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	98.64 206	99.94 2	98.51 108	99.32 26	99.75 42	99.58 37	98.60 256	99.62 40	98.22 102	99.51 383	97.70 182	99.73 174	97.89 416
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 81	99.44 51	99.78 39	99.76 15	96.39 237	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 65	99.48 43	99.92 8	99.71 22	98.07 116	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 53	98.90 130	99.43 101	99.35 102	98.86 34	99.67 312	97.81 171	99.81 126	99.24 264

APD_test2		99.25 41	99.16 60	99.51 48	99.89 6	99.63 4	98.71 104	99.69 53	98.90 130	99.43 101	99.35 102	98.86 34	99.67 312	97.81 171	99.81 126	99.24 264

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 53	98.93 126	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 74	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 47	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 62	99.09 105	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 95	99.11 95	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 79	99.59 35	99.71 48	99.57 49	97.12 193	99.90 79	99.21 69	99.87 95	99.54 136

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 81	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		98.75 125	98.62 137	99.16 114	99.83 18	97.96 162	99.28 40	98.20 363	99.37 59	99.70 50	99.65 36	92.65 342	99.93 52	99.04 83	99.84 109	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 69	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	98.86 104	99.36 70	99.82 19	98.55 103	97.47 284	99.57 88	99.37 59	99.21 153	99.61 43	96.76 219	99.83 190	98.06 150	99.83 116	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 69	99.30 69	99.65 62	99.60 45	99.16 22	99.82 200	99.07 79	99.83 116	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 88	99.39 57	99.75 44	99.62 40	99.17 20	99.83 190	99.06 81	99.62 228	99.66 75

K. test v3		98.00 236	97.66 261	99.03 141	99.79 23	97.56 198	99.19 52	92.47 449	99.62 32	99.52 83	99.66 32	89.61 373	99.96 14	99.25 66	99.81 126	99.56 123

test_fmvsmconf0.1_n		99.49 15	99.54 14	99.34 79	99.78 24	98.11 139	97.77 238	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		98.83 109	98.66 130	99.34 79	99.78 24	99.47 9	98.42 144	99.45 140	98.28 182	98.98 186	99.19 144	97.76 143	99.58 358	96.57 272	99.55 255	98.97 318

test_vis3_rt		99.14 60	99.17 58	99.07 131	99.78 24	98.38 115	98.92 82	99.94 2	97.80 224	99.91 12	99.67 30	97.15 192	98.91 442	99.76 22	99.56 251	99.92 12

EGC-MVSNET		85.24 429	80.54 432	99.34 79	99.77 27	99.20 39	99.08 61	99.29 220	12.08 467	20.84 468	99.42 87	97.55 162	99.85 154	97.08 224	99.72 182	98.96 320

Anonymous20240521		98.69 136	98.87 100	98.16 281	99.77 27	95.11 322	99.08 61	99.44 148	99.34 63	99.33 124	99.55 57	94.10 317	99.94 41	99.25 66	99.96 28	99.42 198

FC-MVSNet-test		99.27 38	99.25 51	99.34 79	99.77 27	98.37 117	99.30 35	99.57 88	99.61 34	99.40 110	99.50 67	97.12 193	99.85 154	99.02 85	99.94 49	99.80 40

test_vis1_n		98.31 201	98.50 156	97.73 315	99.76 30	94.17 350	98.68 107	99.91 9	96.31 334	99.79 38	99.57 49	92.85 338	99.42 403	99.79 18	99.84 109	99.60 97

test_fmvs3		99.12 67	99.41 26	98.25 269	99.76 30	95.07 323	99.05 67	99.94 2	97.78 227	99.82 33	99.84 3	98.56 68	99.71 288	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 71	98.48 165	99.37 115	99.49 73	98.75 46	99.86 141	98.20 140	99.80 137	99.71 60

TDRefinement		99.42 24	99.38 29	99.55 28	99.76 30	99.33 21	99.68 6	99.71 47	99.38 58	99.53 81	99.61 43	98.64 56	99.80 224	98.24 135	99.84 109	99.52 148

fmvsm_s_conf0.1_n_a		99.17 52	99.30 44	98.80 178	99.75 34	96.59 258	97.97 212	99.86 16	98.22 185	99.88 21	99.71 22	98.59 62	99.84 172	99.73 26	99.98 12	99.98 3

tt0805		98.69 136	98.62 137	98.90 166	99.75 34	99.30 22	99.15 56	96.97 400	98.86 135	98.87 219	97.62 378	98.63 58	98.96 439	99.41 55	98.29 391	98.45 382

test_vis1_n_1920		98.40 185	98.92 93	96.81 377	99.74 36	90.76 428	98.15 170	99.91 9	98.33 173	99.89 18	99.55 57	95.07 288	99.88 113	99.76 22	99.93 54	99.79 42

FOURS1					99.73 37	99.67 3	99.43 15	99.54 104	99.43 53	99.26 141

PEN-MVS		99.41 25	99.34 36	99.62 9	99.73 37	99.14 57	99.29 36	99.54 104	99.62 32	99.56 72	99.42 87	98.16 110	99.96 14	98.78 100	99.93 54	99.77 48

lessismore_v0				98.97 153	99.73 37	97.53 200		86.71 464		99.37 115	99.52 66	89.93 369	99.92 63	98.99 87	99.72 182	99.44 191

SteuartSystems-ACMMP		98.79 118	98.54 150	99.54 31	99.73 37	99.16 48	98.23 160	99.31 204	97.92 215	98.90 208	98.90 228	98.00 122	99.88 113	96.15 304	99.72 182	99.58 112
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 222	98.15 214	98.22 275	99.73 37	95.15 319	97.36 296	99.68 58	94.45 390	98.99 185	99.27 121	96.87 208	99.94 41	97.13 221	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 95	99.27 137	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		98.71 129	98.74 114	98.62 212	99.72 43	96.08 281	98.74 97	98.64 343	99.74 13	99.67 58	99.24 134	94.57 303	99.95 26	99.11 76	99.24 315	99.82 35

test_f		98.67 144	98.87 100	98.05 290	99.72 43	95.59 295	98.51 128	99.81 31	96.30 336	99.78 39	99.82 5	96.14 247	98.63 449	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 99	98.30 177	99.65 62	99.45 83	99.22 17	99.76 260	98.44 126	99.77 154	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	98.64 206	99.71 47	96.10 276	97.87 224	99.85 18	98.56 161	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	99.53 107	99.53 40	99.46 96	99.41 91	98.23 99	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	99.51 112	99.64 27	99.56 72	99.46 79	98.23 99	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 99	99.46 48	99.50 89	99.34 106	97.30 182	99.93 52	98.90 92	99.93 54	99.77 48

HPM-MVS_fast		99.01 80	98.82 107	99.57 21	99.71 47	99.35 17	99.00 72	99.50 115	97.33 271	98.94 203	98.86 238	98.75 46	99.82 200	97.53 194	99.71 191	99.56 123

ACMH+	96.62 9	99.08 74	99.00 85	99.33 85	99.71 47	98.83 83	98.60 114	99.58 81	99.11 95	99.53 81	99.18 148	98.81 38	99.67 312	96.71 261	99.77 154	99.50 154

PMVS	91.26 20	97.86 250	97.94 238	97.65 322	99.71 47	97.94 164	98.52 123	98.68 339	98.99 118	97.52 347	99.35 102	97.41 175	98.18 455	91.59 418	99.67 212	96.82 444
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
KinetiMVS		99.03 78	99.02 81	99.03 141	99.70 55	97.48 203	98.43 141	99.29 220	99.70 16	99.60 69	99.07 176	96.13 248	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	99.52 111	99.48 43	99.24 147	99.41 91	96.79 216	99.82 200	98.69 110	99.88 91	99.76 53

VPNet		98.87 100	98.83 106	99.01 145	99.70 55	97.62 196	98.43 141	99.35 185	99.47 46	99.28 135	99.05 184	96.72 222	99.82 200	98.09 147	99.36 295	99.59 104

fmvsm_s_conf0.1_n_2		99.20 50	99.38 29	98.65 204	99.69 58	96.08 281	97.49 281	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		98.33 198	98.68 127	97.27 353	99.69 58	92.29 402	98.03 193	99.85 18	97.62 236	99.96 4	99.62 40	93.98 318	99.74 273	99.52 48	99.86 102	99.79 42

MP-MVS-pluss		98.57 160	98.23 202	99.60 15	99.69 58	99.35 17	97.16 315	99.38 171	94.87 380	98.97 190	98.99 205	98.01 121	99.88 113	97.29 209	99.70 198	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	99.48 124	99.69 18	99.63 65	99.68 25	99.03 24	99.96 14	97.97 160	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	99.30 212	99.69 18	99.63 65	99.68 25	99.25 16	99.96 14	97.25 212	99.92 67	99.57 117

test_fmvs1_n		98.09 227	98.28 193	97.52 339	99.68 61	93.47 381	98.63 110	99.93 5	95.41 368	99.68 56	99.64 37	91.88 352	99.48 390	99.82 11	99.87 95	99.62 87

CHOSEN 1792x2688		97.49 279	97.14 294	98.54 234	99.68 61	96.09 279	96.50 351	99.62 71	91.58 428	98.84 222	98.97 212	92.36 344	99.88 113	96.76 254	99.95 38	99.67 73

tfpnnormal		98.90 96	98.90 95	98.91 163	99.67 65	97.82 179	99.00 72	99.44 148	99.45 49	99.51 88	99.24 134	98.20 105	99.86 141	95.92 313	99.69 201	99.04 305

MTAPA		98.88 99	98.64 133	99.61 13	99.67 65	99.36 16	98.43 141	99.20 244	98.83 139	98.89 211	98.90 228	96.98 203	99.92 63	97.16 216	99.70 198	99.56 123

test_fmvsmvis_n_1920		99.26 40	99.49 16	98.54 234	99.66 67	96.97 238	98.00 200	99.85 18	99.24 74	99.92 8	99.50 67	99.39 12	99.95 26	99.89 3	99.98 12	98.71 359

mvs5depth		99.30 34	99.59 12	98.44 248	99.65 68	95.35 311	99.82 3	99.94 2	99.83 7	99.42 105	99.94 2	98.13 113	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	97.05 234	97.80 233	99.76 39	98.70 144	99.78 39	99.11 167	98.79 42	99.95 26	99.85 5	99.96 28	99.83 32

WB-MVS		98.52 173	98.55 148	98.43 249	99.65 68	95.59 295	98.52 123	98.77 328	99.65 26	99.52 83	99.00 203	94.34 309	99.93 52	98.65 112	98.83 363	99.76 53

CP-MVSNet		99.21 48	99.09 73	99.56 26	99.65 68	98.96 77	99.13 58	99.34 191	99.42 54	99.33 124	99.26 127	97.01 201	99.94 41	98.74 105	99.93 54	99.79 42

HPM-MVS		98.79 118	98.53 152	99.59 19	99.65 68	99.29 24	99.16 54	99.43 154	96.74 316	98.61 254	98.38 323	98.62 59	99.87 132	96.47 284	99.67 212	99.59 104
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 153	98.36 182	99.42 64	99.65 68	99.42 11	98.55 119	99.57 88	97.72 230	98.90 208	99.26 127	96.12 250	99.52 378	95.72 324	99.71 191	99.32 242

NormalMVS		98.26 208	97.97 235	99.15 117	99.64 74	97.83 174	98.28 154	99.43 154	99.24 74	98.80 229	98.85 241	89.76 371	99.94 41	98.04 152	99.67 212	99.68 68

lecture		99.25 41	99.12 68	99.62 9	99.64 74	99.40 12	98.89 87	99.51 112	99.19 85	99.37 115	99.25 132	98.36 82	99.88 113	98.23 137	99.67 212	99.59 104

fmvsm_l_conf0.5_n		99.21 48	99.28 46	99.02 144	99.64 74	97.28 217	97.82 229	99.76 39	98.73 141	99.82 33	99.09 175	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	97.68 251	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.		98.63 150	98.49 161	99.06 137	99.64 74	97.90 168	98.51 128	98.94 293	96.96 302	99.24 147	98.89 234	97.83 135	99.81 216	96.88 244	99.49 275	99.48 172
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 112	98.72 118	99.12 120	99.64 74	98.54 106	97.98 208	99.68 58	97.62 236	99.34 122	99.18 148	97.54 163	99.77 254	97.79 173	99.74 171	99.04 305

Elysia		99.15 57	99.14 66	99.18 109	99.63 80	97.92 165	98.50 130	99.43 154	99.67 21	99.70 50	99.13 163	96.66 225	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	99.43 154	99.67 21	99.70 50	99.13 163	96.66 225	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	99.54 104	99.31 67	99.62 68	99.53 63	97.36 179	99.86 141	99.24 68	99.71 191	99.39 211

EU-MVSNet		97.66 267	98.50 156	95.13 419	99.63 80	85.84 450	98.35 150	98.21 362	98.23 184	99.54 77	99.46 79	95.02 289	99.68 308	98.24 135	99.87 95	99.87 21

HyFIR lowres test		97.19 305	96.60 329	98.96 154	99.62 84	97.28 217	95.17 416	99.50 115	94.21 395	99.01 182	98.32 331	86.61 391	99.99 2	97.10 223	99.84 109	99.60 97

fmvsm_l_conf0.5_n_9		99.32 33	99.43 24	98.98 151	99.59 85	97.18 227	97.44 287	99.83 25	99.56 38	99.91 12	99.34 106	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	97.82 229	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

