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 10	99.98 1	99.99 1	99.96 1	99.77 2	100.00 1	99.81 11	100.00 1	99.85 18

Gipuma		99.03 58	99.16 45	98.64 182	99.94 2	98.51 101	99.32 22	99.75 31	99.58 25	98.60 210	99.62 33	98.22 76	99.51 333	97.70 143	99.73 143	97.89 361
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 24	99.31 30	99.53 33	99.91 3	98.98 65	99.63 6	99.58 54	99.44 37	99.78 26	99.76 10	96.39 197	99.92 49	99.44 35	99.92 54	99.68 53

pmmvs6		99.67 3	99.70 3	99.60 11	99.90 4	99.27 22	99.53 7	99.76 28	99.64 15	99.84 20	99.83 3	99.50 8	99.87 99	99.36 37	99.92 54	99.64 62

PS-MVSNAJss		99.46 14	99.49 12	99.35 69	99.90 4	98.15 127	99.20 44	99.65 45	99.48 31	99.92 8	99.71 17	98.07 88	99.96 11	99.53 30	100.00 1	99.93 8

testf1		99.25 33	99.16 45	99.51 42	99.89 6	99.63 3	98.71 93	99.69 36	98.90 99	99.43 75	99.35 82	98.86 28	99.67 268	97.81 134	99.81 100	99.24 220

APD_test2		99.25 33	99.16 45	99.51 42	99.89 6	99.63 3	98.71 93	99.69 36	98.90 99	99.43 75	99.35 82	98.86 28	99.67 268	97.81 134	99.81 100	99.24 220

ANet_high		99.57 7	99.67 5	99.28 84	99.89 6	98.09 134	99.14 53	99.93 4	99.82 3	99.93 6	99.81 5	99.17 18	99.94 34	99.31 40	100.00 1	99.82 24

anonymousdsp		99.51 11	99.47 16	99.62 6	99.88 9	99.08 63	99.34 19	99.69 36	98.93 97	99.65 45	99.72 16	98.93 26	99.95 22	99.11 51	100.00 1	99.82 24

v7n		99.53 9	99.57 9	99.41 59	99.88 9	98.54 99	99.45 9	99.61 50	99.66 13	99.68 39	99.66 27	98.44 61	99.95 22	99.73 19	99.96 24	99.75 42

mvs_tets		99.63 5	99.67 5	99.49 47	99.88 9	98.61 91	99.34 19	99.71 33	99.27 56	99.90 12	99.74 13	99.68 4	99.97 4	99.55 29	99.99 5	99.88 14

test_fmvsmconf0.01_n		99.57 7	99.63 7	99.36 63	99.87 12	98.13 130	98.08 160	99.95 1	99.45 35	99.98 2	99.75 11	99.80 1	99.97 4	99.82 8	99.99 5	99.99 1

jajsoiax		99.58 6	99.61 8	99.48 50	99.87 12	98.61 91	99.28 36	99.66 44	99.09 82	99.89 15	99.68 20	99.53 7	99.97 4	99.50 32	99.99 5	99.87 15

test_djsdf		99.52 10	99.51 11	99.53 33	99.86 14	98.74 81	99.39 16	99.56 68	99.11 72	99.70 35	99.73 15	99.00 22	99.97 4	99.26 42	99.98 12	99.89 11

MIMVSNet1		99.38 23	99.32 28	99.55 23	99.86 14	99.19 37	99.41 12	99.59 52	99.59 23	99.71 33	99.57 41	97.12 157	99.90 63	99.21 47	99.87 75	99.54 107

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 21	99.85 16	99.11 59	99.90 1	99.78 26	99.63 17	99.78 26	99.67 25	99.48 9	99.81 178	99.30 41	99.97 19	99.77 34
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 15	99.69 4	99.58 54	99.90 2	99.86 18	99.78 8	99.58 6	99.95 22	99.00 60	99.95 31	99.78 32

mvsmamba		99.24 37	99.15 50	99.49 47	99.83 18	98.85 74	99.41 12	99.55 72	99.54 27	99.40 82	99.52 56	95.86 225	99.91 58	99.32 39	99.95 31	99.70 50

SixPastTwentyTwo		98.75 94	98.62 103	99.16 104	99.83 18	97.96 154	99.28 36	98.20 318	99.37 44	99.70 35	99.65 30	92.65 303	99.93 39	99.04 57	99.84 83	99.60 73

Baseline_NR-MVSNet		98.98 64	98.86 73	99.36 63	99.82 20	98.55 96	97.47 244	99.57 61	99.37 44	99.21 118	99.61 36	96.76 181	99.83 153	98.06 118	99.83 91	99.71 45

pm-mvs1		99.44 15	99.48 14	99.33 77	99.80 21	98.63 88	99.29 32	99.63 46	99.30 53	99.65 45	99.60 38	99.16 20	99.82 163	99.07 54	99.83 91	99.56 96

TransMVSNet (Re)		99.44 15	99.47 16	99.36 63	99.80 21	98.58 94	99.27 38	99.57 61	99.39 42	99.75 30	99.62 33	99.17 18	99.83 153	99.06 55	99.62 188	99.66 57

K. test v3		98.00 195	97.66 218	99.03 129	99.79 23	97.56 187	99.19 48	92.47 394	99.62 20	99.52 61	99.66 27	89.61 326	99.96 11	99.25 44	99.81 100	99.56 96

test_fmvsmconf0.1_n		99.49 12	99.54 10	99.34 72	99.78 24	98.11 131	97.77 203	99.90 9	99.33 49	99.97 3	99.66 27	99.71 3	99.96 11	99.79 13	99.99 5	99.96 5

APD_test1		98.83 82	98.66 97	99.34 72	99.78 24	99.47 6	98.42 130	99.45 111	98.28 138	98.98 148	99.19 113	97.76 110	99.58 310	96.57 222	99.55 214	98.97 266

test_vis3_rt		99.14 46	99.17 43	99.07 119	99.78 24	98.38 108	98.92 76	99.94 2	97.80 174	99.91 11	99.67 25	97.15 156	98.91 391	99.76 16	99.56 211	99.92 9

EGC-MVSNET		85.24 373	80.54 376	99.34 72	99.77 27	99.20 34	99.08 57	99.29 181	12.08 411	20.84 412	99.42 72	97.55 128	99.85 118	97.08 177	99.72 150	98.96 268

Anonymous20240521		98.69 105	98.87 70	98.16 243	99.77 27	95.11 285	99.08 57	99.44 115	99.34 48	99.33 95	99.55 47	94.10 280	99.94 34	99.25 44	99.96 24	99.42 160

FC-MVSNet-test		99.27 30	99.25 38	99.34 72	99.77 27	98.37 110	99.30 31	99.57 61	99.61 22	99.40 82	99.50 58	97.12 157	99.85 118	99.02 59	99.94 39	99.80 28

test_vis1_n		98.31 164	98.50 120	97.73 275	99.76 30	94.17 310	98.68 96	99.91 7	96.31 280	99.79 25	99.57 41	92.85 300	99.42 352	99.79 13	99.84 83	99.60 73

test_fmvs3		99.12 51	99.41 19	98.25 235	99.76 30	95.07 286	99.05 63	99.94 2	97.78 177	99.82 21	99.84 2	98.56 54	99.71 248	99.96 1	99.96 24	99.97 3

XXY-MVS		99.14 46	99.15 50	99.10 113	99.76 30	97.74 175	98.85 83	99.62 47	98.48 125	99.37 88	99.49 62	98.75 36	99.86 106	98.20 108	99.80 110	99.71 45

TDRefinement		99.42 19	99.38 21	99.55 23	99.76 30	99.33 16	99.68 5	99.71 33	99.38 43	99.53 59	99.61 36	98.64 44	99.80 185	98.24 105	99.84 83	99.52 117

fmvsm_s_conf0.1_n_a		99.17 42	99.30 32	98.80 159	99.75 34	96.59 236	97.97 180	99.86 13	98.22 141	99.88 17	99.71 17	98.59 50	99.84 135	99.73 19	99.98 12	99.98 2

tt0805		98.69 105	98.62 103	98.90 149	99.75 34	99.30 17	99.15 52	96.97 350	98.86 102	98.87 176	97.62 325	98.63 46	98.96 388	99.41 36	98.29 339	98.45 329

test_vis1_n_1920		98.40 151	98.92 67	96.81 329	99.74 36	90.76 378	98.15 152	99.91 7	98.33 130	99.89 15	99.55 47	95.07 251	99.88 82	99.76 16	99.93 43	99.79 29

FOURS1					99.73 37	99.67 2	99.43 10	99.54 77	99.43 39	99.26 110

PEN-MVS		99.41 20	99.34 25	99.62 6	99.73 37	99.14 52	99.29 32	99.54 77	99.62 20	99.56 52	99.42 72	98.16 84	99.96 11	98.78 71	99.93 43	99.77 34

lessismore_v0				98.97 137	99.73 37	97.53 189		86.71 408		99.37 88	99.52 56	89.93 324	99.92 49	98.99 61	99.72 150	99.44 153

SteuartSystems-ACMMP		98.79 87	98.54 115	99.54 26	99.73 37	99.16 43	98.23 143	99.31 164	97.92 165	98.90 167	98.90 188	98.00 94	99.88 82	96.15 253	99.72 150	99.58 85
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 182	98.15 173	98.22 238	99.73 37	95.15 282	97.36 250	99.68 41	94.45 334	98.99 147	99.27 97	96.87 171	99.94 34	97.13 174	99.91 61	99.57 90

Vis-MVSNet		99.34 25	99.36 22	99.27 87	99.73 37	98.26 117	99.17 49	99.78 26	99.11 72	99.27 106	99.48 63	98.82 31	99.95 22	98.94 63	99.93 43	99.59 79
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
SSC-MVS		98.71 98	98.74 82	98.62 187	99.72 43	96.08 254	98.74 87	98.64 299	99.74 6	99.67 41	99.24 104	94.57 266	99.95 22	99.11 51	99.24 268	99.82 24

test_f		98.67 113	98.87 70	98.05 252	99.72 43	95.59 264	98.51 117	99.81 23	96.30 282	99.78 26	99.82 4	96.14 206	98.63 396	99.82 8	99.93 43	99.95 6

ACMH	96.65 7	99.25 33	99.24 39	99.26 89	99.72 43	98.38 108	99.07 60	99.55 72	98.30 133	99.65 45	99.45 69	99.22 15	99.76 223	98.44 95	99.77 125	99.64 62
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
fmvsm_s_conf0.1_n		99.16 45	99.33 26	98.64 182	99.71 46	96.10 249	97.87 192	99.85 15	98.56 122	99.90 12	99.68 20	98.69 41	99.85 118	99.72 21	99.98 12	99.97 3

PS-CasMVS		99.40 21	99.33 26	99.62 6	99.71 46	99.10 60	99.29 32	99.53 80	99.53 29	99.46 70	99.41 75	98.23 73	99.95 22	98.89 67	99.95 31	99.81 27

DTE-MVSNet		99.43 18	99.35 23	99.66 4	99.71 46	99.30 17	99.31 26	99.51 85	99.64 15	99.56 52	99.46 65	98.23 73	99.97 4	98.78 71	99.93 43	99.72 44

WR-MVS_H		99.33 26	99.22 40	99.65 5	99.71 46	99.24 25	99.32 22	99.55 72	99.46 34	99.50 66	99.34 86	97.30 146	99.93 39	98.90 65	99.93 43	99.77 34

HPM-MVS_fast		99.01 59	98.82 76	99.57 16	99.71 46	99.35 12	99.00 67	99.50 88	97.33 220	98.94 163	98.86 199	98.75 36	99.82 163	97.53 150	99.71 155	99.56 96

ACMH+	96.62 9	99.08 56	99.00 62	99.33 77	99.71 46	98.83 76	98.60 103	99.58 54	99.11 72	99.53 59	99.18 116	98.81 32	99.67 268	96.71 214	99.77 125	99.50 122

PMVS	91.26 20	97.86 206	97.94 194	97.65 279	99.71 46	97.94 156	98.52 112	98.68 295	98.99 91	97.52 297	99.35 82	97.41 141	98.18 400	91.59 365	99.67 174	96.82 388
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FIs		99.14 46	99.09 55	99.29 83	99.70 53	98.28 116	99.13 54	99.52 83	99.48 31	99.24 115	99.41 75	96.79 178	99.82 163	98.69 80	99.88 72	99.76 38

