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 13	100.00 1	99.85 28

Gipuma		99.03 76	99.16 58	98.64 201	99.94 2	98.51 108	99.32 26	99.75 40	99.58 36	98.60 239	99.62 40	98.22 91	99.51 365	97.70 171	99.73 165	97.89 397
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 29	99.31 39	99.53 38	99.91 3	98.98 71	99.63 7	99.58 70	99.44 49	99.78 37	99.76 15	96.39 219	99.92 61	99.44 51	99.92 65	99.68 66

pmmvs6		99.67 3	99.70 3	99.60 15	99.90 4	99.27 27	99.53 9	99.76 37	99.64 26	99.84 28	99.83 4	99.50 9	99.87 126	99.36 54	99.92 65	99.64 78

PS-MVSNAJss		99.46 17	99.49 16	99.35 76	99.90 4	98.15 135	99.20 48	99.65 58	99.48 41	99.92 8	99.71 22	98.07 105	99.96 14	99.53 44	100.00 1	99.93 11

testf1		99.25 40	99.16 58	99.51 48	99.89 6	99.63 4	98.71 103	99.69 48	98.90 121	99.43 97	99.35 99	98.86 33	99.67 297	97.81 162	99.81 119	99.24 251

APD_test2		99.25 40	99.16 58	99.51 48	99.89 6	99.63 4	98.71 103	99.69 48	98.90 121	99.43 97	99.35 99	98.86 33	99.67 297	97.81 162	99.81 119	99.24 251

ANet_high		99.57 10	99.67 6	99.28 92	99.89 6	98.09 142	99.14 57	99.93 5	99.82 8	99.93 6	99.81 8	99.17 19	99.94 41	99.31 58	100.00 1	99.82 33

anonymousdsp		99.51 14	99.47 21	99.62 9	99.88 9	99.08 69	99.34 23	99.69 48	98.93 119	99.65 60	99.72 21	98.93 31	99.95 26	99.11 74	100.00 1	99.82 33

v7n		99.53 12	99.57 13	99.41 66	99.88 9	98.54 106	99.45 14	99.61 66	99.66 23	99.68 54	99.66 32	98.44 71	99.95 26	99.73 24	99.96 27	99.75 55

mvs_tets		99.63 6	99.67 6	99.49 54	99.88 9	98.61 98	99.34 23	99.71 44	99.27 70	99.90 13	99.74 18	99.68 4	99.97 7	99.55 39	99.99 5	99.88 19

test_fmvsmconf0.01_n		99.57 10	99.63 10	99.36 70	99.87 12	98.13 138	98.08 178	99.95 1	99.45 47	99.98 2	99.75 16	99.80 1	99.97 7	99.82 9	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 57	99.09 100	99.89 16	99.68 25	99.53 7	99.97 7	99.50 47	99.99 5	99.87 20

test_djsdf		99.52 13	99.51 15	99.53 38	99.86 14	98.74 88	99.39 20	99.56 84	99.11 90	99.70 48	99.73 20	99.00 26	99.97 7	99.26 62	99.98 12	99.89 16

MIMVSNet1		99.38 28	99.32 37	99.55 28	99.86 14	99.19 42	99.41 17	99.59 68	99.59 34	99.71 46	99.57 49	97.12 177	99.90 77	99.21 67	99.87 93	99.54 131

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 26	99.85 16	99.11 64	99.90 1	99.78 35	99.63 28	99.78 37	99.67 30	99.48 10	99.81 208	99.30 59	99.97 20	99.77 46
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 70	99.90 3	99.86 22	99.78 13	99.58 6	99.95 26	99.00 84	99.95 37	99.78 43

SixPastTwentyTwo		98.75 116	98.62 127	99.16 114	99.83 18	97.96 162	99.28 40	98.20 344	99.37 57	99.70 48	99.65 36	92.65 324	99.93 51	99.04 81	99.84 104	99.60 94

sc_t1		99.62 7	99.66 8	99.53 38	99.82 19	99.09 68	99.50 11	99.63 61	99.88 4	99.86 22	99.80 11	99.03 23	99.89 92	99.48 49	99.93 53	99.60 94

Baseline_NR-MVSNet		98.98 84	98.86 95	99.36 70	99.82 19	98.55 103	97.47 273	99.57 77	99.37 57	99.21 144	99.61 43	96.76 201	99.83 183	98.06 145	99.83 111	99.71 58

pm-mvs1		99.44 19	99.48 18	99.33 85	99.80 21	98.63 95	99.29 36	99.63 61	99.30 67	99.65 60	99.60 45	99.16 21	99.82 193	99.07 77	99.83 111	99.56 120

TransMVSNet (Re)		99.44 19	99.47 21	99.36 70	99.80 21	98.58 101	99.27 42	99.57 77	99.39 55	99.75 42	99.62 40	99.17 19	99.83 183	99.06 79	99.62 214	99.66 72

K. test v3		98.00 218	97.66 243	99.03 140	99.79 23	97.56 197	99.19 52	92.47 430	99.62 31	99.52 79	99.66 32	89.61 354	99.96 14	99.25 64	99.81 119	99.56 120

test_fmvsmconf0.1_n		99.49 15	99.54 14	99.34 79	99.78 24	98.11 139	97.77 229	99.90 11	99.33 62	99.97 3	99.66 32	99.71 3	99.96 14	99.79 16	99.99 5	99.96 8

APD_test1		98.83 102	98.66 121	99.34 79	99.78 24	99.47 9	98.42 143	99.45 127	98.28 172	98.98 174	99.19 139	97.76 130	99.58 340	96.57 254	99.55 241	98.97 299

test_vis3_rt		99.14 58	99.17 56	99.07 130	99.78 24	98.38 115	98.92 82	99.94 2	97.80 209	99.91 12	99.67 30	97.15 176	98.91 423	99.76 20	99.56 237	99.92 12

EGC-MVSNET		85.24 410	80.54 413	99.34 79	99.77 27	99.20 39	99.08 61	99.29 202	12.08 448	20.84 449	99.42 86	97.55 148	99.85 147	97.08 206	99.72 173	98.96 301

Anonymous20240521		98.69 127	98.87 92	98.16 268	99.77 27	95.11 309	99.08 61	99.44 131	99.34 61	99.33 120	99.55 57	94.10 299	99.94 41	99.25 64	99.96 27	99.42 190

FC-MVSNet-test		99.27 37	99.25 49	99.34 79	99.77 27	98.37 117	99.30 35	99.57 77	99.61 33	99.40 106	99.50 67	97.12 177	99.85 147	99.02 83	99.94 48	99.80 38

test_vis1_n		98.31 187	98.50 143	97.73 301	99.76 30	94.17 335	98.68 106	99.91 9	96.31 316	99.79 36	99.57 49	92.85 320	99.42 384	99.79 16	99.84 104	99.60 94

test_fmvs3		99.12 65	99.41 25	98.25 259	99.76 30	95.07 310	99.05 67	99.94 2	97.78 211	99.82 31	99.84 3	98.56 62	99.71 277	99.96 1	99.96 27	99.97 4

XXY-MVS		99.14 58	99.15 63	99.10 123	99.76 30	97.74 186	98.85 91	99.62 63	98.48 156	99.37 111	99.49 73	98.75 43	99.86 134	98.20 135	99.80 130	99.71 58

TDRefinement		99.42 24	99.38 28	99.55 28	99.76 30	99.33 21	99.68 6	99.71 44	99.38 56	99.53 77	99.61 43	98.64 52	99.80 216	98.24 131	99.84 104	99.52 143

fmvsm_s_conf0.1_n_a		99.17 51	99.30 42	98.80 174	99.75 34	96.59 253	97.97 203	99.86 16	98.22 175	99.88 19	99.71 22	98.59 58	99.84 165	99.73 24	99.98 12	99.98 3

tt0805		98.69 127	98.62 127	98.90 164	99.75 34	99.30 22	99.15 56	96.97 381	98.86 126	98.87 203	97.62 359	98.63 54	98.96 420	99.41 53	98.29 372	98.45 363

test_vis1_n_1920		98.40 173	98.92 87	96.81 358	99.74 36	90.76 409	98.15 168	99.91 9	98.33 163	99.89 16	99.55 57	95.07 270	99.88 107	99.76 20	99.93 53	99.79 40

FOURS1					99.73 37	99.67 3	99.43 15	99.54 92	99.43 51	99.26 136

PEN-MVS		99.41 25	99.34 34	99.62 9	99.73 37	99.14 57	99.29 36	99.54 92	99.62 31	99.56 68	99.42 86	98.16 99	99.96 14	98.78 98	99.93 53	99.77 46

lessismore_v0				98.97 151	99.73 37	97.53 199		86.71 445		99.37 111	99.52 66	89.93 351	99.92 61	98.99 85	99.72 173	99.44 183

SteuartSystems-ACMMP		98.79 109	98.54 138	99.54 31	99.73 37	99.16 48	98.23 158	99.31 186	97.92 200	98.90 194	98.90 217	98.00 111	99.88 107	96.15 286	99.72 173	99.58 109
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 205	98.15 197	98.22 262	99.73 37	95.15 306	97.36 281	99.68 53	94.45 371	98.99 173	99.27 117	96.87 191	99.94 41	97.13 203	99.91 74	99.57 114

Vis-MVSNet		99.34 30	99.36 31	99.27 95	99.73 37	98.26 124	99.17 53	99.78 35	99.11 90	99.27 132	99.48 74	98.82 36	99.95 26	98.94 88	99.93 53	99.59 101
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 19	99.82 5	99.02 25	99.90 77	99.54 40	99.95 37	99.61 92

SSC-MVS		98.71 120	98.74 105	98.62 207	99.72 43	96.08 272	98.74 96	98.64 324	99.74 13	99.67 56	99.24 129	94.57 285	99.95 26	99.11 74	99.24 296	99.82 33

test_f		98.67 135	98.87 92	98.05 277	99.72 43	95.59 285	98.51 127	99.81 30	96.30 318	99.78 37	99.82 5	96.14 229	98.63 430	99.82 9	99.93 53	99.95 9

ACMH	96.65 7	99.25 40	99.24 50	99.26 97	99.72 43	98.38 115	99.07 64	99.55 88	98.30 167	99.65 60	99.45 82	99.22 16	99.76 252	98.44 122	99.77 146	99.64 78
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 16	99.82 5	98.75 43	99.90 77	99.54 40	99.95 37	99.59 101

fmvsm_s_conf0.1_n		99.16 54	99.33 35	98.64 201	99.71 47	96.10 267	97.87 215	99.85 18	98.56 152	99.90 13	99.68 25	98.69 49	99.85 147	99.72 26	99.98 12	99.97 4

PS-CasMVS		99.40 26	99.33 35	99.62 9	99.71 47	99.10 65	99.29 36	99.53 95	99.53 38	99.46 92	99.41 90	98.23 88	99.95 26	98.89 92	99.95 37	99.81 36

DTE-MVSNet		99.43 23	99.35 32	99.66 7	99.71 47	99.30 22	99.31 30	99.51 99	99.64 26	99.56 68	99.46 78	98.23 88	99.97 7	98.78 98	99.93 53	99.72 57

WR-MVS_H		99.33 31	99.22 51	99.65 8	99.71 47	99.24 30	99.32 26	99.55 88	99.46 46	99.50 85	99.34 103	97.30 166	99.93 51	98.90 90	99.93 53	99.77 46

HPM-MVS_fast		99.01 78	98.82 98	99.57 21	99.71 47	99.35 17	99.00 72	99.50 102	97.33 254	98.94 189	98.86 227	98.75 43	99.82 193	97.53 181	99.71 178	99.56 120

ACMH+	96.62 9	99.08 72	99.00 80	99.33 85	99.71 47	98.83 83	98.60 113	99.58 70	99.11 90	99.53 77	99.18 143	98.81 37	99.67 297	96.71 243	99.77 146	99.50 149

PMVS	91.26 20	97.86 232	97.94 220	97.65 305	99.71 47	97.94 164	98.52 122	98.68 320	98.99 111	97.52 329	99.35 99	97.41 161	98.18 436	91.59 400	99.67 199	96.82 425
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
KinetiMVS		99.03 76	99.02 77	99.03 140	99.70 55	97.48 202	98.43 140	99.29 202	99.70 15	99.60 67	99.07 170	96.13 230	99.94 41	99.42 52	99.87 93	99.68 66

FIs		99.14 58	99.09 71	99.29 91	99.70 55	98.28 123	99.13 58	99.52 98	99.48 41	99.24 141	99.41 90	96.79 198	99.82 193	98.69 108	99.88 89	99.76 51

VPNet		98.87 97	98.83 97	99.01 144	99.70 55	97.62 195	98.43 140	99.35 167	99.47 44	99.28 130	99.05 178	96.72 204	99.82 193	98.09 142	99.36 276	99.59 101

fmvsm_s_conf0.1_n_2		99.20 49	99.38 28	98.65 199	99.69 58	96.08 272	97.49 270	99.90 11	99.53 38	99.88 19	99.64 37	98.51 65	99.90 77	99.83 8	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 184	98.68 118	97.27 334	99.69 58	92.29 383	98.03 187	99.85 18	97.62 220	99.96 4	99.62 40	93.98 300	99.74 264	99.52 46	99.86 99	99.79 40

