	85.83 438	97.98 203	95.96 408	89.29 433	94.99 418	98.63 278	78.63 425	99.62 327	94.54 340	96.50 426	98.09 393

FMVSNet5		96.01 340	95.20 359	98.41 244	97.53 410	96.10 269	98.74 97	99.50 104	97.22 278	98.03 298	99.04 181	69.80 437	99.88 110	97.27 197	99.71 180	99.25 250

PMMVS		96.51 323	95.98 330	98.09 273	97.53 410	95.84 282	94.92 410	98.84 304	91.58 415	96.05 399	95.58 414	95.68 258	99.66 313	95.59 317	98.09 389	98.76 342

reproduce_monomvs		95.00 367	95.25 356	94.22 415	97.51 415	83.34 447	97.86 220	98.44 339	98.51 157	99.29 131	99.30 112	67.68 442	99.56 350	98.89 93	99.81 120	99.77 47

PAPR		95.29 359	94.47 370	97.75 299	97.50 416	95.14 310	94.89 411	98.71 325	91.39 419	95.35 414	95.48 419	94.57 290	99.14 421	84.95 437	97.37 412	98.97 305

testing222		91.96 411	90.37 415	96.72 368	97.47 417	92.59 381	96.11 365	94.76 421	96.83 299	92.90 439	92.87 445	57.92 455	99.55 354	86.93 433	97.52 404	98.00 399

PatchT		96.65 319	96.35 323	97.54 324	97.40 418	95.32 303	97.98 203	96.64 396	99.33 63	96.89 369	99.42 87	84.32 398	99.81 212	97.69 176	97.49 405	97.48 421

tpm cat1		93.29 393	93.13 390	93.75 421	97.39 419	84.74 441	97.39 282	97.65 368	83.39 445	94.16 427	98.41 306	82.86 409	99.39 394	91.56 406	95.35 438	97.14 427

PatchmatchNet		95.58 354	95.67 339	95.30 405	97.34 420	87.32 433	97.65 251	96.65 395	95.30 356	97.07 356	98.69 264	84.77 393	99.75 263	94.97 330	98.64 365	98.83 326
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 278	96.97 288	98.50 235	97.31 421	96.47 260	98.18 165	98.92 286	98.95 121	98.78 218	99.37 95	85.44 390	99.85 150	95.96 299	99.83 112	99.17 275

LS3D		98.63 143	98.38 168	99.36 70	97.25 422	99.38 13	99.12 60	99.32 186	99.21 78	98.44 263	98.88 226	97.31 169	99.80 220	96.58 257	99.34 286	98.92 314

IB-MVS	91.63 19	92.24 409	90.90 413	96.27 379	97.22 423	91.24 407	94.36 426	93.33 434	92.37 408	92.24 443	94.58 434	66.20 447	99.89 93	93.16 380	94.63 441	97.66 416
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		92.38 406	91.76 409	94.21 416	97.16 424	84.65 442	95.42 397	88.45 448	95.96 336	96.17 394	95.84 412	66.36 445	99.71 282	91.87 399	98.64 365	98.28 384

tpmrst		95.07 364	95.46 347	93.91 419	97.11 425	84.36 445	97.62 256	96.96 388	94.98 363	96.35 392	98.80 243	85.46 389	99.59 339	95.60 316	96.23 430	97.79 411

Syy-MVS		96.04 339	95.56 345	97.49 329	97.10 426	94.48 329	96.18 361	96.58 397	95.65 344	94.77 419	92.29 448	91.27 346	99.36 397	98.17 139	98.05 393	98.63 356

myMVS_eth3d		91.92 412	90.45 414	96.30 377	97.10 426	90.90 412	96.18 361	96.58 397	95.65 344	94.77 419	92.29 448	53.88 456	99.36 397	89.59 425	98.05 393	98.63 356

MDTV_nov1_ep13			95.22 358		97.06 428	83.20 448	97.74 239	96.16 403	94.37 379	96.99 361	98.83 237	83.95 402	99.53 361	93.90 361	97.95 397

MVS		93.19 395	92.09 400	96.50 372	96.91 429	94.03 345	98.07 184	98.06 357	68.01 450	94.56 424	96.48 397	95.96 249	99.30 407	83.84 439	96.89 423	96.17 437

E-PMN		94.17 378	94.37 373	93.58 423	96.86 430	85.71 439	90.11 447	97.07 384	98.17 186	97.82 314	97.19 383	84.62 395	98.94 427	89.77 423	97.68 402	96.09 441

JIA-IIPM		95.52 356	95.03 362	97.00 352	96.85 431	94.03 345	96.93 316	95.82 411	99.20 80	94.63 423	99.71 22	83.09 407	99.60 335	94.42 346	94.64 440	97.36 425

EMVS		93.83 384	94.02 376	93.23 428	96.83 432	84.96 440	89.77 448	96.32 401	97.92 205	97.43 343	96.36 402	86.17 382	98.93 428	87.68 430	97.73 401	95.81 442

cl22		95.79 348	95.39 352	96.98 354	96.77 433	92.79 378	94.40 425	98.53 335	94.59 372	97.89 306	98.17 328	82.82 410	99.24 413	96.37 277	99.03 331	98.92 314

