High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

LCM-MVSNet		99.93 1	99.92 1	99.94 1	99.99 1	99.97 1	99.90 1	99.89 13	99.98 1	99.99 1	99.96 1	99.77 2	100.00 1	99.81 14	100.00 1	99.85 29

Gipuma		99.03 77	99.16 59	98.64 202	99.94 2	98.51 108	99.32 26	99.75 41	99.58 37	98.60 242	99.62 40	98.22 92	99.51 368	97.70 173	99.73 166	97.89 401
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 29	99.31 40	99.53 38	99.91 3	98.98 71	99.63 7	99.58 71	99.44 50	99.78 38	99.76 15	96.39 222	99.92 62	99.44 52	99.92 66	99.68 67

pmmvs6		99.67 3	99.70 3	99.60 15	99.90 4	99.27 27	99.53 9	99.76 38	99.64 27	99.84 29	99.83 4	99.50 9	99.87 128	99.36 55	99.92 66	99.64 80

PS-MVSNAJss		99.46 17	99.49 16	99.35 76	99.90 4	98.15 135	99.20 48	99.65 59	99.48 42	99.92 8	99.71 22	98.07 106	99.96 14	99.53 45	100.00 1	99.93 11

testf1		99.25 40	99.16 59	99.51 48	99.89 6	99.63 4	98.71 104	99.69 49	98.90 123	99.43 98	99.35 100	98.86 33	99.67 300	97.81 164	99.81 120	99.24 253

APD_test2		99.25 40	99.16 59	99.51 48	99.89 6	99.63 4	98.71 104	99.69 49	98.90 123	99.43 98	99.35 100	98.86 33	99.67 300	97.81 164	99.81 120	99.24 253

ANet_high		99.57 10	99.67 6	99.28 92	99.89 6	98.09 142	99.14 57	99.93 5	99.82 8	99.93 6	99.81 8	99.17 19	99.94 41	99.31 59	100.00 1	99.82 34

anonymousdsp		99.51 14	99.47 21	99.62 9	99.88 9	99.08 69	99.34 23	99.69 49	98.93 121	99.65 61	99.72 21	98.93 31	99.95 26	99.11 75	100.00 1	99.82 34

v7n		99.53 12	99.57 13	99.41 66	99.88 9	98.54 106	99.45 14	99.61 67	99.66 24	99.68 55	99.66 32	98.44 72	99.95 26	99.73 25	99.96 27	99.75 56

mvs_tets		99.63 6	99.67 6	99.49 54	99.88 9	98.61 98	99.34 23	99.71 45	99.27 71	99.90 13	99.74 18	99.68 4	99.97 7	99.55 40	99.99 5	99.88 20

test_fmvsmconf0.01_n		99.57 10	99.63 10	99.36 70	99.87 12	98.13 138	98.08 180	99.95 1	99.45 48	99.98 2	99.75 16	99.80 1	99.97 7	99.82 10	99.99 5	99.99 2

jajsoiax		99.58 9	99.61 11	99.48 56	99.87 12	98.61 98	99.28 40	99.66 58	99.09 102	99.89 17	99.68 25	99.53 7	99.97 7	99.50 48	99.99 5	99.87 21

test_djsdf		99.52 13	99.51 15	99.53 38	99.86 14	98.74 88	99.39 20	99.56 85	99.11 92	99.70 49	99.73 20	99.00 26	99.97 7	99.26 63	99.98 12	99.89 16

MIMVSNet1		99.38 28	99.32 38	99.55 28	99.86 14	99.19 42	99.41 17	99.59 69	99.59 35	99.71 47	99.57 49	97.12 180	99.90 78	99.21 68	99.87 94	99.54 133

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 26	99.85 16	99.11 64	99.90 1	99.78 35	99.63 29	99.78 38	99.67 30	99.48 10	99.81 210	99.30 60	99.97 20	99.77 47
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 17	99.34 20	99.69 5	99.58 71	99.90 3	99.86 23	99.78 13	99.58 6	99.95 26	99.00 85	99.95 37	99.78 44

SixPastTwentyTwo		98.75 117	98.62 128	99.16 114	99.83 18	97.96 162	99.28 40	98.20 348	99.37 58	99.70 49	99.65 36	92.65 327	99.93 52	99.04 82	99.84 105	99.60 96

sc_t1		99.62 7	99.66 8	99.53 38	99.82 19	99.09 68	99.50 11	99.63 62	99.88 4	99.86 23	99.80 11	99.03 23	99.89 93	99.48 50	99.93 53	99.60 96