VPNet		98.87 77	98.83 75	99.01 132	99.70 53	97.62 185	98.43 128	99.35 146	99.47 33	99.28 104	99.05 147	96.72 184	99.82 163	98.09 115	99.36 248	99.59 79

test_cas_vis1_n_1920		98.33 161	98.68 94	97.27 306	99.69 55	92.29 355	98.03 168	99.85 15	97.62 186	99.96 4	99.62 33	93.98 281	99.74 235	99.52 31	99.86 78	99.79 29

MP-MVS-pluss		98.57 127	98.23 163	99.60 11	99.69 55	99.35 12	97.16 267	99.38 132	94.87 324	98.97 152	98.99 166	98.01 93	99.88 82	97.29 162	99.70 160	99.58 85
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 38	99.32 28	98.96 138	99.68 57	97.35 198	98.84 85	99.48 97	99.69 9	99.63 48	99.68 20	99.03 21	99.96 11	97.97 125	99.92 54	99.57 90

sd_testset		99.28 29	99.31 30	99.19 100	99.68 57	98.06 143	99.41 12	99.30 173	99.69 9	99.63 48	99.68 20	99.25 14	99.96 11	97.25 165	99.92 54	99.57 90

test_fmvs1_n		98.09 187	98.28 155	97.52 292	99.68 57	93.47 334	98.63 99	99.93 4	95.41 313	99.68 39	99.64 31	91.88 312	99.48 340	99.82 8	99.87 75	99.62 66

CHOSEN 1792x2688		97.49 234	97.14 250	98.54 205	99.68 57	96.09 252	96.50 299	99.62 47	91.58 372	98.84 179	98.97 172	92.36 305	99.88 82	96.76 207	99.95 31	99.67 56

tfpnnormal		98.90 74	98.90 69	98.91 146	99.67 61	97.82 167	99.00 67	99.44 115	99.45 35	99.51 65	99.24 104	98.20 79	99.86 106	95.92 262	99.69 163	99.04 254

MTAPA		98.88 76	98.64 100	99.61 9	99.67 61	99.36 11	98.43 128	99.20 204	98.83 106	98.89 169	98.90 188	96.98 167	99.92 49	97.16 169	99.70 160	99.56 96

test_fmvsmvis_n_1920		99.26 32	99.49 12	98.54 205	99.66 63	96.97 221	98.00 174	99.85 15	99.24 58	99.92 8	99.50 58	99.39 11	99.95 22	99.89 3	99.98 12	98.71 306

fmvsm_l_conf0.5_n_a		99.19 41	99.27 35	98.94 141	99.65 64	97.05 217	97.80 199	99.76 28	98.70 110	99.78 26	99.11 133	98.79 34	99.95 22	99.85 5	99.96 24	99.83 21

WB-MVS		98.52 139	98.55 113	98.43 217	99.65 64	95.59 264	98.52 112	98.77 286	99.65 14	99.52 61	99.00 165	94.34 272	99.93 39	98.65 82	98.83 312	99.76 38

CP-MVSNet		99.21 39	99.09 55	99.56 21	99.65 64	98.96 70	99.13 54	99.34 152	99.42 40	99.33 95	99.26 99	97.01 165	99.94 34	98.74 75	99.93 43	99.79 29

HPM-MVS		98.79 87	98.53 116	99.59 15	99.65 64	99.29 19	99.16 50	99.43 121	96.74 262	98.61 208	98.38 271	98.62 47	99.87 99	96.47 234	99.67 174	99.59 79
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 121	98.36 145	99.42 57	99.65 64	99.42 7	98.55 108	99.57 61	97.72 180	98.90 167	99.26 99	96.12 208	99.52 329	95.72 273	99.71 155	99.32 201

fmvsm_l_conf0.5_n		99.21 39	99.28 34	99.02 131	99.64 69	97.28 202	97.82 196	99.76 28	98.73 107	99.82 21	99.09 139	98.81 32	99.95 22	99.86 4	99.96 24	99.83 21

test_fmvsmconf_n		99.44 15	99.48 14	99.31 82	99.64 69	98.10 133	97.68 214	99.84 18	99.29 54	99.92 8	99.57 41	99.60 5	99.96 11	99.74 18	99.98 12	99.89 11

TSAR-MVS + MP.		98.63 119	98.49 124	99.06 125	99.64 69	97.90 158	98.51 117	98.94 253	96.96 249	99.24 115	98.89 194	97.83 104	99.81 178	96.88 197	99.49 233	99.48 136
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 83	98.72 86	99.12 109	99.64 69	98.54 99	97.98 177	99.68 41	97.62 186	99.34 94	99.18 116	97.54 129	99.77 217	97.79 136	99.74 140	99.04 254

KD-MVS_self_test		99.25 33	99.18 42	99.44 56	99.63 73	99.06 64	98.69 95	99.54 77	99.31 51	99.62 51	99.53 53	97.36 144	99.86 106	99.24 46	99.71 155	99.39 173

EU-MVSNet		97.66 224	98.50 120	95.13 367	99.63 73	85.84 397	98.35 136	98.21 317	98.23 140	99.54 55	99.46 65	95.02 252	99.68 265	98.24 105	99.87 75	99.87 15

HyFIR lowres test		97.19 258	96.60 282	98.96 138	99.62 75	97.28 202	95.17 360	99.50 88	94.21 339	99.01 145	98.32 279	86.61 344	99.99 2	97.10 176	99.84 83	99.60 73

ACMMP_NAP		98.75 94	98.48 125	99.57 16	99.58 76	99.29 19	97.82 196	99.25 193	96.94 251	98.78 186	99.12 132	98.02 92	99.84 135	97.13 174	99.67 174	99.59 79

nrg030		99.40 21	99.35 23	99.54 26	99.58 76	99.13 55	98.98 70	99.48 97	99.68 11	99.46 70	99.26 99	98.62 47	99.73 240	99.17 50	99.92 54	99.76 38

VDDNet		98.21 177	97.95 192	99.01 132	99.58 76	97.74 175	99.01 65	97.29 343	99.67 12	98.97 152	99.50 58	90.45 321	99.80 185	97.88 131	99.20 274	99.48 136

COLMAP_ROB	96.50 10	98.99 61	98.85 74	99.41 59	99.58 76	99.10 60	98.74 87	99.56 68	99.09 82	99.33 95	99.19 113	98.40 63	99.72 247	95.98 260	99.76 136	99.42 160
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 26	99.45 18	98.99 134	99.57 80	97.73 177	97.93 181	99.83 20	99.22 59	99.93 6	99.30 93	99.42 10	99.96 11	99.85 5	99.99 5	99.29 210

ZNCC-MVS		98.68 110	98.40 137	99.54 26	99.57 80	99.21 28	98.46 125	99.29 181	97.28 226	98.11 253	98.39 269	98.00 94	99.87 99	96.86 200	99.64 182	99.55 103

MSP-MVS		98.40 151	98.00 188	99.61 9	99.57 80	99.25 24	98.57 106	99.35 146	97.55 198	99.31 103	97.71 318	94.61 265	99.88 82	96.14 254	99.19 277	99.70 50
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		98.32 162	98.39 140	98.13 244	99.57 80	95.54 267	97.78 201	99.49 95	97.37 217	99.19 120	97.65 322	98.96 24	99.49 337	96.50 233	98.99 301	99.34 194

MP-MVS		98.46 144	98.09 178	99.54 26	99.57 80	99.22 27	98.50 119	99.19 208	97.61 189	97.58 291	98.66 235	97.40 142	99.88 82	94.72 298	99.60 195	99.54 107
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 98	98.46 129	99.47 53	99.57 80	98.97 66	98.23 143	99.48 97	96.60 267	99.10 130	99.06 140	98.71 39	99.83 153	95.58 280	99.78 120	99.62 66

LGP-MVS_train				99.47 53	99.57 80	98.97 66		99.48 97	96.60 267	99.10 130	99.06 140	98.71 39	99.83 153	95.58 280	99.78 120	99.62 66

IS-MVSNet		98.19 179	97.90 198	99.08 117	99.57 80	97.97 151	99.31 26	98.32 313	99.01 90	98.98 148	99.03 151	91.59 313	99.79 200	95.49 282	99.80 110	99.48 136

dcpmvs_2		98.78 89	99.11 52	97.78 266	99.56 88	93.67 330	99.06 61	99.86 13	99.50 30	99.66 42	99.26 99	97.21 154	99.99 2	98.00 123	99.91 61	99.68 53

test_0402		98.76 93	98.71 88	98.93 143	99.56 88	98.14 129	98.45 127	99.34 152	99.28 55	98.95 155	98.91 185	98.34 69	99.79 200	95.63 277	99.91 61	98.86 284

EPP-MVSNet		98.30 165	98.04 184	99.07 119	99.56 88	97.83 164	99.29 32	98.07 324	99.03 88	98.59 212	99.13 130	92.16 308	99.90 63	96.87 198	99.68 168	99.49 126

ACMMP		98.75 94	98.50 120	99.52 38	99.56 88	99.16 43	98.87 80	99.37 137	97.16 241	98.82 183	99.01 161	97.71 113	99.87 99	96.29 245	99.69 163	99.54 107
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 53	99.20 41	98.78 165	99.55 92	96.59 236	97.79 200	99.82 22	98.21 142	99.81 23	99.53 53	98.46 60	99.84 135	99.70 22	99.97 19	99.90 10

fmvsm_s_conf0.5_n		99.09 54	99.26 37	98.61 190	99.55 92	96.09 252	97.74 208	99.81 23	98.55 123	99.85 19	99.55 47	98.60 49	99.84 135	99.69 24	99.98 12	99.89 11

FMVSNet1		99.17 42	99.17 43	99.17 101	99.55 92	98.24 119	99.20 44	99.44 115	99.21 61	99.43 75	99.55 47	97.82 107	99.86 106	98.42 97	99.89 71	99.41 163

Vis-MVSNet (Re-imp)		97.46 236	97.16 247	98.34 225	99.55 92	96.10 249	98.94 74	98.44 308	98.32 132	98.16 247	98.62 244	88.76 331	99.73 240	93.88 324	99.79 115	99.18 234

ACMM	96.08 12	98.91 72	98.73 84	99.48 50	99.55 92	99.14 52	98.07 162	99.37 137	97.62 186	99.04 141	98.96 175	98.84 30	99.79 200	97.43 156	99.65 180	99.49 126
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 102	98.97 65	97.89 259	99.54 97	94.05 312	98.55 108	99.92 6	96.78 260	99.72 31	99.78 8	96.60 189	99.67 268	99.91 2	99.90 67	99.94 7

mPP-MVS		98.64 117	98.34 148	99.54 26	99.54 97	99.17 39	98.63 99	99.24 198	97.47 204	98.09 255	98.68 230	97.62 122	99.89 73	96.22 248	99.62 188	99.57 90

XVG-ACMP-BASELINE		98.56 128	98.34 148	99.22 97	99.54 97	98.59 93	97.71 211	99.46 107	97.25 229	98.98 148	98.99 166	97.54 129	99.84 135	95.88 263	99.74 140	99.23 222

region2R		98.69 105	98.40 137	99.54 26	99.53 100	99.17 39	98.52 112	99.31 164	97.46 209	98.44 229	98.51 256	97.83 104	99.88 82	96.46 235	99.58 204	99.58 85

PGM-MVS		98.66 114	98.37 144	99.55 23	99.53 100	99.18 38	98.23 143	99.49 95	97.01 248	98.69 197	98.88 196	98.00 94	99.89 73	95.87 266	99.59 199	99.58 85

Patchmatch-RL test		97.26 251	97.02 254	97.99 256	99.52 102	95.53 268	96.13 322	99.71 33	97.47 204	99.27 106	99.16 122	84.30 365	99.62 293	97.89 128	99.77 125	98.81 291

ACMMPR		98.70 102	98.42 135	99.54 26	99.52 102	99.14 52	98.52 112	99.31 164	97.47 204	98.56 217	98.54 252	97.75 111	99.88 82	96.57 222	99.59 199	99.58 85

GST-MVS		98.61 123	98.30 153	99.52 38	99.51 104	99.20 34	98.26 141	99.25 193	97.44 212	98.67 199	98.39 269	97.68 114	99.85 118	96.00 258	99.51 225	99.52 117

Anonymous20231206		98.21 177	98.21 164	98.20 239	99.51 104	95.43 273	98.13 153	99.32 159	96.16 285	98.93 164	98.82 208	96.00 214	99.83 153	97.32 161	99.73 143	99.36 188