MP-MVS-pluss		98.57 149	98.23 186	99.60 15	99.69 58	99.35 17	97.16 300	99.38 153	94.87 361	98.97 178	98.99 196	98.01 110	99.88 107	97.29 191	99.70 185	99.58 109
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 45	99.32 37	98.96 152	99.68 61	97.35 210	98.84 93	99.48 111	99.69 17	99.63 63	99.68 25	99.03 23	99.96 14	97.97 153	99.92 65	99.57 114

sd_testset		99.28 36	99.31 39	99.19 108	99.68 61	98.06 151	99.41 17	99.30 194	99.69 17	99.63 63	99.68 25	99.25 15	99.96 14	97.25 194	99.92 65	99.57 114

test_fmvs1_n		98.09 210	98.28 178	97.52 320	99.68 61	93.47 362	98.63 109	99.93 5	95.41 349	99.68 54	99.64 37	91.88 334	99.48 372	99.82 9	99.87 93	99.62 84

CHOSEN 1792x2688		97.49 261	97.14 276	98.54 225	99.68 61	96.09 270	96.50 333	99.62 63	91.58 409	98.84 206	98.97 202	92.36 326	99.88 107	96.76 236	99.95 37	99.67 70

tfpnnormal		98.90 94	98.90 89	98.91 161	99.67 65	97.82 178	99.00 72	99.44 131	99.45 47	99.51 84	99.24 129	98.20 94	99.86 134	95.92 295	99.69 188	99.04 286

MTAPA		98.88 96	98.64 124	99.61 13	99.67 65	99.36 16	98.43 140	99.20 226	98.83 130	98.89 196	98.90 217	96.98 187	99.92 61	97.16 198	99.70 185	99.56 120

test_fmvsmvis_n_1920		99.26 39	99.49 16	98.54 225	99.66 67	96.97 233	98.00 194	99.85 18	99.24 72	99.92 8	99.50 67	99.39 12	99.95 26	99.89 3	99.98 12	98.71 340

mvs5depth		99.30 33	99.59 12	98.44 238	99.65 68	95.35 298	99.82 3	99.94 2	99.83 7	99.42 101	99.94 2	98.13 102	99.96 14	99.63 32	99.96 27	100.00 1

fmvsm_l_conf0.5_n_a		99.19 50	99.27 45	98.94 155	99.65 68	97.05 229	97.80 224	99.76 37	98.70 135	99.78 37	99.11 162	98.79 41	99.95 26	99.85 5	99.96 27	99.83 30

WB-MVS		98.52 162	98.55 136	98.43 239	99.65 68	95.59 285	98.52 122	98.77 310	99.65 25	99.52 79	99.00 195	94.34 291	99.93 51	98.65 110	98.83 344	99.76 51

CP-MVSNet		99.21 47	99.09 71	99.56 26	99.65 68	98.96 77	99.13 58	99.34 173	99.42 52	99.33 120	99.26 122	97.01 185	99.94 41	98.74 103	99.93 53	99.79 40

HPM-MVS		98.79 109	98.53 139	99.59 19	99.65 68	99.29 24	99.16 54	99.43 137	96.74 298	98.61 237	98.38 305	98.62 55	99.87 126	96.47 266	99.67 199	99.59 101
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 144	98.36 167	99.42 64	99.65 68	99.42 11	98.55 118	99.57 77	97.72 214	98.90 194	99.26 122	96.12 232	99.52 360	95.72 306	99.71 178	99.32 232

lecture		99.25 40	99.12 66	99.62 9	99.64 74	99.40 12	98.89 87	99.51 99	99.19 82	99.37 111	99.25 127	98.36 75	99.88 107	98.23 133	99.67 199	99.59 101

fmvsm_l_conf0.5_n		99.21 47	99.28 44	99.02 143	99.64 74	97.28 214	97.82 220	99.76 37	98.73 132	99.82 31	99.09 169	98.81 37	99.95 26	99.86 4	99.96 27	99.83 30

test_fmvsmconf_n		99.44 19	99.48 18	99.31 90	99.64 74	98.10 141	97.68 241	99.84 22	99.29 68	99.92 8	99.57 49	99.60 5	99.96 14	99.74 23	99.98 12	99.89 16

TSAR-MVS + MP.		98.63 141	98.49 147	99.06 136	99.64 74	97.90 168	98.51 127	98.94 275	96.96 285	99.24 141	98.89 223	97.83 123	99.81 208	96.88 226	99.49 261	99.48 165
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 105	98.72 109	99.12 119	99.64 74	98.54 106	97.98 200	99.68 53	97.62 220	99.34 118	99.18 143	97.54 149	99.77 246	97.79 164	99.74 162	99.04 286

Elysia		99.15 55	99.14 64	99.18 109	99.63 79	97.92 165	98.50 129	99.43 137	99.67 20	99.70 48	99.13 158	96.66 207	99.98 4	99.54 40	99.96 27	99.64 78

StellarMVS		99.15 55	99.14 64	99.18 109	99.63 79	97.92 165	98.50 129	99.43 137	99.67 20	99.70 48	99.13 158	96.66 207	99.98 4	99.54 40	99.96 27	99.64 78

KD-MVS_self_test		99.25 40	99.18 55	99.44 63	99.63 79	99.06 70	98.69 105	99.54 92	99.31 65	99.62 66	99.53 63	97.36 164	99.86 134	99.24 66	99.71 178	99.39 203

EU-MVSNet		97.66 249	98.50 143	95.13 400	99.63 79	85.84 431	98.35 149	98.21 343	98.23 174	99.54 73	99.46 78	95.02 271	99.68 294	98.24 131	99.87 93	99.87 20

HyFIR lowres test		97.19 287	96.60 311	98.96 152	99.62 83	97.28 214	95.17 397	99.50 102	94.21 376	99.01 171	98.32 313	86.61 372	99.99 2	97.10 205	99.84 104	99.60 94

fmvsm_l_conf0.5_n_3		99.45 18	99.48 18	99.34 79	99.59 84	98.21 132	97.82 220	99.84 22	99.41 54	99.92 8	99.41 90	99.51 8	99.95 26	99.84 7	99.97 20	99.87 20

mmtdpeth		99.30 33	99.42 24	98.92 160	99.58 85	96.89 240	99.48 13	99.92 7	99.92 2	98.26 274	99.80 11	98.33 81	99.91 70	99.56 37	99.95 37	99.97 4

ACMMP_NAP		98.75 116	98.48 148	99.57 21	99.58 85	99.29 24	97.82 220	99.25 215	96.94 287	98.78 214	99.12 161	98.02 109	99.84 165	97.13 203	99.67 199	99.59 101

nrg030		99.40 26	99.35 32	99.54 31	99.58 85	99.13 60	98.98 75	99.48 111	99.68 19	99.46 92	99.26 122	98.62 55	99.73 269	99.17 71	99.92 65	99.76 51

VDDNet		98.21 200	97.95 218	99.01 144	99.58 85	97.74 186	99.01 70	97.29 372	99.67 20	98.97 178	99.50 67	90.45 348	99.80 216	97.88 159	99.20 304	99.48 165

COLMAP_ROB	96.50 10	98.99 81	98.85 96	99.41 66	99.58 85	99.10 65	98.74 96	99.56 84	99.09 100	99.33 120	99.19 139	98.40 73	99.72 276	95.98 293	99.76 158	99.42 190
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	98.99 146	99.57 90	97.73 188	97.93 204	99.83 25	99.22 74	99.93 6	99.30 111	99.42 11	99.96 14	99.85 5	99.99 5	99.29 241

ZNCC-MVS		98.68 132	98.40 160	99.54 31	99.57 90	99.21 33	98.46 137	99.29 202	97.28 260	98.11 286	98.39 303	98.00 111	99.87 126	96.86 229	99.64 208	99.55 127

MSP-MVS		98.40 173	98.00 213	99.61 13	99.57 90	99.25 29	98.57 116	99.35 167	97.55 231	99.31 128	97.71 352	94.61 284	99.88 107	96.14 287	99.19 307	99.70 63
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		98.32 185	98.39 163	98.13 269	99.57 90	95.54 288	97.78 226	99.49 109	97.37 251	99.19 146	97.65 356	98.96 28	99.49 369	96.50 265	98.99 332	99.34 225

MP-MVS		98.46 167	98.09 202	99.54 31	99.57 90	99.22 32	98.50 129	99.19 230	97.61 223	97.58 323	98.66 266	97.40 162	99.88 107	94.72 332	99.60 221	99.54 131
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 120	98.46 152	99.47 60	99.57 90	98.97 73	98.23 158	99.48 111	96.60 303	99.10 156	99.06 171	98.71 47	99.83 183	95.58 313	99.78 140	99.62 84

LGP-MVS_train				99.47 60	99.57 90	98.97 73		99.48 111	96.60 303	99.10 156	99.06 171	98.71 47	99.83 183	95.58 313	99.78 140	99.62 84

IS-MVSNet		98.19 202	97.90 225	99.08 128	99.57 90	97.97 159	99.31 30	98.32 339	99.01 110	98.98 174	99.03 182	91.59 336	99.79 229	95.49 315	99.80 130	99.48 165

dcpmvs_2		98.78 111	99.11 67	97.78 291	99.56 98	93.67 357	99.06 65	99.86 16	99.50 40	99.66 57	99.26 122	97.21 174	99.99 2	98.00 151	99.91 74	99.68 66

test_0402		98.76 115	98.71 112	98.93 157	99.56 98	98.14 137	98.45 139	99.34 173	99.28 69	98.95 182	98.91 214	98.34 80	99.79 229	95.63 310	99.91 74	98.86 318

EPP-MVSNet		98.30 188	98.04 209	99.07 130	99.56 98	97.83 174	99.29 36	98.07 350	99.03 108	98.59 241	99.13 158	92.16 330	99.90 77	96.87 227	99.68 193	99.49 154

ACMMP		98.75 116	98.50 143	99.52 44	99.56 98	99.16 48	98.87 88	99.37 157	97.16 275	98.82 210	99.01 192	97.71 133	99.87 126	96.29 278	99.69 188	99.54 131
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 67	99.20 54	98.78 180	99.55 102	96.59 253	97.79 225	99.82 29	98.21 176	99.81 34	99.53 63	98.46 69	99.84 165	99.70 29	99.97 20	99.90 15

fmvsm_s_conf0.5_n		99.09 68	99.26 47	98.61 210	99.55 102	96.09 270	97.74 235	99.81 30	98.55 153	99.85 25	99.55 57	98.60 57	99.84 165	99.69 31	99.98 12	99.89 16

FMVSNet1		99.17 51	99.17 56	99.17 111	99.55 102	98.24 126	99.20 48	99.44 131	99.21 76	99.43 97	99.55 57	97.82 126	99.86 134	98.42 124	99.89 87	99.41 193

Vis-MVSNet (Re-imp)		97.46 263	97.16 273	98.34 251	99.55 102	96.10 267	98.94 80	98.44 333	98.32 165	98.16 280	98.62 275	88.76 359	99.73 269	93.88 358	99.79 135	99.18 266

ACMM	96.08 12	98.91 92	98.73 107	99.48 56	99.55 102	99.14 57	98.07 181	99.37 157	97.62 220	99.04 167	98.96 205	98.84 35	99.79 229	97.43 185	99.65 206	99.49 154
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 124	98.97 84	97.89 284	99.54 107	94.05 338	98.55 118	99.92 7	96.78 296	99.72 44	99.78 13	96.60 211	99.67 297	99.91 2	99.90 81	99.94 10

mPP-MVS		98.64 139	98.34 170	99.54 31	99.54 107	99.17 44	98.63 109	99.24 220	97.47 238	98.09 288	98.68 261	97.62 142	99.89 92	96.22 281	99.62 214	99.57 114

XVG-ACMP-BASELINE		98.56 150	98.34 170	99.22 105	99.54 107	98.59 100	97.71 238	99.46 123	97.25 263	98.98 174	98.99 196	97.54 149	99.84 165	95.88 296	99.74 162	99.23 253

region2R		98.69 127	98.40 160	99.54 31	99.53 110	99.17 44	98.52 122	99.31 186	97.46 243	98.44 259	98.51 289	97.83 123	99.88 107	96.46 267	99.58 230	99.58 109

PGM-MVS		98.66 136	98.37 166	99.55 28	99.53 110	99.18 43	98.23 158	99.49 109	97.01 284	98.69 225	98.88 224	98.00 111	99.89 92	95.87 299	99.59 225	99.58 109

Patchmatch-RL test		97.26 280	97.02 281	97.99 281	99.52 112	95.53 289	96.13 358	99.71 44	97.47 238	99.27 132	99.16 149	84.30 393	99.62 322	97.89 156	99.77 146	98.81 326

ACMMPR		98.70 124	98.42 158	99.54 31	99.52 112	99.14 57	98.52 122	99.31 186	97.47 238	98.56 246	98.54 284	97.75 131	99.88 107	96.57 254	99.59 225	99.58 109

AstraMVS		98.16 207	98.07 207	98.41 241	99.51 114	95.86 279	98.00 194	95.14 413	98.97 114	99.43 97	99.24 129	93.25 308	99.84 165	99.21 67	99.87 93	99.54 131

fmvsm_s_conf0.5_n_8		99.13 62	99.26 47	98.74 191	99.51 114	96.44 259	97.65 247	99.65 58	99.66 23	99.78 37	99.48 74	97.92 118	99.93 51	99.72 26	99.95 37	99.87 20

GST-MVS		98.61 145	98.30 176	99.52 44	99.51 114	99.20 39	98.26 156	99.25 215	97.44 246	98.67 228	98.39 303	97.68 134	99.85 147	96.00 291	99.51 252	99.52 143