Baseline_NR-MVSNet		98.98 85	98.86 96	99.36 70	99.82 19	98.55 103	97.47 277	99.57 78	99.37 58	99.21 145	99.61 43	96.76 204	99.83 185	98.06 146	99.83 112	99.71 59

pm-mvs1		99.44 19	99.48 18	99.33 85	99.80 21	98.63 95	99.29 36	99.63 62	99.30 68	99.65 61	99.60 45	99.16 21	99.82 195	99.07 78	99.83 112	99.56 122

TransMVSNet (Re)		99.44 19	99.47 21	99.36 70	99.80 21	98.58 101	99.27 42	99.57 78	99.39 56	99.75 43	99.62 40	99.17 19	99.83 185	99.06 80	99.62 216	99.66 74

K. test v3		98.00 221	97.66 246	99.03 141	99.79 23	97.56 198	99.19 52	92.47 434	99.62 32	99.52 80	99.66 32	89.61 358	99.96 14	99.25 65	99.81 120	99.56 122

test_fmvsmconf0.1_n		99.49 15	99.54 14	99.34 79	99.78 24	98.11 139	97.77 232	99.90 11	99.33 63	99.97 3	99.66 32	99.71 3	99.96 14	99.79 17	99.99 5	99.96 8

APD_test1		98.83 103	98.66 122	99.34 79	99.78 24	99.47 9	98.42 144	99.45 128	98.28 174	98.98 175	99.19 140	97.76 132	99.58 343	96.57 257	99.55 243	98.97 303

test_vis3_rt		99.14 59	99.17 57	99.07 131	99.78 24	98.38 115	98.92 82	99.94 2	97.80 212	99.91 12	99.67 30	97.15 179	98.91 427	99.76 21	99.56 239	99.92 12

EGC-MVSNET		85.24 414	80.54 417	99.34 79	99.77 27	99.20 39	99.08 61	99.29 205	12.08 452	20.84 453	99.42 87	97.55 150	99.85 149	97.08 209	99.72 174	98.96 305

Anonymous20240521		98.69 128	98.87 93	98.16 270	99.77 27	95.11 311	99.08 61	99.44 133	99.34 62	99.33 121	99.55 57	94.10 302	99.94 41	99.25 65	99.96 27	99.42 192

FC-MVSNet-test		99.27 37	99.25 50	99.34 79	99.77 27	98.37 117	99.30 35	99.57 78	99.61 34	99.40 107	99.50 67	97.12 180	99.85 149	99.02 84	99.94 48	99.80 39

test_vis1_n		98.31 189	98.50 145	97.73 303	99.76 30	94.17 338	98.68 107	99.91 9	96.31 320	99.79 37	99.57 49	92.85 323	99.42 388	99.79 17	99.84 105	99.60 96

test_fmvs3		99.12 66	99.41 25	98.25 261	99.76 30	95.07 312	99.05 67	99.94 2	97.78 215	99.82 32	99.84 3	98.56 63	99.71 280	99.96 1	99.96 27	99.97 4

XXY-MVS		99.14 59	99.15 64	99.10 124	99.76 30	97.74 187	98.85 92	99.62 64	98.48 158	99.37 112	99.49 73	98.75 43	99.86 136	98.20 136	99.80 131	99.71 59

TDRefinement		99.42 24	99.38 28	99.55 28	99.76 30	99.33 21	99.68 6	99.71 45	99.38 57	99.53 78	99.61 43	98.64 53	99.80 218	98.24 132	99.84 105	99.52 145

fmvsm_s_conf0.1_n_a		99.17 51	99.30 43	98.80 175	99.75 34	96.59 254	97.97 206	99.86 16	98.22 177	99.88 20	99.71 22	98.59 59	99.84 167	99.73 25	99.98 12	99.98 3

tt0805		98.69 128	98.62 128	98.90 165	99.75 34	99.30 22	99.15 56	96.97 385	98.86 128	98.87 205	97.62 363	98.63 55	98.96 424	99.41 54	98.29 376	98.45 367

test_vis1_n_1920		98.40 174	98.92 88	96.81 362	99.74 36	90.76 413	98.15 170	99.91 9	98.33 165	99.89 17	99.55 57	95.07 273	99.88 109	99.76 21	99.93 53	99.79 41