FE-MVSNET		98.59 157	98.50 156	98.87 167	99.58 87	97.30 215	98.08 182	99.74 43	96.94 304	98.97 190	99.10 170	96.94 204	99.74 273	97.33 207	99.86 102	99.55 130

mmtdpeth		99.30 34	99.42 25	98.92 162	99.58 87	96.89 245	99.48 13	99.92 7	99.92 2	98.26 291	99.80 11	98.33 88	99.91 72	99.56 39	99.95 38	99.97 4

ACMMP_NAP		98.75 125	98.48 162	99.57 21	99.58 87	99.29 24	97.82 229	99.25 233	96.94 304	98.78 231	99.12 166	98.02 120	99.84 172	97.13 221	99.67 212	99.59 104

nrg030		99.40 26	99.35 34	99.54 31	99.58 87	99.13 60	98.98 75	99.48 124	99.68 20	99.46 96	99.26 127	98.62 59	99.73 280	99.17 73	99.92 67	99.76 53

VDDNet		98.21 215	97.95 236	99.01 145	99.58 87	97.74 187	99.01 70	97.29 391	99.67 21	98.97 190	99.50 67	90.45 366	99.80 224	97.88 166	99.20 323	99.48 172

COLMAP_ROB	96.50 10	98.99 83	98.85 105	99.41 66	99.58 87	99.10 65	98.74 97	99.56 95	99.09 105	99.33 124	99.19 144	98.40 79	99.72 287	95.98 311	99.76 167	99.42 198
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 93	97.73 189	97.93 213	99.83 25	99.22 77	99.93 6	99.30 115	99.42 11	99.96 14	99.85 5	99.99 5	99.29 251

ZNCC-MVS		98.68 141	98.40 174	99.54 31	99.57 93	99.21 33	98.46 138	99.29 220	97.28 277	98.11 303	98.39 321	98.00 122	99.87 132	96.86 247	99.64 222	99.55 130

MSP-MVS		98.40 185	98.00 230	99.61 13	99.57 93	99.25 29	98.57 117	99.35 185	97.55 247	99.31 132	97.71 371	94.61 302	99.88 113	96.14 305	99.19 326	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		98.32 199	98.39 177	98.13 282	99.57 93	95.54 298	97.78 235	99.49 122	97.37 268	99.19 155	97.65 375	98.96 29	99.49 387	96.50 283	98.99 351	99.34 234

MP-MVS		98.46 179	98.09 219	99.54 31	99.57 93	99.22 32	98.50 130	99.19 248	97.61 239	97.58 341	98.66 284	97.40 176	99.88 113	94.72 350	99.60 235	99.54 136
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 129	98.46 166	99.47 60	99.57 93	98.97 73	98.23 160	99.48 124	96.60 321	99.10 165	99.06 177	98.71 50	99.83 190	95.58 331	99.78 148	99.62 87

LGP-MVS_train				99.47 60	99.57 93	98.97 73		99.48 124	96.60 321	99.10 165	99.06 177	98.71 50	99.83 190	95.58 331	99.78 148	99.62 87

IS-MVSNet		98.19 218	97.90 243	99.08 129	99.57 93	97.97 159	99.31 30	98.32 358	99.01 117	98.98 186	99.03 188	91.59 354	99.79 237	95.49 333	99.80 137	99.48 172

viewdifsd2359ckpt11		98.84 106	99.04 78	98.24 271	99.56 101	95.51 300	97.38 291	99.70 51	99.16 90	99.57 70	99.40 94	98.26 95	99.71 288	98.55 121	99.82 120	99.50 154

viewmsd2359difaftdt		98.84 106	99.04 78	98.24 271	99.56 101	95.51 300	97.38 291	99.70 51	99.16 90	99.57 70	99.40 94	98.26 95	99.71 288	98.55 121	99.82 120	99.50 154

dcpmvs_2		98.78 120	99.11 69	97.78 305	99.56 101	93.67 376	99.06 65	99.86 16	99.50 42	99.66 59	99.26 127	97.21 190	99.99 2	98.00 157	99.91 76	99.68 68

test_0402		98.76 124	98.71 121	98.93 159	99.56 101	98.14 137	98.45 140	99.34 191	99.28 71	98.95 196	98.91 225	98.34 87	99.79 237	95.63 328	99.91 76	98.86 337

EPP-MVSNet		98.30 202	98.04 226	99.07 131	99.56 101	97.83 174	99.29 36	98.07 369	99.03 115	98.59 258	99.13 163	92.16 348	99.90 79	96.87 245	99.68 206	99.49 161

ACMMP		98.75 125	98.50 156	99.52 44	99.56 101	99.16 48	98.87 88	99.37 175	97.16 292	98.82 226	99.01 200	97.71 146	99.87 132	96.29 296	99.69 201	99.54 136
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	98.78 184	99.55 107	96.59 258	97.79 234	99.82 30	98.21 187	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	98.61 215	99.55 107	96.09 279	97.74 244	99.81 31	98.55 162	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	99.55 107	98.24 126	99.20 48	99.44 148	99.21 79	99.43 101	99.55 57	97.82 138	99.86 141	98.42 128	99.89 89	99.41 201

Vis-MVSNet (Re-imp)		97.46 281	97.16 291	98.34 261	99.55 107	96.10 276	98.94 80	98.44 352	98.32 175	98.16 297	98.62 293	88.76 378	99.73 280	93.88 376	99.79 143	99.18 284

ACMM	96.08 12	98.91 94	98.73 116	99.48 56	99.55 107	99.14 57	98.07 186	99.37 175	97.62 236	99.04 178	98.96 215	98.84 36	99.79 237	97.43 202	99.65 220	99.49 161
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 133	98.97 89	97.89 298	99.54 112	94.05 353	98.55 119	99.92 7	96.78 314	99.72 46	99.78 13	96.60 229	99.67 312	99.91 2	99.90 83	99.94 10

mPP-MVS		98.64 148	98.34 185	99.54 31	99.54 112	99.17 44	98.63 110	99.24 238	97.47 255	98.09 305	98.68 279	97.62 155	99.89 95	96.22 299	99.62 228	99.57 117

XVG-ACMP-BASELINE		98.56 161	98.34 185	99.22 105	99.54 112	98.59 100	97.71 247	99.46 136	97.25 280	98.98 186	98.99 205	97.54 163	99.84 172	95.88 314	99.74 171	99.23 266

viewmacassd2359aftdt		98.86 103	98.87 100	98.83 172	99.53 115	97.32 214	97.70 249	99.64 67	98.22 185	99.25 145	99.27 121	98.40 79	99.61 344	97.98 159	99.87 95	99.55 130

region2R		98.69 136	98.40 174	99.54 31	99.53 115	99.17 44	98.52 123	99.31 204	97.46 260	98.44 276	98.51 307	97.83 135	99.88 113	96.46 285	99.58 244	99.58 112

PGM-MVS		98.66 145	98.37 181	99.55 28	99.53 115	99.18 43	98.23 160	99.49 122	97.01 301	98.69 242	98.88 235	98.00 122	99.89 95	95.87 317	99.59 239	99.58 112

Patchmatch-RL test		97.26 298	97.02 299	97.99 294	99.52 118	95.53 299	96.13 376	99.71 47	97.47 255	99.27 137	99.16 154	84.30 412	99.62 337	97.89 163	99.77 154	98.81 345

ACMMPR		98.70 133	98.42 172	99.54 31	99.52 118	99.14 57	98.52 123	99.31 204	97.47 255	98.56 263	98.54 302	97.75 144	99.88 113	96.57 272	99.59 239	99.58 112

fmvsm_s_conf0.5_n_9		99.17 52	99.38 29	98.53 236	99.51 120	95.82 291	97.62 262	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		98.16 224	98.07 224	98.41 251	99.51 120	95.86 288	98.00 200	95.14 432	98.97 121	99.43 101	99.24 134	93.25 326	99.84 172	99.21 69	99.87 95	99.54 136

fmvsm_s_conf0.5_n_8		99.13 64	99.26 49	98.74 195	99.51 120	96.44 268	97.65 257	99.65 65	99.66 24	99.78 39	99.48 74	97.92 129	99.93 52	99.72 28	99.95 38	99.87 21

GST-MVS		98.61 154	98.30 191	99.52 44	99.51 120	99.20 39	98.26 158	99.25 233	97.44 263	98.67 245	98.39 321	97.68 147	99.85 154	96.00 309	99.51 266	99.52 148

Anonymous20231206		98.21 215	98.21 203	98.20 276	99.51 120	95.43 309	98.13 172	99.32 199	96.16 340	98.93 204	98.82 251	96.00 255	99.83 190	97.32 208	99.73 174	99.36 228

ACMP	95.32 15	98.41 183	98.09 219	99.36 70	99.51 120	98.79 86	97.68 251	99.38 171	95.76 355	98.81 228	98.82 251	98.36 82	99.82 200	94.75 347	99.77 154	99.48 172
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LuminaMVS		98.39 191	98.20 204	98.98 151	99.50 126	97.49 201	97.78 235	97.69 378	98.75 140	99.49 90	99.25 132	92.30 346	99.94 41	99.14 74	99.88 91	99.50 154

DVP-MVS		98.77 123	98.52 153	99.52 44	99.50 126	99.21 33	98.02 196	98.84 317	97.97 209	99.08 167	99.02 189	97.61 157	99.88 113	96.99 231	99.63 225	99.48 172
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	99.50 126	99.23 31	98.02 196	99.32 199					99.88 113	96.99 231	99.63 225	99.68 68

test0726					99.50 126	99.21 33	98.17 168	99.35 185	97.97 209	99.26 141	99.06 177	97.61 157

AllTest		98.44 181	98.20 204	99.16 114	99.50 126	98.55 103	98.25 159	99.58 81	96.80 312	98.88 215	99.06 177	97.65 150	99.57 360	94.45 357	99.61 233	99.37 221

TestCases				99.16 114	99.50 126	98.55 103		99.58 81	96.80 312	98.88 215	99.06 177	97.65 150	99.57 360	94.45 357	99.61 233	99.37 221

XVG-OURS		98.53 169	98.34 185	99.11 122	99.50 126	98.82 85	95.97 382	99.50 115	97.30 275	99.05 176	98.98 210	99.35 14	99.32 417	95.72 324	99.68 206	99.18 284

EG-PatchMatch MVS		98.99 83	99.01 83	98.94 157	99.50 126	97.47 204	98.04 191	99.59 79	98.15 202	99.40 110	99.36 101	98.58 67	99.76 260	98.78 100	99.68 206	99.59 104

fmvsm_s_conf0.5_n_2		99.14 60	99.31 41	98.63 210	99.49 134	96.08 281	97.38 291	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	98.72 118	99.49 54	99.49 134	99.17 44	98.10 179	99.31 204	98.03 205	99.66 59	99.02 189	98.36 82	99.88 113	96.91 237	99.62 228	99.41 201

IU-MVS					99.49 134	99.15 52		98.87 308	92.97 413	99.41 107				96.76 254	99.62 228	99.66 75

test_241102_ONE					99.49 134	99.17 44		99.31 204	97.98 208	99.66 59	98.90 228	98.36 82	99.48 390

UA-Net		99.47 16	99.40 27	99.70 2	99.49 134	99.29 24	99.80 4	99.72 45	99.82 8	99.04 178	99.81 8	98.05 119	99.96 14	98.85 96	99.99 5	99.86 27

HFP-MVS		98.71 129	98.44 169	99.51 48	99.49 134	99.16 48	98.52 123	99.31 204	97.47 255	98.58 260	98.50 311	97.97 126	99.85 154	96.57 272	99.59 239	99.53 145

VPA-MVSNet		99.30 34	99.30 44	99.28 92	99.49 134	98.36 120	99.00 72	99.45 140	99.63 29	99.52 83	99.44 84	98.25 97	99.88 113	99.09 78	99.84 109	99.62 87

XVG-OURS-SEG-HR		98.49 176	98.28 193	99.14 118	99.49 134	98.83 83	96.54 347	99.48 124	97.32 273	99.11 162	98.61 295	99.33 15	99.30 420	96.23 298	98.38 387	99.28 253

114514_t		96.50 338	95.77 347	98.69 200	99.48 142	97.43 208	97.84 228	99.55 99	81.42 460	96.51 400	98.58 299	95.53 275	99.67 312	93.41 389	99.58 244	98.98 315

IterMVS-LS		98.55 165	98.70 124	98.09 283	99.48 142	94.73 333	97.22 310	99.39 169	98.97 121	99.38 113	99.31 114	96.00 255	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	99.47 144	97.22 222	97.40 289	99.83 25	97.61 239	99.85 27	99.30 115	98.80 40	99.95 26	99.71 30	99.90 83	99.78 45

v8		99.01 80	99.16 60	98.57 222	99.47 144	96.31 273	98.90 83	99.47 132	99.03 115	99.52 83	99.57 49	96.93 205	99.81 216	99.60 35	99.98 12	99.60 97

SSC-MVS3.2		98.53 169	98.79 110	97.74 312	99.46 146	93.62 379	96.45 353	99.34 191	99.33 64	98.93 204	98.70 275	97.90 130	99.90 79	99.12 75	99.92 67	99.69 67

fmvsm_s_conf0.5_n_3		99.22 47	99.37 32	98.78 184	99.46 146	96.58 261	97.65 257	99.72 45	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		98.72 128	98.45 167	99.53 38	99.46 146	99.21 33	98.65 108	99.34 191	98.62 151	97.54 345	98.63 291	97.50 169	99.83 190	96.79 250	99.53 261	99.56 123