Anonymous20231206		98.21 200	98.21 187	98.20 263	99.51 114	95.43 296	98.13 170	99.32 181	96.16 321	98.93 190	98.82 237	96.00 237	99.83 183	97.32 190	99.73 165	99.36 219

ACMP	95.32 15	98.41 171	98.09 202	99.36 70	99.51 114	98.79 86	97.68 241	99.38 153	95.76 336	98.81 212	98.82 237	98.36 75	99.82 193	94.75 329	99.77 146	99.48 165
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LuminaMVS		98.39 179	98.20 188	98.98 150	99.50 119	97.49 200	97.78 226	97.69 359	98.75 131	99.49 86	99.25 127	92.30 328	99.94 41	99.14 72	99.88 89	99.50 149

DVP-MVS		98.77 114	98.52 140	99.52 44	99.50 119	99.21 33	98.02 190	98.84 299	97.97 194	99.08 158	99.02 183	97.61 143	99.88 107	96.99 213	99.63 211	99.48 165
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	99.50 119	99.23 31	98.02 190	99.32 181					99.88 107	96.99 213	99.63 211	99.68 66

test0726					99.50 119	99.21 33	98.17 166	99.35 167	97.97 194	99.26 136	99.06 171	97.61 143

AllTest		98.44 169	98.20 188	99.16 114	99.50 119	98.55 103	98.25 157	99.58 70	96.80 294	98.88 199	99.06 171	97.65 137	99.57 342	94.45 339	99.61 219	99.37 212

TestCases				99.16 114	99.50 119	98.55 103		99.58 70	96.80 294	98.88 199	99.06 171	97.65 137	99.57 342	94.45 339	99.61 219	99.37 212

XVG-OURS		98.53 158	98.34 170	99.11 121	99.50 119	98.82 85	95.97 364	99.50 102	97.30 258	99.05 165	98.98 200	99.35 13	99.32 398	95.72 306	99.68 193	99.18 266

EG-PatchMatch MVS		98.99 81	99.01 79	98.94 155	99.50 119	97.47 203	98.04 186	99.59 68	98.15 187	99.40 106	99.36 98	98.58 61	99.76 252	98.78 98	99.68 193	99.59 101

fmvsm_s_conf0.5_n_2		99.14 58	99.31 39	98.63 205	99.49 127	96.08 272	97.38 278	99.81 30	99.48 41	99.84 28	99.57 49	98.46 69	99.89 92	99.82 9	99.97 20	99.91 13

SED-MVS		98.91 92	98.72 109	99.49 54	99.49 127	99.17 44	98.10 176	99.31 186	98.03 190	99.66 57	99.02 183	98.36 75	99.88 107	96.91 219	99.62 214	99.41 193

IU-MVS					99.49 127	99.15 52		98.87 290	92.97 394	99.41 103				96.76 236	99.62 214	99.66 72

test_241102_ONE					99.49 127	99.17 44		99.31 186	97.98 193	99.66 57	98.90 217	98.36 75	99.48 372

UA-Net		99.47 16	99.40 26	99.70 2	99.49 127	99.29 24	99.80 4	99.72 42	99.82 8	99.04 167	99.81 8	98.05 108	99.96 14	98.85 94	99.99 5	99.86 26

HFP-MVS		98.71 120	98.44 155	99.51 48	99.49 127	99.16 48	98.52 122	99.31 186	97.47 238	98.58 243	98.50 293	97.97 115	99.85 147	96.57 254	99.59 225	99.53 140

VPA-MVSNet		99.30 33	99.30 42	99.28 92	99.49 127	98.36 120	99.00 72	99.45 127	99.63 28	99.52 79	99.44 83	98.25 86	99.88 107	99.09 76	99.84 104	99.62 84

XVG-OURS-SEG-HR		98.49 164	98.28 178	99.14 117	99.49 127	98.83 83	96.54 329	99.48 111	97.32 256	99.11 153	98.61 277	99.33 14	99.30 401	96.23 280	98.38 368	99.28 243

114514_t		96.50 320	95.77 328	98.69 195	99.48 135	97.43 207	97.84 219	99.55 88	81.42 441	96.51 381	98.58 281	95.53 257	99.67 297	93.41 371	99.58 230	98.98 296

IterMVS-LS		98.55 154	98.70 115	98.09 270	99.48 135	94.73 319	97.22 295	99.39 151	98.97 114	99.38 109	99.31 110	96.00 237	99.93 51	98.58 113	99.97 20	99.60 94
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 74	99.10 69	98.99 146	99.47 137	97.22 219	97.40 276	99.83 25	97.61 223	99.85 25	99.30 111	98.80 39	99.95 26	99.71 28	99.90 81	99.78 43

v8		99.01 78	99.16 58	98.57 217	99.47 137	96.31 264	98.90 83	99.47 119	99.03 108	99.52 79	99.57 49	96.93 188	99.81 208	99.60 33	99.98 12	99.60 94

SSC-MVS3.2		98.53 158	98.79 101	97.74 298	99.46 139	93.62 360	96.45 335	99.34 173	99.33 62	98.93 190	98.70 257	97.90 119	99.90 77	99.12 73	99.92 65	99.69 65

fmvsm_s_conf0.5_n_3		99.22 46	99.37 30	98.78 180	99.46 139	96.58 255	97.65 247	99.72 42	99.47 44	99.86 22	99.50 67	98.94 29	99.89 92	99.75 22	99.97 20	99.86 26

XVS		98.72 119	98.45 153	99.53 38	99.46 139	99.21 33	98.65 107	99.34 173	98.62 142	97.54 327	98.63 273	97.50 155	99.83 183	96.79 232	99.53 247	99.56 120

X-MVStestdata		94.32 368	92.59 387	99.53 38	99.46 139	99.21 33	98.65 107	99.34 173	98.62 142	97.54 327	45.85 446	97.50 155	99.83 183	96.79 232	99.53 247	99.56 120

test20.03		98.78 111	98.77 104	98.78 180	99.46 139	97.20 222	97.78 226	99.24 220	99.04 107	99.41 103	98.90 217	97.65 137	99.76 252	97.70 171	99.79 135	99.39 203

guyue		98.01 217	97.93 222	98.26 258	99.45 144	95.48 292	98.08 178	96.24 396	98.89 123	99.34 118	99.14 156	91.32 340	99.82 193	99.07 77	99.83 111	99.48 165

CSCG		98.68 132	98.50 143	99.20 106	99.45 144	98.63 95	98.56 117	99.57 77	97.87 204	98.85 204	98.04 334	97.66 136	99.84 165	96.72 241	99.81 119	99.13 275

GeoE		99.05 75	98.99 82	99.25 100	99.44 146	98.35 121	98.73 100	99.56 84	98.42 159	98.91 193	98.81 239	98.94 29	99.91 70	98.35 126	99.73 165	99.49 154

v148		98.45 168	98.60 132	98.00 280	99.44 146	94.98 311	97.44 275	99.06 256	98.30 167	99.32 126	98.97 202	96.65 209	99.62 322	98.37 125	99.85 100	99.39 203

v10		98.97 85	99.11 67	98.55 222	99.44 146	96.21 266	98.90 83	99.55 88	98.73 132	99.48 87	99.60 45	96.63 210	99.83 183	99.70 29	99.99 5	99.61 92

V42		98.78 111	98.78 103	98.76 185	99.44 146	97.04 230	98.27 155	99.19 230	97.87 204	99.25 140	99.16 149	96.84 192	99.78 240	99.21 67	99.84 104	99.46 175

MDA-MVSNet-bldmvs		97.94 223	97.91 224	98.06 275	99.44 146	94.96 312	96.63 327	99.15 246	98.35 161	98.83 207	99.11 162	94.31 292	99.85 147	96.60 251	98.72 350	99.37 212

casdiffmvs_mvg		99.12 65	99.16 58	98.99 146	99.43 151	97.73 188	98.00 194	99.62 63	99.22 74	99.55 71	99.22 135	98.93 31	99.75 259	98.66 109	99.81 119	99.50 149
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test1111		96.49 321	96.82 295	95.52 393	99.42 152	87.08 428	99.22 45	87.14 444	99.11 90	99.46 92	99.58 47	88.69 360	99.86 134	98.80 96	99.95 37	99.62 84

v2v482		98.56 150	98.62 127	98.37 248	99.42 152	95.81 282	97.58 259	99.16 241	97.90 202	99.28 130	99.01 192	95.98 242	99.79 229	99.33 56	99.90 81	99.51 146

OPM-MVS		98.56 150	98.32 174	99.25 100	99.41 154	98.73 91	97.13 302	99.18 234	97.10 278	98.75 220	98.92 213	98.18 95	99.65 313	96.68 245	99.56 237	99.37 212
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 212	98.08 205	98.04 278	99.41 154	94.59 325	94.59 415	99.40 149	97.50 235	98.82 210	98.83 234	96.83 194	99.84 165	97.50 183	99.81 119	99.71 58

test_one_0601					99.39 156	99.20 39		99.31 186	98.49 155	98.66 230	99.02 183	97.64 140

mvsany_test3		98.87 97	98.92 87	98.74 191	99.38 157	96.94 237	98.58 115	99.10 251	96.49 308	99.96 4	99.81 8	98.18 95	99.45 379	98.97 86	99.79 135	99.83 30

patch_mono-2		98.51 163	98.63 125	98.17 266	99.38 157	94.78 316	97.36 281	99.69 48	98.16 186	98.49 255	99.29 114	97.06 180	99.97 7	98.29 130	99.91 74	99.76 51

test2506		92.39 399	91.89 401	93.89 414	99.38 157	82.28 445	99.32 26	66.03 452	99.08 102	98.77 217	99.57 49	66.26 440	99.84 165	98.71 106	99.95 37	99.54 131

ECVR-MVS		96.42 323	96.61 309	95.85 385	99.38 157	88.18 423	99.22 45	86.00 446	99.08 102	99.36 114	99.57 49	88.47 365	99.82 193	98.52 119	99.95 37	99.54 131

casdiffmvs		98.95 88	99.00 80	98.81 172	99.38 157	97.33 211	97.82 220	99.57 77	99.17 86	99.35 116	99.17 147	98.35 79	99.69 285	98.46 121	99.73 165	99.41 193
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 87	99.02 77	98.76 185	99.38 157	97.26 216	98.49 132	99.50 102	98.86 126	99.19 146	99.06 171	98.23 88	99.69 285	98.71 106	99.76 158	99.33 230

TranMVSNet+NR-MVSNet		99.17 51	99.07 74	99.46 62	99.37 163	98.87 81	98.39 145	99.42 142	99.42 52	99.36 114	99.06 171	98.38 74	99.95 26	98.34 127	99.90 81	99.57 114

fmvsm_s_conf0.5_n_6		99.08 72	99.21 53	98.69 195	99.36 164	96.51 257	97.62 252	99.68 53	98.43 158	99.85 25	99.10 165	99.12 22	99.88 107	99.77 19	99.92 65	99.67 70

tttt0517		95.64 347	94.98 357	97.64 307	99.36 164	93.81 352	98.72 101	90.47 438	98.08 189	98.67 228	98.34 310	73.88 426	99.92 61	97.77 166	99.51 252	99.20 258

test_part2					99.36 164	99.10 65				99.05 165

v1144		98.60 146	98.66 121	98.41 241	99.36 164	95.90 277	97.58 259	99.34 173	97.51 234	99.27 132	99.15 153	96.34 224	99.80 216	99.47 50	99.93 53	99.51 146

CP-MVS		98.70 124	98.42 158	99.52 44	99.36 164	99.12 62	98.72 101	99.36 161	97.54 232	98.30 268	98.40 302	97.86 122	99.89 92	96.53 263	99.72 173	99.56 120

Test_1112_low_res		96.99 302	96.55 313	98.31 254	99.35 169	95.47 294	95.84 376	99.53 95	91.51 411	96.80 369	98.48 296	91.36 339	99.83 183	96.58 252	99.53 247	99.62 84

DeepC-MVS	97.60 4	98.97 85	98.93 86	99.10 123	99.35 169	97.98 158	98.01 193	99.46 123	97.56 229	99.54 73	99.50 67	98.97 27	99.84 165	98.06 145	99.92 65	99.49 154
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 279	96.86 291	98.58 214	99.34 171	96.32 263	96.75 321	99.58 70	93.14 392	96.89 364	97.48 366	92.11 331	99.86 134	96.91 219	99.54 243	99.57 114

reproduce_model		99.15 55	98.97 84	99.67 4	99.33 172	99.44 10	98.15 168	99.47 119	99.12 89	99.52 79	99.32 109	98.31 82	99.90 77	97.78 165	99.73 165	99.66 72

MVSMamba_PlusPlus		98.83 102	98.98 83	98.36 249	99.32 173	96.58 255	98.90 83	99.41 146	99.75 11	98.72 223	99.50 67	96.17 228	99.94 41	99.27 61	99.78 140	98.57 356

fmvsm_s_conf0.5_n_4		99.01 78	99.22 51	98.38 245	99.31 174	95.48 292	97.56 261	99.73 41	98.87 124	99.75 42	99.27 117	98.80 39	99.86 134	99.80 14	99.90 81	99.81 36

SF-MVS		98.53 158	98.27 181	99.32 87	99.31 174	98.75 87	98.19 162	99.41 146	96.77 297	98.83 207	98.90 217	97.80 128	99.82 193	95.68 309	99.52 250	99.38 210