ACMP	95.32 15	98.41 149	98.09 178	99.36 63	99.51 104	98.79 79	97.68 214	99.38 132	95.76 300	98.81 185	98.82 208	98.36 65	99.82 163	94.75 295	99.77 125	99.48 136
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DVP-MVS		98.77 92	98.52 117	99.52 38	99.50 107	99.21 28	98.02 170	98.84 275	97.97 160	99.08 132	99.02 152	97.61 123	99.88 82	96.99 184	99.63 185	99.48 136
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 11	99.50 107	99.23 26	98.02 170	99.32 159					99.88 82	96.99 184	99.63 185	99.68 53

test0726					99.50 107	99.21 28	98.17 151	99.35 146	97.97 160	99.26 110	99.06 140	97.61 123

AllTest		98.44 147	98.20 165	99.16 104	99.50 107	98.55 96	98.25 142	99.58 54	96.80 258	98.88 172	99.06 140	97.65 117	99.57 312	94.45 305	99.61 193	99.37 182

TestCases				99.16 104	99.50 107	98.55 96		99.58 54	96.80 258	98.88 172	99.06 140	97.65 117	99.57 312	94.45 305	99.61 193	99.37 182

XVG-OURS		98.53 136	98.34 148	99.11 111	99.50 107	98.82 78	95.97 328	99.50 88	97.30 224	99.05 139	98.98 170	99.35 12	99.32 366	95.72 273	99.68 168	99.18 234

EG-PatchMatch MVS		98.99 61	99.01 61	98.94 141	99.50 107	97.47 191	98.04 167	99.59 52	98.15 153	99.40 82	99.36 81	98.58 53	99.76 223	98.78 71	99.68 168	99.59 79

SED-MVS		98.91 72	98.72 86	99.49 47	99.49 114	99.17 39	98.10 158	99.31 164	98.03 157	99.66 42	99.02 152	98.36 65	99.88 82	96.91 190	99.62 188	99.41 163

IU-MVS					99.49 114	99.15 47		98.87 266	92.97 357	99.41 79				96.76 207	99.62 188	99.66 57

test_241102_ONE					99.49 114	99.17 39		99.31 164	97.98 159	99.66 42	98.90 188	98.36 65	99.48 340

UA-Net		99.47 13	99.40 20	99.70 2	99.49 114	99.29 19	99.80 3	99.72 32	99.82 3	99.04 141	99.81 5	98.05 91	99.96 11	98.85 68	99.99 5	99.86 17

HFP-MVS		98.71 98	98.44 132	99.51 42	99.49 114	99.16 43	98.52 112	99.31 164	97.47 204	98.58 214	98.50 260	97.97 98	99.85 118	96.57 222	99.59 199	99.53 114

VPA-MVSNet		99.30 28	99.30 32	99.28 84	99.49 114	98.36 113	99.00 67	99.45 111	99.63 17	99.52 61	99.44 70	98.25 71	99.88 82	99.09 53	99.84 83	99.62 66

XVG-OURS-SEG-HR		98.49 141	98.28 155	99.14 107	99.49 114	98.83 76	96.54 296	99.48 97	97.32 222	99.11 127	98.61 246	99.33 13	99.30 369	96.23 247	98.38 335	99.28 212

114514_t		96.50 291	95.77 298	98.69 179	99.48 121	97.43 195	97.84 195	99.55 72	81.42 404	96.51 347	98.58 249	95.53 236	99.67 268	93.41 337	99.58 204	98.98 263

IterMVS-LS		98.55 132	98.70 91	98.09 245	99.48 121	94.73 294	97.22 263	99.39 130	98.97 93	99.38 86	99.31 92	96.00 214	99.93 39	98.58 85	99.97 19	99.60 73
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v8		99.01 59	99.16 45	98.57 197	99.47 123	96.31 246	98.90 77	99.47 105	99.03 88	99.52 61	99.57 41	96.93 168	99.81 178	99.60 25	99.98 12	99.60 73

XVS		98.72 97	98.45 130	99.53 33	99.46 124	99.21 28	98.65 97	99.34 152	98.62 115	97.54 295	98.63 242	97.50 135	99.83 153	96.79 203	99.53 220	99.56 96

X-MVStestdata		94.32 335	92.59 353	99.53 33	99.46 124	99.21 28	98.65 97	99.34 152	98.62 115	97.54 295	45.85 409	97.50 135	99.83 153	96.79 203	99.53 220	99.56 96

test20.03		98.78 89	98.77 81	98.78 165	99.46 124	97.20 209	97.78 201	99.24 198	99.04 87	99.41 79	98.90 188	97.65 117	99.76 223	97.70 143	99.79 115	99.39 173

CSCG		98.68 110	98.50 120	99.20 98	99.45 127	98.63 88	98.56 107	99.57 61	97.87 169	98.85 177	98.04 300	97.66 116	99.84 135	96.72 212	99.81 100	99.13 243

GeoE		99.05 57	98.99 64	99.25 92	99.44 128	98.35 114	98.73 90	99.56 68	98.42 126	98.91 166	98.81 210	98.94 25	99.91 58	98.35 99	99.73 143	99.49 126

v148		98.45 146	98.60 108	98.00 255	99.44 128	94.98 287	97.44 246	99.06 234	98.30 133	99.32 101	98.97 172	96.65 187	99.62 293	98.37 98	99.85 79	99.39 173

v10		98.97 65	99.11 52	98.55 202	99.44 128	96.21 248	98.90 77	99.55 72	98.73 107	99.48 67	99.60 38	96.63 188	99.83 153	99.70 22	99.99 5	99.61 72

V42		98.78 89	98.78 80	98.76 169	99.44 128	97.04 218	98.27 140	99.19 208	97.87 169	99.25 114	99.16 122	96.84 172	99.78 211	99.21 47	99.84 83	99.46 145

MDA-MVSNet-bldmvs		97.94 199	97.91 197	98.06 250	99.44 128	94.96 288	96.63 294	99.15 224	98.35 128	98.83 180	99.11 133	94.31 273	99.85 118	96.60 219	98.72 318	99.37 182

casdiffmvs_mvg		99.12 51	99.16 45	98.99 134	99.43 133	97.73 177	98.00 174	99.62 47	99.22 59	99.55 54	99.22 108	98.93 26	99.75 230	98.66 81	99.81 100	99.50 122
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		96.49 292	96.82 266	95.52 361	99.42 134	87.08 394	99.22 41	87.14 407	99.11 72	99.46 70	99.58 40	88.69 332	99.86 106	98.80 70	99.95 31	99.62 66

v2v482		98.56 128	98.62 103	98.37 223	99.42 134	95.81 261	97.58 229	99.16 219	97.90 167	99.28 104	99.01 161	95.98 219	99.79 200	99.33 38	99.90 67	99.51 119

OPM-MVS		98.56 128	98.32 152	99.25 92	99.41 136	98.73 84	97.13 269	99.18 212	97.10 244	98.75 192	98.92 184	98.18 80	99.65 284	96.68 216	99.56 211	99.37 182
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 190	98.08 181	98.04 253	99.41 136	94.59 300	94.59 378	99.40 128	97.50 201	98.82 183	98.83 205	96.83 174	99.84 135	97.50 153	99.81 100	99.71 45

test_one_0601					99.39 138	99.20 34		99.31 164	98.49 124	98.66 201	99.02 152	97.64 120

mvsany_test3		98.87 77	98.92 67	98.74 177	99.38 139	96.94 225	98.58 105	99.10 229	96.49 272	99.96 4	99.81 5	98.18 80	99.45 347	98.97 62	99.79 115	99.83 21

patch_mono-2		98.51 140	98.63 101	98.17 241	99.38 139	94.78 291	97.36 250	99.69 36	98.16 152	98.49 225	99.29 94	97.06 160	99.97 4	98.29 104	99.91 61	99.76 38

test2506		92.39 363	91.89 365	93.89 379	99.38 139	82.28 409	99.32 22	66.03 415	99.08 84	98.77 189	99.57 41	66.26 405	99.84 135	98.71 78	99.95 31	99.54 107

ECVR-MVS		96.42 294	96.61 280	95.85 353	99.38 139	88.18 390	99.22 41	86.00 409	99.08 84	99.36 90	99.57 41	88.47 337	99.82 163	98.52 92	99.95 31	99.54 107

casdiffmvs		98.95 68	99.00 62	98.81 157	99.38 139	97.33 199	97.82 196	99.57 61	99.17 70	99.35 92	99.17 120	98.35 68	99.69 256	98.46 94	99.73 143	99.41 163
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 67	99.02 60	98.76 169	99.38 139	97.26 204	98.49 120	99.50 88	98.86 102	99.19 120	99.06 140	98.23 73	99.69 256	98.71 78	99.76 136	99.33 199

TranMVSNet+NR-MVSNet		99.17 42	99.07 58	99.46 55	99.37 145	98.87 73	98.39 132	99.42 124	99.42 40	99.36 90	99.06 140	98.38 64	99.95 22	98.34 100	99.90 67	99.57 90

tttt0517		95.64 316	94.98 325	97.64 281	99.36 146	93.81 326	98.72 91	90.47 402	98.08 156	98.67 199	98.34 276	73.88 396	99.92 49	97.77 137	99.51 225	99.20 227

test_part2					99.36 146	99.10 60				99.05 139

v1144		98.60 124	98.66 97	98.41 219	99.36 146	95.90 257	97.58 229	99.34 152	97.51 200	99.27 106	99.15 126	96.34 202	99.80 185	99.47 34	99.93 43	99.51 119

CP-MVS		98.70 102	98.42 135	99.52 38	99.36 146	99.12 57	98.72 91	99.36 141	97.54 199	98.30 239	98.40 268	97.86 103	99.89 73	96.53 231	99.72 150	99.56 96

Test_1112_low_res		96.99 273	96.55 284	98.31 229	99.35 150	95.47 271	95.84 339	99.53 80	91.51 374	96.80 336	98.48 263	91.36 315	99.83 153	96.58 220	99.53 220	99.62 66

DeepC-MVS	97.60 4	98.97 65	98.93 66	99.10 113	99.35 150	97.98 150	98.01 173	99.46 107	97.56 196	99.54 55	99.50 58	98.97 23	99.84 135	98.06 118	99.92 54	99.49 126
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 250	96.86 262	98.58 194	99.34 152	96.32 245	96.75 288	99.58 54	93.14 355	96.89 331	97.48 333	92.11 309	99.86 106	96.91 190	99.54 216	99.57 90

SF-MVS		98.53 136	98.27 158	99.32 79	99.31 153	98.75 80	98.19 147	99.41 125	96.77 261	98.83 180	98.90 188	97.80 108	99.82 163	95.68 276	99.52 223	99.38 180

CPTT-MVS		97.84 213	97.36 237	99.27 87	99.31 153	98.46 104	98.29 138	99.27 187	94.90 323	97.83 275	98.37 272	94.90 254	99.84 135	93.85 326	99.54 216	99.51 119

UnsupCasMVSNet_eth		97.89 202	97.60 223	98.75 173	99.31 153	97.17 212	97.62 223	99.35 146	98.72 109	98.76 191	98.68 230	92.57 304	99.74 235	97.76 141	95.60 394	99.34 194

pmmvs-eth3d		98.47 143	98.34 148	98.86 151	99.30 156	97.76 173	97.16 267	99.28 184	95.54 306	99.42 78	99.19 113	97.27 149	99.63 290	97.89 128	99.97 19	99.20 227

Anonymous20231211		99.27 30	99.27 35	99.26 89	99.29 157	98.18 125	99.49 8	99.51 85	99.70 8	99.80 24	99.68 20	96.84 172	99.83 153	99.21 47	99.91 61	99.77 34

UnsupCasMVSNet_bld		97.30 248	96.92 258	98.45 215	99.28 158	96.78 232	96.20 317	99.27 187	95.42 310	98.28 241	98.30 280	93.16 291	99.71 248	94.99 290	97.37 370	98.87 283

EC-MVSNet		99.09 54	99.05 59	99.20 98	99.28 158	98.93 71	99.24 40	99.84 18	99.08 84	98.12 252	98.37 272	98.72 38	99.90 63	99.05 56	99.77 125	98.77 300