X-MVStestdata		94.32 387	92.59 406	99.53 38	99.46 146	99.21 33	98.65 108	99.34 191	98.62 151	97.54 345	45.85 465	97.50 169	99.83 190	96.79 250	99.53 261	99.56 123

test20.03		98.78 120	98.77 113	98.78 184	99.46 146	97.20 225	97.78 235	99.24 238	99.04 114	99.41 107	98.90 228	97.65 150	99.76 260	97.70 182	99.79 143	99.39 211

guyue		98.01 235	97.93 240	98.26 268	99.45 151	95.48 304	98.08 182	96.24 415	98.89 132	99.34 122	99.14 161	91.32 358	99.82 200	99.07 79	99.83 116	99.48 172

CSCG		98.68 141	98.50 156	99.20 106	99.45 151	98.63 95	98.56 118	99.57 88	97.87 219	98.85 220	98.04 352	97.66 149	99.84 172	96.72 259	99.81 126	99.13 294

GeoE		99.05 77	98.99 87	99.25 100	99.44 153	98.35 121	98.73 101	99.56 95	98.42 168	98.91 207	98.81 253	98.94 30	99.91 72	98.35 130	99.73 174	99.49 161

v148		98.45 180	98.60 142	98.00 293	99.44 153	94.98 325	97.44 287	99.06 274	98.30 177	99.32 130	98.97 212	96.65 227	99.62 337	98.37 129	99.85 104	99.39 211

v10		98.97 87	99.11 69	98.55 229	99.44 153	96.21 275	98.90 83	99.55 99	98.73 141	99.48 91	99.60 45	96.63 228	99.83 190	99.70 31	99.99 5	99.61 95

V42		98.78 120	98.78 112	98.76 189	99.44 153	97.04 235	98.27 157	99.19 248	97.87 219	99.25 145	99.16 154	96.84 209	99.78 248	99.21 69	99.84 109	99.46 182

MDA-MVSNet-bldmvs		97.94 241	97.91 242	98.06 288	99.44 153	94.96 326	96.63 343	99.15 264	98.35 171	98.83 223	99.11 167	94.31 310	99.85 154	96.60 269	98.72 369	99.37 221

casdiffmvs_mvg		99.12 67	99.16 60	98.99 147	99.43 158	97.73 189	98.00 200	99.62 71	99.22 77	99.55 75	99.22 140	98.93 32	99.75 268	98.66 111	99.81 126	99.50 154
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 83	98.57 222	99.42 159	96.59 258	98.13 172	99.66 62	99.09 105	99.30 133	99.02 189	98.79 42	99.89 95	97.87 168	99.80 137	99.23 266

test1111		96.49 339	96.82 313	95.52 412	99.42 159	87.08 447	99.22 45	87.14 463	99.11 95	99.46 96	99.58 47	88.69 379	99.86 141	98.80 98	99.95 38	99.62 87

v2v482		98.56 161	98.62 137	98.37 258	99.42 159	95.81 292	97.58 270	99.16 259	97.90 217	99.28 135	99.01 200	95.98 260	99.79 237	99.33 58	99.90 83	99.51 151

OPM-MVS		98.56 161	98.32 189	99.25 100	99.41 162	98.73 91	97.13 317	99.18 252	97.10 295	98.75 237	98.92 223	98.18 106	99.65 328	96.68 263	99.56 251	99.37 221
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 229	98.08 222	98.04 291	99.41 162	94.59 339	94.59 434	99.40 167	97.50 252	98.82 226	98.83 248	96.83 211	99.84 172	97.50 196	99.81 126	99.71 60

test_one_0601					99.39 164	99.20 39		99.31 204	98.49 164	98.66 247	99.02 189	97.64 153

mvsany_test3		98.87 100	98.92 93	98.74 195	99.38 165	96.94 242	98.58 116	99.10 269	96.49 326	99.96 4	99.81 8	98.18 106	99.45 398	98.97 88	99.79 143	99.83 32

patch_mono-2		98.51 174	98.63 135	98.17 279	99.38 165	94.78 330	97.36 296	99.69 53	98.16 197	98.49 272	99.29 118	97.06 196	99.97 7	98.29 134	99.91 76	99.76 53

test2506		92.39 418	91.89 420	93.89 433	99.38 165	82.28 464	99.32 26	66.03 471	99.08 109	98.77 234	99.57 49	66.26 459	99.84 172	98.71 108	99.95 38	99.54 136

ECVR-MVS		96.42 341	96.61 327	95.85 404	99.38 165	88.18 442	99.22 45	86.00 465	99.08 109	99.36 118	99.57 49	88.47 384	99.82 200	98.52 123	99.95 38	99.54 136

casdiffmvs		98.95 90	99.00 85	98.81 176	99.38 165	97.33 212	97.82 229	99.57 88	99.17 89	99.35 120	99.17 152	98.35 86	99.69 299	98.46 125	99.73 174	99.41 201
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 81	98.76 189	99.38 165	97.26 219	98.49 133	99.50 115	98.86 135	99.19 155	99.06 177	98.23 99	99.69 299	98.71 108	99.76 167	99.33 239

TranMVSNet+NR-MVSNet		99.17 52	99.07 76	99.46 62	99.37 171	98.87 81	98.39 146	99.42 160	99.42 54	99.36 118	99.06 177	98.38 81	99.95 26	98.34 131	99.90 83	99.57 117

fmvsm_s_conf0.5_n_6		99.08 74	99.21 55	98.69 200	99.36 172	96.51 263	97.62 262	99.68 58	98.43 167	99.85 27	99.10 170	99.12 23	99.88 113	99.77 21	99.92 67	99.67 73

tttt0517		95.64 366	94.98 376	97.64 325	99.36 172	93.81 371	98.72 102	90.47 457	98.08 204	98.67 245	98.34 328	73.88 445	99.92 63	97.77 175	99.51 266	99.20 276

test_part2					99.36 172	99.10 65				99.05 176

v1144		98.60 155	98.66 130	98.41 251	99.36 172	95.90 286	97.58 270	99.34 191	97.51 251	99.27 137	99.15 158	96.34 242	99.80 224	99.47 52	99.93 54	99.51 151

CP-MVS		98.70 133	98.42 172	99.52 44	99.36 172	99.12 62	98.72 102	99.36 179	97.54 249	98.30 285	98.40 320	97.86 134	99.89 95	96.53 281	99.72 182	99.56 123

diffmvs_AUTHOR		98.50 175	98.59 144	98.23 274	99.35 177	95.48 304	96.61 344	99.60 75	98.37 169	98.90 208	99.00 203	97.37 178	99.76 260	98.22 138	99.85 104	99.46 182

Test_1112_low_res		96.99 320	96.55 331	98.31 264	99.35 177	95.47 307	95.84 394	99.53 107	91.51 430	96.80 387	98.48 314	91.36 357	99.83 190	96.58 270	99.53 261	99.62 87

DeepC-MVS	97.60 4	98.97 87	98.93 92	99.10 124	99.35 177	97.98 158	98.01 199	99.46 136	97.56 245	99.54 77	99.50 67	98.97 28	99.84 172	98.06 150	99.92 67	99.49 161
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 297	96.86 309	98.58 219	99.34 180	96.32 272	96.75 336	99.58 81	93.14 411	96.89 382	97.48 385	92.11 349	99.86 141	96.91 237	99.54 257	99.57 117

reproduce_model		99.15 57	98.97 89	99.67 4	99.33 181	99.44 10	98.15 170	99.47 132	99.12 94	99.52 83	99.32 113	98.31 89	99.90 79	97.78 174	99.73 174	99.66 75

MVSMamba_PlusPlus		98.83 109	98.98 88	98.36 259	99.32 182	96.58 261	98.90 83	99.41 164	99.75 11	98.72 240	99.50 67	96.17 246	99.94 41	99.27 63	99.78 148	98.57 375

fmvsm_s_conf0.5_n_4		99.01 80	99.22 53	98.38 255	99.31 183	95.48 304	97.56 272	99.73 44	98.87 133	99.75 44	99.27 121	98.80 40	99.86 141	99.80 16	99.90 83	99.81 38

SF-MVS		98.53 169	98.27 196	99.32 87	99.31 183	98.75 87	98.19 164	99.41 164	96.77 315	98.83 223	98.90 228	97.80 140	99.82 200	95.68 327	99.52 264	99.38 219

CPTT-MVS		97.84 256	97.36 280	99.27 95	99.31 183	98.46 111	98.29 153	99.27 227	94.90 379	97.83 325	98.37 324	94.90 291	99.84 172	93.85 378	99.54 257	99.51 151

UnsupCasMVSNet_eth		97.89 245	97.60 266	98.75 191	99.31 183	97.17 229	97.62 262	99.35 185	98.72 143	98.76 236	98.68 279	92.57 343	99.74 273	97.76 179	95.60 449	99.34 234

fmvsm_s_conf0.5_n_7		98.83 109	99.04 78	98.20 276	99.30 187	94.83 328	97.23 306	99.36 179	98.64 146	99.84 30	99.43 86	98.10 115	99.91 72	99.56 39	99.96 28	99.87 21

pmmvs-eth3d		98.47 178	98.34 185	98.86 169	99.30 187	97.76 185	97.16 315	99.28 224	95.54 361	99.42 105	99.19 144	97.27 185	99.63 334	97.89 163	99.97 21	99.20 276

mamv4		99.44 19	99.39 28	99.58 20	99.30 187	99.74 2	99.04 68	99.81 31	99.77 10	99.82 33	99.57 49	97.82 138	99.98 4	99.53 46	99.89 89	99.01 309

SymmetryMVS		98.05 231	97.71 256	99.09 128	99.29 190	97.83 174	98.28 154	97.64 383	99.24 74	98.80 229	98.85 241	89.76 371	99.94 41	98.04 152	99.50 273	99.49 161

Anonymous20231211		99.27 38	99.27 47	99.26 97	99.29 190	98.18 133	99.49 12	99.51 112	99.70 16	99.80 37	99.68 25	96.84 209	99.83 190	99.21 69	99.91 76	99.77 48

viewmanbaseed2359cas		98.58 159	98.54 150	98.70 199	99.28 192	97.13 233	97.47 284	99.55 99	97.55 247	98.96 195	98.92 223	97.77 142	99.59 351	97.59 190	99.77 154	99.39 211

UnsupCasMVSNet_bld		97.30 295	96.92 305	98.45 246	99.28 192	96.78 252	96.20 370	99.27 227	95.42 365	98.28 289	98.30 332	93.16 329	99.71 288	94.99 341	97.37 425	98.87 336

EC-MVSNet		99.09 70	99.05 77	99.20 106	99.28 192	98.93 79	99.24 44	99.84 22	99.08 109	98.12 302	98.37 324	98.72 49	99.90 79	99.05 82	99.77 154	98.77 353

mamba_0408		98.80 116	98.88 98	98.55 229	99.27 195	96.50 264	98.00 200	99.60 75	98.93 126	99.22 150	98.84 246	98.59 62	99.89 95	97.74 180	99.72 182	99.27 254

SSM_04072		98.80 116	98.88 98	98.56 227	99.27 195	96.50 264	98.00 200	99.60 75	98.93 126	99.22 150	98.84 246	98.59 62	99.90 79	97.74 180	99.72 182	99.27 254

SSM_0407		98.86 103	98.96 91	98.55 229	99.27 195	96.50 264	98.04 191	99.66 62	99.09 105	99.22 150	99.02 189	98.79 42	99.87 132	97.87 168	99.72 182	99.27 254

reproduce-ours		99.09 70	98.90 95	99.67 4	99.27 195	99.49 6	98.00 200	99.42 160	99.05 112	99.48 91	99.27 121	98.29 91	99.89 95	97.61 187	99.71 191	99.62 87

our_new_method		99.09 70	98.90 95	99.67 4	99.27 195	99.49 6	98.00 200	99.42 160	99.05 112	99.48 91	99.27 121	98.29 91	99.89 95	97.61 187	99.71 191	99.62 87

DPE-MVS		98.59 157	98.26 197	99.57 21	99.27 195	99.15 52	97.01 320	99.39 169	97.67 232	99.44 100	98.99 205	97.53 165	99.89 95	95.40 335	99.68 206	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		97.85 255	98.18 209	96.87 373	99.27 195	91.16 422	95.53 404	99.25 233	99.10 102	99.41 107	99.35 102	93.10 331	99.96 14	98.65 112	99.94 49	99.49 161

v1192		98.60 155	98.66 130	98.41 251	99.27 195	95.88 287	97.52 277	99.36 179	97.41 264	99.33 124	99.20 143	96.37 240	99.82 200	99.57 37	99.92 67	99.55 130

N_pmnet		97.63 269	97.17 290	98.99 147	99.27 195	97.86 171	95.98 381	93.41 446	95.25 370	99.47 95	98.90 228	95.63 272	99.85 154	96.91 237	99.73 174	99.27 254

FPMVS		93.44 404	92.23 411	97.08 361	99.25 204	97.86 171	95.61 401	97.16 395	92.90 415	93.76 448	98.65 286	75.94 443	95.66 462	79.30 460	97.49 418	97.73 426

new-patchmatchnet		98.35 193	98.74 114	97.18 356	99.24 205	92.23 404	96.42 357	99.48 124	98.30 177	99.69 54	99.53 63	97.44 174	99.82 200	98.84 97	99.77 154	99.49 161