CPTT-MVS		97.84 238	97.36 262	99.27 95	99.31 174	98.46 111	98.29 152	99.27 209	94.90 360	97.83 307	98.37 306	94.90 273	99.84 165	93.85 360	99.54 243	99.51 146

UnsupCasMVSNet_eth		97.89 227	97.60 248	98.75 187	99.31 174	97.17 225	97.62 252	99.35 167	98.72 134	98.76 219	98.68 261	92.57 325	99.74 264	97.76 170	95.60 430	99.34 225

fmvsm_s_conf0.5_n_7		98.83 102	99.04 76	98.20 263	99.30 178	94.83 314	97.23 291	99.36 161	98.64 137	99.84 28	99.43 85	98.10 104	99.91 70	99.56 37	99.96 27	99.87 20

pmmvs-eth3d		98.47 166	98.34 170	98.86 166	99.30 178	97.76 184	97.16 300	99.28 206	95.54 342	99.42 101	99.19 139	97.27 169	99.63 319	97.89 156	99.97 20	99.20 258

mamv4		99.44 19	99.39 27	99.58 20	99.30 178	99.74 2	99.04 68	99.81 30	99.77 10	99.82 31	99.57 49	97.82 126	99.98 4	99.53 44	99.89 87	99.01 290

SymmetryMVS		98.05 213	97.71 238	99.09 127	99.29 181	97.83 174	98.28 153	97.64 364	99.24 72	98.80 213	98.85 230	89.76 353	99.94 41	98.04 147	99.50 259	99.49 154

Anonymous20231211		99.27 37	99.27 45	99.26 97	99.29 181	98.18 133	99.49 12	99.51 99	99.70 15	99.80 35	99.68 25	96.84 192	99.83 183	99.21 67	99.91 74	99.77 46

UnsupCasMVSNet_bld		97.30 277	96.92 287	98.45 236	99.28 183	96.78 247	96.20 352	99.27 209	95.42 346	98.28 272	98.30 314	93.16 311	99.71 277	94.99 323	97.37 406	98.87 317

EC-MVSNet		99.09 68	99.05 75	99.20 106	99.28 183	98.93 79	99.24 44	99.84 22	99.08 102	98.12 285	98.37 306	98.72 46	99.90 77	99.05 80	99.77 146	98.77 334

reproduce-ours		99.09 68	98.90 89	99.67 4	99.27 185	99.49 6	98.00 194	99.42 142	99.05 105	99.48 87	99.27 117	98.29 84	99.89 92	97.61 175	99.71 178	99.62 84

our_new_method		99.09 68	98.90 89	99.67 4	99.27 185	99.49 6	98.00 194	99.42 142	99.05 105	99.48 87	99.27 117	98.29 84	99.89 92	97.61 175	99.71 178	99.62 84

DPE-MVS		98.59 148	98.26 182	99.57 21	99.27 185	99.15 52	97.01 305	99.39 151	97.67 216	99.44 96	98.99 196	97.53 151	99.89 92	95.40 317	99.68 193	99.66 72
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 237	98.18 192	96.87 354	99.27 185	91.16 403	95.53 385	99.25 215	99.10 97	99.41 103	99.35 99	93.10 313	99.96 14	98.65 110	99.94 48	99.49 154

v1192		98.60 146	98.66 121	98.41 241	99.27 185	95.88 278	97.52 266	99.36 161	97.41 247	99.33 120	99.20 138	96.37 222	99.82 193	99.57 35	99.92 65	99.55 127

N_pmnet		97.63 251	97.17 272	98.99 146	99.27 185	97.86 171	95.98 363	93.41 427	95.25 351	99.47 91	98.90 217	95.63 254	99.85 147	96.91 219	99.73 165	99.27 244

FPMVS		93.44 385	92.23 392	97.08 342	99.25 191	97.86 171	95.61 382	97.16 376	92.90 396	93.76 429	98.65 268	75.94 424	95.66 443	79.30 442	97.49 399	97.73 407

new-patchmatchnet		98.35 180	98.74 105	97.18 337	99.24 192	92.23 385	96.42 339	99.48 111	98.30 167	99.69 52	99.53 63	97.44 160	99.82 193	98.84 95	99.77 146	99.49 154

MCST-MVS		98.00 218	97.63 246	99.10 123	99.24 192	98.17 134	96.89 314	98.73 317	95.66 337	97.92 298	97.70 354	97.17 175	99.66 308	96.18 285	99.23 299	99.47 173

UniMVSNet (Re)		98.87 97	98.71 112	99.35 76	99.24 192	98.73 91	97.73 237	99.38 153	98.93 119	99.12 152	98.73 251	96.77 199	99.86 134	98.63 112	99.80 130	99.46 175

jason		97.45 265	97.35 263	97.76 295	99.24 192	93.93 346	95.86 373	98.42 335	94.24 375	98.50 254	98.13 324	94.82 277	99.91 70	97.22 195	99.73 165	99.43 187
jason: jason.
IterMVS		97.73 243	98.11 201	96.57 364	99.24 192	90.28 412	95.52 387	99.21 224	98.86 126	99.33 120	99.33 105	93.11 312	99.94 41	98.49 120	99.94 48	99.48 165
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 154	98.62 127	98.32 252	99.22 197	95.58 287	97.51 268	99.45 127	97.16 275	99.45 95	99.24 129	96.12 232	99.85 147	99.60 33	99.88 89	99.55 127

ITE_SJBPF				98.87 165	99.22 197	98.48 110		99.35 167	97.50 235	98.28 272	98.60 279	97.64 140	99.35 394	93.86 359	99.27 291	98.79 332

h-mvs33		97.77 241	97.33 265	99.10 123	99.21 199	97.84 173	98.35 149	98.57 327	99.11 90	98.58 243	99.02 183	88.65 363	99.96 14	98.11 140	96.34 422	99.49 154

v144192		98.54 156	98.57 135	98.45 236	99.21 199	95.98 275	97.63 251	99.36 161	97.15 277	99.32 126	99.18 143	95.84 249	99.84 165	99.50 47	99.91 74	99.54 131

APDe-MVS		98.99 81	98.79 101	99.60 15	99.21 199	99.15 52	98.87 88	99.48 111	97.57 227	99.35 116	99.24 129	97.83 123	99.89 92	97.88 159	99.70 185	99.75 55
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 90	98.81 100	99.28 92	99.21 199	98.45 112	98.46 137	99.33 179	99.63 28	99.48 87	99.15 153	97.23 172	99.75 259	97.17 197	99.66 205	99.63 83

SR-MVS-dyc-post		98.81 107	98.55 136	99.57 21	99.20 203	99.38 13	98.48 135	99.30 194	98.64 137	98.95 182	98.96 205	97.49 158	99.86 134	96.56 258	99.39 272	99.45 179

RE-MVS-def			98.58 134		99.20 203	99.38 13	98.48 135	99.30 194	98.64 137	98.95 182	98.96 205	97.75 131		96.56 258	99.39 272	99.45 179

v1921920		98.54 156	98.60 132	98.38 245	99.20 203	95.76 284	97.56 261	99.36 161	97.23 269	99.38 109	99.17 147	96.02 235	99.84 165	99.57 35	99.90 81	99.54 131

thisisatest0530		95.27 354	94.45 365	97.74 298	99.19 206	94.37 329	97.86 216	90.20 439	97.17 274	98.22 275	97.65 356	73.53 427	99.90 77	96.90 224	99.35 278	98.95 302

Anonymous20240529		98.93 90	98.87 92	99.12 119	99.19 206	98.22 131	99.01 70	98.99 273	99.25 71	99.54 73	99.37 94	97.04 181	99.80 216	97.89 156	99.52 250	99.35 223

APD-MVS_3200maxsize		98.84 101	98.61 131	99.53 38	99.19 206	99.27 27	98.49 132	99.33 179	98.64 137	99.03 170	98.98 200	97.89 120	99.85 147	96.54 262	99.42 269	99.46 175

HQP_MVS		97.99 221	97.67 240	98.93 157	99.19 206	97.65 192	97.77 229	99.27 209	98.20 180	97.79 310	97.98 337	94.90 273	99.70 281	94.42 341	99.51 252	99.45 179

plane_prior7					99.19 206	97.87 170

ab-mvs		98.41 171	98.36 167	98.59 213	99.19 206	97.23 217	99.32 26	98.81 304	97.66 217	98.62 235	99.40 93	96.82 195	99.80 216	95.88 296	99.51 252	98.75 337

F-COLMAP		97.30 277	96.68 304	99.14 117	99.19 206	98.39 114	97.27 290	99.30 194	92.93 395	96.62 375	98.00 335	95.73 252	99.68 294	92.62 387	98.46 367	99.35 223

SR-MVS		98.71 120	98.43 156	99.57 21	99.18 213	99.35 17	98.36 148	99.29 202	98.29 170	98.88 199	98.85 230	97.53 151	99.87 126	96.14 287	99.31 284	99.48 165

UniMVSNet_NR-MVSNet		98.86 100	98.68 118	99.40 68	99.17 214	98.74 88	97.68 241	99.40 149	99.14 88	99.06 160	98.59 280	96.71 205	99.93 51	98.57 115	99.77 146	99.53 140

LF4IMVS		97.90 225	97.69 239	98.52 227	99.17 214	97.66 191	97.19 299	99.47 119	96.31 316	97.85 306	98.20 321	96.71 205	99.52 360	94.62 333	99.72 173	98.38 373

SMA-MVS		98.40 173	98.03 210	99.51 48	99.16 216	99.21 33	98.05 184	99.22 223	94.16 377	98.98 174	99.10 165	97.52 153	99.79 229	96.45 268	99.64 208	99.53 140
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		98.82 105	98.63 125	99.39 69	99.16 216	98.74 88	97.54 264	99.25 215	98.84 129	99.06 160	98.76 248	96.76 201	99.93 51	98.57 115	99.77 146	99.50 149

NR-MVSNet		98.95 88	98.82 98	99.36 70	99.16 216	98.72 93	99.22 45	99.20 226	99.10 97	99.72 44	98.76 248	96.38 221	99.86 134	98.00 151	99.82 115	99.50 149

MVS_111021_LR		98.30 188	98.12 200	98.83 169	99.16 216	98.03 153	96.09 360	99.30 194	97.58 226	98.10 287	98.24 317	98.25 86	99.34 395	96.69 244	99.65 206	99.12 276

DSMNet-mixed		97.42 268	97.60 248	96.87 354	99.15 220	91.46 392	98.54 120	99.12 248	92.87 397	97.58 323	99.63 39	96.21 227	99.90 77	95.74 305	99.54 243	99.27 244

D2MVS		97.84 238	97.84 229	97.83 287	99.14 221	94.74 318	96.94 309	98.88 288	95.84 334	98.89 196	98.96 205	94.40 289	99.69 285	97.55 178	99.95 37	99.05 282

pmmvs5		97.64 250	97.49 254	98.08 273	99.14 221	95.12 308	96.70 324	99.05 259	93.77 384	98.62 235	98.83 234	93.23 309	99.75 259	98.33 129	99.76 158	99.36 219

SPE-MVS-test		99.13 62	99.09 71	99.26 97	99.13 223	98.97 73	99.31 30	99.88 14	99.44 49	98.16 280	98.51 289	98.64 52	99.93 51	98.91 89	99.85 100	98.88 316

VDD-MVS		98.56 150	98.39 163	99.07 130	99.13 223	98.07 148	98.59 114	97.01 379	99.59 34	99.11 153	99.27 117	94.82 277	99.79 229	98.34 127	99.63 211	99.34 225

save fliter					99.11 225	97.97 159	96.53 331	99.02 267	98.24 173

APD-MVS		98.10 208	97.67 240	99.42 64	99.11 225	98.93 79	97.76 232	99.28 206	94.97 358	98.72 223	98.77 246	97.04 181	99.85 147	93.79 361	99.54 243	99.49 154
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 127	98.71 112	98.62 207	99.10 227	96.37 261	97.23 291	98.87 290	99.20 78	99.19 146	98.99 196	97.30 166	99.85 147	98.77 101	99.79 135	99.65 77

EI-MVSNet		98.40 173	98.51 141	98.04 278	99.10 227	94.73 319	97.20 296	98.87 290	98.97 114	99.06 160	99.02 183	96.00 237	99.80 216	98.58 113	99.82 115	99.60 94

CVMVSNet		96.25 328	97.21 271	93.38 421	99.10 227	80.56 449	97.20 296	98.19 346	96.94 287	99.00 172	99.02 183	89.50 356	99.80 216	96.36 274	99.59 225	99.78 43

EI-MVSNet-Vis-set		98.68 132	98.70 115	98.63 205	99.09 230	96.40 260	97.23 291	98.86 295	99.20 78	99.18 150	98.97 202	97.29 168	99.85 147	98.72 105	99.78 140	99.64 78

HPM-MVS++		98.10 208	97.64 245	99.48 56	99.09 230	99.13 60	97.52 266	98.75 314	97.46 243	96.90 363	97.83 347	96.01 236	99.84 165	95.82 303	99.35 278	99.46 175

DP-MVS Recon		97.33 275	96.92 287	98.57 217	99.09 230	97.99 155	96.79 317	99.35 167	93.18 391	97.71 314	98.07 332	95.00 272	99.31 399	93.97 354	99.13 315	98.42 370

MVS_111021_HR		98.25 196	98.08 205	98.75 187	99.09 230	97.46 204	95.97 364	99.27 209	97.60 225	97.99 296	98.25 316	98.15 101	99.38 390	96.87 227	99.57 234	99.42 190