WB-MVSnew		95.73 350	95.57 344	96.23 382	96.70 434	90.70 416	96.07 367	93.86 431	95.60 346	97.04 358	95.45 423	96.00 242	99.55 354	91.04 414	98.31 377	98.43 374

dp		93.47 390	93.59 383	93.13 429	96.64 435	81.62 454	97.66 249	96.42 400	92.80 404	96.11 396	98.64 276	78.55 427	99.59 339	93.31 377	92.18 448	98.16 389

MonoMVSNet		96.25 334	96.53 320	95.39 403	96.57 436	91.01 410	98.82 95	97.68 367	98.57 152	98.03 298	99.37 95	90.92 349	97.78 444	94.99 328	93.88 444	97.38 424

test-LLR		93.90 383	93.85 378	94.04 417	96.53 437	84.62 443	94.05 431	92.39 437	96.17 325	94.12 428	95.07 424	82.30 411	99.67 302	95.87 304	98.18 382	97.82 406

test-mter		92.33 408	91.76 409	94.04 417	96.53 437	84.62 443	94.05 431	92.39 437	94.00 388	94.12 428	95.07 424	65.63 450	99.67 302	95.87 304	98.18 382	97.82 406

TESTMET0.1,1		92.19 410	91.77 408	93.46 424	96.48 439	82.80 450	94.05 431	91.52 442	94.45 377	94.00 431	94.88 430	66.65 444	99.56 350	95.78 309	98.11 388	98.02 396

MVS_0304		97.44 271	97.01 287	98.72 194	96.42 440	96.74 249	97.20 301	91.97 440	98.46 160	98.30 272	98.79 245	92.74 327	99.91 71	99.30 60	99.94 48	99.52 145

miper_enhance_ethall		96.01 340	95.74 335	96.81 364	96.41 441	92.27 390	93.69 436	98.89 292	91.14 422	98.30 272	97.35 381	90.58 352	99.58 345	96.31 281	99.03 331	98.60 358

tpmvs		95.02 366	95.25 356	94.33 413	96.39 442	85.87 436	98.08 181	96.83 393	95.46 351	95.51 412	98.69 264	85.91 385	99.53 361	94.16 352	96.23 430	97.58 419

CMPMVS	75.91 23	96.29 331	95.44 349	98.84 169	96.25 443	98.69 94	97.02 309	99.12 253	88.90 434	97.83 312	98.86 229	89.51 361	98.90 430	91.92 397	99.51 255	98.92 314
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 371	93.69 381	96.99 353	96.05 444	93.61 367	94.97 409	93.49 432	96.17 325	97.57 330	94.88 430	82.30 411	99.01 425	93.60 370	94.17 443	98.37 381

EPMVS		93.72 387	93.27 386	95.09 408	96.04 445	87.76 430	98.13 172	85.01 453	94.69 370	96.92 363	98.64 276	78.47 428	99.31 405	95.04 327	96.46 427	98.20 387

cascas		94.79 369	94.33 375	96.15 388	96.02 446	92.36 388	92.34 443	99.26 219	85.34 442	95.08 417	94.96 429	92.96 322	98.53 437	94.41 349	98.59 369	97.56 420

MVStest1		95.86 345	95.60 341	96.63 369	95.87 447	91.70 395	97.93 208	98.94 280	98.03 195	99.56 69	99.66 32	71.83 434	98.26 440	99.35 56	99.24 302	99.91 13

gg-mvs-nofinetune		92.37 407	91.20 411	95.85 391	95.80 448	92.38 387	99.31 30	81.84 455	99.75 11	91.83 444	99.74 18	68.29 439	99.02 423	87.15 431	97.12 419	96.16 438

gm-plane-assit					94.83 449	81.97 452			88.07 437		94.99 427		99.60 335	91.76 401

GG-mvs-BLEND				94.76 410	94.54 450	92.13 392	99.31 30	80.47 456		88.73 450	91.01 450	67.59 443	98.16 443	82.30 444	94.53 442	93.98 446

UWE-MVS-28		90.22 415	89.28 418	93.02 430	94.50 451	82.87 449	96.52 338	87.51 449	95.21 359	92.36 442	96.04 404	71.57 435	98.25 441	72.04 451	97.77 400	97.94 401

EPNet_dtu		94.93 368	94.78 368	95.38 404	93.58 452	87.68 431	96.78 323	95.69 415	97.35 259	89.14 449	98.09 335	88.15 373	99.49 374	94.95 331	99.30 293	98.98 302
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 419	75.95 422	77.12 435	92.39 453	67.91 459	90.16 446	59.44 460	82.04 446	89.42 448	94.67 433	49.68 458	81.74 453	48.06 453	77.66 451	81.72 449

KD-MVS_2432*1600		92.87 401	91.99 403	95.51 400	91.37 454	89.27 423	94.07 429	98.14 353	95.42 352	97.25 351	96.44 399	67.86 440	99.24 413	91.28 410	96.08 433	98.02 396

miper_refine_blended		92.87 401	91.99 403	95.51 400	91.37 454	89.27 423	94.07 429	98.14 353	95.42 352	97.25 351	96.44 399	67.86 440	99.24 413	91.28 410	96.08 433	98.02 396