FOURS1					99.73 37	99.67 3	99.43 15	99.54 93	99.43 52	99.26 137

PEN-MVS		99.41 25	99.34 35	99.62 9	99.73 37	99.14 57	99.29 36	99.54 93	99.62 32	99.56 69	99.42 87	98.16 100	99.96 14	98.78 99	99.93 53	99.77 47

lessismore_v0				98.97 152	99.73 37	97.53 200		86.71 449		99.37 112	99.52 66	89.93 354	99.92 62	98.99 86	99.72 174	99.44 185

SteuartSystems-ACMMP		98.79 110	98.54 140	99.54 31	99.73 37	99.16 48	98.23 160	99.31 189	97.92 203	98.90 195	98.90 218	98.00 112	99.88 109	96.15 289	99.72 174	99.58 111
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 208	98.15 199	98.22 264	99.73 37	95.15 308	97.36 285	99.68 54	94.45 375	98.99 174	99.27 118	96.87 194	99.94 41	97.13 206	99.91 75	99.57 116

Vis-MVSNet		99.34 30	99.36 32	99.27 95	99.73 37	98.26 124	99.17 53	99.78 35	99.11 92	99.27 133	99.48 74	98.82 36	99.95 26	98.94 89	99.93 53	99.59 103
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
tt0320-xc		99.64 5	99.68 5	99.50 53	99.72 43	98.98 71	99.51 10	99.85 18	99.86 6	99.88 20	99.82 5	99.02 25	99.90 78	99.54 41	99.95 37	99.61 94

SSC-MVS		98.71 121	98.74 106	98.62 208	99.72 43	96.08 273	98.74 97	98.64 328	99.74 13	99.67 57	99.24 130	94.57 288	99.95 26	99.11 75	99.24 300	99.82 34

test_f		98.67 136	98.87 93	98.05 279	99.72 43	95.59 287	98.51 128	99.81 30	96.30 322	99.78 38	99.82 5	96.14 232	98.63 434	99.82 10	99.93 53	99.95 9

ACMH	96.65 7	99.25 40	99.24 51	99.26 97	99.72 43	98.38 115	99.07 64	99.55 89	98.30 169	99.65 61	99.45 83	99.22 16	99.76 254	98.44 123	99.77 147	99.64 80
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0320		99.61 8	99.65 9	99.48 56	99.71 47	98.94 78	99.54 8	99.83 25	99.87 5	99.89 17	99.82 5	98.75 43	99.90 78	99.54 41	99.95 37	99.59 103

fmvsm_s_conf0.1_n		99.16 55	99.33 36	98.64 202	99.71 47	96.10 268	97.87 218	99.85 18	98.56 154	99.90 13	99.68 25	98.69 49	99.85 149	99.72 27	99.98 12	99.97 4

PS-CasMVS		99.40 26	99.33 36	99.62 9	99.71 47	99.10 65	99.29 36	99.53 96	99.53 39	99.46 93	99.41 91	98.23 89	99.95 26	98.89 93	99.95 37	99.81 37

DTE-MVSNet		99.43 23	99.35 33	99.66 7	99.71 47	99.30 22	99.31 30	99.51 100	99.64 27	99.56 69	99.46 79	98.23 89	99.97 7	98.78 99	99.93 53	99.72 58

WR-MVS_H		99.33 31	99.22 52	99.65 8	99.71 47	99.24 30	99.32 26	99.55 89	99.46 47	99.50 86	99.34 104	97.30 169	99.93 52	98.90 91	99.93 53	99.77 47

HPM-MVS_fast		99.01 79	98.82 99	99.57 21	99.71 47	99.35 17	99.00 72	99.50 103	97.33 258	98.94 190	98.86 228	98.75 43	99.82 195	97.53 183	99.71 179	99.56 122

ACMH+	96.62 9	99.08 73	99.00 81	99.33 85	99.71 47	98.83 83	98.60 114	99.58 71	99.11 92	99.53 78	99.18 144	98.81 37	99.67 300	96.71 246	99.77 147	99.50 151