BP-MVS1		97.40 270	96.97 283	98.71 194	99.07 234	96.81 243	98.34 151	97.18 374	98.58 148	98.17 277	98.61 277	84.01 395	99.94 41	98.97 86	99.78 140	99.37 212

9.14			97.78 231		99.07 234		97.53 265	99.32 181	95.53 343	98.54 250	98.70 257	97.58 145	99.76 252	94.32 346	99.46 263

PAPM_NR		96.82 309	96.32 320	98.30 255	99.07 234	96.69 251	97.48 271	98.76 311	95.81 335	96.61 376	96.47 392	94.12 298	99.17 412	90.82 414	97.78 393	99.06 281

TAMVS		98.24 197	98.05 208	98.80 174	99.07 234	97.18 224	97.88 212	98.81 304	96.66 302	99.17 151	99.21 136	94.81 279	99.77 246	96.96 217	99.88 89	99.44 183

CLD-MVS		97.49 261	97.16 273	98.48 233	99.07 234	97.03 231	94.71 408	99.21 224	94.46 369	98.06 290	97.16 378	97.57 146	99.48 372	94.46 338	99.78 140	98.95 302
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 62	99.10 69	99.24 102	99.06 239	99.15 52	99.36 22	99.88 14	99.36 60	98.21 276	98.46 297	98.68 50	99.93 51	99.03 82	99.85 100	98.64 349

thres100view900		94.19 371	93.67 376	95.75 388	99.06 239	91.35 396	98.03 187	94.24 422	98.33 163	97.40 339	94.98 422	79.84 411	99.62 322	83.05 435	98.08 384	96.29 429

thres600view7		94.45 366	93.83 373	96.29 372	99.06 239	91.53 391	97.99 199	94.24 422	98.34 162	97.44 337	95.01 420	79.84 411	99.67 297	84.33 433	98.23 373	97.66 410

plane_prior1					99.05 242

YYNet1		97.60 252	97.67 240	97.39 330	99.04 243	93.04 369	95.27 394	98.38 338	97.25 263	98.92 192	98.95 209	95.48 261	99.73 269	96.99 213	98.74 348	99.41 193

MDA-MVSNet_test_wron		97.60 252	97.66 243	97.41 329	99.04 243	93.09 365	95.27 394	98.42 335	97.26 262	98.88 199	98.95 209	95.43 262	99.73 269	97.02 210	98.72 350	99.41 193

MIMVSNet		96.62 316	96.25 324	97.71 302	99.04 243	94.66 322	99.16 54	96.92 385	97.23 269	97.87 303	99.10 165	86.11 378	99.65 313	91.65 398	99.21 303	98.82 321

PatchMatch-RL		97.24 283	96.78 298	98.61 210	99.03 246	97.83 174	96.36 342	99.06 256	93.49 389	97.36 343	97.78 348	95.75 251	99.49 369	93.44 370	98.77 347	98.52 358

GDP-MVS		97.50 258	97.11 277	98.67 198	99.02 247	96.85 241	98.16 167	99.71 44	98.32 165	98.52 253	98.54 284	83.39 399	99.95 26	98.79 97	99.56 237	99.19 263

ZD-MVS					99.01 248	98.84 82		99.07 255	94.10 379	98.05 292	98.12 326	96.36 223	99.86 134	92.70 386	99.19 307

CDPH-MVS		97.26 280	96.66 307	99.07 130	99.00 249	98.15 135	96.03 362	99.01 270	91.21 415	97.79 310	97.85 346	96.89 190	99.69 285	92.75 384	99.38 275	99.39 203

diffmvs		98.22 198	98.24 185	98.17 266	99.00 249	95.44 295	96.38 341	99.58 70	97.79 210	98.53 251	98.50 293	96.76 201	99.74 264	97.95 155	99.64 208	99.34 225
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		98.40 173	98.19 191	99.03 140	99.00 249	97.65 192	96.85 315	98.94 275	98.57 149	98.89 196	98.50 293	95.60 255	99.85 147	97.54 180	99.85 100	99.59 101

plane_prior6					98.99 252	97.70 190						94.90 273

xiu_mvs_v1_base_debu		97.86 232	98.17 193	96.92 351	98.98 253	93.91 347	96.45 335	99.17 238	97.85 206	98.41 262	97.14 380	98.47 66	99.92 61	98.02 148	99.05 321	96.92 422

xiu_mvs_v1_base		97.86 232	98.17 193	96.92 351	98.98 253	93.91 347	96.45 335	99.17 238	97.85 206	98.41 262	97.14 380	98.47 66	99.92 61	98.02 148	99.05 321	96.92 422

xiu_mvs_v1_base_debi		97.86 232	98.17 193	96.92 351	98.98 253	93.91 347	96.45 335	99.17 238	97.85 206	98.41 262	97.14 380	98.47 66	99.92 61	98.02 148	99.05 321	96.92 422

MVP-Stereo		98.08 211	97.92 223	98.57 217	98.96 256	96.79 244	97.90 210	99.18 234	96.41 312	98.46 257	98.95 209	95.93 246	99.60 330	96.51 264	98.98 335	99.31 236
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 173	98.68 118	97.54 318	98.96 256	97.99 155	97.88 212	99.36 161	98.20 180	99.63 63	99.04 180	98.76 42	95.33 445	96.56 258	99.74 162	99.31 236
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				98.91 161	98.94 258	97.76 184		98.76 311	87.58 432	96.75 371	98.10 328	94.80 280	99.78 240	92.73 385	99.00 330	99.20 258

USDC		97.41 269	97.40 258	97.44 327	98.94 258	93.67 357	95.17 397	99.53 95	94.03 381	98.97 178	99.10 165	95.29 264	99.34 395	95.84 302	99.73 165	99.30 239

tfpn200view9		94.03 375	93.44 378	95.78 387	98.93 260	91.44 394	97.60 256	94.29 420	97.94 198	97.10 349	94.31 429	79.67 413	99.62 322	83.05 435	98.08 384	96.29 429

testdata				98.09 270	98.93 260	95.40 297		98.80 306	90.08 423	97.45 336	98.37 306	95.26 265	99.70 281	93.58 366	98.95 338	99.17 270

thres400		94.14 373	93.44 378	96.24 375	98.93 260	91.44 394	97.60 256	94.29 420	97.94 198	97.10 349	94.31 429	79.67 413	99.62 322	83.05 435	98.08 384	97.66 410

TAPA-MVS	96.21 11	96.63 315	95.95 326	98.65 199	98.93 260	98.09 142	96.93 311	99.28 206	83.58 438	98.13 284	97.78 348	96.13 230	99.40 386	93.52 367	99.29 289	98.45 363
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 264	96.93 238	95.54 384	98.78 309	85.72 435	96.86 366	98.11 327	94.43 287			99.10 320	99.23 253

PVSNet_BlendedMVS		97.55 257	97.53 251	97.60 310	98.92 264	93.77 354	96.64 326	99.43 137	94.49 367	97.62 319	99.18 143	96.82 195	99.67 297	94.73 330	99.93 53	99.36 219

PVSNet_Blended		96.88 305	96.68 304	97.47 325	98.92 264	93.77 354	94.71 408	99.43 137	90.98 417	97.62 319	97.36 374	96.82 195	99.67 297	94.73 330	99.56 237	98.98 296

MSDG		97.71 245	97.52 252	98.28 257	98.91 267	96.82 242	94.42 418	99.37 157	97.65 218	98.37 267	98.29 315	97.40 162	99.33 397	94.09 352	99.22 300	98.68 347

Anonymous202405211		97.90 225	97.50 253	99.08 128	98.90 268	98.25 125	98.53 121	96.16 397	98.87 124	99.11 153	98.86 227	90.40 349	99.78 240	97.36 188	99.31 284	99.19 263

原ACMM1				98.35 250	98.90 268	96.25 265		98.83 303	92.48 401	96.07 392	98.10 328	95.39 263	99.71 277	92.61 388	98.99 332	99.08 278

GBi-Net		98.65 137	98.47 150	99.17 111	98.90 268	98.24 126	99.20 48	99.44 131	98.59 145	98.95 182	99.55 57	94.14 295	99.86 134	97.77 166	99.69 188	99.41 193

test1		98.65 137	98.47 150	99.17 111	98.90 268	98.24 126	99.20 48	99.44 131	98.59 145	98.95 182	99.55 57	94.14 295	99.86 134	97.77 166	99.69 188	99.41 193

FMVSNet2		98.49 164	98.40 160	98.75 187	98.90 268	97.14 228	98.61 112	99.13 247	98.59 145	99.19 146	99.28 115	94.14 295	99.82 193	97.97 153	99.80 130	99.29 241

OMC-MVS		97.88 229	97.49 254	99.04 139	98.89 273	98.63 95	96.94 309	99.25 215	95.02 356	98.53 251	98.51 289	97.27 169	99.47 375	93.50 369	99.51 252	99.01 290

VortexMVS		97.98 222	98.31 175	97.02 345	98.88 274	91.45 393	98.03 187	99.47 119	98.65 136	99.55 71	99.47 76	91.49 338	99.81 208	99.32 57	99.91 74	99.80 38

MVSFormer		98.26 194	98.43 156	97.77 292	98.88 274	93.89 350	99.39 20	99.56 84	99.11 90	98.16 280	98.13 324	93.81 303	99.97 7	99.26 62	99.57 234	99.43 187

lupinMVS		97.06 295	96.86 291	97.65 305	98.88 274	93.89 350	95.48 388	97.97 352	93.53 387	98.16 280	97.58 360	93.81 303	99.91 70	96.77 235	99.57 234	99.17 270

dmvs_re		95.98 336	95.39 346	97.74 298	98.86 277	97.45 205	98.37 147	95.69 409	97.95 196	96.56 377	95.95 401	90.70 346	97.68 439	88.32 423	96.13 426	98.11 385

DELS-MVS		98.27 192	98.20 188	98.48 233	98.86 277	96.70 250	95.60 383	99.20 226	97.73 213	98.45 258	98.71 254	97.50 155	99.82 193	98.21 134	99.59 225	98.93 307
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		97.89 227	97.98 215	97.60 310	98.86 277	94.35 330	96.21 351	99.44 131	97.45 245	99.06 160	98.88 224	97.99 114	99.28 405	94.38 345	99.58 230	99.18 266

LCM-MVSNet-Re		98.64 139	98.48 148	99.11 121	98.85 280	98.51 108	98.49 132	99.83 25	98.37 160	99.69 52	99.46 78	98.21 93	99.92 61	94.13 351	99.30 287	98.91 311

pmmvs4		97.58 255	97.28 266	98.51 228	98.84 281	96.93 238	95.40 392	98.52 330	93.60 386	98.61 237	98.65 268	95.10 269	99.60 330	96.97 216	99.79 135	98.99 295

NP-MVS					98.84 281	97.39 209					96.84 383

sss		97.21 285	96.93 285	98.06 275	98.83 283	95.22 304	96.75 321	98.48 332	94.49 367	97.27 345	97.90 343	92.77 321	99.80 216	96.57 254	99.32 282	99.16 273

PVSNet	93.40 17	95.67 345	95.70 331	95.57 392	98.83 283	88.57 419	92.50 435	97.72 357	92.69 399	96.49 384	96.44 393	93.72 306	99.43 382	93.61 364	99.28 290	98.71 340

MVE	83.40 22	92.50 398	91.92 400	94.25 408	98.83 283	91.64 390	92.71 434	83.52 448	95.92 332	86.46 446	95.46 414	95.20 266	95.40 444	80.51 440	98.64 359	95.73 437
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 379	93.91 371	93.39 420	98.82 286	81.72 447	97.76 232	95.28 411	98.60 144	96.54 378	96.66 387	65.85 443	99.62 322	96.65 247	98.99 332	98.82 321

ambc				98.24 261	98.82 286	95.97 276	98.62 111	99.00 272		99.27 132	99.21 136	96.99 186	99.50 366	96.55 261	99.50 259	99.26 247

旧先验1					98.82 286	97.45 205		98.76 311			98.34 310	95.50 260			99.01 329	99.23 253

test_vis1_rt		97.75 242	97.72 237	97.83 287	98.81 289	96.35 262	97.30 286	99.69 48	94.61 365	97.87 303	98.05 333	96.26 226	98.32 433	98.74 103	98.18 376	98.82 321

WTY-MVS		96.67 313	96.27 323	97.87 285	98.81 289	94.61 324	96.77 319	97.92 354	94.94 359	97.12 348	97.74 351	91.11 342	99.82 193	93.89 357	98.15 380	99.18 266

3Dnovator+	97.89 3	98.69 127	98.51 141	99.24 102	98.81 289	98.40 113	99.02 69	99.19 230	98.99 111	98.07 289	99.28 115	97.11 179	99.84 165	96.84 230	99.32 282	99.47 173

QAPM		97.31 276	96.81 297	98.82 170	98.80 292	97.49 200	99.06 65	99.19 230	90.22 421	97.69 316	99.16 149	96.91 189	99.90 77	90.89 413	99.41 270	99.07 280

VNet		98.42 170	98.30 176	98.79 177	98.79 293	97.29 213	98.23 158	98.66 321	99.31 65	98.85 204	98.80 240	94.80 280	99.78 240	98.13 139	99.13 315	99.31 236

DPM-MVS		96.32 325	95.59 337	98.51 228	98.76 294	97.21 221	94.54 417	98.26 341	91.94 406	96.37 385	97.25 376	93.06 315	99.43 382	91.42 403	98.74 348	98.89 313

