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	98.64 205	99.94 2	98.51 108	99.32 26	99.75 42	99.58 37	98.60 254	99.62 40	98.22 101	99.51 381	97.70 181	99.73 172	97.89 414
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 79	99.44 51	99.78 39	99.76 15	96.39 235	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 63	99.48 43	99.92 8	99.71 22	98.07 115	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 51	98.90 129	99.43 100	99.35 101	98.86 34	99.67 310	97.81 170	99.81 124	99.24 262

APD_test2		99.25 41	99.16 60	99.51 48	99.89 6	99.63 4	98.71 104	99.69 51	98.90 129	99.43 100	99.35 101	98.86 34	99.67 310	97.81 170	99.81 124	99.24 262

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 51	98.93 125	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 72	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 60	99.09 104	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 93	99.11 94	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 77	99.59 35	99.71 48	99.57 49	97.12 192	99.90 79	99.21 69	99.87 95	99.54 135

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 79	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		98.75 124	98.62 136	99.16 114	99.83 18	97.96 162	99.28 40	98.20 361	99.37 59	99.70 50	99.65 36	92.65 340	99.93 52	99.04 83	99.84 108	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 67	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	98.86 103	99.36 70	99.82 19	98.55 103	97.47 283	99.57 86	99.37 59	99.21 152	99.61 43	96.76 217	99.83 190	98.06 149	99.83 115	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 67	99.30 69	99.65 62	99.60 45	99.16 22	99.82 200	99.07 79	99.83 115	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 86	99.39 57	99.75 44	99.62 40	99.17 20	99.83 190	99.06 81	99.62 226	99.66 75

K. test v3		98.00 234	97.66 259	99.03 141	99.79 23	97.56 198	99.19 52	92.47 447	99.62 32	99.52 82	99.66 32	89.61 371	99.96 14	99.25 66	99.81 124	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		98.83 108	98.66 129	99.34 79	99.78 24	99.47 9	98.42 144	99.45 138	98.28 181	98.98 185	99.19 143	97.76 142	99.58 356	96.57 270	99.55 253	98.97 316

test_vis3_rt		99.14 60	99.17 58	99.07 131	99.78 24	98.38 115	98.92 82	99.94 2	97.80 223	99.91 12	99.67 30	97.15 191	98.91 440	99.76 22	99.56 249	99.92 12

EGC-MVSNET		85.24 427	80.54 430	99.34 79	99.77 27	99.20 39	99.08 61	99.29 218	12.08 465	20.84 466	99.42 87	97.55 161	99.85 154	97.08 222	99.72 180	98.96 318

Anonymous20240521		98.69 135	98.87 99	98.16 279	99.77 27	95.11 320	99.08 61	99.44 146	99.34 63	99.33 123	99.55 57	94.10 315	99.94 41	99.25 66	99.96 28	99.42 196

FC-MVSNet-test		99.27 38	99.25 51	99.34 79	99.77 27	98.37 117	99.30 35	99.57 86	99.61 34	99.40 109	99.50 67	97.12 192	99.85 154	99.02 85	99.94 49	99.80 40

test_vis1_n		98.31 199	98.50 155	97.73 313	99.76 30	94.17 348	98.68 107	99.91 9	96.31 332	99.79 38	99.57 49	92.85 336	99.42 401	99.79 18	99.84 108	99.60 97

test_fmvs3		99.12 67	99.41 26	98.25 268	99.76 30	95.07 321	99.05 67	99.94 2	97.78 226	99.82 33	99.84 3	98.56 68	99.71 287	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 69	98.48 164	99.37 114	99.49 73	98.75 46	99.86 141	98.20 139	99.80 135	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 80	99.61 43	98.64 56	99.80 224	98.24 134	99.84 108	99.52 147

fmvsm_s_conf0.1_n_a		99.17 52	99.30 44	98.80 177	99.75 34	96.59 257	97.97 211	99.86 16	98.22 184	99.88 21	99.71 22	98.59 62	99.84 172	99.73 26	99.98 12	99.98 3

tt0805		98.69 135	98.62 136	98.90 166	99.75 34	99.30 22	99.15 56	96.97 398	98.86 134	98.87 217	97.62 376	98.63 58	98.96 437	99.41 55	98.29 389	98.45 380

test_vis1_n_1920		98.40 183	98.92 92	96.81 375	99.74 36	90.76 426	98.15 170	99.91 9	98.33 172	99.89 18	99.55 57	95.07 286	99.88 113	99.76 22	99.93 54	99.79 42

FOURS1					99.73 37	99.67 3	99.43 15	99.54 102	99.43 53	99.26 140

PEN-MVS		99.41 25	99.34 36	99.62 9	99.73 37	99.14 57	99.29 36	99.54 102	99.62 32	99.56 71	99.42 87	98.16 109	99.96 14	98.78 100	99.93 54	99.77 48

lessismore_v0				98.97 153	99.73 37	97.53 200		86.71 462		99.37 114	99.52 66	89.93 367	99.92 63	98.99 87	99.72 180	99.44 189

SteuartSystems-ACMMP		98.79 117	98.54 149	99.54 31	99.73 37	99.16 48	98.23 160	99.31 202	97.92 214	98.90 206	98.90 226	98.00 121	99.88 113	96.15 302	99.72 180	99.58 112
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 220	98.15 212	98.22 273	99.73 37	95.15 317	97.36 294	99.68 56	94.45 388	98.99 184	99.27 120	96.87 206	99.94 41	97.13 219	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 94	99.27 136	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		98.71 128	98.74 113	98.62 211	99.72 43	96.08 280	98.74 97	98.64 341	99.74 13	99.67 58	99.24 133	94.57 301	99.95 26	99.11 76	99.24 313	99.82 35

test_f		98.67 143	98.87 99	98.05 288	99.72 43	95.59 294	98.51 128	99.81 31	96.30 334	99.78 39	99.82 5	96.14 245	98.63 447	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 97	98.30 176	99.65 62	99.45 83	99.22 17	99.76 260	98.44 125	99.77 152	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	98.64 205	99.71 47	96.10 275	97.87 223	99.85 18	98.56 160	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	99.53 105	99.53 40	99.46 95	99.41 91	98.23 98	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	99.51 110	99.64 27	99.56 71	99.46 79	98.23 98	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 97	99.46 48	99.50 88	99.34 105	97.30 181	99.93 52	98.90 92	99.93 54	99.77 48

HPM-MVS_fast		99.01 80	98.82 106	99.57 21	99.71 47	99.35 17	99.00 72	99.50 113	97.33 270	98.94 201	98.86 236	98.75 46	99.82 200	97.53 193	99.71 189	99.56 123

ACMH+	96.62 9	99.08 74	99.00 84	99.33 85	99.71 47	98.83 83	98.60 114	99.58 79	99.11 94	99.53 80	99.18 147	98.81 38	99.67 310	96.71 259	99.77 152	99.50 153

PMVS	91.26 20	97.86 248	97.94 236	97.65 320	99.71 47	97.94 164	98.52 123	98.68 337	98.99 117	97.52 345	99.35 101	97.41 174	98.18 453	91.59 416	99.67 210	96.82 442
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
KinetiMVS		99.03 78	99.02 80	99.03 141	99.70 55	97.48 203	98.43 141	99.29 218	99.70 16	99.60 69	99.07 174	96.13 246	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	99.52 109	99.48 43	99.24 146	99.41 91	96.79 214	99.82 200	98.69 110	99.88 91	99.76 53

VPNet		98.87 100	98.83 105	99.01 145	99.70 55	97.62 196	98.43 141	99.35 183	99.47 46	99.28 134	99.05 182	96.72 220	99.82 200	98.09 146	99.36 293	99.59 104

fmvsm_s_conf0.1_n_2		99.20 50	99.38 29	98.65 203	99.69 58	96.08 280	97.49 280	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		98.33 196	98.68 126	97.27 351	99.69 58	92.29 400	98.03 192	99.85 18	97.62 235	99.96 4	99.62 40	93.98 316	99.74 273	99.52 48	99.86 102	99.79 42

MP-MVS-pluss		98.57 158	98.23 200	99.60 15	99.69 58	99.35 17	97.16 313	99.38 169	94.87 378	98.97 189	98.99 203	98.01 120	99.88 113	97.29 207	99.70 196	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	99.48 122	99.69 18	99.63 65	99.68 25	99.03 24	99.96 14	97.97 159	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	99.30 210	99.69 18	99.63 65	99.68 25	99.25 16	99.96 14	97.25 210	99.92 67	99.57 117

test_fmvs1_n		98.09 225	98.28 191	97.52 337	99.68 61	93.47 379	98.63 110	99.93 5	95.41 366	99.68 56	99.64 37	91.88 350	99.48 388	99.82 11	99.87 95	99.62 87

CHOSEN 1792x2688		97.49 277	97.14 292	98.54 233	99.68 61	96.09 278	96.50 349	99.62 69	91.58 426	98.84 220	98.97 210	92.36 342	99.88 113	96.76 252	99.95 38	99.67 73

tfpnnormal		98.90 96	98.90 94	98.91 163	99.67 65	97.82 179	99.00 72	99.44 146	99.45 49	99.51 87	99.24 133	98.20 104	99.86 141	95.92 311	99.69 199	99.04 303

MTAPA		98.88 99	98.64 132	99.61 13	99.67 65	99.36 16	98.43 141	99.20 242	98.83 138	98.89 209	98.90 226	96.98 202	99.92 63	97.16 214	99.70 196	99.56 123

test_fmvsmvis_n_1920		99.26 40	99.49 16	98.54 233	99.66 67	96.97 237	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	98.71 357

mvs5depth		99.30 34	99.59 12	98.44 247	99.65 68	95.35 309	99.82 3	99.94 2	99.83 7	99.42 104	99.94 2	98.13 112	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	97.05 233	97.80 232	99.76 39	98.70 143	99.78 39	99.11 166	98.79 42	99.95 26	99.85 5	99.96 28	99.83 32

WB-MVS		98.52 171	98.55 147	98.43 248	99.65 68	95.59 294	98.52 123	98.77 326	99.65 26	99.52 82	99.00 201	94.34 307	99.93 52	98.65 112	98.83 361	99.76 53

CP-MVSNet		99.21 48	99.09 73	99.56 26	99.65 68	98.96 77	99.13 58	99.34 189	99.42 54	99.33 123	99.26 126	97.01 200	99.94 41	98.74 105	99.93 54	99.79 42

HPM-MVS		98.79 117	98.53 151	99.59 19	99.65 68	99.29 24	99.16 54	99.43 152	96.74 314	98.61 252	98.38 321	98.62 59	99.87 132	96.47 282	99.67 210	99.59 104
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 152	98.36 180	99.42 64	99.65 68	99.42 11	98.55 119	99.57 86	97.72 229	98.90 206	99.26 126	96.12 248	99.52 376	95.72 322	99.71 189	99.32 240

NormalMVS		98.26 206	97.97 233	99.15 117	99.64 74	97.83 174	98.28 154	99.43 152	99.24 74	98.80 227	98.85 239	89.76 369	99.94 41	98.04 151	99.67 210	99.68 68

lecture		99.25 41	99.12 68	99.62 9	99.64 74	99.40 12	98.89 87	99.51 110	99.19 85	99.37 114	99.25 131	98.36 82	99.88 113	98.23 136	99.67 210	99.59 104

fmvsm_l_conf0.5_n		99.21 48	99.28 46	99.02 144	99.64 74	97.28 216	97.82 228	99.76 39	98.73 140	99.82 33	99.09 173	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	97.68 250	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.		98.63 149	98.49 159	99.06 137	99.64 74	97.90 168	98.51 128	98.94 291	96.96 301	99.24 146	98.89 232	97.83 134	99.81 216	96.88 242	99.49 273	99.48 170
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 111	98.72 117	99.12 120	99.64 74	98.54 106	97.98 207	99.68 56	97.62 235	99.34 121	99.18 147	97.54 162	99.77 254	97.79 172	99.74 169	99.04 303

Elysia		99.15 57	99.14 66	99.18 109	99.63 80	97.92 165	98.50 130	99.43 152	99.67 21	99.70 50	99.13 162	96.66 223	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	99.43 152	99.67 21	99.70 50	99.13 162	96.66 223	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	99.54 102	99.31 67	99.62 68	99.53 63	97.36 178	99.86 141	99.24 68	99.71 189	99.39 209

EU-MVSNet		97.66 265	98.50 155	95.13 417	99.63 80	85.84 448	98.35 150	98.21 360	98.23 183	99.54 76	99.46 79	95.02 287	99.68 306	98.24 134	99.87 95	99.87 21

HyFIR lowres test		97.19 303	96.60 327	98.96 154	99.62 84	97.28 216	95.17 414	99.50 113	94.21 393	99.01 181	98.32 329	86.61 389	99.99 2	97.10 221	99.84 108	99.60 97

fmvsm_l_conf0.5_n_9		99.32 33	99.43 24	98.98 151	99.59 85	97.18 226	97.44 286	99.83 25	99.56 38	99.91 12	99.34 105	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	96.89 244	99.48 13	99.92 7	99.92 2	98.26 289	99.80 11	98.33 88	99.91 72	99.56 39	99.95 38	99.97 4