DPE-MVS		98.59 126	98.26 159	99.57 16	99.27 160	99.15 47	97.01 272	99.39 130	97.67 182	99.44 74	98.99 166	97.53 131	99.89 73	95.40 284	99.68 168	99.66 57
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 211	98.18 168	96.87 325	99.27 160	91.16 373	95.53 347	99.25 193	99.10 79	99.41 79	99.35 82	93.10 293	99.96 11	98.65 82	99.94 39	99.49 126

v1192		98.60 124	98.66 97	98.41 219	99.27 160	95.88 258	97.52 237	99.36 141	97.41 213	99.33 95	99.20 111	96.37 200	99.82 163	99.57 27	99.92 54	99.55 103

iter_conf05		98.46 144	98.38 142	98.70 178	99.27 160	97.15 214	97.51 239	99.51 85	97.57 192	98.95 155	98.89 194	95.48 240	99.82 163	98.30 103	99.96 24	99.14 242

N_pmnet		97.63 226	97.17 246	98.99 134	99.27 160	97.86 161	95.98 327	93.41 391	95.25 315	99.47 69	98.90 188	95.63 231	99.85 118	96.91 190	99.73 143	99.27 213

FPMVS		93.44 351	92.23 356	97.08 314	99.25 165	97.86 161	95.61 344	97.16 345	92.90 359	93.76 393	98.65 237	75.94 394	95.66 406	79.30 406	97.49 363	97.73 371

new-patchmatchnet		98.35 157	98.74 82	97.18 309	99.24 166	92.23 357	96.42 304	99.48 97	98.30 133	99.69 37	99.53 53	97.44 140	99.82 163	98.84 69	99.77 125	99.49 126

MCST-MVS		98.00 195	97.63 221	99.10 113	99.24 166	98.17 126	96.89 281	98.73 293	95.66 301	97.92 265	97.70 320	97.17 155	99.66 279	96.18 252	99.23 270	99.47 143

UniMVSNet (Re)		98.87 77	98.71 88	99.35 69	99.24 166	98.73 84	97.73 210	99.38 132	98.93 97	99.12 126	98.73 221	96.77 179	99.86 106	98.63 84	99.80 110	99.46 145

jason		97.45 238	97.35 238	97.76 270	99.24 166	93.93 320	95.86 336	98.42 309	94.24 338	98.50 224	98.13 290	94.82 258	99.91 58	97.22 166	99.73 143	99.43 157
jason: jason.
IterMVS		97.73 218	98.11 177	96.57 334	99.24 166	90.28 381	95.52 350	99.21 202	98.86 102	99.33 95	99.33 88	93.11 292	99.94 34	98.49 93	99.94 39	99.48 136
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 132	98.62 103	98.32 226	99.22 171	95.58 266	97.51 239	99.45 111	97.16 241	99.45 73	99.24 104	96.12 208	99.85 118	99.60 25	99.88 72	99.55 103

ITE_SJBPF				98.87 150	99.22 171	98.48 103		99.35 146	97.50 201	98.28 241	98.60 247	97.64 120	99.35 362	93.86 325	99.27 263	98.79 298

h-mvs33		97.77 216	97.33 240	99.10 113	99.21 173	97.84 163	98.35 136	98.57 302	99.11 72	98.58 214	99.02 152	88.65 335	99.96 11	98.11 113	96.34 386	99.49 126

v144192		98.54 134	98.57 111	98.45 215	99.21 173	95.98 255	97.63 222	99.36 141	97.15 243	99.32 101	99.18 116	95.84 226	99.84 135	99.50 32	99.91 61	99.54 107

APDe-MVS		98.99 61	98.79 79	99.60 11	99.21 173	99.15 47	98.87 80	99.48 97	97.57 192	99.35 92	99.24 104	97.83 104	99.89 73	97.88 131	99.70 160	99.75 42
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 70	98.81 78	99.28 84	99.21 173	98.45 105	98.46 125	99.33 157	99.63 17	99.48 67	99.15 126	97.23 152	99.75 230	97.17 168	99.66 179	99.63 65

SR-MVS-dyc-post		98.81 85	98.55 113	99.57 16	99.20 177	99.38 8	98.48 123	99.30 173	98.64 111	98.95 155	98.96 175	97.49 138	99.86 106	96.56 226	99.39 244	99.45 149

RE-MVS-def			98.58 110		99.20 177	99.38 8	98.48 123	99.30 173	98.64 111	98.95 155	98.96 175	97.75 111		96.56 226	99.39 244	99.45 149

v1921920		98.54 134	98.60 108	98.38 222	99.20 177	95.76 263	97.56 232	99.36 141	97.23 235	99.38 86	99.17 120	96.02 212	99.84 135	99.57 27	99.90 67	99.54 107

thisisatest0530		95.27 323	94.45 332	97.74 273	99.19 180	94.37 304	97.86 193	90.20 403	97.17 240	98.22 243	97.65 322	73.53 397	99.90 63	96.90 195	99.35 250	98.95 269

Anonymous20240529		98.93 70	98.87 70	99.12 109	99.19 180	98.22 124	99.01 65	98.99 251	99.25 57	99.54 55	99.37 78	97.04 161	99.80 185	97.89 128	99.52 223	99.35 192

APD-MVS_3200maxsize		98.84 81	98.61 107	99.53 33	99.19 180	99.27 22	98.49 120	99.33 157	98.64 111	99.03 144	98.98 170	97.89 101	99.85 118	96.54 230	99.42 241	99.46 145

HQP_MVS		97.99 198	97.67 215	98.93 143	99.19 180	97.65 181	97.77 203	99.27 187	98.20 146	97.79 278	97.98 303	94.90 254	99.70 252	94.42 307	99.51 225	99.45 149

plane_prior7					99.19 180	97.87 160

ab-mvs		98.41 149	98.36 145	98.59 193	99.19 180	97.23 205	99.32 22	98.81 280	97.66 183	98.62 206	99.40 77	96.82 175	99.80 185	95.88 263	99.51 225	98.75 303

F-COLMAP		97.30 248	96.68 275	99.14 107	99.19 180	98.39 107	97.27 259	99.30 173	92.93 358	96.62 342	98.00 301	95.73 228	99.68 265	92.62 353	98.46 334	99.35 192

SR-MVS		98.71 98	98.43 133	99.57 16	99.18 187	99.35 12	98.36 135	99.29 181	98.29 136	98.88 172	98.85 202	97.53 131	99.87 99	96.14 254	99.31 256	99.48 136

UniMVSNet_NR-MVSNet		98.86 80	98.68 94	99.40 61	99.17 188	98.74 81	97.68 214	99.40 128	99.14 71	99.06 134	98.59 248	96.71 185	99.93 39	98.57 88	99.77 125	99.53 114

LF4IMVS		97.90 200	97.69 214	98.52 207	99.17 188	97.66 180	97.19 266	99.47 105	96.31 280	97.85 273	98.20 287	96.71 185	99.52 329	94.62 299	99.72 150	98.38 338

SMA-MVS		98.40 151	98.03 185	99.51 42	99.16 190	99.21 28	98.05 165	99.22 201	94.16 340	98.98 148	99.10 136	97.52 133	99.79 200	96.45 236	99.64 182	99.53 114
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 83	98.63 101	99.39 62	99.16 190	98.74 81	97.54 234	99.25 193	98.84 105	99.06 134	98.76 218	96.76 181	99.93 39	98.57 88	99.77 125	99.50 122

NR-MVSNet		98.95 68	98.82 76	99.36 63	99.16 190	98.72 86	99.22 41	99.20 204	99.10 79	99.72 31	98.76 218	96.38 199	99.86 106	98.00 123	99.82 95	99.50 122

MVS_111021_LR		98.30 165	98.12 176	98.83 154	99.16 190	98.03 145	96.09 324	99.30 173	97.58 191	98.10 254	98.24 283	98.25 71	99.34 363	96.69 215	99.65 180	99.12 244

DSMNet-mixed		97.42 240	97.60 223	96.87 325	99.15 194	91.46 363	98.54 110	99.12 226	92.87 360	97.58 291	99.63 32	96.21 205	99.90 63	95.74 272	99.54 216	99.27 213

D2MVS		97.84 213	97.84 204	97.83 262	99.14 195	94.74 293	96.94 276	98.88 264	95.84 298	98.89 169	98.96 175	94.40 270	99.69 256	97.55 147	99.95 31	99.05 250

pmmvs5		97.64 225	97.49 229	98.08 248	99.14 195	95.12 284	96.70 291	99.05 237	93.77 347	98.62 206	98.83 205	93.23 289	99.75 230	98.33 102	99.76 136	99.36 188

CS-MVS-test		99.13 49	99.09 55	99.26 89	99.13 197	98.97 66	99.31 26	99.88 11	99.44 37	98.16 247	98.51 256	98.64 44	99.93 39	98.91 64	99.85 79	98.88 282

VDD-MVS		98.56 128	98.39 140	99.07 119	99.13 197	98.07 140	98.59 104	97.01 348	99.59 23	99.11 127	99.27 97	94.82 258	99.79 200	98.34 100	99.63 185	99.34 194

save fliter					99.11 199	97.97 151	96.53 298	99.02 245	98.24 139

APD-MVS		98.10 184	97.67 215	99.42 57	99.11 199	98.93 71	97.76 206	99.28 184	94.97 321	98.72 195	98.77 216	97.04 161	99.85 118	93.79 327	99.54 216	99.49 126
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 105	98.71 88	98.62 187	99.10 201	96.37 243	97.23 260	98.87 266	99.20 63	99.19 120	98.99 166	97.30 146	99.85 118	98.77 74	99.79 115	99.65 61

EI-MVSNet		98.40 151	98.51 118	98.04 253	99.10 201	94.73 294	97.20 264	98.87 266	98.97 93	99.06 134	99.02 152	96.00 214	99.80 185	98.58 85	99.82 95	99.60 73

CVMVSNet		96.25 299	97.21 245	93.38 385	99.10 201	80.56 412	97.20 264	98.19 320	96.94 251	99.00 146	99.02 152	89.50 328	99.80 185	96.36 241	99.59 199	99.78 32

EI-MVSNet-Vis-set		98.68 110	98.70 91	98.63 186	99.09 204	96.40 242	97.23 260	98.86 271	99.20 63	99.18 124	98.97 172	97.29 148	99.85 118	98.72 77	99.78 120	99.64 62

HPM-MVS++		98.10 184	97.64 220	99.48 50	99.09 204	99.13 55	97.52 237	98.75 290	97.46 209	96.90 330	97.83 313	96.01 213	99.84 135	95.82 270	99.35 250	99.46 145

DP-MVS Recon		97.33 246	96.92 258	98.57 197	99.09 204	97.99 147	96.79 284	99.35 146	93.18 354	97.71 282	98.07 298	95.00 253	99.31 367	93.97 320	99.13 285	98.42 335

MVS_111021_HR		98.25 173	98.08 181	98.75 173	99.09 204	97.46 192	95.97 328	99.27 187	97.60 190	97.99 262	98.25 282	98.15 86	99.38 358	96.87 198	99.57 208	99.42 160

9.14			97.78 206		99.07 208		97.53 235	99.32 159	95.53 307	98.54 221	98.70 227	97.58 125	99.76 223	94.32 312	99.46 235

PAPM_NR		96.82 280	96.32 290	98.30 231	99.07 208	96.69 235	97.48 242	98.76 287	95.81 299	96.61 343	96.47 358	94.12 279	99.17 380	90.82 379	97.78 358	99.06 249

TAMVS		98.24 174	98.05 183	98.80 159	99.07 208	97.18 211	97.88 189	98.81 280	96.66 266	99.17 125	99.21 109	94.81 260	99.77 217	96.96 188	99.88 72	99.44 153

CLD-MVS		97.49 234	97.16 247	98.48 212	99.07 208	97.03 219	94.71 371	99.21 202	94.46 332	98.06 257	97.16 345	97.57 126	99.48 340	94.46 304	99.78 120	98.95 269
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 49	99.10 54	99.24 94	99.06 212	99.15 47	99.36 18	99.88 11	99.36 47	98.21 244	98.46 264	98.68 42	99.93 39	99.03 58	99.85 79	98.64 315

thres100view900		94.19 338	93.67 342	95.75 356	99.06 212	91.35 366	98.03 168	94.24 386	98.33 130	97.40 307	94.98 387	79.84 381	99.62 293	83.05 399	98.08 351	96.29 392

thres600view7		94.45 333	93.83 339	96.29 341	99.06 212	91.53 362	97.99 176	94.24 386	98.34 129	97.44 305	95.01 385	79.84 381	99.67 268	84.33 397	98.23 340	97.66 374

plane_prior1					99.05 215

YYNet1		97.60 227	97.67 215	97.39 302	99.04 216	93.04 341	95.27 357	98.38 312	97.25 229	98.92 165	98.95 180	95.48 240	99.73 240	96.99 184	98.74 316	99.41 163