3Dnovator	98.27 2	98.81 107	98.73 107	99.05 137	98.76 294	97.81 181	99.25 43	99.30 194	98.57 149	98.55 248	99.33 105	97.95 116	99.90 77	97.16 198	99.67 199	99.44 183

PLC	94.65 16	96.51 318	95.73 330	98.85 167	98.75 296	97.91 167	96.42 339	99.06 256	90.94 418	95.59 398	97.38 372	94.41 288	99.59 334	90.93 411	98.04 389	99.05 282
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 307	96.75 300	97.08 342	98.74 297	93.33 363	96.71 323	98.26 341	96.72 299	98.44 259	97.37 373	95.20 266	99.47 375	91.89 393	97.43 403	98.44 366

hse-mvs2		97.46 263	97.07 278	98.64 201	98.73 298	97.33 211	97.45 274	97.64 364	99.11 90	98.58 243	97.98 337	88.65 363	99.79 229	98.11 140	97.39 405	98.81 326

CDS-MVSNet		97.69 246	97.35 263	98.69 195	98.73 298	97.02 232	96.92 313	98.75 314	95.89 333	98.59 241	98.67 263	92.08 332	99.74 264	96.72 241	99.81 119	99.32 232
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EIA-MVS		98.00 218	97.74 234	98.80 174	98.72 300	98.09 142	98.05 184	99.60 67	97.39 249	96.63 374	95.55 409	97.68 134	99.80 216	96.73 240	99.27 291	98.52 358

LFMVS		97.20 286	96.72 301	98.64 201	98.72 300	96.95 236	98.93 81	94.14 424	99.74 13	98.78 214	99.01 192	84.45 390	99.73 269	97.44 184	99.27 291	99.25 248

new_pmnet		96.99 302	96.76 299	97.67 303	98.72 300	94.89 313	95.95 368	98.20 344	92.62 400	98.55 248	98.54 284	94.88 276	99.52 360	93.96 355	99.44 268	98.59 355

Fast-Effi-MVS+		97.67 248	97.38 260	98.57 217	98.71 303	97.43 207	97.23 291	99.45 127	94.82 362	96.13 389	96.51 389	98.52 64	99.91 70	96.19 283	98.83 344	98.37 375

TEST9					98.71 303	98.08 146	95.96 366	99.03 264	91.40 412	95.85 395	97.53 362	96.52 214	99.76 252

train_agg		97.10 292	96.45 317	99.07 130	98.71 303	98.08 146	95.96 366	99.03 264	91.64 407	95.85 395	97.53 362	96.47 216	99.76 252	93.67 363	99.16 310	99.36 219

TSAR-MVS + GP.		98.18 203	97.98 215	98.77 184	98.71 303	97.88 169	96.32 345	98.66 321	96.33 314	99.23 143	98.51 289	97.48 159	99.40 386	97.16 198	99.46 263	99.02 289

FA-MVS(test-final)		96.99 302	96.82 295	97.50 322	98.70 307	94.78 316	99.34 23	96.99 380	95.07 355	98.48 256	99.33 105	88.41 366	99.65 313	96.13 289	98.92 341	98.07 388

AUN-MVS		96.24 330	95.45 342	98.60 212	98.70 307	97.22 219	97.38 278	97.65 362	95.95 331	95.53 405	97.96 341	82.11 407	99.79 229	96.31 276	97.44 402	98.80 331

our_test_3		97.39 271	97.73 236	96.34 370	98.70 307	89.78 415	94.61 414	98.97 274	96.50 307	99.04 167	98.85 230	95.98 242	99.84 165	97.26 193	99.67 199	99.41 193

ppachtmachnet_test		97.50 258	97.74 234	96.78 360	98.70 307	91.23 402	94.55 416	99.05 259	96.36 313	99.21 144	98.79 242	96.39 219	99.78 240	96.74 238	99.82 115	99.34 225

PCF-MVS	92.86 18	94.36 367	93.00 385	98.42 240	98.70 307	97.56 197	93.16 433	99.11 250	79.59 442	97.55 326	97.43 369	92.19 329	99.73 269	79.85 441	99.45 265	97.97 394
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 224	98.02 211	97.58 312	98.69 312	94.10 337	98.13 170	98.90 284	97.95 196	97.32 344	99.58 47	95.95 245	98.75 428	96.41 270	99.22 300	99.87 20

ETV-MVS		98.03 214	97.86 228	98.56 221	98.69 312	98.07 148	97.51 268	99.50 102	98.10 188	97.50 331	95.51 410	98.41 72	99.88 107	96.27 279	99.24 296	97.71 409

test_prior				98.95 154	98.69 312	97.95 163		99.03 264					99.59 334			99.30 239

mvsmamba		97.57 256	97.26 267	98.51 228	98.69 312	96.73 249	98.74 96	97.25 373	97.03 283	97.88 302	99.23 134	90.95 343	99.87 126	96.61 250	99.00 330	98.91 311

agg_prior					98.68 316	97.99 155		99.01 270		95.59 398			99.77 246

test_8					98.67 317	98.01 154	95.91 372	99.02 267	91.64 407	95.79 397	97.50 365	96.47 216	99.76 252

HQP-NCC					98.67 317		96.29 347		96.05 324	95.55 401

ACMP_Plane					98.67 317		96.29 347		96.05 324	95.55 401

CNVR-MVS		98.17 205	97.87 227	99.07 130	98.67 317	98.24 126	97.01 305	98.93 278	97.25 263	97.62 319	98.34 310	97.27 169	99.57 342	96.42 269	99.33 281	99.39 203

HQP-MVS		97.00 301	96.49 316	98.55 222	98.67 317	96.79 244	96.29 347	99.04 262	96.05 324	95.55 401	96.84 383	93.84 301	99.54 354	92.82 381	99.26 294	99.32 232

MM		98.22 198	97.99 214	98.91 161	98.66 322	96.97 233	97.89 211	94.44 418	99.54 37	98.95 182	99.14 156	93.50 307	99.92 61	99.80 14	99.96 27	99.85 28

test_fmvs1		97.72 244	97.94 220	97.07 344	98.66 322	92.39 380	97.68 241	99.81 30	95.20 354	99.54 73	99.44 83	91.56 337	99.41 385	99.78 18	99.77 146	99.40 202

balanced_conf03		98.63 141	98.72 109	98.38 245	98.66 322	96.68 252	98.90 83	99.42 142	98.99 111	98.97 178	99.19 139	95.81 250	99.85 147	98.77 101	99.77 146	98.60 352

thres200		93.72 381	93.14 383	95.46 396	98.66 322	91.29 398	96.61 328	94.63 417	97.39 249	96.83 367	93.71 432	79.88 410	99.56 345	82.40 438	98.13 381	95.54 438

wuyk23d		96.06 332	97.62 247	91.38 425	98.65 326	98.57 102	98.85 91	96.95 383	96.86 292	99.90 13	99.16 149	99.18 18	98.40 432	89.23 421	99.77 146	77.18 445

NCCC		97.86 232	97.47 257	99.05 137	98.61 327	98.07 148	96.98 307	98.90 284	97.63 219	97.04 353	97.93 342	95.99 241	99.66 308	95.31 318	98.82 346	99.43 187

DeepC-MVS_fast	96.85 6	98.30 188	98.15 197	98.75 187	98.61 327	97.23 217	97.76 232	99.09 253	97.31 257	98.75 220	98.66 266	97.56 147	99.64 316	96.10 290	99.55 241	99.39 203
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 383	92.09 394	97.75 296	98.60 329	94.40 328	97.32 284	95.26 412	97.56 229	96.79 370	95.50 411	53.57 451	99.77 246	95.26 319	98.97 336	99.08 278

thisisatest0515		94.12 374	93.16 382	96.97 349	98.60 329	92.90 370	93.77 429	90.61 437	94.10 379	96.91 360	95.87 404	74.99 425	99.80 216	94.52 336	99.12 318	98.20 381

GA-MVS		95.86 339	95.32 349	97.49 323	98.60 329	94.15 336	93.83 428	97.93 353	95.49 344	96.68 372	97.42 370	83.21 400	99.30 401	96.22 281	98.55 365	99.01 290

dmvs_testset		92.94 393	92.21 393	95.13 400	98.59 332	90.99 405	97.65 247	92.09 433	96.95 286	94.00 425	93.55 433	92.34 327	96.97 442	72.20 444	92.52 440	97.43 417

OPU-MVS				98.82 170	98.59 332	98.30 122	98.10 176				98.52 288	98.18 95	98.75 428	94.62 333	99.48 262	99.41 193

MSLP-MVS++		98.02 215	98.14 199	97.64 307	98.58 334	95.19 305	97.48 271	99.23 222	97.47 238	97.90 300	98.62 275	97.04 181	98.81 426	97.55 178	99.41 270	98.94 306

test12				98.93 157	98.58 334	97.83 174		98.66 321		96.53 379		95.51 259	99.69 285		99.13 315	99.27 244

CL-MVSNet_self_test		97.44 266	97.22 270	98.08 273	98.57 336	95.78 283	94.30 421	98.79 307	96.58 305	98.60 239	98.19 322	94.74 283	99.64 316	96.41 270	98.84 343	98.82 321

PS-MVSNAJ		97.08 294	97.39 259	96.16 381	98.56 337	92.46 378	95.24 396	98.85 298	97.25 263	97.49 332	95.99 400	98.07 105	99.90 77	96.37 272	98.67 358	96.12 434

CNLPA		97.17 289	96.71 302	98.55 222	98.56 337	98.05 152	96.33 344	98.93 278	96.91 289	97.06 352	97.39 371	94.38 290	99.45 379	91.66 397	99.18 309	98.14 384

xiu_mvs_v2_base		97.16 290	97.49 254	96.17 379	98.54 339	92.46 378	95.45 389	98.84 299	97.25 263	97.48 333	96.49 390	98.31 82	99.90 77	96.34 275	98.68 357	96.15 433

alignmvs		97.35 273	96.88 290	98.78 180	98.54 339	98.09 142	97.71 238	97.69 359	99.20 78	97.59 322	95.90 403	88.12 368	99.55 349	98.18 136	98.96 337	98.70 343

FE-MVS		95.66 346	94.95 359	97.77 292	98.53 341	95.28 301	99.40 19	96.09 400	93.11 393	97.96 297	99.26 122	79.10 417	99.77 246	92.40 390	98.71 352	98.27 379

Effi-MVS+		98.02 215	97.82 230	98.62 207	98.53 341	97.19 223	97.33 283	99.68 53	97.30 258	96.68 372	97.46 368	98.56 62	99.80 216	96.63 248	98.20 375	98.86 318

baseline1		95.96 337	95.44 343	97.52 320	98.51 343	93.99 344	98.39 145	96.09 400	98.21 176	98.40 266	97.76 350	86.88 370	99.63 319	95.42 316	89.27 443	98.95 302

MVS_Test		98.18 203	98.36 167	97.67 303	98.48 344	94.73 319	98.18 163	99.02 267	97.69 215	98.04 293	99.11 162	97.22 173	99.56 345	98.57 115	98.90 342	98.71 340

MGCFI-Net		98.34 181	98.28 178	98.51 228	98.47 345	97.59 196	98.96 77	99.48 111	99.18 85	97.40 339	95.50 411	98.66 51	99.50 366	98.18 136	98.71 352	98.44 366

BH-RMVSNet		96.83 307	96.58 312	97.58 312	98.47 345	94.05 338	96.67 325	97.36 368	96.70 301	97.87 303	97.98 337	95.14 268	99.44 381	90.47 416	98.58 364	99.25 248

sasdasda		98.34 181	98.26 182	98.58 214	98.46 347	97.82 178	98.96 77	99.46 123	99.19 82	97.46 334	95.46 414	98.59 58	99.46 377	98.08 143	98.71 352	98.46 360

canonicalmvs		98.34 181	98.26 182	98.58 214	98.46 347	97.82 178	98.96 77	99.46 123	99.19 82	97.46 334	95.46 414	98.59 58	99.46 377	98.08 143	98.71 352	98.46 360

MVS-HIRNet		94.32 368	95.62 334	90.42 426	98.46 347	75.36 450	96.29 347	89.13 441	95.25 351	95.38 407	99.75 16	92.88 318	99.19 411	94.07 353	99.39 272	96.72 427

PHI-MVS		98.29 191	97.95 218	99.34 79	98.44 350	99.16 48	98.12 173	99.38 153	96.01 328	98.06 290	98.43 300	97.80 128	99.67 297	95.69 308	99.58 230	99.20 258

DVP-MVS++		98.90 94	98.70 115	99.51 48	98.43 351	99.15 52	99.43 15	99.32 181	98.17 183	99.26 136	99.02 183	98.18 95	99.88 107	97.07 207	99.45 265	99.49 154

MSC_two_6792asdad				99.32 87	98.43 351	98.37 117		98.86 295					99.89 92	97.14 201	99.60 221	99.71 58

No_MVS				99.32 87	98.43 351	98.37 117		98.86 295					99.89 92	97.14 201	99.60 221	99.71 58

Fast-Effi-MVS+-dtu		98.27 192	98.09 202	98.81 172	98.43 351	98.11 139	97.61 255	99.50 102	98.64 137	97.39 341	97.52 364	98.12 103	99.95 26	96.90 224	98.71 352	98.38 373