ACMMP_NAP		98.75 124	98.48 160	99.57 21	99.58 87	99.29 24	97.82 228	99.25 231	96.94 303	98.78 229	99.12 165	98.02 119	99.84 172	97.13 219	99.67 210	99.59 104

nrg030		99.40 26	99.35 34	99.54 31	99.58 87	99.13 60	98.98 75	99.48 122	99.68 20	99.46 95	99.26 126	98.62 59	99.73 279	99.17 73	99.92 67	99.76 53

VDDNet		98.21 213	97.95 234	99.01 145	99.58 87	97.74 187	99.01 70	97.29 389	99.67 21	98.97 189	99.50 67	90.45 364	99.80 224	97.88 165	99.20 321	99.48 170

COLMAP_ROB	96.50 10	98.99 83	98.85 104	99.41 66	99.58 87	99.10 65	98.74 97	99.56 93	99.09 104	99.33 123	99.19 143	98.40 79	99.72 286	95.98 309	99.76 165	99.42 196
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	99.30 114	99.42 11	99.96 14	99.85 5	99.99 5	99.29 249

ZNCC-MVS		98.68 140	98.40 172	99.54 31	99.57 92	99.21 33	98.46 138	99.29 218	97.28 276	98.11 301	98.39 319	98.00 121	99.87 132	96.86 245	99.64 220	99.55 130

MSP-MVS		98.40 183	98.00 228	99.61 13	99.57 92	99.25 29	98.57 117	99.35 183	97.55 246	99.31 131	97.71 369	94.61 300	99.88 113	96.14 303	99.19 324	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		98.32 197	98.39 175	98.13 280	99.57 92	95.54 297	97.78 234	99.49 120	97.37 267	99.19 154	97.65 373	98.96 29	99.49 385	96.50 281	98.99 349	99.34 232

MP-MVS		98.46 177	98.09 217	99.54 31	99.57 92	99.22 32	98.50 130	99.19 246	97.61 238	97.58 339	98.66 282	97.40 175	99.88 113	94.72 348	99.60 233	99.54 135
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 128	98.46 164	99.47 60	99.57 92	98.97 73	98.23 160	99.48 122	96.60 319	99.10 164	99.06 175	98.71 50	99.83 190	95.58 329	99.78 146	99.62 87

LGP-MVS_train				99.47 60	99.57 92	98.97 73		99.48 122	96.60 319	99.10 164	99.06 175	98.71 50	99.83 190	95.58 329	99.78 146	99.62 87

IS-MVSNet		98.19 216	97.90 241	99.08 129	99.57 92	97.97 159	99.31 30	98.32 356	99.01 116	98.98 185	99.03 186	91.59 352	99.79 237	95.49 331	99.80 135	99.48 170

viewmsd2359difaftdt		98.84 106	99.04 78	98.24 270	99.56 100	95.51 299	97.38 290	99.70 50	99.16 90	99.57 70	99.40 94	98.26 95	99.71 287	98.55 121	99.82 119	99.50 153

dcpmvs_2		98.78 119	99.11 69	97.78 303	99.56 100	93.67 374	99.06 65	99.86 16	99.50 42	99.66 59	99.26 126	97.21 189	99.99 2	98.00 156	99.91 76	99.68 68

test_0402		98.76 123	98.71 120	98.93 159	99.56 100	98.14 137	98.45 140	99.34 189	99.28 71	98.95 194	98.91 223	98.34 87	99.79 237	95.63 326	99.91 76	98.86 335

EPP-MVSNet		98.30 200	98.04 224	99.07 131	99.56 100	97.83 174	99.29 36	98.07 367	99.03 114	98.59 256	99.13 162	92.16 346	99.90 79	96.87 243	99.68 204	99.49 159

ACMMP		98.75 124	98.50 155	99.52 44	99.56 100	99.16 48	98.87 88	99.37 173	97.16 291	98.82 224	99.01 198	97.71 145	99.87 132	96.29 294	99.69 199	99.54 135
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	98.78 183	99.55 105	96.59 257	97.79 233	99.82 30	98.21 186	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	98.61 214	99.55 105	96.09 278	97.74 243	99.81 31	98.55 161	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	99.55 105	98.24 126	99.20 48	99.44 146	99.21 79	99.43 100	99.55 57	97.82 137	99.86 141	98.42 127	99.89 89	99.41 199

Vis-MVSNet (Re-imp)		97.46 279	97.16 289	98.34 260	99.55 105	96.10 275	98.94 80	98.44 350	98.32 174	98.16 295	98.62 291	88.76 376	99.73 279	93.88 374	99.79 141	99.18 282

ACMM	96.08 12	98.91 94	98.73 115	99.48 56	99.55 105	99.14 57	98.07 185	99.37 173	97.62 235	99.04 177	98.96 213	98.84 36	99.79 237	97.43 201	99.65 218	99.49 159
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 132	98.97 88	97.89 296	99.54 110	94.05 351	98.55 119	99.92 7	96.78 312	99.72 46	99.78 13	96.60 227	99.67 310	99.91 2	99.90 83	99.94 10

mPP-MVS		98.64 147	98.34 183	99.54 31	99.54 110	99.17 44	98.63 110	99.24 236	97.47 254	98.09 303	98.68 277	97.62 154	99.89 95	96.22 297	99.62 226	99.57 117

XVG-ACMP-BASELINE		98.56 159	98.34 183	99.22 105	99.54 110	98.59 100	97.71 246	99.46 134	97.25 279	98.98 185	98.99 203	97.54 162	99.84 172	95.88 312	99.74 169	99.23 264

viewmacassd2359aftdt		98.86 103	98.87 99	98.83 171	99.53 113	97.32 214	97.70 248	99.64 65	98.22 184	99.25 144	99.27 120	98.40 79	99.61 342	97.98 158	99.87 95	99.55 130

region2R		98.69 135	98.40 172	99.54 31	99.53 113	99.17 44	98.52 123	99.31 202	97.46 259	98.44 274	98.51 305	97.83 134	99.88 113	96.46 283	99.58 242	99.58 112

PGM-MVS		98.66 144	98.37 179	99.55 28	99.53 113	99.18 43	98.23 160	99.49 120	97.01 300	98.69 240	98.88 233	98.00 121	99.89 95	95.87 315	99.59 237	99.58 112

Patchmatch-RL test		97.26 296	97.02 297	97.99 292	99.52 116	95.53 298	96.13 374	99.71 46	97.47 254	99.27 136	99.16 153	84.30 410	99.62 335	97.89 162	99.77 152	98.81 343

ACMMPR		98.70 132	98.42 170	99.54 31	99.52 116	99.14 57	98.52 123	99.31 202	97.47 254	98.56 261	98.54 300	97.75 143	99.88 113	96.57 270	99.59 237	99.58 112

fmvsm_s_conf0.5_n_9		99.17 52	99.38 29	98.53 235	99.51 118	95.82 290	97.62 261	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		98.16 222	98.07 222	98.41 250	99.51 118	95.86 287	98.00 199	95.14 430	98.97 120	99.43 100	99.24 133	93.25 324	99.84 172	99.21 69	99.87 95	99.54 135

fmvsm_s_conf0.5_n_8		99.13 64	99.26 49	98.74 194	99.51 118	96.44 267	97.65 256	99.65 63	99.66 24	99.78 39	99.48 74	97.92 128	99.93 52	99.72 28	99.95 38	99.87 21

GST-MVS		98.61 153	98.30 189	99.52 44	99.51 118	99.20 39	98.26 158	99.25 231	97.44 262	98.67 243	98.39 319	97.68 146	99.85 154	96.00 307	99.51 264	99.52 147

Anonymous20231206		98.21 213	98.21 201	98.20 274	99.51 118	95.43 307	98.13 172	99.32 197	96.16 338	98.93 202	98.82 249	96.00 253	99.83 190	97.32 206	99.73 172	99.36 226

ACMP	95.32 15	98.41 181	98.09 217	99.36 70	99.51 118	98.79 86	97.68 250	99.38 169	95.76 353	98.81 226	98.82 249	98.36 82	99.82 200	94.75 345	99.77 152	99.48 170
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LuminaMVS		98.39 189	98.20 202	98.98 151	99.50 124	97.49 201	97.78 234	97.69 376	98.75 139	99.49 89	99.25 131	92.30 344	99.94 41	99.14 74	99.88 91	99.50 153

DVP-MVS		98.77 122	98.52 152	99.52 44	99.50 124	99.21 33	98.02 195	98.84 315	97.97 208	99.08 166	99.02 187	97.61 156	99.88 113	96.99 229	99.63 223	99.48 170
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	99.50 124	99.23 31	98.02 195	99.32 197					99.88 113	96.99 229	99.63 223	99.68 68

test0726					99.50 124	99.21 33	98.17 168	99.35 183	97.97 208	99.26 140	99.06 175	97.61 156

AllTest		98.44 179	98.20 202	99.16 114	99.50 124	98.55 103	98.25 159	99.58 79	96.80 310	98.88 213	99.06 175	97.65 149	99.57 358	94.45 355	99.61 231	99.37 219

TestCases				99.16 114	99.50 124	98.55 103		99.58 79	96.80 310	98.88 213	99.06 175	97.65 149	99.57 358	94.45 355	99.61 231	99.37 219

XVG-OURS		98.53 167	98.34 183	99.11 122	99.50 124	98.82 85	95.97 380	99.50 113	97.30 274	99.05 175	98.98 208	99.35 14	99.32 415	95.72 322	99.68 204	99.18 282

EG-PatchMatch MVS		98.99 83	99.01 82	98.94 157	99.50 124	97.47 204	98.04 190	99.59 77	98.15 201	99.40 109	99.36 100	98.58 67	99.76 260	98.78 100	99.68 204	99.59 104

fmvsm_s_conf0.5_n_2		99.14 60	99.31 41	98.63 209	99.49 132	96.08 280	97.38 290	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	98.72 117	99.49 54	99.49 132	99.17 44	98.10 179	99.31 202	98.03 204	99.66 59	99.02 187	98.36 82	99.88 113	96.91 235	99.62 226	99.41 199

IU-MVS					99.49 132	99.15 52		98.87 306	92.97 411	99.41 106				96.76 252	99.62 226	99.66 75

test_241102_ONE					99.49 132	99.17 44		99.31 202	97.98 207	99.66 59	98.90 226	98.36 82	99.48 388

UA-Net		99.47 16	99.40 27	99.70 2	99.49 132	99.29 24	99.80 4	99.72 44	99.82 8	99.04 177	99.81 8	98.05 118	99.96 14	98.85 96	99.99 5	99.86 27

HFP-MVS		98.71 128	98.44 167	99.51 48	99.49 132	99.16 48	98.52 123	99.31 202	97.47 254	98.58 258	98.50 309	97.97 125	99.85 154	96.57 270	99.59 237	99.53 144

VPA-MVSNet		99.30 34	99.30 44	99.28 92	99.49 132	98.36 120	99.00 72	99.45 138	99.63 29	99.52 82	99.44 84	98.25 96	99.88 113	99.09 78	99.84 108	99.62 87

XVG-OURS-SEG-HR		98.49 174	98.28 191	99.14 118	99.49 132	98.83 83	96.54 345	99.48 122	97.32 272	99.11 161	98.61 293	99.33 15	99.30 418	96.23 296	98.38 385	99.28 251

114514_t		96.50 336	95.77 345	98.69 199	99.48 140	97.43 208	97.84 227	99.55 97	81.42 458	96.51 398	98.58 297	95.53 273	99.67 310	93.41 387	99.58 242	98.98 313

IterMVS-LS		98.55 163	98.70 123	98.09 281	99.48 140	94.73 331	97.22 308	99.39 167	98.97 120	99.38 112	99.31 113	96.00 253	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	99.47 142	97.22 221	97.40 288	99.83 25	97.61 238	99.85 27	99.30 114	98.80 40	99.95 26	99.71 30	99.90 83	99.78 45

v8		99.01 80	99.16 60	98.57 221	99.47 142	96.31 272	98.90 83	99.47 130	99.03 114	99.52 82	99.57 49	96.93 203	99.81 216	99.60 35	99.98 12	99.60 97

SSC-MVS3.2		98.53 167	98.79 109	97.74 310	99.46 144	93.62 377	96.45 351	99.34 189	99.33 64	98.93 202	98.70 273	97.90 129	99.90 79	99.12 75	99.92 67	99.69 67

fmvsm_s_conf0.5_n_3		99.22 47	99.37 32	98.78 183	99.46 144	96.58 260	97.65 256	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		98.72 127	98.45 165	99.53 38	99.46 144	99.21 33	98.65 108	99.34 189	98.62 150	97.54 343	98.63 289	97.50 168	99.83 190	96.79 248	99.53 259	99.56 123