MCST-MVS		98.00 236	97.63 264	99.10 124	99.24 205	98.17 134	96.89 329	98.73 336	95.66 356	97.92 316	97.70 373	97.17 191	99.66 323	96.18 303	99.23 318	99.47 180

UniMVSNet (Re)		98.87 100	98.71 121	99.35 76	99.24 205	98.73 91	97.73 246	99.38 171	98.93 126	99.12 161	98.73 265	96.77 217	99.86 141	98.63 114	99.80 137	99.46 182

jason		97.45 283	97.35 281	97.76 309	99.24 205	93.93 365	95.86 391	98.42 354	94.24 394	98.50 271	98.13 342	94.82 295	99.91 72	97.22 213	99.73 174	99.43 195
jason: jason.
IterMVS		97.73 261	98.11 218	96.57 383	99.24 205	90.28 431	95.52 406	99.21 242	98.86 135	99.33 124	99.33 109	93.11 330	99.94 41	98.49 124	99.94 49	99.48 172
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 165	98.62 137	98.32 262	99.22 210	95.58 297	97.51 279	99.45 140	97.16 292	99.45 99	99.24 134	96.12 250	99.85 154	99.60 35	99.88 91	99.55 130

ITE_SJBPF				98.87 167	99.22 210	98.48 110		99.35 185	97.50 252	98.28 289	98.60 297	97.64 153	99.35 413	93.86 377	99.27 310	98.79 351

h-mvs33		97.77 259	97.33 283	99.10 124	99.21 212	97.84 173	98.35 150	98.57 346	99.11 95	98.58 260	99.02 189	88.65 382	99.96 14	98.11 145	96.34 441	99.49 161

v144192		98.54 167	98.57 146	98.45 246	99.21 212	95.98 284	97.63 261	99.36 179	97.15 294	99.32 130	99.18 148	95.84 267	99.84 172	99.50 49	99.91 76	99.54 136

APDe-MVS		98.99 83	98.79 110	99.60 15	99.21 212	99.15 52	98.87 88	99.48 124	97.57 243	99.35 120	99.24 134	97.83 135	99.89 95	97.88 166	99.70 198	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	98.81 109	99.28 92	99.21 212	98.45 112	98.46 138	99.33 197	99.63 29	99.48 91	99.15 158	97.23 188	99.75 268	97.17 215	99.66 219	99.63 86

SR-MVS-dyc-post		98.81 114	98.55 148	99.57 21	99.20 216	99.38 13	98.48 136	99.30 212	98.64 146	98.95 196	98.96 215	97.49 172	99.86 141	96.56 276	99.39 291	99.45 187

RE-MVS-def			98.58 145		99.20 216	99.38 13	98.48 136	99.30 212	98.64 146	98.95 196	98.96 215	97.75 144		96.56 276	99.39 291	99.45 187

v1921920		98.54 167	98.60 142	98.38 255	99.20 216	95.76 294	97.56 272	99.36 179	97.23 286	99.38 113	99.17 152	96.02 253	99.84 172	99.57 37	99.90 83	99.54 136

thisisatest0530		95.27 373	94.45 384	97.74 312	99.19 219	94.37 343	97.86 225	90.20 458	97.17 291	98.22 292	97.65 375	73.53 446	99.90 79	96.90 242	99.35 297	98.95 321

Anonymous20240529		98.93 92	98.87 100	99.12 120	99.19 219	98.22 131	99.01 70	98.99 291	99.25 73	99.54 77	99.37 97	97.04 197	99.80 224	97.89 163	99.52 264	99.35 232

APD-MVS_3200maxsize		98.84 106	98.61 141	99.53 38	99.19 219	99.27 27	98.49 133	99.33 197	98.64 146	99.03 181	98.98 210	97.89 132	99.85 154	96.54 280	99.42 288	99.46 182

HQP_MVS		97.99 239	97.67 258	98.93 159	99.19 219	97.65 193	97.77 238	99.27 227	98.20 191	97.79 328	97.98 356	94.90 291	99.70 295	94.42 359	99.51 266	99.45 187

plane_prior7					99.19 219	97.87 170

ab-mvs		98.41 183	98.36 182	98.59 218	99.19 219	97.23 220	99.32 26	98.81 322	97.66 233	98.62 252	99.40 94	96.82 212	99.80 224	95.88 314	99.51 266	98.75 356

F-COLMAP		97.30 295	96.68 322	99.14 118	99.19 219	98.39 114	97.27 305	99.30 212	92.93 414	96.62 393	98.00 354	95.73 270	99.68 308	92.62 405	98.46 386	99.35 232

SR-MVS		98.71 129	98.43 170	99.57 21	99.18 226	99.35 17	98.36 149	99.29 220	98.29 180	98.88 215	98.85 241	97.53 165	99.87 132	96.14 305	99.31 303	99.48 172

UniMVSNet_NR-MVSNet		98.86 103	98.68 127	99.40 68	99.17 227	98.74 88	97.68 251	99.40 167	99.14 93	99.06 169	98.59 298	96.71 223	99.93 52	98.57 117	99.77 154	99.53 145

LF4IMVS		97.90 243	97.69 257	98.52 237	99.17 227	97.66 192	97.19 314	99.47 132	96.31 334	97.85 324	98.20 339	96.71 223	99.52 378	94.62 351	99.72 182	98.38 392

SMA-MVS		98.40 185	98.03 227	99.51 48	99.16 229	99.21 33	98.05 189	99.22 241	94.16 396	98.98 186	99.10 170	97.52 167	99.79 237	96.45 286	99.64 222	99.53 145
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		98.82 112	98.63 135	99.39 69	99.16 229	98.74 88	97.54 275	99.25 233	98.84 138	99.06 169	98.76 262	96.76 219	99.93 52	98.57 117	99.77 154	99.50 154

NR-MVSNet		98.95 90	98.82 107	99.36 70	99.16 229	98.72 93	99.22 45	99.20 244	99.10 102	99.72 46	98.76 262	96.38 239	99.86 141	98.00 157	99.82 120	99.50 154

MVS_111021_LR		98.30 202	98.12 217	98.83 172	99.16 229	98.03 153	96.09 378	99.30 212	97.58 242	98.10 304	98.24 335	98.25 97	99.34 414	96.69 262	99.65 220	99.12 295

DSMNet-mixed		97.42 286	97.60 266	96.87 373	99.15 233	91.46 411	98.54 121	99.12 266	92.87 416	97.58 341	99.63 39	96.21 245	99.90 79	95.74 323	99.54 257	99.27 254

D2MVS		97.84 256	97.84 247	97.83 301	99.14 234	94.74 332	96.94 324	98.88 306	95.84 353	98.89 211	98.96 215	94.40 307	99.69 299	97.55 191	99.95 38	99.05 301

pmmvs5		97.64 268	97.49 272	98.08 286	99.14 234	95.12 321	96.70 339	99.05 277	93.77 403	98.62 252	98.83 248	93.23 327	99.75 268	98.33 133	99.76 167	99.36 228

SPE-MVS-test		99.13 64	99.09 73	99.26 97	99.13 236	98.97 73	99.31 30	99.88 14	99.44 51	98.16 297	98.51 307	98.64 56	99.93 52	98.91 91	99.85 104	98.88 335

VDD-MVS		98.56 161	98.39 177	99.07 131	99.13 236	98.07 148	98.59 115	97.01 398	99.59 35	99.11 162	99.27 121	94.82 295	99.79 237	98.34 131	99.63 225	99.34 234

save fliter					99.11 238	97.97 159	96.53 349	99.02 285	98.24 183

APD-MVS		98.10 225	97.67 258	99.42 64	99.11 238	98.93 79	97.76 241	99.28 224	94.97 377	98.72 240	98.77 260	97.04 197	99.85 154	93.79 379	99.54 257	99.49 161
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 136	98.71 121	98.62 212	99.10 240	96.37 270	97.23 306	98.87 308	99.20 81	99.19 155	98.99 205	97.30 182	99.85 154	98.77 103	99.79 143	99.65 80

EI-MVSNet		98.40 185	98.51 154	98.04 291	99.10 240	94.73 333	97.20 311	98.87 308	98.97 121	99.06 169	99.02 189	96.00 255	99.80 224	98.58 115	99.82 120	99.60 97

CVMVSNet		96.25 347	97.21 289	93.38 440	99.10 240	80.56 468	97.20 311	98.19 365	96.94 304	99.00 183	99.02 189	89.50 375	99.80 224	96.36 292	99.59 239	99.78 45

EI-MVSNet-Vis-set		98.68 141	98.70 124	98.63 210	99.09 243	96.40 269	97.23 306	98.86 313	99.20 81	99.18 159	98.97 212	97.29 184	99.85 154	98.72 107	99.78 148	99.64 81

HPM-MVS++		98.10 225	97.64 263	99.48 56	99.09 243	99.13 60	97.52 277	98.75 333	97.46 260	96.90 381	97.83 366	96.01 254	99.84 172	95.82 321	99.35 297	99.46 182

DP-MVS Recon		97.33 293	96.92 305	98.57 222	99.09 243	97.99 155	96.79 332	99.35 185	93.18 410	97.71 332	98.07 350	95.00 290	99.31 418	93.97 372	99.13 334	98.42 389

MVS_111021_HR		98.25 211	98.08 222	98.75 191	99.09 243	97.46 205	95.97 382	99.27 227	97.60 241	97.99 314	98.25 334	98.15 112	99.38 409	96.87 245	99.57 248	99.42 198

BP-MVS1		97.40 288	96.97 301	98.71 198	99.07 247	96.81 248	98.34 152	97.18 393	98.58 157	98.17 294	98.61 295	84.01 414	99.94 41	98.97 88	99.78 148	99.37 221

9.14			97.78 249		99.07 247		97.53 276	99.32 199	95.53 362	98.54 267	98.70 275	97.58 159	99.76 260	94.32 364	99.46 278

PAPM_NR		96.82 327	96.32 338	98.30 265	99.07 247	96.69 256	97.48 282	98.76 330	95.81 354	96.61 394	96.47 411	94.12 316	99.17 431	90.82 432	97.78 412	99.06 300

TAMVS		98.24 212	98.05 225	98.80 178	99.07 247	97.18 227	97.88 221	98.81 322	96.66 320	99.17 160	99.21 141	94.81 297	99.77 254	96.96 235	99.88 91	99.44 191

CLD-MVS		97.49 279	97.16 291	98.48 243	99.07 247	97.03 236	94.71 427	99.21 242	94.46 388	98.06 307	97.16 397	97.57 160	99.48 390	94.46 356	99.78 148	98.95 321
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	99.06 252	99.15 52	99.36 22	99.88 14	99.36 62	98.21 293	98.46 315	98.68 53	99.93 52	99.03 84	99.85 104	98.64 368

thres100view900		94.19 390	93.67 395	95.75 407	99.06 252	91.35 415	98.03 193	94.24 441	98.33 173	97.40 357	94.98 441	79.84 430	99.62 337	83.05 453	98.08 403	96.29 448

thres600view7		94.45 385	93.83 392	96.29 391	99.06 252	91.53 410	97.99 207	94.24 441	98.34 172	97.44 355	95.01 439	79.84 430	99.67 312	84.33 451	98.23 392	97.66 429

plane_prior1					99.05 255

YYNet1		97.60 270	97.67 258	97.39 349	99.04 256	93.04 388	95.27 413	98.38 357	97.25 280	98.92 206	98.95 219	95.48 279	99.73 280	96.99 231	98.74 367	99.41 201

MDA-MVSNet_test_wron		97.60 270	97.66 261	97.41 348	99.04 256	93.09 384	95.27 413	98.42 354	97.26 279	98.88 215	98.95 219	95.43 280	99.73 280	97.02 228	98.72 369	99.41 201

MIMVSNet		96.62 334	96.25 342	97.71 316	99.04 256	94.66 336	99.16 54	96.92 404	97.23 286	97.87 321	99.10 170	86.11 397	99.65 328	91.65 416	99.21 322	98.82 340

icg_test_0407_2		98.20 217	98.38 179	97.65 322	99.03 259	94.03 356	95.78 396	99.45 140	98.16 197	99.06 169	98.71 268	98.27 93	99.68 308	97.50 196	99.45 280	99.22 271

IMVS_0407		98.39 191	98.64 133	97.66 320	99.03 259	94.03 356	98.10 179	99.45 140	98.16 197	99.06 169	98.71 268	98.27 93	99.71 288	97.50 196	99.45 280	99.22 271

IMVS_0404		98.07 229	98.20 204	97.69 317	99.03 259	94.03 356	96.67 340	99.45 140	98.16 197	98.03 311	98.71 268	96.80 215	99.82 200	97.50 196	99.45 280	99.22 271

IMVS_0403		98.34 194	98.56 147	97.66 320	99.03 259	94.03 356	97.98 208	99.45 140	98.16 197	98.89 211	98.71 268	97.90 130	99.74 273	97.50 196	99.45 280	99.22 271

PatchMatch-RL		97.24 301	96.78 316	98.61 215	99.03 259	97.83 174	96.36 360	99.06 274	93.49 408	97.36 361	97.78 367	95.75 269	99.49 387	93.44 388	98.77 366	98.52 377

viewmambaseed2359dif		98.19 218	98.26 197	97.99 294	99.02 264	95.03 324	96.59 346	99.53 107	96.21 337	99.00 183	98.99 205	97.62 155	99.61 344	97.62 186	99.72 182	99.33 239