MDA-MVSNet_test_wron		97.60 227	97.66 218	97.41 301	99.04 216	93.09 337	95.27 357	98.42 309	97.26 228	98.88 172	98.95 180	95.43 243	99.73 240	97.02 181	98.72 318	99.41 163

MIMVSNet		96.62 287	96.25 294	97.71 276	99.04 216	94.66 297	99.16 50	96.92 354	97.23 235	97.87 270	99.10 136	86.11 350	99.65 284	91.65 363	99.21 273	98.82 287

PatchMatch-RL		97.24 254	96.78 269	98.61 190	99.03 219	97.83 164	96.36 307	99.06 234	93.49 352	97.36 311	97.78 314	95.75 227	99.49 337	93.44 336	98.77 315	98.52 324

ZD-MVS					99.01 220	98.84 75		99.07 233	94.10 342	98.05 259	98.12 292	96.36 201	99.86 106	92.70 352	99.19 277

CDPH-MVS		97.26 251	96.66 278	99.07 119	99.00 221	98.15 127	96.03 326	99.01 248	91.21 378	97.79 278	97.85 312	96.89 170	99.69 256	92.75 350	99.38 247	99.39 173

diffmvs		98.22 175	98.24 162	98.17 241	99.00 221	95.44 272	96.38 306	99.58 54	97.79 175	98.53 222	98.50 260	96.76 181	99.74 235	97.95 127	99.64 182	99.34 194
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		98.40 151	98.19 167	99.03 129	99.00 221	97.65 181	96.85 282	98.94 253	98.57 120	98.89 169	98.50 260	95.60 232	99.85 118	97.54 149	99.85 79	99.59 79

plane_prior6					98.99 224	97.70 179						94.90 254

xiu_mvs_v1_base_debu		97.86 206	98.17 169	96.92 322	98.98 225	93.91 321	96.45 301	99.17 216	97.85 171	98.41 232	97.14 347	98.47 57	99.92 49	98.02 120	99.05 291	96.92 385

xiu_mvs_v1_base		97.86 206	98.17 169	96.92 322	98.98 225	93.91 321	96.45 301	99.17 216	97.85 171	98.41 232	97.14 347	98.47 57	99.92 49	98.02 120	99.05 291	96.92 385

xiu_mvs_v1_base_debi		97.86 206	98.17 169	96.92 322	98.98 225	93.91 321	96.45 301	99.17 216	97.85 171	98.41 232	97.14 347	98.47 57	99.92 49	98.02 120	99.05 291	96.92 385

MVP-Stereo		98.08 189	97.92 196	98.57 197	98.96 228	96.79 229	97.90 186	99.18 212	96.41 276	98.46 227	98.95 180	95.93 222	99.60 300	96.51 232	98.98 303	99.31 205
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 151	98.68 94	97.54 290	98.96 228	97.99 147	97.88 189	99.36 141	98.20 146	99.63 48	99.04 149	98.76 35	95.33 408	96.56 226	99.74 140	99.31 205
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				98.91 146	98.94 230	97.76 173		98.76 287	87.58 395	96.75 338	98.10 294	94.80 261	99.78 211	92.73 351	99.00 300	99.20 227

USDC		97.41 241	97.40 233	97.44 299	98.94 230	93.67 330	95.17 360	99.53 80	94.03 344	98.97 152	99.10 136	95.29 245	99.34 363	95.84 269	99.73 143	99.30 208

tfpn200view9		94.03 342	93.44 344	95.78 355	98.93 232	91.44 364	97.60 226	94.29 384	97.94 163	97.10 316	94.31 394	79.67 383	99.62 293	83.05 399	98.08 351	96.29 392

testdata				98.09 245	98.93 232	95.40 274		98.80 282	90.08 386	97.45 304	98.37 272	95.26 246	99.70 252	93.58 332	98.95 306	99.17 238

thres400		94.14 340	93.44 344	96.24 344	98.93 232	91.44 364	97.60 226	94.29 384	97.94 163	97.10 316	94.31 394	79.67 383	99.62 293	83.05 399	98.08 351	97.66 374

TAPA-MVS	96.21 11	96.63 286	95.95 296	98.65 181	98.93 232	98.09 134	96.93 278	99.28 184	83.58 401	98.13 251	97.78 314	96.13 207	99.40 354	93.52 333	99.29 261	98.45 329
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 236	96.93 226	95.54 346	98.78 285	85.72 398	96.86 333	98.11 293	94.43 268			99.10 290	99.23 222

PVSNet_BlendedMVS		97.55 231	97.53 226	97.60 283	98.92 236	93.77 328	96.64 293	99.43 121	94.49 330	97.62 287	99.18 116	96.82 175	99.67 268	94.73 296	99.93 43	99.36 188

PVSNet_Blended		96.88 276	96.68 275	97.47 297	98.92 236	93.77 328	94.71 371	99.43 121	90.98 380	97.62 287	97.36 341	96.82 175	99.67 268	94.73 296	99.56 211	98.98 263

MSDG		97.71 220	97.52 227	98.28 233	98.91 239	96.82 228	94.42 381	99.37 137	97.65 184	98.37 237	98.29 281	97.40 142	99.33 365	94.09 318	99.22 271	98.68 313

Anonymous202405211		97.90 200	97.50 228	99.08 117	98.90 240	98.25 118	98.53 111	96.16 365	98.87 101	99.11 127	98.86 199	90.40 322	99.78 211	97.36 159	99.31 256	99.19 232

原ACMM1				98.35 224	98.90 240	96.25 247		98.83 279	92.48 364	96.07 358	98.10 294	95.39 244	99.71 248	92.61 354	98.99 301	99.08 246

GBi-Net		98.65 115	98.47 127	99.17 101	98.90 240	98.24 119	99.20 44	99.44 115	98.59 117	98.95 155	99.55 47	94.14 276	99.86 106	97.77 137	99.69 163	99.41 163

test1		98.65 115	98.47 127	99.17 101	98.90 240	98.24 119	99.20 44	99.44 115	98.59 117	98.95 155	99.55 47	94.14 276	99.86 106	97.77 137	99.69 163	99.41 163

FMVSNet2		98.49 141	98.40 137	98.75 173	98.90 240	97.14 216	98.61 102	99.13 225	98.59 117	99.19 120	99.28 95	94.14 276	99.82 163	97.97 125	99.80 110	99.29 210

OMC-MVS		97.88 204	97.49 229	99.04 128	98.89 245	98.63 88	96.94 276	99.25 193	95.02 319	98.53 222	98.51 256	97.27 149	99.47 343	93.50 335	99.51 225	99.01 258

MVSFormer		98.26 171	98.43 133	97.77 267	98.88 246	93.89 324	99.39 16	99.56 68	99.11 72	98.16 247	98.13 290	93.81 284	99.97 4	99.26 42	99.57 208	99.43 157

lupinMVS		97.06 266	96.86 262	97.65 279	98.88 246	93.89 324	95.48 351	97.97 326	93.53 350	98.16 247	97.58 326	93.81 284	99.91 58	96.77 206	99.57 208	99.17 238

dmvs_re		95.98 306	95.39 315	97.74 273	98.86 248	97.45 193	98.37 134	95.69 375	97.95 162	96.56 344	95.95 366	90.70 319	97.68 402	88.32 387	96.13 390	98.11 351

DELS-MVS		98.27 169	98.20 165	98.48 212	98.86 248	96.70 234	95.60 345	99.20 204	97.73 179	98.45 228	98.71 224	97.50 135	99.82 163	98.21 107	99.59 199	98.93 274
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		97.89 202	97.98 190	97.60 283	98.86 248	94.35 305	96.21 316	99.44 115	97.45 211	99.06 134	98.88 196	97.99 97	99.28 373	94.38 311	99.58 204	99.18 234

LCM-MVSNet-Re		98.64 117	98.48 125	99.11 111	98.85 251	98.51 101	98.49 120	99.83 20	98.37 127	99.69 37	99.46 65	98.21 78	99.92 49	94.13 317	99.30 259	98.91 278

pmmvs4		97.58 230	97.28 241	98.51 208	98.84 252	96.93 226	95.40 355	98.52 305	93.60 349	98.61 208	98.65 237	95.10 250	99.60 300	96.97 187	99.79 115	98.99 262

NP-MVS					98.84 252	97.39 197					96.84 350

sss		97.21 256	96.93 256	98.06 250	98.83 254	95.22 280	96.75 288	98.48 307	94.49 330	97.27 312	97.90 309	92.77 301	99.80 185	96.57 222	99.32 254	99.16 241

PVSNet	93.40 17	95.67 314	95.70 301	95.57 360	98.83 254	88.57 386	92.50 398	97.72 331	92.69 362	96.49 350	96.44 359	93.72 287	99.43 350	93.61 330	99.28 262	98.71 306

MVE	83.40 22	92.50 362	91.92 364	94.25 374	98.83 254	91.64 361	92.71 397	83.52 411	95.92 296	86.46 409	95.46 379	95.20 247	95.40 407	80.51 404	98.64 327	95.73 400
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
MVS_0304		98.10 184	97.88 201	98.76 169	98.82 257	96.50 240	97.90 186	91.35 400	99.56 26	98.32 238	99.13 130	96.06 210	99.93 39	99.84 7	99.97 19	99.85 18

ambc				98.24 237	98.82 257	95.97 256	98.62 101	99.00 250		99.27 106	99.21 109	96.99 166	99.50 334	96.55 229	99.50 232	99.26 216

旧先验1					98.82 257	97.45 193		98.76 287			98.34 276	95.50 239			99.01 299	99.23 222

test_vis1_rt		97.75 217	97.72 212	97.83 262	98.81 260	96.35 244	97.30 255	99.69 36	94.61 328	97.87 270	98.05 299	96.26 204	98.32 399	98.74 75	98.18 343	98.82 287

WTY-MVS		96.67 284	96.27 293	97.87 260	98.81 260	94.61 299	96.77 286	97.92 328	94.94 322	97.12 315	97.74 317	91.11 317	99.82 163	93.89 323	98.15 347	99.18 234

3Dnovator+	97.89 3	98.69 105	98.51 118	99.24 94	98.81 260	98.40 106	99.02 64	99.19 208	98.99 91	98.07 256	99.28 95	97.11 159	99.84 135	96.84 201	99.32 254	99.47 143

QAPM		97.31 247	96.81 268	98.82 155	98.80 263	97.49 190	99.06 61	99.19 208	90.22 384	97.69 284	99.16 122	96.91 169	99.90 63	90.89 378	99.41 242	99.07 248

VNet		98.42 148	98.30 153	98.79 162	98.79 264	97.29 201	98.23 143	98.66 296	99.31 51	98.85 177	98.80 211	94.80 261	99.78 211	98.13 112	99.13 285	99.31 205

DPM-MVS		96.32 296	95.59 306	98.51 208	98.76 265	97.21 208	94.54 380	98.26 315	91.94 369	96.37 351	97.25 343	93.06 295	99.43 350	91.42 368	98.74 316	98.89 279

3Dnovator	98.27 2	98.81 85	98.73 84	99.05 126	98.76 265	97.81 170	99.25 39	99.30 173	98.57 120	98.55 219	99.33 88	97.95 99	99.90 63	97.16 169	99.67 174	99.44 153

PLC	94.65 16	96.51 289	95.73 300	98.85 152	98.75 267	97.91 157	96.42 304	99.06 234	90.94 381	95.59 364	97.38 339	94.41 269	99.59 304	90.93 376	98.04 356	99.05 250
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 278	96.75 271	97.08 314	98.74 268	93.33 335	96.71 290	98.26 315	96.72 263	98.44 229	97.37 340	95.20 247	99.47 343	91.89 359	97.43 367	98.44 331

hse-mvs2		97.46 236	97.07 251	98.64 182	98.73 269	97.33 199	97.45 245	97.64 336	99.11 72	98.58 214	97.98 303	88.65 335	99.79 200	98.11 113	97.39 369	98.81 291