X-MVStestdata		94.32 385	92.59 404	99.53 38	99.46 144	99.21 33	98.65 108	99.34 189	98.62 150	97.54 343	45.85 463	97.50 168	99.83 190	96.79 248	99.53 259	99.56 123

test20.03		98.78 119	98.77 112	98.78 183	99.46 144	97.20 224	97.78 234	99.24 236	99.04 113	99.41 106	98.90 226	97.65 149	99.76 260	97.70 181	99.79 141	99.39 209

guyue		98.01 233	97.93 238	98.26 267	99.45 149	95.48 302	98.08 182	96.24 413	98.89 131	99.34 121	99.14 160	91.32 356	99.82 200	99.07 79	99.83 115	99.48 170

CSCG		98.68 140	98.50 155	99.20 106	99.45 149	98.63 95	98.56 118	99.57 86	97.87 218	98.85 218	98.04 350	97.66 148	99.84 172	96.72 257	99.81 124	99.13 292

GeoE		99.05 77	98.99 86	99.25 100	99.44 151	98.35 121	98.73 101	99.56 93	98.42 167	98.91 205	98.81 251	98.94 30	99.91 72	98.35 129	99.73 172	99.49 159

v148		98.45 178	98.60 141	98.00 291	99.44 151	94.98 323	97.44 286	99.06 272	98.30 176	99.32 129	98.97 210	96.65 225	99.62 335	98.37 128	99.85 103	99.39 209

v10		98.97 87	99.11 69	98.55 228	99.44 151	96.21 274	98.90 83	99.55 97	98.73 140	99.48 90	99.60 45	96.63 226	99.83 190	99.70 31	99.99 5	99.61 95

V42		98.78 119	98.78 111	98.76 188	99.44 151	97.04 234	98.27 157	99.19 246	97.87 218	99.25 144	99.16 153	96.84 207	99.78 248	99.21 69	99.84 108	99.46 180

MDA-MVSNet-bldmvs		97.94 239	97.91 240	98.06 286	99.44 151	94.96 324	96.63 341	99.15 262	98.35 170	98.83 221	99.11 166	94.31 308	99.85 154	96.60 267	98.72 367	99.37 219

casdiffmvs_mvg		99.12 67	99.16 60	98.99 147	99.43 156	97.73 189	98.00 199	99.62 69	99.22 77	99.55 74	99.22 139	98.93 32	99.75 268	98.66 111	99.81 124	99.50 153
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SSM_0404		98.90 96	99.01 82	98.57 221	99.42 157	96.59 257	98.13 172	99.66 60	99.09 104	99.30 132	99.02 187	98.79 42	99.89 95	97.87 167	99.80 135	99.23 264

test1111		96.49 337	96.82 311	95.52 410	99.42 157	87.08 445	99.22 45	87.14 461	99.11 94	99.46 95	99.58 47	88.69 377	99.86 141	98.80 98	99.95 38	99.62 87

v2v482		98.56 159	98.62 136	98.37 257	99.42 157	95.81 291	97.58 269	99.16 257	97.90 216	99.28 134	99.01 198	95.98 258	99.79 237	99.33 58	99.90 83	99.51 150

OPM-MVS		98.56 159	98.32 187	99.25 100	99.41 160	98.73 91	97.13 315	99.18 250	97.10 294	98.75 235	98.92 221	98.18 105	99.65 326	96.68 261	99.56 249	99.37 219
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 227	98.08 220	98.04 289	99.41 160	94.59 337	94.59 432	99.40 165	97.50 251	98.82 224	98.83 246	96.83 209	99.84 172	97.50 195	99.81 124	99.71 60

test_one_0601					99.39 162	99.20 39		99.31 202	98.49 163	98.66 245	99.02 187	97.64 152

mvsany_test3		98.87 100	98.92 92	98.74 194	99.38 163	96.94 241	98.58 116	99.10 267	96.49 324	99.96 4	99.81 8	98.18 105	99.45 396	98.97 88	99.79 141	99.83 32

patch_mono-2		98.51 172	98.63 134	98.17 277	99.38 163	94.78 328	97.36 294	99.69 51	98.16 196	98.49 270	99.29 117	97.06 195	99.97 7	98.29 133	99.91 76	99.76 53

test2506		92.39 416	91.89 418	93.89 431	99.38 163	82.28 462	99.32 26	66.03 469	99.08 108	98.77 232	99.57 49	66.26 457	99.84 172	98.71 108	99.95 38	99.54 135

ECVR-MVS		96.42 339	96.61 325	95.85 402	99.38 163	88.18 440	99.22 45	86.00 463	99.08 108	99.36 117	99.57 49	88.47 382	99.82 200	98.52 122	99.95 38	99.54 135

casdiffmvs		98.95 90	99.00 84	98.81 175	99.38 163	97.33 212	97.82 228	99.57 86	99.17 89	99.35 119	99.17 151	98.35 86	99.69 297	98.46 124	99.73 172	99.41 199
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 80	98.76 188	99.38 163	97.26 218	98.49 133	99.50 113	98.86 134	99.19 154	99.06 175	98.23 98	99.69 297	98.71 108	99.76 165	99.33 237

TranMVSNet+NR-MVSNet		99.17 52	99.07 76	99.46 62	99.37 169	98.87 81	98.39 146	99.42 158	99.42 54	99.36 117	99.06 175	98.38 81	99.95 26	98.34 130	99.90 83	99.57 117

fmvsm_s_conf0.5_n_6		99.08 74	99.21 55	98.69 199	99.36 170	96.51 262	97.62 261	99.68 56	98.43 166	99.85 27	99.10 169	99.12 23	99.88 113	99.77 21	99.92 67	99.67 73

tttt0517		95.64 364	94.98 374	97.64 323	99.36 170	93.81 369	98.72 102	90.47 455	98.08 203	98.67 243	98.34 326	73.88 443	99.92 63	97.77 174	99.51 264	99.20 274

test_part2					99.36 170	99.10 65				99.05 175

v1144		98.60 154	98.66 129	98.41 250	99.36 170	95.90 285	97.58 269	99.34 189	97.51 250	99.27 136	99.15 157	96.34 240	99.80 224	99.47 52	99.93 54	99.51 150

CP-MVS		98.70 132	98.42 170	99.52 44	99.36 170	99.12 62	98.72 102	99.36 177	97.54 248	98.30 283	98.40 318	97.86 133	99.89 95	96.53 279	99.72 180	99.56 123

diffmvs_AUTHOR		98.50 173	98.59 143	98.23 272	99.35 175	95.48 302	96.61 342	99.60 73	98.37 168	98.90 206	99.00 201	97.37 177	99.76 260	98.22 137	99.85 103	99.46 180

Test_1112_low_res		96.99 318	96.55 329	98.31 263	99.35 175	95.47 305	95.84 392	99.53 105	91.51 428	96.80 385	98.48 312	91.36 355	99.83 190	96.58 268	99.53 259	99.62 87

DeepC-MVS	97.60 4	98.97 87	98.93 91	99.10 124	99.35 175	97.98 158	98.01 198	99.46 134	97.56 244	99.54 76	99.50 67	98.97 28	99.84 172	98.06 149	99.92 67	99.49 159
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 295	96.86 307	98.58 218	99.34 178	96.32 271	96.75 334	99.58 79	93.14 409	96.89 380	97.48 383	92.11 347	99.86 141	96.91 235	99.54 255	99.57 117

reproduce_model		99.15 57	98.97 88	99.67 4	99.33 179	99.44 10	98.15 170	99.47 130	99.12 93	99.52 82	99.32 112	98.31 89	99.90 79	97.78 173	99.73 172	99.66 75

MVSMamba_PlusPlus		98.83 108	98.98 87	98.36 258	99.32 180	96.58 260	98.90 83	99.41 162	99.75 11	98.72 238	99.50 67	96.17 244	99.94 41	99.27 63	99.78 146	98.57 373

fmvsm_s_conf0.5_n_4		99.01 80	99.22 53	98.38 254	99.31 181	95.48 302	97.56 271	99.73 43	98.87 132	99.75 44	99.27 120	98.80 40	99.86 141	99.80 16	99.90 83	99.81 38

SF-MVS		98.53 167	98.27 194	99.32 87	99.31 181	98.75 87	98.19 164	99.41 162	96.77 313	98.83 221	98.90 226	97.80 139	99.82 200	95.68 325	99.52 262	99.38 217

CPTT-MVS		97.84 254	97.36 278	99.27 95	99.31 181	98.46 111	98.29 153	99.27 225	94.90 377	97.83 323	98.37 322	94.90 289	99.84 172	93.85 376	99.54 255	99.51 150

UnsupCasMVSNet_eth		97.89 243	97.60 264	98.75 190	99.31 181	97.17 228	97.62 261	99.35 183	98.72 142	98.76 234	98.68 277	92.57 341	99.74 273	97.76 178	95.60 447	99.34 232

fmvsm_s_conf0.5_n_7		98.83 108	99.04 78	98.20 274	99.30 185	94.83 326	97.23 304	99.36 177	98.64 145	99.84 30	99.43 86	98.10 114	99.91 72	99.56 39	99.96 28	99.87 21

pmmvs-eth3d		98.47 176	98.34 183	98.86 168	99.30 185	97.76 185	97.16 313	99.28 222	95.54 359	99.42 104	99.19 143	97.27 184	99.63 332	97.89 162	99.97 21	99.20 274

mamv4		99.44 19	99.39 28	99.58 20	99.30 185	99.74 2	99.04 68	99.81 31	99.77 10	99.82 33	99.57 49	97.82 137	99.98 4	99.53 46	99.89 89	99.01 307

SymmetryMVS		98.05 229	97.71 254	99.09 128	99.29 188	97.83 174	98.28 154	97.64 381	99.24 74	98.80 227	98.85 239	89.76 369	99.94 41	98.04 151	99.50 271	99.49 159

Anonymous20231211		99.27 38	99.27 47	99.26 97	99.29 188	98.18 133	99.49 12	99.51 110	99.70 16	99.80 37	99.68 25	96.84 207	99.83 190	99.21 69	99.91 76	99.77 48

viewmanbaseed2359cas		98.58 157	98.54 149	98.70 198	99.28 190	97.13 232	97.47 283	99.55 97	97.55 246	98.96 193	98.92 221	97.77 141	99.59 349	97.59 189	99.77 152	99.39 209

UnsupCasMVSNet_bld		97.30 293	96.92 303	98.45 245	99.28 190	96.78 251	96.20 368	99.27 225	95.42 363	98.28 287	98.30 330	93.16 327	99.71 287	94.99 339	97.37 423	98.87 334

EC-MVSNet		99.09 70	99.05 77	99.20 106	99.28 190	98.93 79	99.24 44	99.84 22	99.08 108	98.12 300	98.37 322	98.72 49	99.90 79	99.05 82	99.77 152	98.77 351

mamba_0408		98.80 115	98.88 97	98.55 228	99.27 193	96.50 263	98.00 199	99.60 73	98.93 125	99.22 149	98.84 244	98.59 62	99.89 95	97.74 179	99.72 180	99.27 252

SSM_04072		98.80 115	98.88 97	98.56 226	99.27 193	96.50 263	98.00 199	99.60 73	98.93 125	99.22 149	98.84 244	98.59 62	99.90 79	97.74 179	99.72 180	99.27 252

SSM_0407		98.86 103	98.96 90	98.55 228	99.27 193	96.50 263	98.04 190	99.66 60	99.09 104	99.22 149	99.02 187	98.79 42	99.87 132	97.87 167	99.72 180	99.27 252

reproduce-ours		99.09 70	98.90 94	99.67 4	99.27 193	99.49 6	98.00 199	99.42 158	99.05 111	99.48 90	99.27 120	98.29 91	99.89 95	97.61 186	99.71 189	99.62 87

our_new_method		99.09 70	98.90 94	99.67 4	99.27 193	99.49 6	98.00 199	99.42 158	99.05 111	99.48 90	99.27 120	98.29 91	99.89 95	97.61 186	99.71 189	99.62 87

DPE-MVS		98.59 156	98.26 195	99.57 21	99.27 193	99.15 52	97.01 318	99.39 167	97.67 231	99.44 99	98.99 203	97.53 164	99.89 95	95.40 333	99.68 204	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		97.85 253	98.18 207	96.87 371	99.27 193	91.16 420	95.53 402	99.25 231	99.10 101	99.41 106	99.35 101	93.10 329	99.96 14	98.65 112	99.94 49	99.49 159

v1192		98.60 154	98.66 129	98.41 250	99.27 193	95.88 286	97.52 276	99.36 177	97.41 263	99.33 123	99.20 142	96.37 238	99.82 200	99.57 37	99.92 67	99.55 130

N_pmnet		97.63 267	97.17 288	98.99 147	99.27 193	97.86 171	95.98 379	93.41 444	95.25 368	99.47 94	98.90 226	95.63 270	99.85 154	96.91 235	99.73 172	99.27 252