GDP-MVS		97.50 276	97.11 295	98.67 203	99.02 264	96.85 246	98.16 169	99.71 47	98.32 175	98.52 270	98.54 302	83.39 418	99.95 26	98.79 99	99.56 251	99.19 281

ZD-MVS					99.01 266	98.84 82		99.07 273	94.10 398	98.05 309	98.12 344	96.36 241	99.86 141	92.70 404	99.19 326

CDPH-MVS		97.26 298	96.66 325	99.07 131	99.00 267	98.15 135	96.03 380	99.01 288	91.21 434	97.79 328	97.85 365	96.89 207	99.69 299	92.75 402	99.38 294	99.39 211

diffmvs		98.22 213	98.24 201	98.17 279	99.00 267	95.44 308	96.38 359	99.58 81	97.79 226	98.53 268	98.50 311	96.76 219	99.74 273	97.95 162	99.64 222	99.34 234
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WR-MVS		98.40 185	98.19 208	99.03 141	99.00 267	97.65 193	96.85 330	98.94 293	98.57 158	98.89 211	98.50 311	95.60 273	99.85 154	97.54 193	99.85 104	99.59 104

plane_prior6					98.99 270	97.70 191						94.90 291

xiu_mvs_v1_base_debu		97.86 250	98.17 210	96.92 370	98.98 271	93.91 366	96.45 353	99.17 256	97.85 221	98.41 279	97.14 399	98.47 72	99.92 63	98.02 154	99.05 340	96.92 441

xiu_mvs_v1_base		97.86 250	98.17 210	96.92 370	98.98 271	93.91 366	96.45 353	99.17 256	97.85 221	98.41 279	97.14 399	98.47 72	99.92 63	98.02 154	99.05 340	96.92 441

xiu_mvs_v1_base_debi		97.86 250	98.17 210	96.92 370	98.98 271	93.91 366	96.45 353	99.17 256	97.85 221	98.41 279	97.14 399	98.47 72	99.92 63	98.02 154	99.05 340	96.92 441

MVP-Stereo		98.08 228	97.92 241	98.57 222	98.96 274	96.79 249	97.90 219	99.18 252	96.41 330	98.46 274	98.95 219	95.93 264	99.60 347	96.51 282	98.98 354	99.31 246
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 185	98.68 127	97.54 337	98.96 274	97.99 155	97.88 221	99.36 179	98.20 191	99.63 65	99.04 186	98.76 45	95.33 464	96.56 276	99.74 171	99.31 246
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	98.94 276	97.76 185		98.76 330	87.58 451	96.75 389	98.10 346	94.80 298	99.78 248	92.73 403	99.00 349	99.20 276

USDC		97.41 287	97.40 276	97.44 346	98.94 276	93.67 376	95.17 416	99.53 107	94.03 400	98.97 190	99.10 170	95.29 282	99.34 414	95.84 320	99.73 174	99.30 249

tfpn200view9		94.03 394	93.44 397	95.78 406	98.93 278	91.44 413	97.60 267	94.29 439	97.94 213	97.10 367	94.31 448	79.67 432	99.62 337	83.05 453	98.08 403	96.29 448

testdata				98.09 283	98.93 278	95.40 310		98.80 324	90.08 442	97.45 354	98.37 324	95.26 283	99.70 295	93.58 384	98.95 357	99.17 288

thres400		94.14 392	93.44 397	96.24 394	98.93 278	91.44 413	97.60 267	94.29 439	97.94 213	97.10 367	94.31 448	79.67 432	99.62 337	83.05 453	98.08 403	97.66 429

TAPA-MVS	96.21 11	96.63 333	95.95 344	98.65 204	98.93 278	98.09 142	96.93 326	99.28 224	83.58 457	98.13 301	97.78 367	96.13 248	99.40 405	93.52 385	99.29 308	98.45 382
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 282	96.93 243	95.54 403	98.78 327	85.72 454	96.86 384	98.11 345	94.43 305			99.10 339	99.23 266

PVSNet_BlendedMVS		97.55 275	97.53 269	97.60 329	98.92 282	93.77 373	96.64 342	99.43 154	94.49 386	97.62 337	99.18 148	96.82 212	99.67 312	94.73 348	99.93 54	99.36 228

PVSNet_Blended		96.88 323	96.68 322	97.47 344	98.92 282	93.77 373	94.71 427	99.43 154	90.98 436	97.62 337	97.36 393	96.82 212	99.67 312	94.73 348	99.56 251	98.98 315

MSDG		97.71 263	97.52 270	98.28 267	98.91 285	96.82 247	94.42 437	99.37 175	97.65 234	98.37 284	98.29 333	97.40 176	99.33 416	94.09 370	99.22 319	98.68 366

Anonymous202405211		97.90 243	97.50 271	99.08 129	98.90 286	98.25 125	98.53 122	96.16 416	98.87 133	99.11 162	98.86 238	90.40 367	99.78 248	97.36 205	99.31 303	99.19 281

原ACMM1				98.35 260	98.90 286	96.25 274		98.83 321	92.48 420	96.07 411	98.10 346	95.39 281	99.71 288	92.61 406	98.99 351	99.08 297

GBi-Net		98.65 146	98.47 164	99.17 111	98.90 286	98.24 126	99.20 48	99.44 148	98.59 154	98.95 196	99.55 57	94.14 313	99.86 141	97.77 175	99.69 201	99.41 201

test1		98.65 146	98.47 164	99.17 111	98.90 286	98.24 126	99.20 48	99.44 148	98.59 154	98.95 196	99.55 57	94.14 313	99.86 141	97.77 175	99.69 201	99.41 201

FMVSNet2		98.49 176	98.40 174	98.75 191	98.90 286	97.14 232	98.61 113	99.13 265	98.59 154	99.19 155	99.28 119	94.14 313	99.82 200	97.97 160	99.80 137	99.29 251

OMC-MVS		97.88 247	97.49 272	99.04 140	98.89 291	98.63 95	96.94 324	99.25 233	95.02 375	98.53 268	98.51 307	97.27 185	99.47 393	93.50 387	99.51 266	99.01 309

VortexMVS		97.98 240	98.31 190	97.02 364	98.88 292	91.45 412	98.03 193	99.47 132	98.65 145	99.55 75	99.47 77	91.49 356	99.81 216	99.32 59	99.91 76	99.80 40

MVSFormer		98.26 208	98.43 170	97.77 306	98.88 292	93.89 369	99.39 20	99.56 95	99.11 95	98.16 297	98.13 342	93.81 321	99.97 7	99.26 64	99.57 248	99.43 195

lupinMVS		97.06 313	96.86 309	97.65 322	98.88 292	93.89 369	95.48 407	97.97 371	93.53 406	98.16 297	97.58 379	93.81 321	99.91 72	96.77 253	99.57 248	99.17 288

dmvs_re		95.98 355	95.39 365	97.74 312	98.86 295	97.45 206	98.37 148	95.69 428	97.95 211	96.56 395	95.95 420	90.70 364	97.68 458	88.32 441	96.13 445	98.11 404

DELS-MVS		98.27 206	98.20 204	98.48 243	98.86 295	96.70 255	95.60 402	99.20 244	97.73 229	98.45 275	98.71 268	97.50 169	99.82 200	98.21 139	99.59 239	98.93 326
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		97.89 245	97.98 232	97.60 329	98.86 295	94.35 344	96.21 369	99.44 148	97.45 262	99.06 169	98.88 235	97.99 125	99.28 424	94.38 363	99.58 244	99.18 284

LCM-MVSNet-Re		98.64 148	98.48 162	99.11 122	98.85 298	98.51 108	98.49 133	99.83 25	98.37 169	99.69 54	99.46 79	98.21 104	99.92 63	94.13 369	99.30 306	98.91 330

pmmvs4		97.58 273	97.28 284	98.51 238	98.84 299	96.93 243	95.40 411	98.52 349	93.60 405	98.61 254	98.65 286	95.10 287	99.60 347	96.97 234	99.79 143	98.99 314

NP-MVS					98.84 299	97.39 210					96.84 402

sss		97.21 303	96.93 303	98.06 288	98.83 301	95.22 317	96.75 336	98.48 351	94.49 386	97.27 363	97.90 362	92.77 339	99.80 224	96.57 272	99.32 301	99.16 291

PVSNet	93.40 17	95.67 364	95.70 350	95.57 411	98.83 301	88.57 438	92.50 454	97.72 376	92.69 418	96.49 403	96.44 412	93.72 324	99.43 401	93.61 382	99.28 309	98.71 359

MVE	83.40 22	92.50 417	91.92 419	94.25 427	98.83 301	91.64 409	92.71 453	83.52 467	95.92 351	86.46 465	95.46 433	95.20 284	95.40 463	80.51 458	98.64 378	95.73 456
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 398	93.91 390	93.39 439	98.82 304	81.72 466	97.76 241	95.28 430	98.60 153	96.54 396	96.66 406	65.85 462	99.62 337	96.65 265	98.99 351	98.82 340

ambc				98.24 271	98.82 304	95.97 285	98.62 112	99.00 290		99.27 137	99.21 141	96.99 202	99.50 384	96.55 279	99.50 273	99.26 260

旧先验1					98.82 304	97.45 206		98.76 330			98.34 328	95.50 278			99.01 348	99.23 266

test_vis1_rt		97.75 260	97.72 255	97.83 301	98.81 307	96.35 271	97.30 301	99.69 53	94.61 384	97.87 321	98.05 351	96.26 244	98.32 452	98.74 105	98.18 395	98.82 340

WTY-MVS		96.67 331	96.27 341	97.87 299	98.81 307	94.61 338	96.77 334	97.92 373	94.94 378	97.12 366	97.74 370	91.11 360	99.82 200	93.89 375	98.15 399	99.18 284

3Dnovator+	97.89 3	98.69 136	98.51 154	99.24 102	98.81 307	98.40 113	99.02 69	99.19 248	98.99 118	98.07 306	99.28 119	97.11 195	99.84 172	96.84 248	99.32 301	99.47 180

QAPM		97.31 294	96.81 315	98.82 174	98.80 310	97.49 201	99.06 65	99.19 248	90.22 440	97.69 334	99.16 154	96.91 206	99.90 79	90.89 431	99.41 289	99.07 299

VNet		98.42 182	98.30 191	98.79 181	98.79 311	97.29 216	98.23 160	98.66 340	99.31 67	98.85 220	98.80 254	94.80 298	99.78 248	98.13 144	99.13 334	99.31 246

DPM-MVS		96.32 343	95.59 356	98.51 238	98.76 312	97.21 224	94.54 436	98.26 360	91.94 425	96.37 404	97.25 395	93.06 333	99.43 401	91.42 421	98.74 367	98.89 332

3Dnovator	98.27 2	98.81 114	98.73 116	99.05 138	98.76 312	97.81 182	99.25 43	99.30 212	98.57 158	98.55 265	99.33 109	97.95 127	99.90 79	97.16 216	99.67 212	99.44 191

PLC	94.65 16	96.51 336	95.73 349	98.85 170	98.75 314	97.91 167	96.42 357	99.06 274	90.94 437	95.59 417	97.38 391	94.41 306	99.59 351	90.93 429	98.04 408	99.05 301
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 325	96.75 318	97.08 361	98.74 315	93.33 382	96.71 338	98.26 360	96.72 317	98.44 276	97.37 392	95.20 284	99.47 393	91.89 411	97.43 422	98.44 385

hse-mvs2		97.46 281	97.07 296	98.64 206	98.73 316	97.33 212	97.45 286	97.64 383	99.11 95	98.58 260	97.98 356	88.65 382	99.79 237	98.11 145	97.39 424	98.81 345

CDS-MVSNet		97.69 264	97.35 281	98.69 200	98.73 316	97.02 237	96.92 328	98.75 333	95.89 352	98.59 258	98.67 281	92.08 350	99.74 273	96.72 259	99.81 126	99.32 242
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SD_0403		96.28 345	95.83 346	97.64 325	98.72 318	94.30 345	98.87 88	98.77 328	97.80 224	96.53 397	98.02 353	97.34 180	99.47 393	76.93 462	99.48 276	99.16 291

EIA-MVS		98.00 236	97.74 252	98.80 178	98.72 318	98.09 142	98.05 189	99.60 75	97.39 266	96.63 392	95.55 428	97.68 147	99.80 224	96.73 258	99.27 310	98.52 377

LFMVS		97.20 304	96.72 319	98.64 206	98.72 318	96.95 241	98.93 81	94.14 443	99.74 13	98.78 231	99.01 200	84.45 409	99.73 280	97.44 201	99.27 310	99.25 261

new_pmnet		96.99 320	96.76 317	97.67 318	98.72 318	94.89 327	95.95 386	98.20 363	92.62 419	98.55 265	98.54 302	94.88 294	99.52 378	93.96 373	99.44 287	98.59 374

Fast-Effi-MVS+		97.67 266	97.38 278	98.57 222	98.71 322	97.43 208	97.23 306	99.45 140	94.82 381	96.13 408	96.51 408	98.52 70	99.91 72	96.19 301	98.83 363	98.37 394

TEST9					98.71 322	98.08 146	95.96 384	99.03 282	91.40 431	95.85 414	97.53 381	96.52 232	99.76 260

train_agg		97.10 310	96.45 335	99.07 131	98.71 322	98.08 146	95.96 384	99.03 282	91.64 426	95.85 414	97.53 381	96.47 234	99.76 260	93.67 381	99.16 329	99.36 228