CDS-MVSNet		97.69 221	97.35 238	98.69 179	98.73 269	97.02 220	96.92 280	98.75 290	95.89 297	98.59 212	98.67 232	92.08 310	99.74 235	96.72 212	99.81 100	99.32 201
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EIA-MVS		98.00 195	97.74 209	98.80 159	98.72 271	98.09 134	98.05 165	99.60 51	97.39 215	96.63 341	95.55 374	97.68 114	99.80 185	96.73 211	99.27 263	98.52 324

LFMVS		97.20 257	96.72 272	98.64 182	98.72 271	96.95 224	98.93 75	94.14 388	99.74 6	98.78 186	99.01 161	84.45 362	99.73 240	97.44 155	99.27 263	99.25 217

new_pmnet		96.99 273	96.76 270	97.67 277	98.72 271	94.89 289	95.95 332	98.20 318	92.62 363	98.55 219	98.54 252	94.88 257	99.52 329	93.96 321	99.44 240	98.59 320

Fast-Effi-MVS+		97.67 223	97.38 235	98.57 197	98.71 274	97.43 195	97.23 260	99.45 111	94.82 325	96.13 355	96.51 355	98.52 56	99.91 58	96.19 250	98.83 312	98.37 340

TEST9					98.71 274	98.08 138	95.96 330	99.03 242	91.40 375	95.85 361	97.53 329	96.52 192	99.76 223

train_agg		97.10 263	96.45 287	99.07 119	98.71 274	98.08 138	95.96 330	99.03 242	91.64 370	95.85 361	97.53 329	96.47 194	99.76 223	93.67 329	99.16 280	99.36 188

TSAR-MVS + GP.		98.18 180	97.98 190	98.77 168	98.71 274	97.88 159	96.32 310	98.66 296	96.33 278	99.23 117	98.51 256	97.48 139	99.40 354	97.16 169	99.46 235	99.02 257

FA-MVS(test-final)		96.99 273	96.82 266	97.50 294	98.70 278	94.78 291	99.34 19	96.99 349	95.07 318	98.48 226	99.33 88	88.41 338	99.65 284	96.13 256	98.92 309	98.07 354

AUN-MVS		96.24 300	95.45 311	98.60 192	98.70 278	97.22 207	97.38 248	97.65 334	95.95 295	95.53 371	97.96 307	82.11 377	99.79 200	96.31 243	97.44 366	98.80 297

our_test_3		97.39 242	97.73 211	96.34 339	98.70 278	89.78 383	94.61 377	98.97 252	96.50 271	99.04 141	98.85 202	95.98 219	99.84 135	97.26 164	99.67 174	99.41 163

ppachtmachnet_test		97.50 232	97.74 209	96.78 331	98.70 278	91.23 372	94.55 379	99.05 237	96.36 277	99.21 118	98.79 213	96.39 197	99.78 211	96.74 209	99.82 95	99.34 194

PCF-MVS	92.86 18	94.36 334	93.00 351	98.42 218	98.70 278	97.56 187	93.16 396	99.11 228	79.59 405	97.55 294	97.43 336	92.19 307	99.73 240	79.85 405	99.45 237	97.97 360
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
iter_conf05_11		98.62 121	98.57 111	98.76 169	98.69 283	97.65 181	98.90 77	99.52 83	98.15 153	98.72 195	99.20 111	95.57 234	99.84 135	98.58 85	99.83 91	98.81 291

ETV-MVS		98.03 191	97.86 203	98.56 201	98.69 283	98.07 140	97.51 239	99.50 88	98.10 155	97.50 299	95.51 375	98.41 62	99.88 82	96.27 246	99.24 268	97.71 373

test_prior				98.95 140	98.69 283	97.95 155		99.03 242					99.59 304			99.30 208

agg_prior					98.68 286	97.99 147		99.01 248		95.59 364			99.77 217

test_8					98.67 287	98.01 146	95.91 335	99.02 245	91.64 370	95.79 363	97.50 332	96.47 194	99.76 223

HQP-NCC					98.67 287		96.29 312		96.05 289	95.55 367

ACMP_Plane					98.67 287		96.29 312		96.05 289	95.55 367

CNVR-MVS		98.17 182	97.87 202	99.07 119	98.67 287	98.24 119	97.01 272	98.93 255	97.25 229	97.62 287	98.34 276	97.27 149	99.57 312	96.42 237	99.33 253	99.39 173

HQP-MVS		97.00 272	96.49 286	98.55 202	98.67 287	96.79 229	96.29 312	99.04 240	96.05 289	95.55 367	96.84 350	93.84 282	99.54 323	92.82 347	99.26 266	99.32 201

MM		98.22 175	97.99 189	98.91 146	98.66 292	96.97 221	97.89 188	94.44 382	99.54 27	98.95 155	99.14 129	93.50 288	99.92 49	99.80 12	99.96 24	99.85 18

test_fmvs1		97.72 219	97.94 194	97.07 316	98.66 292	92.39 352	97.68 214	99.81 23	95.20 317	99.54 55	99.44 70	91.56 314	99.41 353	99.78 15	99.77 125	99.40 172

thres200		93.72 347	93.14 349	95.46 364	98.66 292	91.29 368	96.61 295	94.63 381	97.39 215	96.83 334	93.71 397	79.88 380	99.56 315	82.40 402	98.13 348	95.54 401

wuyk23d		96.06 302	97.62 222	91.38 388	98.65 295	98.57 95	98.85 83	96.95 352	96.86 256	99.90 12	99.16 122	99.18 17	98.40 398	89.23 385	99.77 125	77.18 408

NCCC		97.86 206	97.47 232	99.05 126	98.61 296	98.07 140	96.98 274	98.90 261	97.63 185	97.04 320	97.93 308	95.99 218	99.66 279	95.31 285	98.82 314	99.43 157

DeepC-MVS_fast	96.85 6	98.30 165	98.15 173	98.75 173	98.61 296	97.23 205	97.76 206	99.09 231	97.31 223	98.75 192	98.66 235	97.56 127	99.64 287	96.10 257	99.55 214	99.39 173
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 349	92.09 358	97.75 271	98.60 298	94.40 303	97.32 253	95.26 377	97.56 196	96.79 337	95.50 376	53.57 414	99.77 217	95.26 286	98.97 304	99.08 246

thisisatest0515		94.12 341	93.16 348	96.97 320	98.60 298	92.90 342	93.77 392	90.61 401	94.10 342	96.91 327	95.87 369	74.99 395	99.80 185	94.52 302	99.12 288	98.20 347

GA-MVS		95.86 309	95.32 318	97.49 295	98.60 298	94.15 311	93.83 391	97.93 327	95.49 308	96.68 339	97.42 337	83.21 370	99.30 369	96.22 248	98.55 333	99.01 258

dmvs_testset		92.94 358	92.21 357	95.13 367	98.59 301	90.99 374	97.65 220	92.09 397	96.95 250	94.00 390	93.55 398	92.34 306	96.97 405	72.20 408	92.52 403	97.43 381

OPU-MVS				98.82 155	98.59 301	98.30 115	98.10 158				98.52 255	98.18 80	98.75 395	94.62 299	99.48 234	99.41 163

MSLP-MVS++		98.02 192	98.14 175	97.64 281	98.58 303	95.19 281	97.48 242	99.23 200	97.47 204	97.90 267	98.62 244	97.04 161	98.81 394	97.55 147	99.41 242	98.94 273

test12				98.93 143	98.58 303	97.83 164		98.66 296		96.53 345		95.51 238	99.69 256		99.13 285	99.27 213

CL-MVSNet_self_test		97.44 239	97.22 244	98.08 248	98.57 305	95.78 262	94.30 384	98.79 283	96.58 269	98.60 210	98.19 288	94.74 264	99.64 287	96.41 238	98.84 311	98.82 287

PS-MVSNAJ		97.08 265	97.39 234	96.16 350	98.56 306	92.46 350	95.24 359	98.85 274	97.25 229	97.49 300	95.99 365	98.07 88	99.90 63	96.37 239	98.67 326	96.12 397

CNLPA		97.17 260	96.71 273	98.55 202	98.56 306	98.05 144	96.33 309	98.93 255	96.91 253	97.06 319	97.39 338	94.38 271	99.45 347	91.66 362	99.18 279	98.14 350

xiu_mvs_v2_base		97.16 261	97.49 229	96.17 348	98.54 308	92.46 350	95.45 352	98.84 275	97.25 229	97.48 301	96.49 356	98.31 70	99.90 63	96.34 242	98.68 325	96.15 396

alignmvs		97.35 244	96.88 261	98.78 165	98.54 308	98.09 134	97.71 211	97.69 333	99.20 63	97.59 290	95.90 368	88.12 340	99.55 318	98.18 109	98.96 305	98.70 309

FE-MVS		95.66 315	94.95 327	97.77 267	98.53 310	95.28 277	99.40 15	96.09 367	93.11 356	97.96 264	99.26 99	79.10 387	99.77 217	92.40 356	98.71 320	98.27 344

Effi-MVS+		98.02 192	97.82 205	98.62 187	98.53 310	97.19 210	97.33 252	99.68 41	97.30 224	96.68 339	97.46 335	98.56 54	99.80 185	96.63 218	98.20 342	98.86 284

baseline1		95.96 307	95.44 312	97.52 292	98.51 312	93.99 318	98.39 132	96.09 367	98.21 142	98.40 236	97.76 316	86.88 342	99.63 290	95.42 283	89.27 406	98.95 269

MVS_Test		98.18 180	98.36 145	97.67 277	98.48 313	94.73 294	98.18 148	99.02 245	97.69 181	98.04 260	99.11 133	97.22 153	99.56 315	98.57 88	98.90 310	98.71 306

MGCFI-Net		98.34 158	98.28 155	98.51 208	98.47 314	97.59 186	98.96 71	99.48 97	99.18 69	97.40 307	95.50 376	98.66 43	99.50 334	98.18 109	98.71 320	98.44 331

BH-RMVSNet		96.83 278	96.58 283	97.58 285	98.47 314	94.05 312	96.67 292	97.36 339	96.70 265	97.87 270	97.98 303	95.14 249	99.44 349	90.47 380	98.58 332	99.25 217

sasdasda		98.34 158	98.26 159	98.58 194	98.46 316	97.82 167	98.96 71	99.46 107	99.19 67	97.46 302	95.46 379	98.59 50	99.46 345	98.08 116	98.71 320	98.46 326

canonicalmvs		98.34 158	98.26 159	98.58 194	98.46 316	97.82 167	98.96 71	99.46 107	99.19 67	97.46 302	95.46 379	98.59 50	99.46 345	98.08 116	98.71 320	98.46 326

MVS-HIRNet		94.32 335	95.62 304	90.42 389	98.46 316	75.36 413	96.29 312	89.13 405	95.25 315	95.38 373	99.75 11	92.88 298	99.19 379	94.07 319	99.39 244	96.72 390

PHI-MVS		98.29 168	97.95 192	99.34 72	98.44 319	99.16 43	98.12 155	99.38 132	96.01 292	98.06 257	98.43 266	97.80 108	99.67 268	95.69 275	99.58 204	99.20 227

DVP-MVS++		98.90 74	98.70 91	99.51 42	98.43 320	99.15 47	99.43 10	99.32 159	98.17 149	99.26 110	99.02 152	98.18 80	99.88 82	97.07 178	99.45 237	99.49 126

MSC_two_6792asdad				99.32 79	98.43 320	98.37 110		98.86 271					99.89 73	97.14 172	99.60 195	99.71 45

No_MVS				99.32 79	98.43 320	98.37 110		98.86 271					99.89 73	97.14 172	99.60 195	99.71 45

Fast-Effi-MVS+-dtu		98.27 169	98.09 178	98.81 157	98.43 320	98.11 131	97.61 225	99.50 88	98.64 111	97.39 309	97.52 331	98.12 87	99.95 22	96.90 195	98.71 320	98.38 338

OpenMVS_ROB	95.38 14	95.84 310	95.18 322	97.81 264	98.41 324	97.15 214	97.37 249	98.62 300	83.86 400	98.65 202	98.37 272	94.29 274	99.68 265	88.41 386	98.62 330	96.60 391

DeepPCF-MVS	96.93 5	98.32 162	98.01 186	99.23 96	98.39 325	98.97 66	95.03 364	99.18 212	96.88 254	99.33 95	98.78 214	98.16 84	99.28 373	96.74 209	99.62 188	99.44 153

Patchmatch-test		96.55 288	96.34 289	97.17 311	98.35 326	93.06 338	98.40 131	97.79 329	97.33 220	98.41 232	98.67 232	83.68 369	99.69 256	95.16 288	99.31 256	98.77 300