FPMVS		93.44 402	92.23 409	97.08 359	99.25 202	97.86 171	95.61 399	97.16 393	92.90 413	93.76 446	98.65 284	75.94 441	95.66 460	79.30 458	97.49 416	97.73 424

new-patchmatchnet		98.35 191	98.74 113	97.18 354	99.24 203	92.23 402	96.42 355	99.48 122	98.30 176	99.69 54	99.53 63	97.44 173	99.82 200	98.84 97	99.77 152	99.49 159

MCST-MVS		98.00 234	97.63 262	99.10 124	99.24 203	98.17 134	96.89 327	98.73 334	95.66 354	97.92 314	97.70 371	97.17 190	99.66 321	96.18 301	99.23 316	99.47 178

UniMVSNet (Re)		98.87 100	98.71 120	99.35 76	99.24 203	98.73 91	97.73 245	99.38 169	98.93 125	99.12 160	98.73 263	96.77 215	99.86 141	98.63 114	99.80 135	99.46 180

jason		97.45 281	97.35 279	97.76 307	99.24 203	93.93 363	95.86 389	98.42 352	94.24 392	98.50 269	98.13 340	94.82 293	99.91 72	97.22 211	99.73 172	99.43 193
jason: jason.
IterMVS		97.73 259	98.11 216	96.57 381	99.24 203	90.28 429	95.52 404	99.21 240	98.86 134	99.33 123	99.33 108	93.11 328	99.94 41	98.49 123	99.94 49	99.48 170
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 163	98.62 136	98.32 261	99.22 208	95.58 296	97.51 278	99.45 138	97.16 291	99.45 98	99.24 133	96.12 248	99.85 154	99.60 35	99.88 91	99.55 130

ITE_SJBPF				98.87 167	99.22 208	98.48 110		99.35 183	97.50 251	98.28 287	98.60 295	97.64 152	99.35 411	93.86 375	99.27 308	98.79 349

h-mvs33		97.77 257	97.33 281	99.10 124	99.21 210	97.84 173	98.35 150	98.57 344	99.11 94	98.58 258	99.02 187	88.65 380	99.96 14	98.11 144	96.34 439	99.49 159

v144192		98.54 165	98.57 145	98.45 245	99.21 210	95.98 283	97.63 260	99.36 177	97.15 293	99.32 129	99.18 147	95.84 265	99.84 172	99.50 49	99.91 76	99.54 135

APDe-MVS		98.99 83	98.79 109	99.60 15	99.21 210	99.15 52	98.87 88	99.48 122	97.57 242	99.35 119	99.24 133	97.83 134	99.89 95	97.88 165	99.70 196	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	98.81 108	99.28 92	99.21 210	98.45 112	98.46 138	99.33 195	99.63 29	99.48 90	99.15 157	97.23 187	99.75 268	97.17 213	99.66 217	99.63 86

SR-MVS-dyc-post		98.81 113	98.55 147	99.57 21	99.20 214	99.38 13	98.48 136	99.30 210	98.64 145	98.95 194	98.96 213	97.49 171	99.86 141	96.56 274	99.39 289	99.45 185

RE-MVS-def			98.58 144		99.20 214	99.38 13	98.48 136	99.30 210	98.64 145	98.95 194	98.96 213	97.75 143		96.56 274	99.39 289	99.45 185

v1921920		98.54 165	98.60 141	98.38 254	99.20 214	95.76 293	97.56 271	99.36 177	97.23 285	99.38 112	99.17 151	96.02 251	99.84 172	99.57 37	99.90 83	99.54 135

thisisatest0530		95.27 371	94.45 382	97.74 310	99.19 217	94.37 341	97.86 224	90.20 456	97.17 290	98.22 290	97.65 373	73.53 444	99.90 79	96.90 240	99.35 295	98.95 319

Anonymous20240529		98.93 92	98.87 99	99.12 120	99.19 217	98.22 131	99.01 70	98.99 289	99.25 73	99.54 76	99.37 96	97.04 196	99.80 224	97.89 162	99.52 262	99.35 230

APD-MVS_3200maxsize		98.84 106	98.61 140	99.53 38	99.19 217	99.27 27	98.49 133	99.33 195	98.64 145	99.03 180	98.98 208	97.89 131	99.85 154	96.54 278	99.42 286	99.46 180

HQP_MVS		97.99 237	97.67 256	98.93 159	99.19 217	97.65 193	97.77 237	99.27 225	98.20 190	97.79 326	97.98 354	94.90 289	99.70 293	94.42 357	99.51 264	99.45 185

plane_prior7					99.19 217	97.87 170

ab-mvs		98.41 181	98.36 180	98.59 217	99.19 217	97.23 219	99.32 26	98.81 320	97.66 232	98.62 250	99.40 94	96.82 210	99.80 224	95.88 312	99.51 264	98.75 354

F-COLMAP		97.30 293	96.68 320	99.14 118	99.19 217	98.39 114	97.27 303	99.30 210	92.93 412	96.62 391	98.00 352	95.73 268	99.68 306	92.62 403	98.46 384	99.35 230

SR-MVS		98.71 128	98.43 168	99.57 21	99.18 224	99.35 17	98.36 149	99.29 218	98.29 179	98.88 213	98.85 239	97.53 164	99.87 132	96.14 303	99.31 301	99.48 170

UniMVSNet_NR-MVSNet		98.86 103	98.68 126	99.40 68	99.17 225	98.74 88	97.68 250	99.40 165	99.14 92	99.06 168	98.59 296	96.71 221	99.93 52	98.57 117	99.77 152	99.53 144

LF4IMVS		97.90 241	97.69 255	98.52 236	99.17 225	97.66 192	97.19 312	99.47 130	96.31 332	97.85 322	98.20 337	96.71 221	99.52 376	94.62 349	99.72 180	98.38 390

SMA-MVS		98.40 183	98.03 225	99.51 48	99.16 227	99.21 33	98.05 188	99.22 239	94.16 394	98.98 185	99.10 169	97.52 166	99.79 237	96.45 284	99.64 220	99.53 144
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		98.82 111	98.63 134	99.39 69	99.16 227	98.74 88	97.54 274	99.25 231	98.84 137	99.06 168	98.76 260	96.76 217	99.93 52	98.57 117	99.77 152	99.50 153

NR-MVSNet		98.95 90	98.82 106	99.36 70	99.16 227	98.72 93	99.22 45	99.20 242	99.10 101	99.72 46	98.76 260	96.38 237	99.86 141	98.00 156	99.82 119	99.50 153

MVS_111021_LR		98.30 200	98.12 215	98.83 171	99.16 227	98.03 153	96.09 376	99.30 210	97.58 241	98.10 302	98.24 333	98.25 96	99.34 412	96.69 260	99.65 218	99.12 293

DSMNet-mixed		97.42 284	97.60 264	96.87 371	99.15 231	91.46 409	98.54 121	99.12 264	92.87 414	97.58 339	99.63 39	96.21 243	99.90 79	95.74 321	99.54 255	99.27 252

D2MVS		97.84 254	97.84 245	97.83 299	99.14 232	94.74 330	96.94 322	98.88 304	95.84 351	98.89 209	98.96 213	94.40 305	99.69 297	97.55 190	99.95 38	99.05 299

pmmvs5		97.64 266	97.49 270	98.08 284	99.14 232	95.12 319	96.70 337	99.05 275	93.77 401	98.62 250	98.83 246	93.23 325	99.75 268	98.33 132	99.76 165	99.36 226

SPE-MVS-test		99.13 64	99.09 73	99.26 97	99.13 234	98.97 73	99.31 30	99.88 14	99.44 51	98.16 295	98.51 305	98.64 56	99.93 52	98.91 91	99.85 103	98.88 333

VDD-MVS		98.56 159	98.39 175	99.07 131	99.13 234	98.07 148	98.59 115	97.01 396	99.59 35	99.11 161	99.27 120	94.82 293	99.79 237	98.34 130	99.63 223	99.34 232

save fliter					99.11 236	97.97 159	96.53 347	99.02 283	98.24 182

APD-MVS		98.10 223	97.67 256	99.42 64	99.11 236	98.93 79	97.76 240	99.28 222	94.97 375	98.72 238	98.77 258	97.04 196	99.85 154	93.79 377	99.54 255	99.49 159
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 135	98.71 120	98.62 211	99.10 238	96.37 269	97.23 304	98.87 306	99.20 81	99.19 154	98.99 203	97.30 181	99.85 154	98.77 103	99.79 141	99.65 80

EI-MVSNet		98.40 183	98.51 153	98.04 289	99.10 238	94.73 331	97.20 309	98.87 306	98.97 120	99.06 168	99.02 187	96.00 253	99.80 224	98.58 115	99.82 119	99.60 97

CVMVSNet		96.25 345	97.21 287	93.38 438	99.10 238	80.56 466	97.20 309	98.19 363	96.94 303	99.00 182	99.02 187	89.50 373	99.80 224	96.36 290	99.59 237	99.78 45

EI-MVSNet-Vis-set		98.68 140	98.70 123	98.63 209	99.09 241	96.40 268	97.23 304	98.86 311	99.20 81	99.18 158	98.97 210	97.29 183	99.85 154	98.72 107	99.78 146	99.64 81

HPM-MVS++		98.10 223	97.64 261	99.48 56	99.09 241	99.13 60	97.52 276	98.75 331	97.46 259	96.90 379	97.83 364	96.01 252	99.84 172	95.82 319	99.35 295	99.46 180

DP-MVS Recon		97.33 291	96.92 303	98.57 221	99.09 241	97.99 155	96.79 330	99.35 183	93.18 408	97.71 330	98.07 348	95.00 288	99.31 416	93.97 370	99.13 332	98.42 387

MVS_111021_HR		98.25 209	98.08 220	98.75 190	99.09 241	97.46 205	95.97 380	99.27 225	97.60 240	97.99 312	98.25 332	98.15 111	99.38 407	96.87 243	99.57 246	99.42 196

BP-MVS1		97.40 286	96.97 299	98.71 197	99.07 245	96.81 247	98.34 152	97.18 391	98.58 156	98.17 292	98.61 293	84.01 412	99.94 41	98.97 88	99.78 146	99.37 219

9.14			97.78 247		99.07 245		97.53 275	99.32 197	95.53 360	98.54 265	98.70 273	97.58 158	99.76 260	94.32 362	99.46 276

PAPM_NR		96.82 325	96.32 336	98.30 264	99.07 245	96.69 255	97.48 281	98.76 328	95.81 352	96.61 392	96.47 409	94.12 314	99.17 429	90.82 430	97.78 410	99.06 298

TAMVS		98.24 210	98.05 223	98.80 177	99.07 245	97.18 226	97.88 220	98.81 320	96.66 318	99.17 159	99.21 140	94.81 295	99.77 254	96.96 233	99.88 91	99.44 189

CLD-MVS		97.49 277	97.16 289	98.48 242	99.07 245	97.03 235	94.71 425	99.21 240	94.46 386	98.06 305	97.16 395	97.57 159	99.48 388	94.46 354	99.78 146	98.95 319
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	99.06 250	99.15 52	99.36 22	99.88 14	99.36 62	98.21 291	98.46 313	98.68 53	99.93 52	99.03 84	99.85 103	98.64 366

thres100view900		94.19 388	93.67 393	95.75 405	99.06 250	91.35 413	98.03 192	94.24 439	98.33 172	97.40 355	94.98 439	79.84 428	99.62 335	83.05 451	98.08 401	96.29 446

thres600view7		94.45 383	93.83 390	96.29 389	99.06 250	91.53 408	97.99 206	94.24 439	98.34 171	97.44 353	95.01 437	79.84 428	99.67 310	84.33 449	98.23 390	97.66 427

plane_prior1					99.05 253

YYNet1		97.60 268	97.67 256	97.39 347	99.04 254	93.04 386	95.27 411	98.38 355	97.25 279	98.92 204	98.95 217	95.48 277	99.73 279	96.99 229	98.74 365	99.41 199

MDA-MVSNet_test_wron		97.60 268	97.66 259	97.41 346	99.04 254	93.09 382	95.27 411	98.42 352	97.26 278	98.88 213	98.95 217	95.43 278	99.73 279	97.02 226	98.72 367	99.41 199

MIMVSNet		96.62 332	96.25 340	97.71 314	99.04 254	94.66 334	99.16 54	96.92 402	97.23 285	97.87 319	99.10 169	86.11 395	99.65 326	91.65 414	99.21 320	98.82 338

icg_test_0407_2		98.20 215	98.38 177	97.65 320	99.03 257	94.03 354	95.78 394	99.45 138	98.16 196	99.06 168	98.71 266	98.27 93	99.68 306	97.50 195	99.45 278	99.22 269

IMVS_0407		98.39 189	98.64 132	97.66 318	99.03 257	94.03 354	98.10 179	99.45 138	98.16 196	99.06 168	98.71 266	98.27 93	99.71 287	97.50 195	99.45 278	99.22 269

IMVS_0404		98.07 227	98.20 202	97.69 315	99.03 257	94.03 354	96.67 338	99.45 138	98.16 196	98.03 309	98.71 266	96.80 213	99.82 200	97.50 195	99.45 278	99.22 269