TSAR-MVS + GP.		98.18 220	97.98 232	98.77 188	98.71 322	97.88 169	96.32 363	98.66 340	96.33 332	99.23 149	98.51 307	97.48 173	99.40 405	97.16 216	99.46 278	99.02 308

FA-MVS(test-final)		96.99 320	96.82 313	97.50 341	98.70 326	94.78 330	99.34 23	96.99 399	95.07 374	98.48 273	99.33 109	88.41 385	99.65 328	96.13 307	98.92 360	98.07 407

AUN-MVS		96.24 349	95.45 361	98.60 217	98.70 326	97.22 222	97.38 291	97.65 381	95.95 350	95.53 424	97.96 360	82.11 426	99.79 237	96.31 294	97.44 421	98.80 350

our_test_3		97.39 289	97.73 254	96.34 389	98.70 326	89.78 434	94.61 433	98.97 292	96.50 325	99.04 178	98.85 241	95.98 260	99.84 172	97.26 211	99.67 212	99.41 201

ppachtmachnet_test		97.50 276	97.74 252	96.78 379	98.70 326	91.23 421	94.55 435	99.05 277	96.36 331	99.21 153	98.79 256	96.39 237	99.78 248	96.74 256	99.82 120	99.34 234

PCF-MVS	92.86 18	94.36 386	93.00 404	98.42 250	98.70 326	97.56 198	93.16 452	99.11 268	79.59 461	97.55 344	97.43 388	92.19 347	99.73 280	79.85 459	99.45 280	97.97 413
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 242	98.02 228	97.58 331	98.69 331	94.10 352	98.13 172	98.90 302	97.95 211	97.32 362	99.58 47	95.95 263	98.75 447	96.41 288	99.22 319	99.87 21

ETV-MVS		98.03 232	97.86 246	98.56 227	98.69 331	98.07 148	97.51 279	99.50 115	98.10 203	97.50 349	95.51 429	98.41 78	99.88 113	96.27 297	99.24 315	97.71 428

test_prior				98.95 156	98.69 331	97.95 163		99.03 282					99.59 351			99.30 249

mvsmamba		97.57 274	97.26 285	98.51 238	98.69 331	96.73 254	98.74 97	97.25 392	97.03 300	97.88 320	99.23 139	90.95 361	99.87 132	96.61 268	99.00 349	98.91 330

agg_prior					98.68 335	97.99 155		99.01 288		95.59 417			99.77 254

test_8					98.67 336	98.01 154	95.91 390	99.02 285	91.64 426	95.79 416	97.50 384	96.47 234	99.76 260

HQP-NCC					98.67 336		96.29 365		96.05 343	95.55 420

ACMP_Plane					98.67 336		96.29 365		96.05 343	95.55 420

CNVR-MVS		98.17 222	97.87 245	99.07 131	98.67 336	98.24 126	97.01 320	98.93 296	97.25 280	97.62 337	98.34 328	97.27 185	99.57 360	96.42 287	99.33 300	99.39 211

HQP-MVS		97.00 319	96.49 334	98.55 229	98.67 336	96.79 249	96.29 365	99.04 280	96.05 343	95.55 420	96.84 402	93.84 319	99.54 372	92.82 399	99.26 313	99.32 242

MM		98.22 213	97.99 231	98.91 163	98.66 341	96.97 238	97.89 220	94.44 437	99.54 39	98.95 196	99.14 161	93.50 325	99.92 63	99.80 16	99.96 28	99.85 29

test_fmvs1		97.72 262	97.94 238	97.07 363	98.66 341	92.39 399	97.68 251	99.81 31	95.20 373	99.54 77	99.44 84	91.56 355	99.41 404	99.78 20	99.77 154	99.40 210

balanced_conf03		98.63 150	98.72 118	98.38 255	98.66 341	96.68 257	98.90 83	99.42 160	98.99 118	98.97 190	99.19 144	95.81 268	99.85 154	98.77 103	99.77 154	98.60 371

thres200		93.72 400	93.14 402	95.46 415	98.66 341	91.29 417	96.61 344	94.63 436	97.39 266	96.83 385	93.71 451	79.88 429	99.56 363	82.40 456	98.13 400	95.54 457

wuyk23d		96.06 351	97.62 265	91.38 444	98.65 345	98.57 102	98.85 92	96.95 402	96.86 310	99.90 14	99.16 154	99.18 19	98.40 451	89.23 439	99.77 154	77.18 464

NCCC		97.86 250	97.47 275	99.05 138	98.61 346	98.07 148	96.98 322	98.90 302	97.63 235	97.04 371	97.93 361	95.99 259	99.66 323	95.31 336	98.82 365	99.43 195

DeepC-MVS_fast	96.85 6	98.30 202	98.15 214	98.75 191	98.61 346	97.23 220	97.76 241	99.09 271	97.31 274	98.75 237	98.66 284	97.56 161	99.64 331	96.10 308	99.55 255	99.39 211
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 402	92.09 413	97.75 310	98.60 348	94.40 342	97.32 299	95.26 431	97.56 245	96.79 388	95.50 430	53.57 470	99.77 254	95.26 337	98.97 355	99.08 297

thisisatest0515		94.12 393	93.16 401	96.97 368	98.60 348	92.90 389	93.77 448	90.61 456	94.10 398	96.91 378	95.87 423	74.99 444	99.80 224	94.52 354	99.12 337	98.20 400

GA-MVS		95.86 358	95.32 368	97.49 342	98.60 348	94.15 351	93.83 447	97.93 372	95.49 363	96.68 390	97.42 389	83.21 419	99.30 420	96.22 299	98.55 384	99.01 309

dmvs_testset		92.94 412	92.21 412	95.13 419	98.59 351	90.99 424	97.65 257	92.09 452	96.95 303	94.00 444	93.55 452	92.34 345	96.97 461	72.20 463	92.52 459	97.43 436

OPU-MVS				98.82 174	98.59 351	98.30 122	98.10 179				98.52 306	98.18 106	98.75 447	94.62 351	99.48 276	99.41 201

MSLP-MVS++		98.02 233	98.14 216	97.64 325	98.58 353	95.19 318	97.48 282	99.23 240	97.47 255	97.90 318	98.62 293	97.04 197	98.81 445	97.55 191	99.41 289	98.94 325

test12				98.93 159	98.58 353	97.83 174		98.66 340		96.53 397		95.51 277	99.69 299		99.13 334	99.27 254

CL-MVSNet_self_test		97.44 284	97.22 288	98.08 286	98.57 355	95.78 293	94.30 440	98.79 325	96.58 323	98.60 256	98.19 340	94.74 301	99.64 331	96.41 288	98.84 362	98.82 340

PS-MVSNAJ		97.08 312	97.39 277	96.16 400	98.56 356	92.46 397	95.24 415	98.85 316	97.25 280	97.49 350	95.99 419	98.07 116	99.90 79	96.37 290	98.67 377	96.12 453

CNLPA		97.17 307	96.71 320	98.55 229	98.56 356	98.05 152	96.33 362	98.93 296	96.91 307	97.06 370	97.39 390	94.38 308	99.45 398	91.66 415	99.18 328	98.14 403

xiu_mvs_v2_base		97.16 308	97.49 272	96.17 398	98.54 358	92.46 397	95.45 408	98.84 317	97.25 280	97.48 351	96.49 409	98.31 89	99.90 79	96.34 293	98.68 376	96.15 452

alignmvs		97.35 291	96.88 308	98.78 184	98.54 358	98.09 142	97.71 247	97.69 378	99.20 81	97.59 340	95.90 422	88.12 387	99.55 367	98.18 141	98.96 356	98.70 362

FE-MVS		95.66 365	94.95 378	97.77 306	98.53 360	95.28 314	99.40 19	96.09 419	93.11 412	97.96 315	99.26 127	79.10 436	99.77 254	92.40 408	98.71 371	98.27 398

Effi-MVS+		98.02 233	97.82 248	98.62 212	98.53 360	97.19 226	97.33 298	99.68 58	97.30 275	96.68 390	97.46 387	98.56 68	99.80 224	96.63 266	98.20 394	98.86 337

baseline1		95.96 356	95.44 362	97.52 339	98.51 362	93.99 363	98.39 146	96.09 419	98.21 187	98.40 283	97.76 369	86.88 389	99.63 334	95.42 334	89.27 462	98.95 321

MVS_Test		98.18 220	98.36 182	97.67 318	98.48 363	94.73 333	98.18 165	99.02 285	97.69 231	98.04 310	99.11 167	97.22 189	99.56 363	98.57 117	98.90 361	98.71 359

MGCFI-Net		98.34 194	98.28 193	98.51 238	98.47 364	97.59 197	98.96 77	99.48 124	99.18 88	97.40 357	95.50 430	98.66 54	99.50 384	98.18 141	98.71 371	98.44 385

BH-RMVSNet		96.83 325	96.58 330	97.58 331	98.47 364	94.05 353	96.67 340	97.36 387	96.70 319	97.87 321	97.98 356	95.14 286	99.44 400	90.47 434	98.58 383	99.25 261

sasdasda		98.34 194	98.26 197	98.58 219	98.46 366	97.82 179	98.96 77	99.46 136	99.19 85	97.46 352	95.46 433	98.59 62	99.46 396	98.08 148	98.71 371	98.46 379

canonicalmvs		98.34 194	98.26 197	98.58 219	98.46 366	97.82 179	98.96 77	99.46 136	99.19 85	97.46 352	95.46 433	98.59 62	99.46 396	98.08 148	98.71 371	98.46 379

MVS-HIRNet		94.32 387	95.62 353	90.42 445	98.46 366	75.36 469	96.29 365	89.13 460	95.25 370	95.38 426	99.75 16	92.88 336	99.19 430	94.07 371	99.39 291	96.72 446

PHI-MVS		98.29 205	97.95 236	99.34 79	98.44 369	99.16 48	98.12 176	99.38 171	96.01 347	98.06 307	98.43 318	97.80 140	99.67 312	95.69 326	99.58 244	99.20 276

DVP-MVS++		98.90 96	98.70 124	99.51 48	98.43 370	99.15 52	99.43 15	99.32 199	98.17 194	99.26 141	99.02 189	98.18 106	99.88 113	97.07 225	99.45 280	99.49 161

MSC_two_6792asdad				99.32 87	98.43 370	98.37 117		98.86 313					99.89 95	97.14 219	99.60 235	99.71 60

No_MVS				99.32 87	98.43 370	98.37 117		98.86 313					99.89 95	97.14 219	99.60 235	99.71 60

Fast-Effi-MVS+-dtu		98.27 206	98.09 219	98.81 176	98.43 370	98.11 139	97.61 266	99.50 115	98.64 146	97.39 359	97.52 383	98.12 114	99.95 26	96.90 242	98.71 371	98.38 392

OpenMVS_ROB	95.38 14	95.84 360	95.18 373	97.81 303	98.41 374	97.15 231	97.37 295	98.62 344	83.86 456	98.65 248	98.37 324	94.29 311	99.68 308	88.41 440	98.62 381	96.60 447

DeepPCF-MVS	96.93 5	98.32 199	98.01 229	99.23 104	98.39 375	98.97 73	95.03 420	99.18 252	96.88 308	99.33 124	98.78 258	98.16 110	99.28 424	96.74 256	99.62 228	99.44 191

Patchmatch-test		96.55 335	96.34 337	97.17 358	98.35 376	93.06 385	98.40 145	97.79 374	97.33 271	98.41 279	98.67 281	83.68 417	99.69 299	95.16 339	99.31 303	98.77 353

AdaColmap		97.14 309	96.71 320	98.46 245	98.34 377	97.80 183	96.95 323	98.93 296	95.58 360	96.92 376	97.66 374	95.87 266	99.53 374	90.97 428	99.14 332	98.04 408

OpenMVS	96.65 7	97.09 311	96.68 322	98.32 262	98.32 378	97.16 230	98.86 91	99.37 175	89.48 444	96.29 406	99.15 158	96.56 230	99.90 79	92.90 396	99.20 323	97.89 416

MG-MVS		96.77 328	96.61 327	97.26 354	98.31 379	93.06 385	95.93 387	98.12 368	96.45 329	97.92 316	98.73 265	93.77 323	99.39 407	91.19 426	99.04 343	99.33 239

test_yl		96.69 329	96.29 339	97.90 296	98.28 380	95.24 315	97.29 302	97.36 387	98.21 187	98.17 294	97.86 363	86.27 393	99.55 367	94.87 345	98.32 388	98.89 332

DCV-MVSNet		96.69 329	96.29 339	97.90 296	98.28 380	95.24 315	97.29 302	97.36 387	98.21 187	98.17 294	97.86 363	86.27 393	99.55 367	94.87 345	98.32 388	98.89 332

CHOSEN 280x420		95.51 370	95.47 359	95.65 410	98.25 382	88.27 441	93.25 451	98.88 306	93.53 406	94.65 435	97.15 398	86.17 395	99.93 52	97.41 203	99.93 54	98.73 358

SCA		96.41 342	96.66 325	95.67 408	98.24 383	88.35 440	95.85 393	96.88 405	96.11 341	97.67 335	98.67 281	93.10 331	99.85 154	94.16 365	99.22 319	98.81 345

DeepMVS_CX				93.44 438	98.24 383	94.21 348		94.34 438	64.28 464	91.34 458	94.87 445	89.45 376	92.77 465	77.54 461	93.14 458	93.35 460