AdaColmap		97.14 262	96.71 273	98.46 214	98.34 327	97.80 171	96.95 275	98.93 255	95.58 305	96.92 325	97.66 321	95.87 224	99.53 325	90.97 375	99.14 283	98.04 355

OpenMVS	96.65 7	97.09 264	96.68 275	98.32 226	98.32 328	97.16 213	98.86 82	99.37 137	89.48 388	96.29 353	99.15 126	96.56 190	99.90 63	92.90 344	99.20 274	97.89 361

bld_raw_dy_0_64		97.85 211	97.71 213	98.26 234	98.31 329	96.74 233	95.53 347	99.31 164	97.79 175	97.85 273	97.56 328	95.70 229	99.82 163	97.52 152	99.84 83	98.22 345

MG-MVS		96.77 281	96.61 280	97.26 307	98.31 329	93.06 338	95.93 333	98.12 323	96.45 275	97.92 265	98.73 221	93.77 286	99.39 356	91.19 373	99.04 294	99.33 199

test_yl		96.69 282	96.29 291	97.90 257	98.28 331	95.24 278	97.29 256	97.36 339	98.21 142	98.17 245	97.86 310	86.27 346	99.55 318	94.87 293	98.32 336	98.89 279

DCV-MVSNet		96.69 282	96.29 291	97.90 257	98.28 331	95.24 278	97.29 256	97.36 339	98.21 142	98.17 245	97.86 310	86.27 346	99.55 318	94.87 293	98.32 336	98.89 279

CHOSEN 280x420		95.51 320	95.47 309	95.65 359	98.25 333	88.27 389	93.25 395	98.88 264	93.53 350	94.65 382	97.15 346	86.17 348	99.93 39	97.41 157	99.93 43	98.73 305

SCA		96.41 295	96.66 278	95.67 357	98.24 334	88.35 388	95.85 338	96.88 355	96.11 286	97.67 285	98.67 232	93.10 293	99.85 118	94.16 313	99.22 271	98.81 291

DeepMVS_CX				93.44 384	98.24 334	94.21 308		94.34 383	64.28 408	91.34 402	94.87 391	89.45 329	92.77 409	77.54 407	93.14 402	93.35 404

MS-PatchMatch		97.68 222	97.75 208	97.45 298	98.23 336	93.78 327	97.29 256	98.84 275	96.10 287	98.64 203	98.65 237	96.04 211	99.36 359	96.84 201	99.14 283	99.20 227

BH-w/o		95.13 325	94.89 329	95.86 352	98.20 337	91.31 367	95.65 343	97.37 338	93.64 348	96.52 346	95.70 372	93.04 296	99.02 385	88.10 388	95.82 393	97.24 383

mvs_anonymous		97.83 215	98.16 172	96.87 325	98.18 338	91.89 359	97.31 254	98.90 261	97.37 217	98.83 180	99.46 65	96.28 203	99.79 200	98.90 65	98.16 346	98.95 269

miper_lstm_enhance		97.18 259	97.16 247	97.25 308	98.16 339	92.85 343	95.15 362	99.31 164	97.25 229	98.74 194	98.78 214	90.07 323	99.78 211	97.19 167	99.80 110	99.11 245

ET-MVSNet_ETH3D		94.30 337	93.21 347	97.58 285	98.14 340	94.47 302	94.78 370	93.24 393	94.72 326	89.56 404	95.87 369	78.57 390	99.81 178	96.91 190	97.11 378	98.46 326

ADS-MVSNet2		95.43 321	94.98 325	96.76 332	98.14 340	91.74 360	97.92 183	97.76 330	90.23 382	96.51 347	98.91 185	85.61 353	99.85 118	92.88 345	96.90 379	98.69 310

ADS-MVSNet		95.24 324	94.93 328	96.18 347	98.14 340	90.10 382	97.92 183	97.32 342	90.23 382	96.51 347	98.91 185	85.61 353	99.74 235	92.88 345	96.90 379	98.69 310

c3_l		97.36 243	97.37 236	97.31 303	98.09 343	93.25 336	95.01 365	99.16 219	97.05 245	98.77 189	98.72 223	92.88 298	99.64 287	96.93 189	99.76 136	99.05 250

FMVSNet3		97.50 232	97.24 243	98.29 232	98.08 344	95.83 260	97.86 193	98.91 260	97.89 168	98.95 155	98.95 180	87.06 341	99.81 178	97.77 137	99.69 163	99.23 222

PAPM		91.88 371	90.34 374	96.51 335	98.06 345	92.56 348	92.44 399	97.17 344	86.35 396	90.38 403	96.01 364	86.61 344	99.21 378	70.65 409	95.43 395	97.75 370

Effi-MVS+-dtu		98.26 171	97.90 198	99.35 69	98.02 346	99.49 5	98.02 170	99.16 219	98.29 136	97.64 286	97.99 302	96.44 196	99.95 22	96.66 217	98.93 308	98.60 318

mamv4		98.09 187	98.01 186	98.31 229	98.02 346	96.58 239	97.53 235	99.41 125	97.57 192	97.89 268	98.96 175	95.45 242	99.80 185	97.48 154	99.78 120	98.57 321

eth_miper_zixun_eth		97.23 255	97.25 242	97.17 311	98.00 348	92.77 345	94.71 371	99.18 212	97.27 227	98.56 217	98.74 220	91.89 311	99.69 256	97.06 180	99.81 100	99.05 250

MVSMamba_pp		98.01 194	97.90 198	98.32 226	97.95 349	96.59 236	97.57 231	99.38 132	96.07 288	97.99 262	99.01 161	95.57 234	99.80 185	97.76 141	99.82 95	98.57 321

HY-MVS	95.94 13	95.90 308	95.35 317	97.55 289	97.95 349	94.79 290	98.81 86	96.94 353	92.28 367	95.17 375	98.57 250	89.90 325	99.75 230	91.20 372	97.33 374	98.10 352

UGNet		98.53 136	98.45 130	98.79 162	97.94 351	96.96 223	99.08 57	98.54 303	99.10 79	96.82 335	99.47 64	96.55 191	99.84 135	98.56 91	99.94 39	99.55 103
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		96.47 293	95.70 301	98.79 162	97.92 352	99.12 57	98.28 139	98.60 301	92.16 368	95.54 370	96.17 363	94.77 263	99.52 329	89.62 383	98.23 340	97.72 372
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		96.86 277	96.55 284	97.79 265	97.91 353	94.21 308	97.56 232	98.87 266	97.49 203	99.06 134	99.05 147	80.72 378	99.80 185	98.44 95	99.82 95	99.37 182

API-MVS		97.04 268	96.91 260	97.42 300	97.88 354	98.23 123	98.18 148	98.50 306	97.57 192	97.39 309	96.75 352	96.77 179	99.15 382	90.16 381	99.02 298	94.88 402

miper_ehance_all_eth		97.06 266	97.03 253	97.16 313	97.83 355	93.06 338	94.66 374	99.09 231	95.99 293	98.69 197	98.45 265	92.73 302	99.61 299	96.79 203	99.03 295	98.82 287

cl____		97.02 269	96.83 265	97.58 285	97.82 356	94.04 314	94.66 374	99.16 219	97.04 246	98.63 204	98.71 224	88.68 334	99.69 256	97.00 182	99.81 100	99.00 261

DIV-MVS_self_test		97.02 269	96.84 264	97.58 285	97.82 356	94.03 315	94.66 374	99.16 219	97.04 246	98.63 204	98.71 224	88.69 332	99.69 256	97.00 182	99.81 100	99.01 258

CANet		97.87 205	97.76 207	98.19 240	97.75 358	95.51 269	96.76 287	99.05 237	97.74 178	96.93 324	98.21 286	95.59 233	99.89 73	97.86 133	99.93 43	99.19 232

mvsany_test1		97.60 227	97.54 225	97.77 267	97.72 359	95.35 275	95.36 356	97.13 346	94.13 341	99.71 33	99.33 88	97.93 100	99.30 369	97.60 146	98.94 307	98.67 314

PVSNet_0	89.98 21	91.15 372	90.30 375	93.70 381	97.72 359	84.34 406	90.24 402	97.42 337	90.20 385	93.79 392	93.09 401	90.90 318	98.89 393	86.57 394	72.76 409	97.87 363

CR-MVSNet		96.28 298	95.95 296	97.28 305	97.71 361	94.22 306	98.11 156	98.92 258	92.31 366	96.91 327	99.37 78	85.44 356	99.81 178	97.39 158	97.36 372	97.81 366

RPMNet		97.02 269	96.93 256	97.30 304	97.71 361	94.22 306	98.11 156	99.30 173	99.37 44	96.91 327	99.34 86	86.72 343	99.87 99	97.53 150	97.36 372	97.81 366

ETVMVS		92.60 361	91.08 370	97.18 309	97.70 363	93.65 332	96.54 296	95.70 373	96.51 270	94.68 381	92.39 404	61.80 411	99.50 334	86.97 391	97.41 368	98.40 336

pmmvs3		95.03 327	94.40 333	96.93 321	97.70 363	92.53 349	95.08 363	97.71 332	88.57 392	97.71 282	98.08 297	79.39 385	99.82 163	96.19 250	99.11 289	98.43 333

baseline2		93.73 346	92.83 352	96.42 338	97.70 363	91.28 369	96.84 283	89.77 404	93.96 346	92.44 399	95.93 367	79.14 386	99.77 217	92.94 343	96.76 383	98.21 346

tpm		94.67 331	94.34 335	95.66 358	97.68 366	88.42 387	97.88 189	94.90 378	94.46 332	96.03 360	98.56 251	78.66 388	99.79 200	95.88 263	95.01 397	98.78 299

CANet_DTU		97.26 251	97.06 252	97.84 261	97.57 367	94.65 298	96.19 318	98.79 283	97.23 235	95.14 376	98.24 283	93.22 290	99.84 135	97.34 160	99.84 83	99.04 254

testing11		93.08 356	92.02 360	96.26 343	97.56 368	90.83 377	96.32 310	95.70 373	96.47 274	92.66 398	93.73 396	64.36 409	99.59 304	93.77 328	97.57 361	98.37 340

tpm2		93.09 355	92.58 354	94.62 371	97.56 368	86.53 395	97.66 218	95.79 372	86.15 397	94.07 389	98.23 285	75.95 393	99.53 325	90.91 377	96.86 382	97.81 366

testing91		93.32 352	92.27 355	96.47 337	97.54 370	91.25 370	96.17 321	96.76 357	97.18 239	93.65 394	93.50 399	65.11 408	99.63 290	93.04 342	97.45 365	98.53 323

TR-MVS		95.55 318	95.12 323	96.86 328	97.54 370	93.94 319	96.49 300	96.53 362	94.36 337	97.03 322	96.61 354	94.26 275	99.16 381	86.91 393	96.31 387	97.47 380

testing99		93.04 357	91.98 363	96.23 345	97.53 372	90.70 379	96.35 308	95.94 370	96.87 255	93.41 395	93.43 400	63.84 410	99.59 304	93.24 340	97.19 375	98.40 336

1314		95.74 312	95.60 305	96.17 348	97.53 372	92.75 346	98.07 162	98.31 314	91.22 377	94.25 385	96.68 353	95.53 236	99.03 384	91.64 364	97.18 376	96.74 389

CostFormer		93.97 343	93.78 340	94.51 372	97.53 372	85.83 398	97.98 177	95.96 369	89.29 390	94.99 378	98.63 242	78.63 389	99.62 293	94.54 301	96.50 384	98.09 353

FMVSNet5		96.01 304	95.20 321	98.41 219	97.53 372	96.10 249	98.74 87	99.50 88	97.22 238	98.03 261	99.04 149	69.80 398	99.88 82	97.27 163	99.71 155	99.25 217

PMMVS		96.51 289	95.98 295	98.09 245	97.53 372	95.84 259	94.92 367	98.84 275	91.58 372	96.05 359	95.58 373	95.68 230	99.66 279	95.59 279	98.09 350	98.76 302

PAPR		95.29 322	94.47 331	97.75 271	97.50 377	95.14 283	94.89 368	98.71 294	91.39 376	95.35 374	95.48 378	94.57 266	99.14 383	84.95 396	97.37 370	98.97 266

testing222		91.96 369	90.37 373	96.72 333	97.47 378	92.59 347	96.11 323	94.76 379	96.83 257	92.90 397	92.87 402	57.92 412	99.55 318	86.93 392	97.52 362	98.00 359