IMVS_0403		98.34 192	98.56 146	97.66 318	99.03 257	94.03 354	97.98 207	99.45 138	98.16 196	98.89 209	98.71 266	97.90 129	99.74 273	97.50 195	99.45 278	99.22 269

PatchMatch-RL		97.24 299	96.78 314	98.61 214	99.03 257	97.83 174	96.36 358	99.06 272	93.49 406	97.36 359	97.78 365	95.75 267	99.49 385	93.44 386	98.77 364	98.52 375

viewmambaseed2359dif		98.19 216	98.26 195	97.99 292	99.02 262	95.03 322	96.59 344	99.53 105	96.21 335	99.00 182	98.99 203	97.62 154	99.61 342	97.62 185	99.72 180	99.33 237

GDP-MVS		97.50 274	97.11 293	98.67 202	99.02 262	96.85 245	98.16 169	99.71 46	98.32 174	98.52 268	98.54 300	83.39 416	99.95 26	98.79 99	99.56 249	99.19 279

ZD-MVS					99.01 264	98.84 82		99.07 271	94.10 396	98.05 307	98.12 342	96.36 239	99.86 141	92.70 402	99.19 324

CDPH-MVS		97.26 296	96.66 323	99.07 131	99.00 265	98.15 135	96.03 378	99.01 286	91.21 432	97.79 326	97.85 363	96.89 205	99.69 297	92.75 400	99.38 292	99.39 209

diffmvs		98.22 211	98.24 199	98.17 277	99.00 265	95.44 306	96.38 357	99.58 79	97.79 225	98.53 266	98.50 309	96.76 217	99.74 273	97.95 161	99.64 220	99.34 232
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		98.40 183	98.19 206	99.03 141	99.00 265	97.65 193	96.85 328	98.94 291	98.57 157	98.89 209	98.50 309	95.60 271	99.85 154	97.54 192	99.85 103	99.59 104

plane_prior6					98.99 268	97.70 191						94.90 289

xiu_mvs_v1_base_debu		97.86 248	98.17 208	96.92 368	98.98 269	93.91 364	96.45 351	99.17 254	97.85 220	98.41 277	97.14 397	98.47 72	99.92 63	98.02 153	99.05 338	96.92 439

xiu_mvs_v1_base		97.86 248	98.17 208	96.92 368	98.98 269	93.91 364	96.45 351	99.17 254	97.85 220	98.41 277	97.14 397	98.47 72	99.92 63	98.02 153	99.05 338	96.92 439

xiu_mvs_v1_base_debi		97.86 248	98.17 208	96.92 368	98.98 269	93.91 364	96.45 351	99.17 254	97.85 220	98.41 277	97.14 397	98.47 72	99.92 63	98.02 153	99.05 338	96.92 439

MVP-Stereo		98.08 226	97.92 239	98.57 221	98.96 272	96.79 248	97.90 218	99.18 250	96.41 328	98.46 272	98.95 217	95.93 262	99.60 345	96.51 280	98.98 352	99.31 244
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 183	98.68 126	97.54 335	98.96 272	97.99 155	97.88 220	99.36 177	98.20 190	99.63 65	99.04 184	98.76 45	95.33 462	96.56 274	99.74 169	99.31 244
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	98.94 274	97.76 185		98.76 328	87.58 449	96.75 387	98.10 344	94.80 296	99.78 248	92.73 401	99.00 347	99.20 274

USDC		97.41 285	97.40 274	97.44 344	98.94 274	93.67 374	95.17 414	99.53 105	94.03 398	98.97 189	99.10 169	95.29 280	99.34 412	95.84 318	99.73 172	99.30 247

tfpn200view9		94.03 392	93.44 395	95.78 404	98.93 276	91.44 411	97.60 266	94.29 437	97.94 212	97.10 365	94.31 446	79.67 430	99.62 335	83.05 451	98.08 401	96.29 446

testdata				98.09 281	98.93 276	95.40 308		98.80 322	90.08 440	97.45 352	98.37 322	95.26 281	99.70 293	93.58 382	98.95 355	99.17 286

thres400		94.14 390	93.44 395	96.24 392	98.93 276	91.44 411	97.60 266	94.29 437	97.94 212	97.10 365	94.31 446	79.67 430	99.62 335	83.05 451	98.08 401	97.66 427

TAPA-MVS	96.21 11	96.63 331	95.95 342	98.65 203	98.93 276	98.09 142	96.93 324	99.28 222	83.58 455	98.13 299	97.78 365	96.13 246	99.40 403	93.52 383	99.29 306	98.45 380
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 280	96.93 242	95.54 401	98.78 325	85.72 452	96.86 382	98.11 343	94.43 303			99.10 337	99.23 264

PVSNet_BlendedMVS		97.55 273	97.53 267	97.60 327	98.92 280	93.77 371	96.64 340	99.43 152	94.49 384	97.62 335	99.18 147	96.82 210	99.67 310	94.73 346	99.93 54	99.36 226

PVSNet_Blended		96.88 321	96.68 320	97.47 342	98.92 280	93.77 371	94.71 425	99.43 152	90.98 434	97.62 335	97.36 391	96.82 210	99.67 310	94.73 346	99.56 249	98.98 313

MSDG		97.71 261	97.52 268	98.28 266	98.91 283	96.82 246	94.42 435	99.37 173	97.65 233	98.37 282	98.29 331	97.40 175	99.33 414	94.09 368	99.22 317	98.68 364

Anonymous202405211		97.90 241	97.50 269	99.08 129	98.90 284	98.25 125	98.53 122	96.16 414	98.87 132	99.11 161	98.86 236	90.40 365	99.78 248	97.36 204	99.31 301	99.19 279

原ACMM1				98.35 259	98.90 284	96.25 273		98.83 319	92.48 418	96.07 409	98.10 344	95.39 279	99.71 287	92.61 404	98.99 349	99.08 295

GBi-Net		98.65 145	98.47 162	99.17 111	98.90 284	98.24 126	99.20 48	99.44 146	98.59 153	98.95 194	99.55 57	94.14 311	99.86 141	97.77 174	99.69 199	99.41 199

test1		98.65 145	98.47 162	99.17 111	98.90 284	98.24 126	99.20 48	99.44 146	98.59 153	98.95 194	99.55 57	94.14 311	99.86 141	97.77 174	99.69 199	99.41 199

FMVSNet2		98.49 174	98.40 172	98.75 190	98.90 284	97.14 231	98.61 113	99.13 263	98.59 153	99.19 154	99.28 118	94.14 311	99.82 200	97.97 159	99.80 135	99.29 249

OMC-MVS		97.88 245	97.49 270	99.04 140	98.89 289	98.63 95	96.94 322	99.25 231	95.02 373	98.53 266	98.51 305	97.27 184	99.47 391	93.50 385	99.51 264	99.01 307

VortexMVS		97.98 238	98.31 188	97.02 362	98.88 290	91.45 410	98.03 192	99.47 130	98.65 144	99.55 74	99.47 77	91.49 354	99.81 216	99.32 59	99.91 76	99.80 40

MVSFormer		98.26 206	98.43 168	97.77 304	98.88 290	93.89 367	99.39 20	99.56 93	99.11 94	98.16 295	98.13 340	93.81 319	99.97 7	99.26 64	99.57 246	99.43 193

lupinMVS		97.06 311	96.86 307	97.65 320	98.88 290	93.89 367	95.48 405	97.97 369	93.53 404	98.16 295	97.58 377	93.81 319	99.91 72	96.77 251	99.57 246	99.17 286

dmvs_re		95.98 353	95.39 363	97.74 310	98.86 293	97.45 206	98.37 148	95.69 426	97.95 210	96.56 393	95.95 418	90.70 362	97.68 456	88.32 439	96.13 443	98.11 402

DELS-MVS		98.27 204	98.20 202	98.48 242	98.86 293	96.70 254	95.60 400	99.20 242	97.73 228	98.45 273	98.71 266	97.50 168	99.82 200	98.21 138	99.59 237	98.93 324
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		97.89 243	97.98 230	97.60 327	98.86 293	94.35 342	96.21 367	99.44 146	97.45 261	99.06 168	98.88 233	97.99 124	99.28 422	94.38 361	99.58 242	99.18 282

LCM-MVSNet-Re		98.64 147	98.48 160	99.11 122	98.85 296	98.51 108	98.49 133	99.83 25	98.37 168	99.69 54	99.46 79	98.21 103	99.92 63	94.13 367	99.30 304	98.91 328

pmmvs4		97.58 271	97.28 282	98.51 237	98.84 297	96.93 242	95.40 409	98.52 347	93.60 403	98.61 252	98.65 284	95.10 285	99.60 345	96.97 232	99.79 141	98.99 312

NP-MVS					98.84 297	97.39 210					96.84 400

sss		97.21 301	96.93 301	98.06 286	98.83 299	95.22 315	96.75 334	98.48 349	94.49 384	97.27 361	97.90 360	92.77 337	99.80 224	96.57 270	99.32 299	99.16 289

PVSNet	93.40 17	95.67 362	95.70 348	95.57 409	98.83 299	88.57 436	92.50 452	97.72 374	92.69 416	96.49 401	96.44 410	93.72 322	99.43 399	93.61 380	99.28 307	98.71 357

MVE	83.40 22	92.50 415	91.92 417	94.25 425	98.83 299	91.64 407	92.71 451	83.52 465	95.92 349	86.46 463	95.46 431	95.20 282	95.40 461	80.51 456	98.64 376	95.73 454
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 396	93.91 388	93.39 437	98.82 302	81.72 464	97.76 240	95.28 428	98.60 152	96.54 394	96.66 404	65.85 460	99.62 335	96.65 263	98.99 349	98.82 338

ambc				98.24 270	98.82 302	95.97 284	98.62 112	99.00 288		99.27 136	99.21 140	96.99 201	99.50 382	96.55 277	99.50 271	99.26 258

旧先验1					98.82 302	97.45 206		98.76 328			98.34 326	95.50 276			99.01 346	99.23 264

test_vis1_rt		97.75 258	97.72 253	97.83 299	98.81 305	96.35 270	97.30 299	99.69 51	94.61 382	97.87 319	98.05 349	96.26 242	98.32 450	98.74 105	98.18 393	98.82 338

WTY-MVS		96.67 329	96.27 339	97.87 297	98.81 305	94.61 336	96.77 332	97.92 371	94.94 376	97.12 364	97.74 368	91.11 358	99.82 200	93.89 373	98.15 397	99.18 282

3Dnovator+	97.89 3	98.69 135	98.51 153	99.24 102	98.81 305	98.40 113	99.02 69	99.19 246	98.99 117	98.07 304	99.28 118	97.11 194	99.84 172	96.84 246	99.32 299	99.47 178

QAPM		97.31 292	96.81 313	98.82 173	98.80 308	97.49 201	99.06 65	99.19 246	90.22 438	97.69 332	99.16 153	96.91 204	99.90 79	90.89 429	99.41 287	99.07 297

VNet		98.42 180	98.30 189	98.79 180	98.79 309	97.29 215	98.23 160	98.66 338	99.31 67	98.85 218	98.80 252	94.80 296	99.78 248	98.13 143	99.13 332	99.31 244

DPM-MVS		96.32 341	95.59 354	98.51 237	98.76 310	97.21 223	94.54 434	98.26 358	91.94 423	96.37 402	97.25 393	93.06 331	99.43 399	91.42 419	98.74 365	98.89 330

3Dnovator	98.27 2	98.81 113	98.73 115	99.05 138	98.76 310	97.81 182	99.25 43	99.30 210	98.57 157	98.55 263	99.33 108	97.95 126	99.90 79	97.16 214	99.67 210	99.44 189

PLC	94.65 16	96.51 334	95.73 347	98.85 169	98.75 312	97.91 167	96.42 355	99.06 272	90.94 435	95.59 415	97.38 389	94.41 304	99.59 349	90.93 427	98.04 406	99.05 299
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 323	96.75 316	97.08 359	98.74 313	93.33 380	96.71 336	98.26 358	96.72 315	98.44 274	97.37 390	95.20 282	99.47 391	91.89 409	97.43 420	98.44 383

hse-mvs2		97.46 279	97.07 294	98.64 205	98.73 314	97.33 212	97.45 285	97.64 381	99.11 94	98.58 258	97.98 354	88.65 380	99.79 237	98.11 144	97.39 422	98.81 343

CDS-MVSNet		97.69 262	97.35 279	98.69 199	98.73 314	97.02 236	96.92 326	98.75 331	95.89 350	98.59 256	98.67 279	92.08 348	99.74 273	96.72 257	99.81 124	99.32 240
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SD_0403		96.28 343	95.83 344	97.64 323	98.72 316	94.30 343	98.87 88	98.77 326	97.80 223	96.53 395	98.02 351	97.34 179	99.47 391	76.93 460	99.48 274	99.16 289

EIA-MVS		98.00 234	97.74 250	98.80 177	98.72 316	98.09 142	98.05 188	99.60 73	97.39 265	96.63 390	95.55 426	97.68 146	99.80 224	96.73 256	99.27 308	98.52 375