MS-PatchMatch		97.68 265	97.75 251	97.45 345	98.23 385	93.78 372	97.29 302	98.84 317	96.10 342	98.64 249	98.65 286	96.04 252	99.36 410	96.84 248	99.14 332	99.20 276

BH-w/o		95.13 376	94.89 380	95.86 403	98.20 386	91.31 416	95.65 400	97.37 386	93.64 404	96.52 399	95.70 426	93.04 334	99.02 436	88.10 442	95.82 448	97.24 439

mvs_anonymous		97.83 258	98.16 213	96.87 373	98.18 387	91.89 406	97.31 300	98.90 302	97.37 268	98.83 223	99.46 79	96.28 243	99.79 237	98.90 92	98.16 398	98.95 321

miper_lstm_enhance		97.18 306	97.16 291	97.25 355	98.16 388	92.85 390	95.15 418	99.31 204	97.25 280	98.74 239	98.78 258	90.07 368	99.78 248	97.19 214	99.80 137	99.11 296

RRT-MVS		97.88 247	97.98 232	97.61 328	98.15 389	93.77 373	98.97 76	99.64 67	99.16 90	98.69 242	99.42 87	91.60 353	99.89 95	97.63 185	98.52 385	99.16 291

ET-MVSNet_ETH3D		94.30 389	93.21 400	97.58 331	98.14 390	94.47 341	94.78 426	93.24 448	94.72 382	89.56 460	95.87 423	78.57 439	99.81 216	96.91 237	97.11 433	98.46 379

ADS-MVSNet2		95.43 371	94.98 376	96.76 380	98.14 390	91.74 407	97.92 216	97.76 375	90.23 438	96.51 400	98.91 225	85.61 400	99.85 154	92.88 397	96.90 434	98.69 363

ADS-MVSNet		95.24 374	94.93 379	96.18 397	98.14 390	90.10 433	97.92 216	97.32 390	90.23 438	96.51 400	98.91 225	85.61 400	99.74 273	92.88 397	96.90 434	98.69 363

c3_l		97.36 290	97.37 279	97.31 350	98.09 393	93.25 383	95.01 421	99.16 259	97.05 297	98.77 234	98.72 267	92.88 336	99.64 331	96.93 236	99.76 167	99.05 301

FMVSNet3		97.50 276	97.24 287	98.29 266	98.08 394	95.83 290	97.86 225	98.91 301	97.89 218	98.95 196	98.95 219	87.06 388	99.81 216	97.77 175	99.69 201	99.23 266

PAPM		91.88 426	90.34 429	96.51 384	98.06 395	92.56 395	92.44 455	97.17 394	86.35 452	90.38 459	96.01 418	86.61 391	99.21 429	70.65 465	95.43 450	97.75 425

Effi-MVS+-dtu		98.26 208	97.90 243	99.35 76	98.02 396	99.49 6	98.02 196	99.16 259	98.29 180	97.64 336	97.99 355	96.44 236	99.95 26	96.66 264	98.93 359	98.60 371

eth_miper_zixun_eth		97.23 302	97.25 286	97.17 358	98.00 397	92.77 392	94.71 427	99.18 252	97.27 278	98.56 263	98.74 264	91.89 351	99.69 299	97.06 227	99.81 126	99.05 301

HY-MVS	95.94 13	95.90 357	95.35 367	97.55 336	97.95 398	94.79 329	98.81 96	96.94 403	92.28 423	95.17 428	98.57 300	89.90 370	99.75 268	91.20 425	97.33 429	98.10 405

UGNet		98.53 169	98.45 167	98.79 181	97.94 399	96.96 240	99.08 61	98.54 347	99.10 102	96.82 386	99.47 77	96.55 231	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		96.47 340	95.70 350	98.79 181	97.92 400	99.12 62	98.28 154	98.60 345	92.16 424	95.54 423	96.17 416	94.77 300	99.52 378	89.62 437	98.23 392	97.72 427
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		96.86 324	96.55 331	97.79 304	97.91 401	94.21 348	97.56 272	98.87 308	97.49 254	99.06 169	99.05 184	80.72 427	99.80 224	98.44 126	99.82 120	99.37 221

API-MVS		97.04 315	96.91 307	97.42 347	97.88 402	98.23 130	98.18 165	98.50 350	97.57 243	97.39 359	96.75 404	96.77 217	99.15 433	90.16 435	99.02 347	94.88 458

myMVS_eth3d28		92.92 413	92.31 409	94.77 422	97.84 403	87.59 445	96.19 371	96.11 418	97.08 296	94.27 438	93.49 454	66.07 461	98.78 446	91.78 413	97.93 411	97.92 415

miper_ehance_all_eth		97.06 313	97.03 298	97.16 360	97.83 404	93.06 385	94.66 430	99.09 271	95.99 348	98.69 242	98.45 316	92.73 341	99.61 344	96.79 250	99.03 344	98.82 340

cl____		97.02 316	96.83 312	97.58 331	97.82 405	94.04 355	94.66 430	99.16 259	97.04 298	98.63 250	98.71 268	88.68 381	99.69 299	97.00 229	99.81 126	99.00 313

DIV-MVS_self_test		97.02 316	96.84 311	97.58 331	97.82 405	94.03 356	94.66 430	99.16 259	97.04 298	98.63 250	98.71 268	88.69 379	99.69 299	97.00 229	99.81 126	99.01 309

CANet		97.87 249	97.76 250	98.19 278	97.75 407	95.51 300	96.76 335	99.05 277	97.74 228	96.93 375	98.21 338	95.59 274	99.89 95	97.86 170	99.93 54	99.19 281

UBG		93.25 407	92.32 408	96.04 402	97.72 408	90.16 432	95.92 389	95.91 423	96.03 346	93.95 446	93.04 457	69.60 451	99.52 378	90.72 433	97.98 409	98.45 382

mvsany_test1		97.60 270	97.54 268	97.77 306	97.72 408	95.35 311	95.36 412	97.13 396	94.13 397	99.71 48	99.33 109	97.93 128	99.30 420	97.60 189	98.94 358	98.67 367

PVSNet_0	89.98 21	91.15 427	90.30 430	93.70 435	97.72 408	84.34 459	90.24 458	97.42 385	90.20 441	93.79 447	93.09 456	90.90 363	98.89 444	86.57 448	72.76 465	97.87 418

CR-MVSNet		96.28 345	95.95 344	97.28 352	97.71 411	94.22 346	98.11 177	98.92 299	92.31 422	96.91 378	99.37 97	85.44 403	99.81 216	97.39 204	97.36 427	97.81 421

RPMNet		97.02 316	96.93 303	97.30 351	97.71 411	94.22 346	98.11 177	99.30 212	99.37 59	96.91 378	99.34 106	86.72 390	99.87 132	97.53 194	97.36 427	97.81 421

ETVMVS		92.60 416	91.08 425	97.18 356	97.70 413	93.65 378	96.54 347	95.70 426	96.51 324	94.68 434	92.39 460	61.80 467	99.50 384	86.97 445	97.41 423	98.40 390

pmmvs3		95.03 378	94.40 385	96.93 369	97.70 413	92.53 396	95.08 419	97.71 377	88.57 448	97.71 332	98.08 349	79.39 434	99.82 200	96.19 301	99.11 338	98.43 387

baseline2		93.73 399	92.83 405	96.42 387	97.70 413	91.28 418	96.84 331	89.77 459	93.96 402	92.44 454	95.93 421	79.14 435	99.77 254	92.94 395	96.76 438	98.21 399

WBMVS		95.18 375	94.78 381	96.37 388	97.68 416	89.74 435	95.80 395	98.73 336	97.54 249	98.30 285	98.44 317	70.06 449	99.82 200	96.62 267	99.87 95	99.54 136

tpm		94.67 383	94.34 387	95.66 409	97.68 416	88.42 439	97.88 221	94.90 433	94.46 388	96.03 413	98.56 301	78.66 437	99.79 237	95.88 314	95.01 452	98.78 352

CANet_DTU		97.26 298	97.06 297	97.84 300	97.57 418	94.65 337	96.19 371	98.79 325	97.23 286	95.14 429	98.24 335	93.22 328	99.84 172	97.34 206	99.84 109	99.04 305

testing11		93.08 410	92.02 415	96.26 393	97.56 419	90.83 427	96.32 363	95.70 426	96.47 328	92.66 453	93.73 450	64.36 465	99.59 351	93.77 380	97.57 416	98.37 394

tpm2		93.09 409	92.58 407	94.62 424	97.56 419	86.53 448	97.66 255	95.79 425	86.15 453	94.07 443	98.23 337	75.95 442	99.53 374	90.91 430	96.86 437	97.81 421

testing91		93.32 405	92.27 410	96.47 386	97.54 421	91.25 419	96.17 375	96.76 407	97.18 290	93.65 449	93.50 453	65.11 464	99.63 334	93.04 394	97.45 420	98.53 376

TR-MVS		95.55 368	95.12 374	96.86 376	97.54 421	93.94 364	96.49 352	96.53 412	94.36 393	97.03 373	96.61 407	94.26 312	99.16 432	86.91 447	96.31 442	97.47 435

testing99		93.04 411	91.98 418	96.23 395	97.53 423	90.70 429	96.35 361	95.94 422	96.87 309	93.41 450	93.43 455	63.84 466	99.59 351	93.24 392	97.19 430	98.40 390

1314		95.74 362	95.60 354	96.17 398	97.53 423	92.75 393	98.07 186	98.31 359	91.22 433	94.25 439	96.68 405	95.53 275	99.03 435	91.64 417	97.18 431	96.74 445

CostFormer		93.97 395	93.78 393	94.51 425	97.53 423	85.83 451	97.98 208	95.96 421	89.29 446	94.99 431	98.63 291	78.63 438	99.62 337	94.54 353	96.50 439	98.09 406

FMVSNet5		96.01 353	95.20 372	98.41 251	97.53 423	96.10 276	98.74 97	99.50 115	97.22 289	98.03 311	99.04 186	69.80 450	99.88 113	97.27 210	99.71 191	99.25 261

PMMVS		96.51 336	95.98 343	98.09 283	97.53 423	95.84 289	94.92 423	98.84 317	91.58 428	96.05 412	95.58 427	95.68 271	99.66 323	95.59 330	98.09 402	98.76 355

reproduce_monomvs		95.00 380	95.25 369	94.22 428	97.51 428	83.34 460	97.86 225	98.44 352	98.51 163	99.29 134	99.30 115	67.68 455	99.56 363	98.89 94	99.81 126	99.77 48

PAPR		95.29 372	94.47 383	97.75 310	97.50 429	95.14 320	94.89 424	98.71 338	91.39 432	95.35 427	95.48 432	94.57 303	99.14 434	84.95 450	97.37 425	98.97 318

testing222		91.96 424	90.37 428	96.72 381	97.47 430	92.59 394	96.11 377	94.76 434	96.83 311	92.90 452	92.87 458	57.92 468	99.55 367	86.93 446	97.52 417	98.00 412

PatchT		96.65 332	96.35 336	97.54 337	97.40 431	95.32 313	97.98 208	96.64 409	99.33 64	96.89 382	99.42 87	84.32 411	99.81 216	97.69 184	97.49 418	97.48 434

tpm cat1		93.29 406	93.13 403	93.75 434	97.39 432	84.74 454	97.39 290	97.65 381	83.39 458	94.16 440	98.41 319	82.86 422	99.39 407	91.56 419	95.35 451	97.14 440

PatchmatchNet		95.58 367	95.67 352	95.30 418	97.34 433	87.32 446	97.65 257	96.65 408	95.30 369	97.07 369	98.69 277	84.77 406	99.75 268	94.97 343	98.64 378	98.83 339
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 291	96.97 301	98.50 242	97.31 434	96.47 267	98.18 165	98.92 299	98.95 125	98.78 231	99.37 97	85.44 403	99.85 154	95.96 312	99.83 116	99.17 288

LS3D		98.63 150	98.38 179	99.36 70	97.25 435	99.38 13	99.12 60	99.32 199	99.21 79	98.44 276	98.88 235	97.31 181	99.80 224	96.58 270	99.34 299	98.92 327

IB-MVS	91.63 19	92.24 422	90.90 426	96.27 392	97.22 436	91.24 420	94.36 439	93.33 447	92.37 421	92.24 456	94.58 447	66.20 460	99.89 95	93.16 393	94.63 454	97.66 429
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		92.38 419	91.76 422	94.21 429	97.16 437	84.65 455	95.42 410	88.45 461	95.96 349	96.17 407	95.84 425	66.36 458	99.71 288	91.87 412	98.64 378	98.28 397

tpmrst		95.07 377	95.46 360	93.91 432	97.11 438	84.36 458	97.62 262	96.96 401	94.98 376	96.35 405	98.80 254	85.46 402	99.59 351	95.60 329	96.23 443	97.79 424

Syy-MVS		96.04 352	95.56 358	97.49 342	97.10 439	94.48 340	96.18 373	96.58 410	95.65 357	94.77 432	92.29 461	91.27 359	99.36 410	98.17 143	98.05 406	98.63 369

myMVS_eth3d		91.92 425	90.45 427	96.30 390	97.10 439	90.90 425	96.18 373	96.58 410	95.65 357	94.77 432	92.29 461	53.88 469	99.36 410	89.59 438	98.05 406	98.63 369