PatchT		96.65 285	96.35 288	97.54 290	97.40 379	95.32 276	97.98 177	96.64 359	99.33 49	96.89 331	99.42 72	84.32 364	99.81 178	97.69 145	97.49 363	97.48 379

tpm cat1		93.29 353	93.13 350	93.75 380	97.39 380	84.74 401	97.39 247	97.65 334	83.39 402	94.16 386	98.41 267	82.86 373	99.39 356	91.56 366	95.35 396	97.14 384

PatchmatchNet		95.58 317	95.67 303	95.30 366	97.34 381	87.32 393	97.65 220	96.65 358	95.30 314	97.07 318	98.69 228	84.77 359	99.75 230	94.97 291	98.64 327	98.83 286
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 244	96.97 255	98.50 211	97.31 382	96.47 241	98.18 148	98.92 258	98.95 96	98.78 186	99.37 78	85.44 356	99.85 118	95.96 261	99.83 91	99.17 238

LS3D		98.63 119	98.38 142	99.36 63	97.25 383	99.38 8	99.12 56	99.32 159	99.21 61	98.44 229	98.88 196	97.31 145	99.80 185	96.58 220	99.34 252	98.92 275

IB-MVS	91.63 19	92.24 367	90.90 371	96.27 342	97.22 384	91.24 371	94.36 383	93.33 392	92.37 365	92.24 400	94.58 393	66.20 406	99.89 73	93.16 341	94.63 399	97.66 374
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		92.38 364	91.76 367	94.21 375	97.16 385	84.65 402	95.42 354	88.45 406	95.96 294	96.17 354	95.84 371	66.36 404	99.71 248	91.87 360	98.64 327	98.28 343

tpmrst		95.07 326	95.46 310	93.91 378	97.11 386	84.36 405	97.62 223	96.96 351	94.98 320	96.35 352	98.80 211	85.46 355	99.59 304	95.60 278	96.23 388	97.79 369

Syy-MVS		96.04 303	95.56 308	97.49 295	97.10 387	94.48 301	96.18 319	96.58 360	95.65 302	94.77 379	92.29 405	91.27 316	99.36 359	98.17 111	98.05 354	98.63 316

myMVS_eth3d		91.92 370	90.45 372	96.30 340	97.10 387	90.90 375	96.18 319	96.58 360	95.65 302	94.77 379	92.29 405	53.88 413	99.36 359	89.59 384	98.05 354	98.63 316

MDTV_nov1_ep13			95.22 320		97.06 389	83.20 407	97.74 208	96.16 365	94.37 336	96.99 323	98.83 205	83.95 367	99.53 325	93.90 322	97.95 357

MVS		93.19 354	92.09 358	96.50 336	96.91 390	94.03 315	98.07 162	98.06 325	68.01 407	94.56 384	96.48 357	95.96 221	99.30 369	83.84 398	96.89 381	96.17 394

E-PMN		94.17 339	94.37 334	93.58 382	96.86 391	85.71 399	90.11 404	97.07 347	98.17 149	97.82 277	97.19 344	84.62 361	98.94 389	89.77 382	97.68 360	96.09 398

JIA-IIPM		95.52 319	95.03 324	97.00 317	96.85 392	94.03 315	96.93 278	95.82 371	99.20 63	94.63 383	99.71 17	83.09 371	99.60 300	94.42 307	94.64 398	97.36 382

EMVS		93.83 345	94.02 337	93.23 386	96.83 393	84.96 400	89.77 405	96.32 364	97.92 165	97.43 306	96.36 362	86.17 348	98.93 390	87.68 389	97.73 359	95.81 399

cl22		95.79 311	95.39 315	96.98 319	96.77 394	92.79 344	94.40 382	98.53 304	94.59 329	97.89 268	98.17 289	82.82 374	99.24 375	96.37 239	99.03 295	98.92 275

WB-MVSnew		95.73 313	95.57 307	96.23 345	96.70 395	90.70 379	96.07 325	93.86 389	95.60 304	97.04 320	95.45 382	96.00 214	99.55 318	91.04 374	98.31 338	98.43 333

dp		93.47 350	93.59 343	93.13 387	96.64 396	81.62 411	97.66 218	96.42 363	92.80 361	96.11 356	98.64 240	78.55 391	99.59 304	93.31 338	92.18 405	98.16 349

test-LLR		93.90 344	93.85 338	94.04 376	96.53 397	84.62 403	94.05 388	92.39 395	96.17 283	94.12 387	95.07 383	82.30 375	99.67 268	95.87 266	98.18 343	97.82 364

test-mter		92.33 366	91.76 367	94.04 376	96.53 397	84.62 403	94.05 388	92.39 395	94.00 345	94.12 387	95.07 383	65.63 407	99.67 268	95.87 266	98.18 343	97.82 364

TESTMET0.1,1		92.19 368	91.77 366	93.46 383	96.48 399	82.80 408	94.05 388	91.52 399	94.45 334	94.00 390	94.88 389	66.65 403	99.56 315	95.78 271	98.11 349	98.02 356

miper_enhance_ethall		96.01 304	95.74 299	96.81 329	96.41 400	92.27 356	93.69 393	98.89 263	91.14 379	98.30 239	97.35 342	90.58 320	99.58 310	96.31 243	99.03 295	98.60 318

tpmvs		95.02 328	95.25 319	94.33 373	96.39 401	85.87 396	98.08 160	96.83 356	95.46 309	95.51 372	98.69 228	85.91 351	99.53 325	94.16 313	96.23 388	97.58 377

CMPMVS	75.91 23	96.29 297	95.44 312	98.84 153	96.25 402	98.69 87	97.02 271	99.12 226	88.90 391	97.83 275	98.86 199	89.51 327	98.90 392	91.92 358	99.51 225	98.92 275
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 332	93.69 341	96.99 318	96.05 403	93.61 333	94.97 366	93.49 390	96.17 283	97.57 293	94.88 389	82.30 375	99.01 387	93.60 331	94.17 401	98.37 340

EPMVS		93.72 347	93.27 346	95.09 369	96.04 404	87.76 391	98.13 153	85.01 410	94.69 327	96.92 325	98.64 240	78.47 392	99.31 367	95.04 289	96.46 385	98.20 347

cascas		94.79 330	94.33 336	96.15 351	96.02 405	92.36 354	92.34 400	99.26 192	85.34 399	95.08 377	94.96 388	92.96 297	98.53 397	94.41 310	98.59 331	97.56 378

gg-mvs-nofinetune		92.37 365	91.20 369	95.85 353	95.80 406	92.38 353	99.31 26	81.84 412	99.75 5	91.83 401	99.74 13	68.29 399	99.02 385	87.15 390	97.12 377	96.16 395

gm-plane-assit					94.83 407	81.97 410			88.07 394		94.99 386		99.60 300	91.76 361

GG-mvs-BLEND				94.76 370	94.54 408	92.13 358	99.31 26	80.47 413		88.73 407	91.01 407	67.59 402	98.16 401	82.30 403	94.53 400	93.98 403

EPNet_dtu		94.93 329	94.78 330	95.38 365	93.58 409	87.68 392	96.78 285	95.69 375	97.35 219	89.14 406	98.09 296	88.15 339	99.49 337	94.95 292	99.30 259	98.98 263
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 376	75.95 379	77.12 392	92.39 410	67.91 416	90.16 403	59.44 417	82.04 403	89.42 405	94.67 392	49.68 415	81.74 410	48.06 410	77.66 408	81.72 406

KD-MVS_2432*1600		92.87 359	91.99 361	95.51 362	91.37 411	89.27 384	94.07 386	98.14 321	95.42 310	97.25 313	96.44 359	67.86 400	99.24 375	91.28 370	96.08 391	98.02 356

miper_refine_blended		92.87 359	91.99 361	95.51 362	91.37 411	89.27 384	94.07 386	98.14 321	95.42 310	97.25 313	96.44 359	67.86 400	99.24 375	91.28 370	96.08 391	98.02 356

EPNet		96.14 301	95.44 312	98.25 235	90.76 413	95.50 270	97.92 183	94.65 380	98.97 93	92.98 396	98.85 202	89.12 330	99.87 99	95.99 259	99.68 168	99.39 173
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 377	68.95 380	70.34 393	87.68 414	65.00 417	91.11 401	59.90 416	69.02 406	74.46 411	88.89 408	48.58 416	68.03 412	28.61 411	72.33 410	77.99 407

test_method		79.78 374	79.50 377	80.62 390	80.21 415	45.76 418	70.82 406	98.41 311	31.08 410	80.89 410	97.71 318	84.85 358	97.37 403	91.51 367	80.03 407	98.75 303

tmp_tt		78.77 375	78.73 378	78.90 391	58.45 416	74.76 415	94.20 385	78.26 414	39.16 409	86.71 408	92.82 403	80.50 379	75.19 411	86.16 395	92.29 404	86.74 405

testmvs		17.12 379	20.53 382	6.87 395	12.05 417	4.20 420	93.62 394	6.73 418	4.62 413	10.41 413	24.33 410	8.28 418	3.56 414	9.69 413	15.07 411	12.86 410

test123		17.04 380	20.11 383	7.82 394	10.25 418	4.91 419	94.80 369	4.47 419	4.93 412	10.00 414	24.28 411	9.69 417	3.64 413	10.14 412	12.43 412	14.92 409

test_blank		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

eth-test2					0.00 419

eth-test					0.00 419

uanet_test		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

DCPMVS		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

cdsmvs_eth3d_5k		24.66 378	32.88 381	0.00 396	0.00 419	0.00 421	0.00 407	99.10 229	0.00 414	0.00 415	97.58 326	99.21 16	0.00 415	0.00 414	0.00 413	0.00 411

pcd_1.5k_mvsjas		8.17 381	10.90 384	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	98.07 88	0.00 415	0.00 414	0.00 413	0.00 411

sosnet-low-res		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

sosnet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uncertanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

Regformer		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

ab-mvs-re		8.12 382	10.83 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	97.48 333	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

WAC-MVS						90.90 375								91.37 369

PC_three_1452									93.27 353	99.40 82	98.54 252	98.22 76	97.00 404	95.17 287	99.45 237	99.49 126

test_241102_TWO								99.30 173	98.03 157	99.26 110	99.02 152	97.51 134	99.88 82	96.91 190	99.60 195	99.66 57

test_0728_THIRD									98.17 149	99.08 132	99.02 152	97.89 101	99.88 82	97.07 178	99.71 155	99.70 50

GSMVS																98.81 291

sam_mvs1												84.74 360				98.81 291

sam_mvs												84.29 366

MTGPA								99.20 204

test_post1							97.59 228				20.48 413	83.07 372	99.66 279	94.16 313

test_post											21.25 412	83.86 368	99.70 252

patchmatchnet-post											98.77 216	84.37 363	99.85 118

MTMP							97.93 181	91.91 398

test9_res														93.28 339	99.15 282	99.38 180

agg_prior2														92.50 355	99.16 280	99.37 182

test_prior4						97.97 151	95.86 336

test_prior2							95.74 341		96.48 273	96.11 356	97.63 324	95.92 223		94.16 313	99.20 274

旧先验2							95.76 340		88.56 393	97.52 297			99.66 279	94.48 303

新几何2							95.93 333

无先验							95.74 341	98.74 292	89.38 389				99.73 240	92.38 357		99.22 226

原ACMM2							95.53 347

testdata2													99.79 200	92.80 349

segment_acmp												97.02 164

testdata1							95.44 353		96.32 279

plane_prior5								99.27 187					99.70 252	94.42 307	99.51 225	99.45 149

plane_prior4											97.98 303

plane_prior3						97.78 172			97.41 213	97.79 278

plane_prior2							97.77 203		98.20 146

plane_prior						97.65 181	97.07 270		96.72 263						99.36 248

n2								0.00 420

nn								0.00 420

door-mid								99.57 61

test11								98.87 266

door								99.41 125

HQP5-MVS						96.79 229

BP-MVS														92.82 347

HQP4-MVS										95.56 366			99.54 323			99.32 201

HQP3-MVS								99.04 240							99.26 266

HQP2-MVS												93.84 282

MDTV_nov1_ep13_2view						74.92 414	97.69 213		90.06 387	97.75 281		85.78 352		93.52 333		98.69 310

ACMMP++_ref															99.77 125

ACMMP++															99.68 168

Test By Simon												96.52 192

High-resolution multi-view benchmark