LFMVS		97.20 302	96.72 317	98.64 205	98.72 316	96.95 240	98.93 81	94.14 441	99.74 13	98.78 229	99.01 198	84.45 407	99.73 279	97.44 200	99.27 308	99.25 259

new_pmnet		96.99 318	96.76 315	97.67 316	98.72 316	94.89 325	95.95 384	98.20 361	92.62 417	98.55 263	98.54 300	94.88 292	99.52 376	93.96 371	99.44 285	98.59 372

Fast-Effi-MVS+		97.67 264	97.38 276	98.57 221	98.71 320	97.43 208	97.23 304	99.45 138	94.82 379	96.13 406	96.51 406	98.52 70	99.91 72	96.19 299	98.83 361	98.37 392

TEST9					98.71 320	98.08 146	95.96 382	99.03 280	91.40 429	95.85 412	97.53 379	96.52 230	99.76 260

train_agg		97.10 308	96.45 333	99.07 131	98.71 320	98.08 146	95.96 382	99.03 280	91.64 424	95.85 412	97.53 379	96.47 232	99.76 260	93.67 379	99.16 327	99.36 226

TSAR-MVS + GP.		98.18 218	97.98 230	98.77 187	98.71 320	97.88 169	96.32 361	98.66 338	96.33 330	99.23 148	98.51 305	97.48 172	99.40 403	97.16 214	99.46 276	99.02 306

FA-MVS(test-final)		96.99 318	96.82 311	97.50 339	98.70 324	94.78 328	99.34 23	96.99 397	95.07 372	98.48 271	99.33 108	88.41 383	99.65 326	96.13 305	98.92 358	98.07 405

AUN-MVS		96.24 347	95.45 359	98.60 216	98.70 324	97.22 221	97.38 290	97.65 379	95.95 348	95.53 422	97.96 358	82.11 424	99.79 237	96.31 292	97.44 419	98.80 348

our_test_3		97.39 287	97.73 252	96.34 387	98.70 324	89.78 432	94.61 431	98.97 290	96.50 323	99.04 177	98.85 239	95.98 258	99.84 172	97.26 209	99.67 210	99.41 199

ppachtmachnet_test		97.50 274	97.74 250	96.78 377	98.70 324	91.23 419	94.55 433	99.05 275	96.36 329	99.21 152	98.79 254	96.39 235	99.78 248	96.74 254	99.82 119	99.34 232

PCF-MVS	92.86 18	94.36 384	93.00 402	98.42 249	98.70 324	97.56 198	93.16 450	99.11 266	79.59 459	97.55 342	97.43 386	92.19 345	99.73 279	79.85 457	99.45 278	97.97 411
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 240	98.02 226	97.58 329	98.69 329	94.10 350	98.13 172	98.90 300	97.95 210	97.32 360	99.58 47	95.95 261	98.75 445	96.41 286	99.22 317	99.87 21

ETV-MVS		98.03 230	97.86 244	98.56 226	98.69 329	98.07 148	97.51 278	99.50 113	98.10 202	97.50 347	95.51 427	98.41 78	99.88 113	96.27 295	99.24 313	97.71 426

test_prior				98.95 156	98.69 329	97.95 163		99.03 280					99.59 349			99.30 247

mvsmamba		97.57 272	97.26 283	98.51 237	98.69 329	96.73 253	98.74 97	97.25 390	97.03 299	97.88 318	99.23 138	90.95 359	99.87 132	96.61 266	99.00 347	98.91 328

agg_prior					98.68 333	97.99 155		99.01 286		95.59 415			99.77 254

test_8					98.67 334	98.01 154	95.91 388	99.02 283	91.64 424	95.79 414	97.50 382	96.47 232	99.76 260

HQP-NCC					98.67 334		96.29 363		96.05 341	95.55 418

ACMP_Plane					98.67 334		96.29 363		96.05 341	95.55 418

CNVR-MVS		98.17 220	97.87 243	99.07 131	98.67 334	98.24 126	97.01 318	98.93 294	97.25 279	97.62 335	98.34 326	97.27 184	99.57 358	96.42 285	99.33 298	99.39 209

HQP-MVS		97.00 317	96.49 332	98.55 228	98.67 334	96.79 248	96.29 363	99.04 278	96.05 341	95.55 418	96.84 400	93.84 317	99.54 370	92.82 397	99.26 311	99.32 240

MM		98.22 211	97.99 229	98.91 163	98.66 339	96.97 237	97.89 219	94.44 435	99.54 39	98.95 194	99.14 160	93.50 323	99.92 63	99.80 16	99.96 28	99.85 29

test_fmvs1		97.72 260	97.94 236	97.07 361	98.66 339	92.39 397	97.68 250	99.81 31	95.20 371	99.54 76	99.44 84	91.56 353	99.41 402	99.78 20	99.77 152	99.40 208

balanced_conf03		98.63 149	98.72 117	98.38 254	98.66 339	96.68 256	98.90 83	99.42 158	98.99 117	98.97 189	99.19 143	95.81 266	99.85 154	98.77 103	99.77 152	98.60 369

thres200		93.72 398	93.14 400	95.46 413	98.66 339	91.29 415	96.61 342	94.63 434	97.39 265	96.83 383	93.71 449	79.88 427	99.56 361	82.40 454	98.13 398	95.54 455

wuyk23d		96.06 349	97.62 263	91.38 442	98.65 343	98.57 102	98.85 92	96.95 400	96.86 308	99.90 14	99.16 153	99.18 19	98.40 449	89.23 437	99.77 152	77.18 462

NCCC		97.86 248	97.47 273	99.05 138	98.61 344	98.07 148	96.98 320	98.90 300	97.63 234	97.04 369	97.93 359	95.99 257	99.66 321	95.31 334	98.82 363	99.43 193

DeepC-MVS_fast	96.85 6	98.30 200	98.15 212	98.75 190	98.61 344	97.23 219	97.76 240	99.09 269	97.31 273	98.75 235	98.66 282	97.56 160	99.64 329	96.10 306	99.55 253	99.39 209
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 400	92.09 411	97.75 308	98.60 346	94.40 340	97.32 297	95.26 429	97.56 244	96.79 386	95.50 428	53.57 468	99.77 254	95.26 335	98.97 353	99.08 295

thisisatest0515		94.12 391	93.16 399	96.97 366	98.60 346	92.90 387	93.77 446	90.61 454	94.10 396	96.91 376	95.87 421	74.99 442	99.80 224	94.52 352	99.12 335	98.20 398

GA-MVS		95.86 356	95.32 366	97.49 340	98.60 346	94.15 349	93.83 445	97.93 370	95.49 361	96.68 388	97.42 387	83.21 417	99.30 418	96.22 297	98.55 382	99.01 307

dmvs_testset		92.94 410	92.21 410	95.13 417	98.59 349	90.99 422	97.65 256	92.09 450	96.95 302	94.00 442	93.55 450	92.34 343	96.97 459	72.20 461	92.52 457	97.43 434

OPU-MVS				98.82 173	98.59 349	98.30 122	98.10 179				98.52 304	98.18 105	98.75 445	94.62 349	99.48 274	99.41 199

MSLP-MVS++		98.02 231	98.14 214	97.64 323	98.58 351	95.19 316	97.48 281	99.23 238	97.47 254	97.90 316	98.62 291	97.04 196	98.81 443	97.55 190	99.41 287	98.94 323

test12				98.93 159	98.58 351	97.83 174		98.66 338		96.53 395		95.51 275	99.69 297		99.13 332	99.27 252

CL-MVSNet_self_test		97.44 282	97.22 286	98.08 284	98.57 353	95.78 292	94.30 438	98.79 323	96.58 321	98.60 254	98.19 338	94.74 299	99.64 329	96.41 286	98.84 360	98.82 338

PS-MVSNAJ		97.08 310	97.39 275	96.16 398	98.56 354	92.46 395	95.24 413	98.85 314	97.25 279	97.49 348	95.99 417	98.07 115	99.90 79	96.37 288	98.67 375	96.12 451

CNLPA		97.17 305	96.71 318	98.55 228	98.56 354	98.05 152	96.33 360	98.93 294	96.91 305	97.06 368	97.39 388	94.38 306	99.45 396	91.66 413	99.18 326	98.14 401

xiu_mvs_v2_base		97.16 306	97.49 270	96.17 396	98.54 356	92.46 395	95.45 406	98.84 315	97.25 279	97.48 349	96.49 407	98.31 89	99.90 79	96.34 291	98.68 374	96.15 450

alignmvs		97.35 289	96.88 306	98.78 183	98.54 356	98.09 142	97.71 246	97.69 376	99.20 81	97.59 338	95.90 420	88.12 385	99.55 365	98.18 140	98.96 354	98.70 360

FE-MVS		95.66 363	94.95 376	97.77 304	98.53 358	95.28 312	99.40 19	96.09 417	93.11 410	97.96 313	99.26 126	79.10 434	99.77 254	92.40 406	98.71 369	98.27 396

Effi-MVS+		98.02 231	97.82 246	98.62 211	98.53 358	97.19 225	97.33 296	99.68 56	97.30 274	96.68 388	97.46 385	98.56 68	99.80 224	96.63 264	98.20 392	98.86 335

baseline1		95.96 354	95.44 360	97.52 337	98.51 360	93.99 361	98.39 146	96.09 417	98.21 186	98.40 281	97.76 367	86.88 387	99.63 332	95.42 332	89.27 460	98.95 319

MVS_Test		98.18 218	98.36 180	97.67 316	98.48 361	94.73 331	98.18 165	99.02 283	97.69 230	98.04 308	99.11 166	97.22 188	99.56 361	98.57 117	98.90 359	98.71 357

MGCFI-Net		98.34 192	98.28 191	98.51 237	98.47 362	97.59 197	98.96 77	99.48 122	99.18 88	97.40 355	95.50 428	98.66 54	99.50 382	98.18 140	98.71 369	98.44 383

BH-RMVSNet		96.83 323	96.58 328	97.58 329	98.47 362	94.05 351	96.67 338	97.36 385	96.70 317	97.87 319	97.98 354	95.14 284	99.44 398	90.47 432	98.58 381	99.25 259

sasdasda		98.34 192	98.26 195	98.58 218	98.46 364	97.82 179	98.96 77	99.46 134	99.19 85	97.46 350	95.46 431	98.59 62	99.46 394	98.08 147	98.71 369	98.46 377

canonicalmvs		98.34 192	98.26 195	98.58 218	98.46 364	97.82 179	98.96 77	99.46 134	99.19 85	97.46 350	95.46 431	98.59 62	99.46 394	98.08 147	98.71 369	98.46 377

MVS-HIRNet		94.32 385	95.62 351	90.42 443	98.46 364	75.36 467	96.29 363	89.13 458	95.25 368	95.38 424	99.75 16	92.88 334	99.19 428	94.07 369	99.39 289	96.72 444

PHI-MVS		98.29 203	97.95 234	99.34 79	98.44 367	99.16 48	98.12 176	99.38 169	96.01 345	98.06 305	98.43 316	97.80 139	99.67 310	95.69 324	99.58 242	99.20 274

DVP-MVS++		98.90 96	98.70 123	99.51 48	98.43 368	99.15 52	99.43 15	99.32 197	98.17 193	99.26 140	99.02 187	98.18 105	99.88 113	97.07 223	99.45 278	99.49 159

MSC_two_6792asdad				99.32 87	98.43 368	98.37 117		98.86 311					99.89 95	97.14 217	99.60 233	99.71 60

No_MVS				99.32 87	98.43 368	98.37 117		98.86 311					99.89 95	97.14 217	99.60 233	99.71 60

Fast-Effi-MVS+-dtu		98.27 204	98.09 217	98.81 175	98.43 368	98.11 139	97.61 265	99.50 113	98.64 145	97.39 357	97.52 381	98.12 113	99.95 26	96.90 240	98.71 369	98.38 390

OpenMVS_ROB	95.38 14	95.84 358	95.18 371	97.81 301	98.41 372	97.15 230	97.37 293	98.62 342	83.86 454	98.65 246	98.37 322	94.29 309	99.68 306	88.41 438	98.62 379	96.60 445

DeepPCF-MVS	96.93 5	98.32 197	98.01 227	99.23 104	98.39 373	98.97 73	95.03 418	99.18 250	96.88 306	99.33 123	98.78 256	98.16 109	99.28 422	96.74 254	99.62 226	99.44 189

Patchmatch-test		96.55 333	96.34 335	97.17 356	98.35 374	93.06 383	98.40 145	97.79 372	97.33 270	98.41 277	98.67 279	83.68 415	99.69 297	95.16 337	99.31 301	98.77 351

AdaColmap		97.14 307	96.71 318	98.46 244	98.34 375	97.80 183	96.95 321	98.93 294	95.58 358	96.92 374	97.66 372	95.87 264	99.53 372	90.97 426	99.14 330	98.04 406