PMVS	91.26 20	97.86 235	97.94 223	97.65 308	99.71 47	97.94 164	98.52 123	98.68 324	98.99 113	97.52 332	99.35 100	97.41 163	98.18 440	91.59 403	99.67 200	96.82 429
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
KinetiMVS		99.03 77	99.02 78	99.03 141	99.70 55	97.48 203	98.43 141	99.29 205	99.70 16	99.60 68	99.07 171	96.13 233	99.94 41	99.42 53	99.87 94	99.68 67

FIs		99.14 59	99.09 72	99.29 91	99.70 55	98.28 123	99.13 58	99.52 99	99.48 42	99.24 142	99.41 91	96.79 201	99.82 195	98.69 109	99.88 90	99.76 52

VPNet		98.87 98	98.83 98	99.01 145	99.70 55	97.62 196	98.43 141	99.35 170	99.47 45	99.28 131	99.05 179	96.72 207	99.82 195	98.09 143	99.36 280	99.59 103

fmvsm_s_conf0.1_n_2		99.20 49	99.38 28	98.65 200	99.69 58	96.08 273	97.49 274	99.90 11	99.53 39	99.88 20	99.64 37	98.51 66	99.90 78	99.83 9	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 186	98.68 119	97.27 338	99.69 58	92.29 387	98.03 189	99.85 18	97.62 224	99.96 4	99.62 40	93.98 303	99.74 266	99.52 47	99.86 100	99.79 41

MP-MVS-pluss		98.57 150	98.23 188	99.60 15	99.69 58	99.35 17	97.16 304	99.38 156	94.87 365	98.97 179	98.99 197	98.01 111	99.88 109	97.29 194	99.70 186	99.58 111
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 45	99.32 38	98.96 153	99.68 61	97.35 211	98.84 94	99.48 112	99.69 18	99.63 64	99.68 25	99.03 23	99.96 14	97.97 155	99.92 66	99.57 116

sd_testset		99.28 36	99.31 40	99.19 108	99.68 61	98.06 151	99.41 17	99.30 197	99.69 18	99.63 64	99.68 25	99.25 15	99.96 14	97.25 197	99.92 66	99.57 116

test_fmvs1_n		98.09 213	98.28 180	97.52 324	99.68 61	93.47 366	98.63 110	99.93 5	95.41 353	99.68 55	99.64 37	91.88 337	99.48 375	99.82 10	99.87 94	99.62 86

CHOSEN 1792x2688		97.49 264	97.14 279	98.54 226	99.68 61	96.09 271	96.50 337	99.62 64	91.58 413	98.84 208	98.97 203	92.36 329	99.88 109	96.76 239	99.95 37	99.67 72

tfpnnormal		98.90 95	98.90 90	98.91 162	99.67 65	97.82 179	99.00 72	99.44 133	99.45 48	99.51 85	99.24 130	98.20 95	99.86 136	95.92 298	99.69 189	99.04 290

MTAPA		98.88 97	98.64 125	99.61 13	99.67 65	99.36 16	98.43 141	99.20 229	98.83 132	98.89 197	98.90 218	96.98 190	99.92 62	97.16 201	99.70 186	99.56 122

test_fmvsmvis_n_1920		99.26 39	99.49 16	98.54 226	99.66 67	96.97 234	98.00 196	99.85 18	99.24 73	99.92 8	99.50 67	99.39 12	99.95 26	99.89 3	99.98 12	98.71 344

mvs5depth		99.30 33	99.59 12	98.44 240	99.65 68	95.35 300	99.82 3	99.94 2	99.83 7	99.42 102	99.94 2	98.13 103	99.96 14	99.63 33	99.96 27	100.00 1

fmvsm_l_conf0.5_n_a		99.19 50	99.27 46	98.94 156	99.65 68	97.05 230	97.80 227	99.76 38	98.70 137	99.78 38	99.11 163	98.79 41	99.95 26	99.85 5	99.96 27	99.83 31

WB-MVS		98.52 163	98.55 138	98.43 241	99.65 68	95.59 287	98.52 123	98.77 313	99.65 26	99.52 80	99.00 196	94.34 294	99.93 52	98.65 111	98.83 348	99.76 52

CP-MVSNet		99.21 47	99.09 72	99.56 26	99.65 68	98.96 77	99.13 58	99.34 176	99.42 53	99.33 121	99.26 123	97.01 188	99.94 41	98.74 104	99.93 53	99.79 41