OpenMVS_ROB	95.38 14	95.84 341	95.18 354	97.81 289	98.41 355	97.15 227	97.37 280	98.62 325	83.86 437	98.65 231	98.37 306	94.29 293	99.68 294	88.41 422	98.62 362	96.60 428

DeepPCF-MVS	96.93 5	98.32 185	98.01 212	99.23 104	98.39 356	98.97 73	95.03 401	99.18 234	96.88 290	99.33 120	98.78 244	98.16 99	99.28 405	96.74 238	99.62 214	99.44 183

Patchmatch-test		96.55 317	96.34 319	97.17 339	98.35 357	93.06 366	98.40 144	97.79 355	97.33 254	98.41 262	98.67 263	83.68 398	99.69 285	95.16 321	99.31 284	98.77 334

AdaColmap		97.14 291	96.71 302	98.46 235	98.34 358	97.80 182	96.95 308	98.93 278	95.58 341	96.92 358	97.66 355	95.87 248	99.53 356	90.97 410	99.14 313	98.04 389

OpenMVS	96.65 7	97.09 293	96.68 304	98.32 252	98.32 359	97.16 226	98.86 90	99.37 157	89.48 425	96.29 387	99.15 153	96.56 212	99.90 77	92.90 378	99.20 304	97.89 397

MG-MVS		96.77 310	96.61 309	97.26 335	98.31 360	93.06 366	95.93 369	98.12 349	96.45 311	97.92 298	98.73 251	93.77 305	99.39 388	91.19 408	99.04 324	99.33 230

test_yl		96.69 311	96.29 321	97.90 282	98.28 361	95.24 302	97.29 287	97.36 368	98.21 176	98.17 277	97.86 344	86.27 374	99.55 349	94.87 327	98.32 369	98.89 313

DCV-MVSNet		96.69 311	96.29 321	97.90 282	98.28 361	95.24 302	97.29 287	97.36 368	98.21 176	98.17 277	97.86 344	86.27 374	99.55 349	94.87 327	98.32 369	98.89 313

CHOSEN 280x420		95.51 351	95.47 340	95.65 391	98.25 363	88.27 422	93.25 432	98.88 288	93.53 387	94.65 416	97.15 379	86.17 376	99.93 51	97.41 186	99.93 53	98.73 339

SCA		96.41 324	96.66 307	95.67 389	98.24 364	88.35 421	95.85 375	96.88 386	96.11 322	97.67 317	98.67 263	93.10 313	99.85 147	94.16 347	99.22 300	98.81 326

DeepMVS_CX				93.44 419	98.24 364	94.21 333		94.34 419	64.28 445	91.34 439	94.87 426	89.45 357	92.77 446	77.54 443	93.14 439	93.35 441

MS-PatchMatch		97.68 247	97.75 233	97.45 326	98.23 366	93.78 353	97.29 287	98.84 299	96.10 323	98.64 232	98.65 268	96.04 234	99.36 391	96.84 230	99.14 313	99.20 258

BH-w/o		95.13 357	94.89 361	95.86 384	98.20 367	91.31 397	95.65 381	97.37 367	93.64 385	96.52 380	95.70 407	93.04 316	99.02 417	88.10 424	95.82 429	97.24 420

mvs_anonymous		97.83 240	98.16 196	96.87 354	98.18 368	91.89 387	97.31 285	98.90 284	97.37 251	98.83 207	99.46 78	96.28 225	99.79 229	98.90 90	98.16 379	98.95 302

miper_lstm_enhance		97.18 288	97.16 273	97.25 336	98.16 369	92.85 371	95.15 399	99.31 186	97.25 263	98.74 222	98.78 244	90.07 350	99.78 240	97.19 196	99.80 130	99.11 277

RRT-MVS		97.88 229	97.98 215	97.61 309	98.15 370	93.77 354	98.97 76	99.64 60	99.16 87	98.69 225	99.42 86	91.60 335	99.89 92	97.63 174	98.52 366	99.16 273

ET-MVSNet_ETH3D		94.30 370	93.21 381	97.58 312	98.14 371	94.47 327	94.78 407	93.24 429	94.72 363	89.56 441	95.87 404	78.57 420	99.81 208	96.91 219	97.11 414	98.46 360

ADS-MVSNet2		95.43 352	94.98 357	96.76 361	98.14 371	91.74 388	97.92 207	97.76 356	90.23 419	96.51 381	98.91 214	85.61 381	99.85 147	92.88 379	96.90 415	98.69 344

ADS-MVSNet		95.24 355	94.93 360	96.18 378	98.14 371	90.10 414	97.92 207	97.32 371	90.23 419	96.51 381	98.91 214	85.61 381	99.74 264	92.88 379	96.90 415	98.69 344

c3_l		97.36 272	97.37 261	97.31 331	98.09 374	93.25 364	95.01 402	99.16 241	97.05 280	98.77 217	98.72 253	92.88 318	99.64 316	96.93 218	99.76 158	99.05 282

FMVSNet3		97.50 258	97.24 269	98.29 256	98.08 375	95.83 281	97.86 216	98.91 283	97.89 203	98.95 182	98.95 209	87.06 369	99.81 208	97.77 166	99.69 188	99.23 253

PAPM		91.88 407	90.34 410	96.51 365	98.06 376	92.56 376	92.44 436	97.17 375	86.35 433	90.38 440	96.01 399	86.61 372	99.21 410	70.65 446	95.43 431	97.75 406

Effi-MVS+-dtu		98.26 194	97.90 225	99.35 76	98.02 377	99.49 6	98.02 190	99.16 241	98.29 170	97.64 318	97.99 336	96.44 218	99.95 26	96.66 246	98.93 340	98.60 352

eth_miper_zixun_eth		97.23 284	97.25 268	97.17 339	98.00 378	92.77 373	94.71 408	99.18 234	97.27 261	98.56 246	98.74 250	91.89 333	99.69 285	97.06 209	99.81 119	99.05 282

HY-MVS	95.94 13	95.90 338	95.35 348	97.55 317	97.95 379	94.79 315	98.81 95	96.94 384	92.28 404	95.17 409	98.57 282	89.90 352	99.75 259	91.20 407	97.33 410	98.10 386

UGNet		98.53 158	98.45 153	98.79 177	97.94 380	96.96 235	99.08 61	98.54 328	99.10 97	96.82 368	99.47 76	96.55 213	99.84 165	98.56 118	99.94 48	99.55 127
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		96.47 322	95.70 331	98.79 177	97.92 381	99.12 62	98.28 153	98.60 326	92.16 405	95.54 404	96.17 397	94.77 282	99.52 360	89.62 419	98.23 373	97.72 408
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		96.86 306	96.55 313	97.79 290	97.91 382	94.21 333	97.56 261	98.87 290	97.49 237	99.06 160	99.05 178	80.72 408	99.80 216	98.44 122	99.82 115	99.37 212

API-MVS		97.04 297	96.91 289	97.42 328	97.88 383	98.23 130	98.18 163	98.50 331	97.57 227	97.39 341	96.75 385	96.77 199	99.15 414	90.16 417	99.02 328	94.88 439

myMVS_eth3d28		92.92 394	92.31 390	94.77 403	97.84 384	87.59 426	96.19 353	96.11 399	97.08 279	94.27 419	93.49 435	66.07 442	98.78 427	91.78 395	97.93 392	97.92 396

miper_ehance_all_eth		97.06 295	97.03 280	97.16 341	97.83 385	93.06 366	94.66 411	99.09 253	95.99 329	98.69 225	98.45 298	92.73 323	99.61 329	96.79 232	99.03 325	98.82 321

cl____		97.02 298	96.83 294	97.58 312	97.82 386	94.04 340	94.66 411	99.16 241	97.04 281	98.63 233	98.71 254	88.68 362	99.69 285	97.00 211	99.81 119	99.00 294

DIV-MVS_self_test		97.02 298	96.84 293	97.58 312	97.82 386	94.03 341	94.66 411	99.16 241	97.04 281	98.63 233	98.71 254	88.69 360	99.69 285	97.00 211	99.81 119	99.01 290

CANet		97.87 231	97.76 232	98.19 265	97.75 388	95.51 290	96.76 320	99.05 259	97.74 212	96.93 357	98.21 320	95.59 256	99.89 92	97.86 161	99.93 53	99.19 263

UBG		93.25 388	92.32 389	96.04 383	97.72 389	90.16 413	95.92 371	95.91 404	96.03 327	93.95 427	93.04 438	69.60 432	99.52 360	90.72 415	97.98 390	98.45 363

mvsany_test1		97.60 252	97.54 250	97.77 292	97.72 389	95.35 298	95.36 393	97.13 377	94.13 378	99.71 46	99.33 105	97.93 117	99.30 401	97.60 177	98.94 339	98.67 348

PVSNet_0	89.98 21	91.15 408	90.30 411	93.70 416	97.72 389	84.34 440	90.24 439	97.42 366	90.20 422	93.79 428	93.09 437	90.90 345	98.89 425	86.57 430	72.76 446	97.87 399

CR-MVSNet		96.28 327	95.95 326	97.28 333	97.71 392	94.22 331	98.11 174	98.92 281	92.31 403	96.91 360	99.37 94	85.44 384	99.81 208	97.39 187	97.36 408	97.81 402

RPMNet		97.02 298	96.93 285	97.30 332	97.71 392	94.22 331	98.11 174	99.30 194	99.37 57	96.91 360	99.34 103	86.72 371	99.87 126	97.53 181	97.36 408	97.81 402

ETVMVS		92.60 397	91.08 406	97.18 337	97.70 394	93.65 359	96.54 329	95.70 407	96.51 306	94.68 415	92.39 441	61.80 448	99.50 366	86.97 427	97.41 404	98.40 371

pmmvs3		95.03 359	94.40 366	96.93 350	97.70 394	92.53 377	95.08 400	97.71 358	88.57 429	97.71 314	98.08 331	79.39 415	99.82 193	96.19 283	99.11 319	98.43 368

baseline2		93.73 380	92.83 386	96.42 368	97.70 394	91.28 399	96.84 316	89.77 440	93.96 383	92.44 435	95.93 402	79.14 416	99.77 246	92.94 377	96.76 419	98.21 380

WBMVS		95.18 356	94.78 362	96.37 369	97.68 397	89.74 416	95.80 377	98.73 317	97.54 232	98.30 268	98.44 299	70.06 430	99.82 193	96.62 249	99.87 93	99.54 131

tpm		94.67 364	94.34 368	95.66 390	97.68 397	88.42 420	97.88 212	94.90 414	94.46 369	96.03 394	98.56 283	78.66 418	99.79 229	95.88 296	95.01 433	98.78 333

CANet_DTU		97.26 280	97.06 279	97.84 286	97.57 399	94.65 323	96.19 353	98.79 307	97.23 269	95.14 410	98.24 317	93.22 310	99.84 165	97.34 189	99.84 104	99.04 286

testing11		93.08 391	92.02 396	96.26 374	97.56 400	90.83 408	96.32 345	95.70 407	96.47 310	92.66 434	93.73 431	64.36 446	99.59 334	93.77 362	97.57 397	98.37 375

tpm2		93.09 390	92.58 388	94.62 405	97.56 400	86.53 429	97.66 245	95.79 406	86.15 434	94.07 424	98.23 319	75.95 423	99.53 356	90.91 412	96.86 418	97.81 402

testing91		93.32 386	92.27 391	96.47 367	97.54 402	91.25 400	96.17 357	96.76 388	97.18 273	93.65 430	93.50 434	65.11 445	99.63 319	93.04 376	97.45 401	98.53 357

TR-MVS		95.55 349	95.12 355	96.86 357	97.54 402	93.94 345	96.49 334	96.53 393	94.36 374	97.03 355	96.61 388	94.26 294	99.16 413	86.91 429	96.31 423	97.47 416

testing99		93.04 392	91.98 399	96.23 376	97.53 404	90.70 410	96.35 343	95.94 403	96.87 291	93.41 431	93.43 436	63.84 447	99.59 334	93.24 374	97.19 411	98.40 371

1314		95.74 343	95.60 335	96.17 379	97.53 404	92.75 374	98.07 181	98.31 340	91.22 414	94.25 420	96.68 386	95.53 257	99.03 416	91.64 399	97.18 412	96.74 426

CostFormer		93.97 376	93.78 374	94.51 406	97.53 404	85.83 432	97.98 200	95.96 402	89.29 427	94.99 412	98.63 273	78.63 419	99.62 322	94.54 335	96.50 420	98.09 387

FMVSNet5		96.01 334	95.20 353	98.41 241	97.53 404	96.10 267	98.74 96	99.50 102	97.22 272	98.03 294	99.04 180	69.80 431	99.88 107	97.27 192	99.71 178	99.25 248

PMMVS		96.51 318	95.98 325	98.09 270	97.53 404	95.84 280	94.92 404	98.84 299	91.58 409	96.05 393	95.58 408	95.68 253	99.66 308	95.59 312	98.09 383	98.76 336

reproduce_monomvs		95.00 361	95.25 350	94.22 409	97.51 409	83.34 441	97.86 216	98.44 333	98.51 154	99.29 129	99.30 111	67.68 436	99.56 345	98.89 92	99.81 119	99.77 46

PAPR		95.29 353	94.47 364	97.75 296	97.50 410	95.14 307	94.89 405	98.71 319	91.39 413	95.35 408	95.48 413	94.57 285	99.14 415	84.95 432	97.37 406	98.97 299

testing222		91.96 405	90.37 409	96.72 362	97.47 411	92.59 375	96.11 359	94.76 415	96.83 293	92.90 433	92.87 439	57.92 449	99.55 349	86.93 428	97.52 398	98.00 393