OpenMVS	96.65 7	97.09 309	96.68 320	98.32 261	98.32 376	97.16 229	98.86 91	99.37 173	89.48 442	96.29 404	99.15 157	96.56 228	99.90 79	92.90 394	99.20 321	97.89 414

MG-MVS		96.77 326	96.61 325	97.26 352	98.31 377	93.06 383	95.93 385	98.12 366	96.45 327	97.92 314	98.73 263	93.77 321	99.39 405	91.19 424	99.04 341	99.33 237

test_yl		96.69 327	96.29 337	97.90 294	98.28 378	95.24 313	97.29 300	97.36 385	98.21 186	98.17 292	97.86 361	86.27 391	99.55 365	94.87 343	98.32 386	98.89 330

DCV-MVSNet		96.69 327	96.29 337	97.90 294	98.28 378	95.24 313	97.29 300	97.36 385	98.21 186	98.17 292	97.86 361	86.27 391	99.55 365	94.87 343	98.32 386	98.89 330

CHOSEN 280x420		95.51 368	95.47 357	95.65 408	98.25 380	88.27 439	93.25 449	98.88 304	93.53 404	94.65 433	97.15 396	86.17 393	99.93 52	97.41 202	99.93 54	98.73 356

SCA		96.41 340	96.66 323	95.67 406	98.24 381	88.35 438	95.85 391	96.88 403	96.11 339	97.67 333	98.67 279	93.10 329	99.85 154	94.16 363	99.22 317	98.81 343

DeepMVS_CX				93.44 436	98.24 381	94.21 346		94.34 436	64.28 462	91.34 456	94.87 443	89.45 374	92.77 463	77.54 459	93.14 456	93.35 458

MS-PatchMatch		97.68 263	97.75 249	97.45 343	98.23 383	93.78 370	97.29 300	98.84 315	96.10 340	98.64 247	98.65 284	96.04 250	99.36 408	96.84 246	99.14 330	99.20 274

BH-w/o		95.13 374	94.89 378	95.86 401	98.20 384	91.31 414	95.65 398	97.37 384	93.64 402	96.52 397	95.70 424	93.04 332	99.02 434	88.10 440	95.82 446	97.24 437

mvs_anonymous		97.83 256	98.16 211	96.87 371	98.18 385	91.89 404	97.31 298	98.90 300	97.37 267	98.83 221	99.46 79	96.28 241	99.79 237	98.90 92	98.16 396	98.95 319

miper_lstm_enhance		97.18 304	97.16 289	97.25 353	98.16 386	92.85 388	95.15 416	99.31 202	97.25 279	98.74 237	98.78 256	90.07 366	99.78 248	97.19 212	99.80 135	99.11 294

RRT-MVS		97.88 245	97.98 230	97.61 326	98.15 387	93.77 371	98.97 76	99.64 65	99.16 90	98.69 240	99.42 87	91.60 351	99.89 95	97.63 184	98.52 383	99.16 289

ET-MVSNet_ETH3D		94.30 387	93.21 398	97.58 329	98.14 388	94.47 339	94.78 424	93.24 446	94.72 380	89.56 458	95.87 421	78.57 437	99.81 216	96.91 235	97.11 431	98.46 377

ADS-MVSNet2		95.43 369	94.98 374	96.76 378	98.14 388	91.74 405	97.92 215	97.76 373	90.23 436	96.51 398	98.91 223	85.61 398	99.85 154	92.88 395	96.90 432	98.69 361

ADS-MVSNet		95.24 372	94.93 377	96.18 395	98.14 388	90.10 431	97.92 215	97.32 388	90.23 436	96.51 398	98.91 223	85.61 398	99.74 273	92.88 395	96.90 432	98.69 361

c3_l		97.36 288	97.37 277	97.31 348	98.09 391	93.25 381	95.01 419	99.16 257	97.05 296	98.77 232	98.72 265	92.88 334	99.64 329	96.93 234	99.76 165	99.05 299

FMVSNet3		97.50 274	97.24 285	98.29 265	98.08 392	95.83 289	97.86 224	98.91 299	97.89 217	98.95 194	98.95 217	87.06 386	99.81 216	97.77 174	99.69 199	99.23 264

PAPM		91.88 424	90.34 427	96.51 382	98.06 393	92.56 393	92.44 453	97.17 392	86.35 450	90.38 457	96.01 416	86.61 389	99.21 427	70.65 463	95.43 448	97.75 423

Effi-MVS+-dtu		98.26 206	97.90 241	99.35 76	98.02 394	99.49 6	98.02 195	99.16 257	98.29 179	97.64 334	97.99 353	96.44 234	99.95 26	96.66 262	98.93 357	98.60 369

eth_miper_zixun_eth		97.23 300	97.25 284	97.17 356	98.00 395	92.77 390	94.71 425	99.18 250	97.27 277	98.56 261	98.74 262	91.89 349	99.69 297	97.06 225	99.81 124	99.05 299

HY-MVS	95.94 13	95.90 355	95.35 365	97.55 334	97.95 396	94.79 327	98.81 96	96.94 401	92.28 421	95.17 426	98.57 298	89.90 368	99.75 268	91.20 423	97.33 427	98.10 403

UGNet		98.53 167	98.45 165	98.79 180	97.94 397	96.96 239	99.08 61	98.54 345	99.10 101	96.82 384	99.47 77	96.55 229	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		96.47 338	95.70 348	98.79 180	97.92 398	99.12 62	98.28 154	98.60 343	92.16 422	95.54 421	96.17 414	94.77 298	99.52 376	89.62 435	98.23 390	97.72 425
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		96.86 322	96.55 329	97.79 302	97.91 399	94.21 346	97.56 271	98.87 306	97.49 253	99.06 168	99.05 182	80.72 425	99.80 224	98.44 125	99.82 119	99.37 219

API-MVS		97.04 313	96.91 305	97.42 345	97.88 400	98.23 130	98.18 165	98.50 348	97.57 242	97.39 357	96.75 402	96.77 215	99.15 431	90.16 433	99.02 345	94.88 456

myMVS_eth3d28		92.92 411	92.31 407	94.77 420	97.84 401	87.59 443	96.19 369	96.11 416	97.08 295	94.27 436	93.49 452	66.07 459	98.78 444	91.78 411	97.93 409	97.92 413

miper_ehance_all_eth		97.06 311	97.03 296	97.16 358	97.83 402	93.06 383	94.66 428	99.09 269	95.99 346	98.69 240	98.45 314	92.73 339	99.61 342	96.79 248	99.03 342	98.82 338

cl____		97.02 314	96.83 310	97.58 329	97.82 403	94.04 353	94.66 428	99.16 257	97.04 297	98.63 248	98.71 266	88.68 379	99.69 297	97.00 227	99.81 124	99.00 311

DIV-MVS_self_test		97.02 314	96.84 309	97.58 329	97.82 403	94.03 354	94.66 428	99.16 257	97.04 297	98.63 248	98.71 266	88.69 377	99.69 297	97.00 227	99.81 124	99.01 307

CANet		97.87 247	97.76 248	98.19 276	97.75 405	95.51 299	96.76 333	99.05 275	97.74 227	96.93 373	98.21 336	95.59 272	99.89 95	97.86 169	99.93 54	99.19 279

UBG		93.25 405	92.32 406	96.04 400	97.72 406	90.16 430	95.92 387	95.91 421	96.03 344	93.95 444	93.04 455	69.60 449	99.52 376	90.72 431	97.98 407	98.45 380

mvsany_test1		97.60 268	97.54 266	97.77 304	97.72 406	95.35 309	95.36 410	97.13 394	94.13 395	99.71 48	99.33 108	97.93 127	99.30 418	97.60 188	98.94 356	98.67 365

PVSNet_0	89.98 21	91.15 425	90.30 428	93.70 433	97.72 406	84.34 457	90.24 456	97.42 383	90.20 439	93.79 445	93.09 454	90.90 361	98.89 442	86.57 446	72.76 463	97.87 416

CR-MVSNet		96.28 343	95.95 342	97.28 350	97.71 409	94.22 344	98.11 177	98.92 297	92.31 420	96.91 376	99.37 96	85.44 401	99.81 216	97.39 203	97.36 425	97.81 419

RPMNet		97.02 314	96.93 301	97.30 349	97.71 409	94.22 344	98.11 177	99.30 210	99.37 59	96.91 376	99.34 105	86.72 388	99.87 132	97.53 193	97.36 425	97.81 419

ETVMVS		92.60 414	91.08 423	97.18 354	97.70 411	93.65 376	96.54 345	95.70 424	96.51 322	94.68 432	92.39 458	61.80 465	99.50 382	86.97 443	97.41 421	98.40 388

pmmvs3		95.03 376	94.40 383	96.93 367	97.70 411	92.53 394	95.08 417	97.71 375	88.57 446	97.71 330	98.08 347	79.39 432	99.82 200	96.19 299	99.11 336	98.43 385

baseline2		93.73 397	92.83 403	96.42 385	97.70 411	91.28 416	96.84 329	89.77 457	93.96 400	92.44 452	95.93 419	79.14 433	99.77 254	92.94 393	96.76 436	98.21 397

WBMVS		95.18 373	94.78 379	96.37 386	97.68 414	89.74 433	95.80 393	98.73 334	97.54 248	98.30 283	98.44 315	70.06 447	99.82 200	96.62 265	99.87 95	99.54 135

tpm		94.67 381	94.34 385	95.66 407	97.68 414	88.42 437	97.88 220	94.90 431	94.46 386	96.03 411	98.56 299	78.66 435	99.79 237	95.88 312	95.01 450	98.78 350

CANet_DTU		97.26 296	97.06 295	97.84 298	97.57 416	94.65 335	96.19 369	98.79 323	97.23 285	95.14 427	98.24 333	93.22 326	99.84 172	97.34 205	99.84 108	99.04 303

testing11		93.08 408	92.02 413	96.26 391	97.56 417	90.83 425	96.32 361	95.70 424	96.47 326	92.66 451	93.73 448	64.36 463	99.59 349	93.77 378	97.57 414	98.37 392

tpm2		93.09 407	92.58 405	94.62 422	97.56 417	86.53 446	97.66 254	95.79 423	86.15 451	94.07 441	98.23 335	75.95 440	99.53 372	90.91 428	96.86 435	97.81 419

testing91		93.32 403	92.27 408	96.47 384	97.54 419	91.25 417	96.17 373	96.76 405	97.18 289	93.65 447	93.50 451	65.11 462	99.63 332	93.04 392	97.45 418	98.53 374

TR-MVS		95.55 366	95.12 372	96.86 374	97.54 419	93.94 362	96.49 350	96.53 410	94.36 391	97.03 371	96.61 405	94.26 310	99.16 430	86.91 445	96.31 440	97.47 433

testing99		93.04 409	91.98 416	96.23 393	97.53 421	90.70 427	96.35 359	95.94 420	96.87 307	93.41 448	93.43 453	63.84 464	99.59 349	93.24 390	97.19 428	98.40 388

1314		95.74 360	95.60 352	96.17 396	97.53 421	92.75 391	98.07 185	98.31 357	91.22 431	94.25 437	96.68 403	95.53 273	99.03 433	91.64 415	97.18 429	96.74 443

CostFormer		93.97 393	93.78 391	94.51 423	97.53 421	85.83 449	97.98 207	95.96 419	89.29 444	94.99 429	98.63 289	78.63 436	99.62 335	94.54 351	96.50 437	98.09 404

FMVSNet5		96.01 351	95.20 370	98.41 250	97.53 421	96.10 275	98.74 97	99.50 113	97.22 288	98.03 309	99.04 184	69.80 448	99.88 113	97.27 208	99.71 189	99.25 259

PMMVS		96.51 334	95.98 341	98.09 281	97.53 421	95.84 288	94.92 421	98.84 315	91.58 426	96.05 410	95.58 425	95.68 269	99.66 321	95.59 328	98.09 400	98.76 353

reproduce_monomvs		95.00 378	95.25 367	94.22 426	97.51 426	83.34 458	97.86 224	98.44 350	98.51 162	99.29 133	99.30 114	67.68 453	99.56 361	98.89 94	99.81 124	99.77 48

PAPR		95.29 370	94.47 381	97.75 308	97.50 427	95.14 318	94.89 422	98.71 336	91.39 430	95.35 425	95.48 430	94.57 301	99.14 432	84.95 448	97.37 423	98.97 316

testing222		91.96 422	90.37 426	96.72 379	97.47 428	92.59 392	96.11 375	94.76 432	96.83 309	92.90 450	92.87 456	57.92 466	99.55 365	86.93 444	97.52 415	98.00 410

PatchT		96.65 330	96.35 334	97.54 335	97.40 429	95.32 311	97.98 207	96.64 407	99.33 64	96.89 380	99.42 87	84.32 409	99.81 216	97.69 183	97.49 416	97.48 432

tpm cat1		93.29 404	93.13 401	93.75 432	97.39 430	84.74 452	97.39 289	97.65 379	83.39 456	94.16 438	98.41 317	82.86 420	99.39 405	91.56 417	95.35 449	97.14 438