MDTV_nov1_ep13			95.22 371		97.06 441	83.20 461	97.74 244	96.16 416	94.37 392	96.99 374	98.83 248	83.95 415	99.53 374	93.90 374	97.95 410

MVS		93.19 408	92.09 413	96.50 385	96.91 442	94.03 356	98.07 186	98.06 370	68.01 463	94.56 437	96.48 410	95.96 262	99.30 420	83.84 452	96.89 436	96.17 450

E-PMN		94.17 391	94.37 386	93.58 436	96.86 443	85.71 452	90.11 460	97.07 397	98.17 194	97.82 327	97.19 396	84.62 408	98.94 440	89.77 436	97.68 415	96.09 454

JIA-IIPM		95.52 369	95.03 375	97.00 365	96.85 444	94.03 356	96.93 326	95.82 424	99.20 81	94.63 436	99.71 22	83.09 420	99.60 347	94.42 359	94.64 453	97.36 438

EMVS		93.83 397	94.02 389	93.23 441	96.83 445	84.96 453	89.77 461	96.32 414	97.92 215	97.43 356	96.36 415	86.17 395	98.93 441	87.68 443	97.73 414	95.81 455

cl22		95.79 361	95.39 365	96.98 367	96.77 446	92.79 391	94.40 438	98.53 348	94.59 385	97.89 319	98.17 341	82.82 423	99.24 426	96.37 290	99.03 344	98.92 327

WB-MVSnew		95.73 363	95.57 357	96.23 395	96.70 447	90.70 429	96.07 379	93.86 444	95.60 359	97.04 371	95.45 436	96.00 255	99.55 367	91.04 427	98.31 390	98.43 387

dp		93.47 403	93.59 396	93.13 442	96.64 448	81.62 467	97.66 255	96.42 413	92.80 417	96.11 409	98.64 289	78.55 440	99.59 351	93.31 390	92.18 461	98.16 402

MonoMVSNet		96.25 347	96.53 333	95.39 416	96.57 449	91.01 423	98.82 95	97.68 380	98.57 158	98.03 311	99.37 97	90.92 362	97.78 457	94.99 341	93.88 457	97.38 437

test-LLR		93.90 396	93.85 391	94.04 430	96.53 450	84.62 456	94.05 444	92.39 450	96.17 338	94.12 441	95.07 437	82.30 424	99.67 312	95.87 317	98.18 395	97.82 419

test-mter		92.33 421	91.76 422	94.04 430	96.53 450	84.62 456	94.05 444	92.39 450	94.00 401	94.12 441	95.07 437	65.63 463	99.67 312	95.87 317	98.18 395	97.82 419

TESTMET0.1,1		92.19 423	91.77 421	93.46 437	96.48 452	82.80 463	94.05 444	91.52 455	94.45 390	94.00 444	94.88 443	66.65 457	99.56 363	95.78 322	98.11 401	98.02 409

MVS_0304		97.44 284	97.01 300	98.72 197	96.42 453	96.74 253	97.20 311	91.97 453	98.46 166	98.30 285	98.79 256	92.74 340	99.91 72	99.30 61	99.94 49	99.52 148

miper_enhance_ethall		96.01 353	95.74 348	96.81 377	96.41 454	92.27 403	93.69 449	98.89 305	91.14 435	98.30 285	97.35 394	90.58 365	99.58 358	96.31 294	99.03 344	98.60 371

tpmvs		95.02 379	95.25 369	94.33 426	96.39 455	85.87 449	98.08 182	96.83 406	95.46 364	95.51 425	98.69 277	85.91 398	99.53 374	94.16 365	96.23 443	97.58 432

CMPMVS	75.91 23	96.29 344	95.44 362	98.84 171	96.25 456	98.69 94	97.02 319	99.12 266	88.90 447	97.83 325	98.86 238	89.51 374	98.90 443	91.92 410	99.51 266	98.92 327
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 384	93.69 394	96.99 366	96.05 457	93.61 380	94.97 422	93.49 445	96.17 338	97.57 343	94.88 443	82.30 424	99.01 438	93.60 383	94.17 456	98.37 394

EPMVS		93.72 400	93.27 399	95.09 421	96.04 458	87.76 443	98.13 172	85.01 466	94.69 383	96.92 376	98.64 289	78.47 441	99.31 418	95.04 340	96.46 440	98.20 400

cascas		94.79 382	94.33 388	96.15 401	96.02 459	92.36 401	92.34 456	99.26 232	85.34 455	95.08 430	94.96 442	92.96 335	98.53 450	94.41 362	98.59 382	97.56 433

MVStest1		95.86 358	95.60 354	96.63 382	95.87 460	91.70 408	97.93 213	98.94 293	98.03 205	99.56 72	99.66 32	71.83 447	98.26 453	99.35 57	99.24 315	99.91 13

gg-mvs-nofinetune		92.37 420	91.20 424	95.85 404	95.80 461	92.38 400	99.31 30	81.84 468	99.75 11	91.83 457	99.74 18	68.29 452	99.02 436	87.15 444	97.12 432	96.16 451

gm-plane-assit					94.83 462	81.97 465			88.07 450		94.99 440		99.60 347	91.76 414

GG-mvs-BLEND				94.76 423	94.54 463	92.13 405	99.31 30	80.47 469		88.73 463	91.01 463	67.59 456	98.16 456	82.30 457	94.53 455	93.98 459

UWE-MVS-28		90.22 428	89.28 431	93.02 443	94.50 464	82.87 462	96.52 350	87.51 462	95.21 372	92.36 455	96.04 417	71.57 448	98.25 454	72.04 464	97.77 413	97.94 414

EPNet_dtu		94.93 381	94.78 381	95.38 417	93.58 465	87.68 444	96.78 333	95.69 428	97.35 270	89.14 462	98.09 348	88.15 386	99.49 387	94.95 344	99.30 306	98.98 315
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 432	75.95 435	77.12 448	92.39 466	67.91 472	90.16 459	59.44 473	82.04 459	89.42 461	94.67 446	49.68 471	81.74 466	48.06 466	77.66 464	81.72 462

KD-MVS_2432*1600		92.87 414	91.99 416	95.51 413	91.37 467	89.27 436	94.07 442	98.14 366	95.42 365	97.25 364	96.44 412	67.86 453	99.24 426	91.28 423	96.08 446	98.02 409

miper_refine_blended		92.87 414	91.99 416	95.51 413	91.37 467	89.27 436	94.07 442	98.14 366	95.42 365	97.25 364	96.44 412	67.86 453	99.24 426	91.28 423	96.08 446	98.02 409

EPNet		96.14 350	95.44 362	98.25 269	90.76 469	95.50 303	97.92 216	94.65 435	98.97 121	92.98 451	98.85 241	89.12 377	99.87 132	95.99 310	99.68 206	99.39 211
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 433	68.95 436	70.34 449	87.68 470	65.00 473	91.11 457	59.90 472	69.02 462	74.46 467	88.89 464	48.58 472	68.03 468	28.61 467	72.33 466	77.99 463

test_method		79.78 430	79.50 433	80.62 446	80.21 471	45.76 474	70.82 462	98.41 356	31.08 466	80.89 466	97.71 371	84.85 405	97.37 459	91.51 420	80.03 463	98.75 356

tmp_tt		78.77 431	78.73 434	78.90 447	58.45 472	74.76 471	94.20 441	78.26 470	39.16 465	86.71 464	92.82 459	80.50 428	75.19 467	86.16 449	92.29 460	86.74 461

testmvs		17.12 435	20.53 438	6.87 451	12.05 473	4.20 476	93.62 450	6.73 474	4.62 469	10.41 469	24.33 466	8.28 474	3.56 470	9.69 469	15.07 467	12.86 466

test123		17.04 436	20.11 439	7.82 450	10.25 474	4.91 475	94.80 425	4.47 475	4.93 468	10.00 470	24.28 467	9.69 473	3.64 469	10.14 468	12.43 468	14.92 465

mmdepth		0.00 439	0.00 442	0.00 452	0.00 475	0.00 477	0.00 463	0.00 476	0.00 470	0.00 471	0.00 470	0.00 475	0.00 471	0.00 470	0.00 469	0.00 467

monomultidepth		0.00 439	0.00 442	0.00 452	0.00 475	0.00 477	0.00 463	0.00 476	0.00 470	0.00 471	0.00 470	0.00 475	0.00 471	0.00 470	0.00 469	0.00 467

test_blank		0.00 439	0.00 442	0.00 452	0.00 475	0.00 477	0.00 463	0.00 476	0.00 470	0.00 471	0.00 470	0.00 475	0.00 471	0.00 470	0.00 469	0.00 467

eth-test2					0.00 475

eth-test					0.00 475

uanet_test		0.00 439	0.00 442	0.00 452	0.00 475	0.00 477	0.00 463	0.00 476	0.00 470	0.00 471	0.00 470	0.00 475	0.00 471	0.00 470	0.00 469	0.00 467

DCPMVS		0.00 439	0.00 442	0.00 452	0.00 475	0.00 477	0.00 463	0.00 476	0.00 470	0.00 471	0.00 470	0.00 475	0.00 471	0.00 470	0.00 469	0.00 467

cdsmvs_eth3d_5k		24.66 434	32.88 437	0.00 452	0.00 475	0.00 477	0.00 463	99.10 269	0.00 470	0.00 471	97.58 379	99.21 18	0.00 471	0.00 470	0.00 469	0.00 467

pcd_1.5k_mvsjas		8.17 437	10.90 440	0.00 452	0.00 475	0.00 477	0.00 463	0.00 476	0.00 470	0.00 471	0.00 470	98.07 116	0.00 471	0.00 470	0.00 469	0.00 467

sosnet-low-res		0.00 439	0.00 442	0.00 452	0.00 475	0.00 477	0.00 463	0.00 476	0.00 470	0.00 471	0.00 470	0.00 475	0.00 471	0.00 470	0.00 469	0.00 467

sosnet		0.00 439	0.00 442	0.00 452	0.00 475	0.00 477	0.00 463	0.00 476	0.00 470	0.00 471	0.00 470	0.00 475	0.00 471	0.00 470	0.00 469	0.00 467

uncertanet		0.00 439	0.00 442	0.00 452	0.00 475	0.00 477	0.00 463	0.00 476	0.00 470	0.00 471	0.00 470	0.00 475	0.00 471	0.00 470	0.00 469	0.00 467

Regformer		0.00 439	0.00 442	0.00 452	0.00 475	0.00 477	0.00 463	0.00 476	0.00 470	0.00 471	0.00 470	0.00 475	0.00 471	0.00 470	0.00 469	0.00 467

ab-mvs-re		8.12 438	10.83 441	0.00 452	0.00 475	0.00 477	0.00 463	0.00 476	0.00 470	0.00 471	97.48 385	0.00 475	0.00 471	0.00 470	0.00 469	0.00 467

uanet		0.00 439	0.00 442	0.00 452	0.00 475	0.00 477	0.00 463	0.00 476	0.00 470	0.00 471	0.00 470	0.00 475	0.00 471	0.00 470	0.00 469	0.00 467

WAC-MVS						90.90 425								91.37 422

PC_three_1452									93.27 409	99.40 110	98.54 302	98.22 102	97.00 460	95.17 338	99.45 280	99.49 161

test_241102_TWO								99.30 212	98.03 205	99.26 141	99.02 189	97.51 168	99.88 113	96.91 237	99.60 235	99.66 75

test_0728_THIRD									98.17 194	99.08 167	99.02 189	97.89 132	99.88 113	97.07 225	99.71 191	99.70 65

GSMVS																98.81 345

sam_mvs1												84.74 407				98.81 345

sam_mvs												84.29 413

MTGPA								99.20 244

test_post1							97.59 269				20.48 469	83.07 421	99.66 323	94.16 365

test_post											21.25 468	83.86 416	99.70 295

patchmatchnet-post											98.77 260	84.37 410	99.85 154

MTMP							97.93 213	91.91 454

test9_res														93.28 391	99.15 331	99.38 219

agg_prior2														92.50 407	99.16 329	99.37 221

test_prior4						97.97 159	95.86 391

test_prior2							95.74 398		96.48 327	96.11 409	97.63 377	95.92 265		94.16 365	99.20 323

旧先验2							95.76 397		88.56 449	97.52 347			99.66 323	94.48 355

新几何2							95.93 387

无先验							95.74 398	98.74 335	89.38 445				99.73 280	92.38 409		99.22 271

原ACMM2							95.53 404

testdata2													99.79 237	92.80 401

segment_acmp												97.02 200

testdata1							95.44 409		96.32 333

plane_prior5								99.27 227					99.70 295	94.42 359	99.51 266	99.45 187

plane_prior4											97.98 356

plane_prior3						97.78 184			97.41 264	97.79 328

plane_prior2							97.77 238		98.20 191

plane_prior						97.65 193	97.07 318		96.72 317						99.36 295

n2								0.00 476

nn								0.00 476

door-mid								99.57 88

test11								98.87 308

door								99.41 164

HQP5-MVS						96.79 249

BP-MVS														92.82 399

HQP4-MVS										95.56 419			99.54 372			99.32 242

HQP3-MVS								99.04 280							99.26 313

HQP2-MVS												93.84 319

MDTV_nov1_ep13_2view						74.92 470	97.69 250		90.06 443	97.75 331		85.78 399		93.52 385		98.69 363

ACMMP++_ref															99.77 154

ACMMP++															99.68 206

Test By Simon												96.52 232

High-resolution multi-view benchmark