PatchT		96.65 314	96.35 318	97.54 318	97.40 412	95.32 300	97.98 200	96.64 390	99.33 62	96.89 364	99.42 86	84.32 392	99.81 208	97.69 173	97.49 399	97.48 415

tpm cat1		93.29 387	93.13 384	93.75 415	97.39 413	84.74 435	97.39 277	97.65 362	83.39 439	94.16 421	98.41 301	82.86 403	99.39 388	91.56 401	95.35 432	97.14 421

PatchmatchNet		95.58 348	95.67 333	95.30 399	97.34 414	87.32 427	97.65 247	96.65 389	95.30 350	97.07 351	98.69 259	84.77 387	99.75 259	94.97 325	98.64 359	98.83 320
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 273	96.97 283	98.50 232	97.31 415	96.47 258	98.18 163	98.92 281	98.95 118	98.78 214	99.37 94	85.44 384	99.85 147	95.96 294	99.83 111	99.17 270

LS3D		98.63 141	98.38 165	99.36 70	97.25 416	99.38 13	99.12 60	99.32 181	99.21 76	98.44 259	98.88 224	97.31 165	99.80 216	96.58 252	99.34 280	98.92 308

IB-MVS	91.63 19	92.24 403	90.90 407	96.27 373	97.22 417	91.24 401	94.36 420	93.33 428	92.37 402	92.24 437	94.58 428	66.20 441	99.89 92	93.16 375	94.63 435	97.66 410
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		92.38 400	91.76 403	94.21 410	97.16 418	84.65 436	95.42 391	88.45 442	95.96 330	96.17 388	95.84 406	66.36 439	99.71 277	91.87 394	98.64 359	98.28 378

tpmrst		95.07 358	95.46 341	93.91 413	97.11 419	84.36 439	97.62 252	96.96 382	94.98 357	96.35 386	98.80 240	85.46 383	99.59 334	95.60 311	96.23 424	97.79 405

Syy-MVS		96.04 333	95.56 339	97.49 323	97.10 420	94.48 326	96.18 355	96.58 391	95.65 338	94.77 413	92.29 442	91.27 341	99.36 391	98.17 138	98.05 387	98.63 350

myMVS_eth3d		91.92 406	90.45 408	96.30 371	97.10 420	90.90 406	96.18 355	96.58 391	95.65 338	94.77 413	92.29 442	53.88 450	99.36 391	89.59 420	98.05 387	98.63 350

MDTV_nov1_ep13			95.22 352		97.06 422	83.20 442	97.74 235	96.16 397	94.37 373	96.99 356	98.83 234	83.95 396	99.53 356	93.90 356	97.95 391

MVS		93.19 389	92.09 394	96.50 366	96.91 423	94.03 341	98.07 181	98.06 351	68.01 444	94.56 418	96.48 391	95.96 244	99.30 401	83.84 434	96.89 417	96.17 431

E-PMN		94.17 372	94.37 367	93.58 417	96.86 424	85.71 433	90.11 441	97.07 378	98.17 183	97.82 309	97.19 377	84.62 389	98.94 421	89.77 418	97.68 396	96.09 435

JIA-IIPM		95.52 350	95.03 356	97.00 346	96.85 425	94.03 341	96.93 311	95.82 405	99.20 78	94.63 417	99.71 22	83.09 401	99.60 330	94.42 341	94.64 434	97.36 419

EMVS		93.83 378	94.02 370	93.23 422	96.83 426	84.96 434	89.77 442	96.32 395	97.92 200	97.43 338	96.36 396	86.17 376	98.93 422	87.68 425	97.73 395	95.81 436

cl22		95.79 342	95.39 346	96.98 348	96.77 427	92.79 372	94.40 419	98.53 329	94.59 366	97.89 301	98.17 323	82.82 404	99.24 407	96.37 272	99.03 325	98.92 308

WB-MVSnew		95.73 344	95.57 338	96.23 376	96.70 428	90.70 410	96.07 361	93.86 425	95.60 340	97.04 353	95.45 417	96.00 237	99.55 349	91.04 409	98.31 371	98.43 368

dp		93.47 384	93.59 377	93.13 423	96.64 429	81.62 448	97.66 245	96.42 394	92.80 398	96.11 390	98.64 271	78.55 421	99.59 334	93.31 372	92.18 442	98.16 383

MonoMVSNet		96.25 328	96.53 315	95.39 397	96.57 430	91.01 404	98.82 94	97.68 361	98.57 149	98.03 294	99.37 94	90.92 344	97.78 438	94.99 323	93.88 438	97.38 418

test-LLR		93.90 377	93.85 372	94.04 411	96.53 431	84.62 437	94.05 425	92.39 431	96.17 319	94.12 422	95.07 418	82.30 405	99.67 297	95.87 299	98.18 376	97.82 400

test-mter		92.33 402	91.76 403	94.04 411	96.53 431	84.62 437	94.05 425	92.39 431	94.00 382	94.12 422	95.07 418	65.63 444	99.67 297	95.87 299	98.18 376	97.82 400

TESTMET0.1,1		92.19 404	91.77 402	93.46 418	96.48 433	82.80 444	94.05 425	91.52 436	94.45 371	94.00 425	94.88 424	66.65 438	99.56 345	95.78 304	98.11 382	98.02 390

MVS_0304		97.44 266	97.01 282	98.72 193	96.42 434	96.74 248	97.20 296	91.97 434	98.46 157	98.30 268	98.79 242	92.74 322	99.91 70	99.30 59	99.94 48	99.52 143

miper_enhance_ethall		96.01 334	95.74 329	96.81 358	96.41 435	92.27 384	93.69 430	98.89 287	91.14 416	98.30 268	97.35 375	90.58 347	99.58 340	96.31 276	99.03 325	98.60 352

tpmvs		95.02 360	95.25 350	94.33 407	96.39 436	85.87 430	98.08 178	96.83 387	95.46 345	95.51 406	98.69 259	85.91 379	99.53 356	94.16 347	96.23 424	97.58 413

CMPMVS	75.91 23	96.29 326	95.44 343	98.84 168	96.25 437	98.69 94	97.02 304	99.12 248	88.90 428	97.83 307	98.86 227	89.51 355	98.90 424	91.92 392	99.51 252	98.92 308
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 365	93.69 375	96.99 347	96.05 438	93.61 361	94.97 403	93.49 426	96.17 319	97.57 325	94.88 424	82.30 405	99.01 419	93.60 365	94.17 437	98.37 375

EPMVS		93.72 381	93.27 380	95.09 402	96.04 439	87.76 424	98.13 170	85.01 447	94.69 364	96.92 358	98.64 271	78.47 422	99.31 399	95.04 322	96.46 421	98.20 381

cascas		94.79 363	94.33 369	96.15 382	96.02 440	92.36 382	92.34 437	99.26 214	85.34 436	95.08 411	94.96 423	92.96 317	98.53 431	94.41 344	98.59 363	97.56 414

MVStest1		95.86 339	95.60 335	96.63 363	95.87 441	91.70 389	97.93 204	98.94 275	98.03 190	99.56 68	99.66 32	71.83 428	98.26 434	99.35 55	99.24 296	99.91 13

gg-mvs-nofinetune		92.37 401	91.20 405	95.85 385	95.80 442	92.38 381	99.31 30	81.84 449	99.75 11	91.83 438	99.74 18	68.29 433	99.02 417	87.15 426	97.12 413	96.16 432

gm-plane-assit					94.83 443	81.97 446			88.07 431		94.99 421		99.60 330	91.76 396

GG-mvs-BLEND				94.76 404	94.54 444	92.13 386	99.31 30	80.47 450		88.73 444	91.01 444	67.59 437	98.16 437	82.30 439	94.53 436	93.98 440

UWE-MVS-28		90.22 409	89.28 412	93.02 424	94.50 445	82.87 443	96.52 332	87.51 443	95.21 353	92.36 436	96.04 398	71.57 429	98.25 435	72.04 445	97.77 394	97.94 395

EPNet_dtu		94.93 362	94.78 362	95.38 398	93.58 446	87.68 425	96.78 318	95.69 409	97.35 253	89.14 443	98.09 330	88.15 367	99.49 369	94.95 326	99.30 287	98.98 296
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 413	75.95 416	77.12 429	92.39 447	67.91 453	90.16 440	59.44 454	82.04 440	89.42 442	94.67 427	49.68 452	81.74 447	48.06 447	77.66 445	81.72 443

KD-MVS_2432*1600		92.87 395	91.99 397	95.51 394	91.37 448	89.27 417	94.07 423	98.14 347	95.42 346	97.25 346	96.44 393	67.86 434	99.24 407	91.28 405	96.08 427	98.02 390

miper_refine_blended		92.87 395	91.99 397	95.51 394	91.37 448	89.27 417	94.07 423	98.14 347	95.42 346	97.25 346	96.44 393	67.86 434	99.24 407	91.28 405	96.08 427	98.02 390

EPNet		96.14 331	95.44 343	98.25 259	90.76 450	95.50 291	97.92 207	94.65 416	98.97 114	92.98 432	98.85 230	89.12 358	99.87 126	95.99 292	99.68 193	99.39 203
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 414	68.95 417	70.34 430	87.68 451	65.00 454	91.11 438	59.90 453	69.02 443	74.46 448	88.89 445	48.58 453	68.03 449	28.61 448	72.33 447	77.99 444

test_method		79.78 411	79.50 414	80.62 427	80.21 452	45.76 455	70.82 443	98.41 337	31.08 447	80.89 447	97.71 352	84.85 386	97.37 440	91.51 402	80.03 444	98.75 337

tmp_tt		78.77 412	78.73 415	78.90 428	58.45 453	74.76 452	94.20 422	78.26 451	39.16 446	86.71 445	92.82 440	80.50 409	75.19 448	86.16 431	92.29 441	86.74 442

testmvs		17.12 416	20.53 419	6.87 432	12.05 454	4.20 457	93.62 431	6.73 455	4.62 450	10.41 450	24.33 447	8.28 455	3.56 451	9.69 450	15.07 448	12.86 447

test123		17.04 417	20.11 420	7.82 431	10.25 455	4.91 456	94.80 406	4.47 456	4.93 449	10.00 451	24.28 448	9.69 454	3.64 450	10.14 449	12.43 449	14.92 446

mmdepth		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

monomultidepth		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

test_blank		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

eth-test2					0.00 456

eth-test					0.00 456

uanet_test		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

DCPMVS		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

cdsmvs_eth3d_5k		24.66 415	32.88 418	0.00 433	0.00 456	0.00 458	0.00 444	99.10 251	0.00 451	0.00 452	97.58 360	99.21 17	0.00 452	0.00 451	0.00 450	0.00 448

pcd_1.5k_mvsjas		8.17 418	10.90 421	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	98.07 105	0.00 452	0.00 451	0.00 450	0.00 448

sosnet-low-res		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

sosnet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uncertanet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

Regformer		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

ab-mvs-re		8.12 419	10.83 422	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	97.48 366	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uanet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

WAC-MVS						90.90 406								91.37 404

PC_three_1452									93.27 390	99.40 106	98.54 284	98.22 91	97.00 441	95.17 320	99.45 265	99.49 154

test_241102_TWO								99.30 194	98.03 190	99.26 136	99.02 183	97.51 154	99.88 107	96.91 219	99.60 221	99.66 72

test_0728_THIRD									98.17 183	99.08 158	99.02 183	97.89 120	99.88 107	97.07 207	99.71 178	99.70 63

GSMVS																98.81 326

sam_mvs1												84.74 388				98.81 326

sam_mvs												84.29 394

MTGPA								99.20 226

test_post1							97.59 258				20.48 450	83.07 402	99.66 308	94.16 347

test_post											21.25 449	83.86 397	99.70 281

patchmatchnet-post											98.77 246	84.37 391	99.85 147

MTMP							97.93 204	91.91 435

test9_res														93.28 373	99.15 312	99.38 210

agg_prior2														92.50 389	99.16 310	99.37 212

test_prior4						97.97 159	95.86 373

test_prior2							95.74 379		96.48 309	96.11 390	97.63 358	95.92 247		94.16 347	99.20 304

旧先验2							95.76 378		88.56 430	97.52 329			99.66 308	94.48 337

新几何2							95.93 369

无先验							95.74 379	98.74 316	89.38 426				99.73 269	92.38 391		99.22 257

原ACMM2							95.53 385

testdata2													99.79 229	92.80 383

segment_acmp												97.02 184

testdata1							95.44 390		96.32 315

plane_prior5								99.27 209					99.70 281	94.42 341	99.51 252	99.45 179

plane_prior4											97.98 337

plane_prior3						97.78 183			97.41 247	97.79 310

plane_prior2							97.77 229		98.20 180

plane_prior						97.65 192	97.07 303		96.72 299						99.36 276

n2								0.00 457

nn								0.00 457

door-mid								99.57 77

test11								98.87 290

door								99.41 146

HQP5-MVS						96.79 244

BP-MVS														92.82 381

HQP4-MVS										95.56 400			99.54 354			99.32 232

HQP3-MVS								99.04 262							99.26 294

HQP2-MVS												93.84 301

MDTV_nov1_ep13_2view						74.92 451	97.69 240		90.06 424	97.75 313		85.78 380		93.52 367		98.69 344

ACMMP++_ref															99.77 146

ACMMP++															99.68 193

Test By Simon												96.52 214

High-resolution multi-view benchmark