PatchmatchNet		95.58 365	95.67 350	95.30 416	97.34 431	87.32 444	97.65 256	96.65 406	95.30 367	97.07 367	98.69 275	84.77 404	99.75 268	94.97 341	98.64 376	98.83 337
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 289	96.97 299	98.50 241	97.31 432	96.47 266	98.18 165	98.92 297	98.95 124	98.78 229	99.37 96	85.44 401	99.85 154	95.96 310	99.83 115	99.17 286

LS3D		98.63 149	98.38 177	99.36 70	97.25 433	99.38 13	99.12 60	99.32 197	99.21 79	98.44 274	98.88 233	97.31 180	99.80 224	96.58 268	99.34 297	98.92 325

IB-MVS	91.63 19	92.24 420	90.90 424	96.27 390	97.22 434	91.24 418	94.36 437	93.33 445	92.37 419	92.24 454	94.58 445	66.20 458	99.89 95	93.16 391	94.63 452	97.66 427
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		92.38 417	91.76 420	94.21 427	97.16 435	84.65 453	95.42 408	88.45 459	95.96 347	96.17 405	95.84 423	66.36 456	99.71 287	91.87 410	98.64 376	98.28 395

tpmrst		95.07 375	95.46 358	93.91 430	97.11 436	84.36 456	97.62 261	96.96 399	94.98 374	96.35 403	98.80 252	85.46 400	99.59 349	95.60 327	96.23 441	97.79 422

Syy-MVS		96.04 350	95.56 356	97.49 340	97.10 437	94.48 338	96.18 371	96.58 408	95.65 355	94.77 430	92.29 459	91.27 357	99.36 408	98.17 142	98.05 404	98.63 367

myMVS_eth3d		91.92 423	90.45 425	96.30 388	97.10 437	90.90 423	96.18 371	96.58 408	95.65 355	94.77 430	92.29 459	53.88 467	99.36 408	89.59 436	98.05 404	98.63 367

MDTV_nov1_ep13			95.22 369		97.06 439	83.20 459	97.74 243	96.16 414	94.37 390	96.99 372	98.83 246	83.95 413	99.53 372	93.90 372	97.95 408

MVS		93.19 406	92.09 411	96.50 383	96.91 440	94.03 354	98.07 185	98.06 368	68.01 461	94.56 435	96.48 408	95.96 260	99.30 418	83.84 450	96.89 434	96.17 448

E-PMN		94.17 389	94.37 384	93.58 434	96.86 441	85.71 450	90.11 458	97.07 395	98.17 193	97.82 325	97.19 394	84.62 406	98.94 438	89.77 434	97.68 413	96.09 452

JIA-IIPM		95.52 367	95.03 373	97.00 363	96.85 442	94.03 354	96.93 324	95.82 422	99.20 81	94.63 434	99.71 22	83.09 418	99.60 345	94.42 357	94.64 451	97.36 436

EMVS		93.83 395	94.02 387	93.23 439	96.83 443	84.96 451	89.77 459	96.32 412	97.92 214	97.43 354	96.36 413	86.17 393	98.93 439	87.68 441	97.73 412	95.81 453

cl22		95.79 359	95.39 363	96.98 365	96.77 444	92.79 389	94.40 436	98.53 346	94.59 383	97.89 317	98.17 339	82.82 421	99.24 424	96.37 288	99.03 342	98.92 325

WB-MVSnew		95.73 361	95.57 355	96.23 393	96.70 445	90.70 427	96.07 377	93.86 442	95.60 357	97.04 369	95.45 434	96.00 253	99.55 365	91.04 425	98.31 388	98.43 385

dp		93.47 401	93.59 394	93.13 440	96.64 446	81.62 465	97.66 254	96.42 411	92.80 415	96.11 407	98.64 287	78.55 438	99.59 349	93.31 388	92.18 459	98.16 400

MonoMVSNet		96.25 345	96.53 331	95.39 414	96.57 447	91.01 421	98.82 95	97.68 378	98.57 157	98.03 309	99.37 96	90.92 360	97.78 455	94.99 339	93.88 455	97.38 435

test-LLR		93.90 394	93.85 389	94.04 428	96.53 448	84.62 454	94.05 442	92.39 448	96.17 336	94.12 439	95.07 435	82.30 422	99.67 310	95.87 315	98.18 393	97.82 417

test-mter		92.33 419	91.76 420	94.04 428	96.53 448	84.62 454	94.05 442	92.39 448	94.00 399	94.12 439	95.07 435	65.63 461	99.67 310	95.87 315	98.18 393	97.82 417

TESTMET0.1,1		92.19 421	91.77 419	93.46 435	96.48 450	82.80 461	94.05 442	91.52 453	94.45 388	94.00 442	94.88 441	66.65 455	99.56 361	95.78 320	98.11 399	98.02 407

MVS_0304		97.44 282	97.01 298	98.72 196	96.42 451	96.74 252	97.20 309	91.97 451	98.46 165	98.30 283	98.79 254	92.74 338	99.91 72	99.30 61	99.94 49	99.52 147

miper_enhance_ethall		96.01 351	95.74 346	96.81 375	96.41 452	92.27 401	93.69 447	98.89 303	91.14 433	98.30 283	97.35 392	90.58 363	99.58 356	96.31 292	99.03 342	98.60 369

tpmvs		95.02 377	95.25 367	94.33 424	96.39 453	85.87 447	98.08 182	96.83 404	95.46 362	95.51 423	98.69 275	85.91 396	99.53 372	94.16 363	96.23 441	97.58 430

CMPMVS	75.91 23	96.29 342	95.44 360	98.84 170	96.25 454	98.69 94	97.02 317	99.12 264	88.90 445	97.83 323	98.86 236	89.51 372	98.90 441	91.92 408	99.51 264	98.92 325
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 382	93.69 392	96.99 364	96.05 455	93.61 378	94.97 420	93.49 443	96.17 336	97.57 341	94.88 441	82.30 422	99.01 436	93.60 381	94.17 454	98.37 392

EPMVS		93.72 398	93.27 397	95.09 419	96.04 456	87.76 441	98.13 172	85.01 464	94.69 381	96.92 374	98.64 287	78.47 439	99.31 416	95.04 338	96.46 438	98.20 398

cascas		94.79 380	94.33 386	96.15 399	96.02 457	92.36 399	92.34 454	99.26 230	85.34 453	95.08 428	94.96 440	92.96 333	98.53 448	94.41 360	98.59 380	97.56 431

MVStest1		95.86 356	95.60 352	96.63 380	95.87 458	91.70 406	97.93 212	98.94 291	98.03 204	99.56 71	99.66 32	71.83 445	98.26 451	99.35 57	99.24 313	99.91 13

gg-mvs-nofinetune		92.37 418	91.20 422	95.85 402	95.80 459	92.38 398	99.31 30	81.84 466	99.75 11	91.83 455	99.74 18	68.29 450	99.02 434	87.15 442	97.12 430	96.16 449

gm-plane-assit					94.83 460	81.97 463			88.07 448		94.99 438		99.60 345	91.76 412

GG-mvs-BLEND				94.76 421	94.54 461	92.13 403	99.31 30	80.47 467		88.73 461	91.01 461	67.59 454	98.16 454	82.30 455	94.53 453	93.98 457

UWE-MVS-28		90.22 426	89.28 429	93.02 441	94.50 462	82.87 460	96.52 348	87.51 460	95.21 370	92.36 453	96.04 415	71.57 446	98.25 452	72.04 462	97.77 411	97.94 412

EPNet_dtu		94.93 379	94.78 379	95.38 415	93.58 463	87.68 442	96.78 331	95.69 426	97.35 269	89.14 460	98.09 346	88.15 384	99.49 385	94.95 342	99.30 304	98.98 313
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 430	75.95 433	77.12 446	92.39 464	67.91 470	90.16 457	59.44 471	82.04 457	89.42 459	94.67 444	49.68 469	81.74 464	48.06 464	77.66 462	81.72 460

KD-MVS_2432*1600		92.87 412	91.99 414	95.51 411	91.37 465	89.27 434	94.07 440	98.14 364	95.42 363	97.25 362	96.44 410	67.86 451	99.24 424	91.28 421	96.08 444	98.02 407

miper_refine_blended		92.87 412	91.99 414	95.51 411	91.37 465	89.27 434	94.07 440	98.14 364	95.42 363	97.25 362	96.44 410	67.86 451	99.24 424	91.28 421	96.08 444	98.02 407

EPNet		96.14 348	95.44 360	98.25 268	90.76 467	95.50 301	97.92 215	94.65 433	98.97 120	92.98 449	98.85 239	89.12 375	99.87 132	95.99 308	99.68 204	99.39 209
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 431	68.95 434	70.34 447	87.68 468	65.00 471	91.11 455	59.90 470	69.02 460	74.46 465	88.89 462	48.58 470	68.03 466	28.61 465	72.33 464	77.99 461

test_method		79.78 428	79.50 431	80.62 444	80.21 469	45.76 472	70.82 460	98.41 354	31.08 464	80.89 464	97.71 369	84.85 403	97.37 457	91.51 418	80.03 461	98.75 354

tmp_tt		78.77 429	78.73 432	78.90 445	58.45 470	74.76 469	94.20 439	78.26 468	39.16 463	86.71 462	92.82 457	80.50 426	75.19 465	86.16 447	92.29 458	86.74 459

testmvs		17.12 433	20.53 436	6.87 449	12.05 471	4.20 474	93.62 448	6.73 472	4.62 467	10.41 467	24.33 464	8.28 472	3.56 468	9.69 467	15.07 465	12.86 464

test123		17.04 434	20.11 437	7.82 448	10.25 472	4.91 473	94.80 423	4.47 473	4.93 466	10.00 468	24.28 465	9.69 471	3.64 467	10.14 466	12.43 466	14.92 463

mmdepth		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

monomultidepth		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

test_blank		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

eth-test2					0.00 473

eth-test					0.00 473

uanet_test		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

DCPMVS		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

cdsmvs_eth3d_5k		24.66 432	32.88 435	0.00 450	0.00 473	0.00 475	0.00 461	99.10 267	0.00 468	0.00 469	97.58 377	99.21 18	0.00 469	0.00 468	0.00 467	0.00 465

pcd_1.5k_mvsjas		8.17 435	10.90 438	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	98.07 115	0.00 469	0.00 468	0.00 467	0.00 465

sosnet-low-res		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

sosnet		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

uncertanet		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

Regformer		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

ab-mvs-re		8.12 436	10.83 439	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	97.48 383	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

uanet		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

WAC-MVS						90.90 423								91.37 420

PC_three_1452									93.27 407	99.40 109	98.54 300	98.22 101	97.00 458	95.17 336	99.45 278	99.49 159

test_241102_TWO								99.30 210	98.03 204	99.26 140	99.02 187	97.51 167	99.88 113	96.91 235	99.60 233	99.66 75

test_0728_THIRD									98.17 193	99.08 166	99.02 187	97.89 131	99.88 113	97.07 223	99.71 189	99.70 65

GSMVS																98.81 343

sam_mvs1												84.74 405				98.81 343

sam_mvs												84.29 411

MTGPA								99.20 242

test_post1							97.59 268				20.48 467	83.07 419	99.66 321	94.16 363

test_post											21.25 466	83.86 414	99.70 293

patchmatchnet-post											98.77 258	84.37 408	99.85 154

MTMP							97.93 212	91.91 452

test9_res														93.28 389	99.15 329	99.38 217

agg_prior2														92.50 405	99.16 327	99.37 219

test_prior4						97.97 159	95.86 389

test_prior2							95.74 396		96.48 325	96.11 407	97.63 375	95.92 263		94.16 363	99.20 321

旧先验2							95.76 395		88.56 447	97.52 345			99.66 321	94.48 353

新几何2							95.93 385

无先验							95.74 396	98.74 333	89.38 443				99.73 279	92.38 407		99.22 269

原ACMM2							95.53 402

testdata2													99.79 237	92.80 399

segment_acmp												97.02 199

testdata1							95.44 407		96.32 331

plane_prior5								99.27 225					99.70 293	94.42 357	99.51 264	99.45 185

plane_prior4											97.98 354

plane_prior3						97.78 184			97.41 263	97.79 326

plane_prior2							97.77 237		98.20 190

plane_prior						97.65 193	97.07 316		96.72 315						99.36 293

n2								0.00 474

nn								0.00 474

door-mid								99.57 86

test11								98.87 306

door								99.41 162

HQP5-MVS						96.79 248

BP-MVS														92.82 397

HQP4-MVS										95.56 417			99.54 370			99.32 240

HQP3-MVS								99.04 278							99.26 311

HQP2-MVS												93.84 317

MDTV_nov1_ep13_2view						74.92 468	97.69 249		90.06 441	97.75 329		85.78 397		93.52 383		98.69 361

ACMMP++_ref															99.77 152

ACMMP++															99.68 204

Test By Simon												96.52 230

High-resolution multi-view benchmark