EPNet		96.14 337	95.44 349	98.25 262	90.76 456	95.50 294	97.92 211	94.65 422	98.97 117	92.98 438	98.85 232	89.12 364	99.87 129	95.99 297	99.68 195	99.39 205
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 420	68.95 423	70.34 436	87.68 457	65.00 460	91.11 444	59.90 459	69.02 449	74.46 454	88.89 451	48.58 459	68.03 455	28.61 454	72.33 453	77.99 450

test_method		79.78 417	79.50 420	80.62 433	80.21 458	45.76 461	70.82 449	98.41 343	31.08 453	80.89 453	97.71 358	84.85 392	97.37 446	91.51 407	80.03 450	98.75 343

tmp_tt		78.77 418	78.73 421	78.90 434	58.45 459	74.76 458	94.20 428	78.26 457	39.16 452	86.71 451	92.82 446	80.50 415	75.19 454	86.16 436	92.29 447	86.74 448

testmvs		17.12 422	20.53 425	6.87 438	12.05 460	4.20 463	93.62 437	6.73 461	4.62 456	10.41 456	24.33 453	8.28 461	3.56 457	9.69 456	15.07 454	12.86 453

test123		17.04 423	20.11 426	7.82 437	10.25 461	4.91 462	94.80 412	4.47 462	4.93 455	10.00 457	24.28 454	9.69 460	3.64 456	10.14 455	12.43 455	14.92 452

mmdepth		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 457	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

monomultidepth		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 457	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

test_blank		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 457	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

eth-test2					0.00 462

eth-test					0.00 462

uanet_test		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 457	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

DCPMVS		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 457	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

cdsmvs_eth3d_5k		24.66 421	32.88 424	0.00 439	0.00 462	0.00 464	0.00 450	99.10 256	0.00 457	0.00 458	97.58 366	99.21 17	0.00 458	0.00 457	0.00 456	0.00 454

pcd_1.5k_mvsjas		8.17 424	10.90 427	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 457	98.07 107	0.00 458	0.00 457	0.00 456	0.00 454

sosnet-low-res		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 457	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

sosnet		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 457	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

uncertanet		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 457	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

Regformer		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 457	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

ab-mvs-re		8.12 425	10.83 428	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	97.48 372	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

uanet		0.00 426	0.00 429	0.00 439	0.00 462	0.00 464	0.00 450	0.00 463	0.00 457	0.00 458	0.00 457	0.00 462	0.00 458	0.00 457	0.00 456	0.00 454

WAC-MVS						90.90 412								91.37 409

PC_three_1452									93.27 396	99.40 107	98.54 289	98.22 93	97.00 447	95.17 325	99.45 269	99.49 156

test_241102_TWO								99.30 199	98.03 195	99.26 138	99.02 184	97.51 157	99.88 110	96.91 224	99.60 224	99.66 74

test_0728_THIRD									98.17 186	99.08 160	99.02 184	97.89 123	99.88 110	97.07 212	99.71 180	99.70 64

GSMVS																98.81 332

sam_mvs1												84.74 394				98.81 332

sam_mvs												84.29 400

MTGPA								99.20 231

test_post1							97.59 263				20.48 456	83.07 408	99.66 313	94.16 352

test_post											21.25 455	83.86 403	99.70 286

patchmatchnet-post											98.77 249	84.37 397	99.85 150

MTMP							97.93 208	91.91 441

test9_res														93.28 378	99.15 318	99.38 212

agg_prior2														92.50 394	99.16 316	99.37 214

test_prior4						97.97 159	95.86 379

test_prior2							95.74 385		96.48 315	96.11 396	97.63 364	95.92 252		94.16 352	99.20 310

旧先验2							95.76 384		88.56 436	97.52 334			99.66 313	94.48 342

新几何2							95.93 375

无先验							95.74 385	98.74 322	89.38 432				99.73 274	92.38 396		99.22 260

原ACMM2							95.53 391

testdata2													99.79 233	92.80 388

segment_acmp												97.02 188

testdata1							95.44 396		96.32 321

plane_prior5								99.27 214					99.70 286	94.42 346	99.51 255	99.45 181

plane_prior4											97.98 343

plane_prior3						97.78 184			97.41 253	97.79 315

plane_prior2							97.77 233		98.20 183

plane_prior						97.65 193	97.07 308		96.72 305						99.36 282

n2								0.00 463

nn								0.00 463

door-mid								99.57 79

test11								98.87 295

door								99.41 151

HQP5-MVS						96.79 245

BP-MVS														92.82 386

HQP4-MVS										95.56 406			99.54 359			99.32 234

HQP3-MVS								99.04 267							99.26 300

HQP2-MVS												93.84 306

MDTV_nov1_ep13_2view						74.92 457	97.69 244		90.06 430	97.75 318		85.78 386		93.52 372		98.69 350

ACMMP++_ref															99.77 148

ACMMP++															99.68 195

Test By Simon												96.52 219

High-resolution multi-view benchmark