HPM-MVS		98.79 110	98.53 141	99.59 19	99.65 68	99.29 24	99.16 54	99.43 139	96.74 302	98.61 240	98.38 308	98.62 56	99.87 128	96.47 269	99.67 200	99.59 103
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 145	98.36 169	99.42 64	99.65 68	99.42 11	98.55 119	99.57 78	97.72 218	98.90 195	99.26 123	96.12 235	99.52 363	95.72 309	99.71 179	99.32 234

NormalMVS		98.26 196	97.97 220	99.15 117	99.64 74	97.83 174	98.28 154	99.43 139	99.24 73	98.80 215	98.85 231	89.76 356	99.94 41	98.04 148	99.67 200	99.68 67

lecture		99.25 40	99.12 67	99.62 9	99.64 74	99.40 12	98.89 87	99.51 100	99.19 84	99.37 112	99.25 128	98.36 76	99.88 109	98.23 134	99.67 200	99.59 103

fmvsm_l_conf0.5_n		99.21 47	99.28 45	99.02 144	99.64 74	97.28 215	97.82 223	99.76 38	98.73 134	99.82 32	99.09 170	98.81 37	99.95 26	99.86 4	99.96 27	99.83 31

test_fmvsmconf_n		99.44 19	99.48 18	99.31 90	99.64 74	98.10 141	97.68 244	99.84 22	99.29 69	99.92 8	99.57 49	99.60 5	99.96 14	99.74 24	99.98 12	99.89 16

TSAR-MVS + MP.		98.63 142	98.49 149	99.06 137	99.64 74	97.90 168	98.51 128	98.94 278	96.96 289	99.24 142	98.89 224	97.83 125	99.81 210	96.88 229	99.49 263	99.48 167
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 106	98.72 110	99.12 120	99.64 74	98.54 106	97.98 202	99.68 54	97.62 224	99.34 119	99.18 144	97.54 151	99.77 248	97.79 166	99.74 163	99.04 290

Elysia		99.15 56	99.14 65	99.18 109	99.63 80	97.92 165	98.50 130	99.43 139	99.67 21	99.70 49	99.13 159	96.66 210	99.98 4	99.54 41	99.96 27	99.64 80

StellarMVS		99.15 56	99.14 65	99.18 109	99.63 80	97.92 165	98.50 130	99.43 139	99.67 21	99.70 49	99.13 159	96.66 210	99.98 4	99.54 41	99.96 27	99.64 80

KD-MVS_self_test		99.25 40	99.18 56	99.44 63	99.63 80	99.06 70	98.69 106	99.54 93	99.31 66	99.62 67	99.53 63	97.36 166	99.86 136	99.24 67	99.71 179	99.39 205

EU-MVSNet		97.66 252	98.50 145	95.13 404	99.63 80	85.84 435	98.35 150	98.21 347	98.23 176	99.54 74	99.46 79	95.02 274	99.68 297	98.24 132	99.87 94	99.87 21

HyFIR lowres test		97.19 290	96.60 314	98.96 153	99.62 84	97.28 215	95.17 401	99.50 103	94.21 380	99.01 172	98.32 316	86.61 376	99.99 2	97.10 208	99.84 105	99.60 96

fmvsm_l_conf0.5_n_3		99.45 18	99.48 18	99.34 79	99.59 85	98.21 132	97.82 223	99.84 22	99.41 55	99.92 8	99.41 91	99.51 8	99.95 26	99.84 8	99.97 20	99.87 21

mmtdpeth		99.30 33	99.42 24	98.92 161	99.58 86	96.89 241	99.48 13	99.92 7	99.92 2	98.26 277	99.80 11	98.33 82	99.91 71	99.56 38	99.95 37	99.97 4

ACMMP_NAP		98.75 117	98.48 150	99.57 21	99.58 86	99.29 24	97.82 223	99.25 218	96.94 291	98.78 217	99.12 162	98.02 110	99.84 167	97.13 206	99.67 200	99.59 103

nrg030		99.40 26	99.35 33	99.54 31	99.58 86	99.13 60	98.98 75	99.48 112	99.68 20	99.46 93	99.26 123	98.62 56	99.73 272	99.17 72	99.92 66	99.76 52

VDDNet		98.21 203	97.95 221	99.01 145	99.58 86	97.74 187	99.01 70	97.29 376	99.67 21	98.97 179	99.50 67	90.45 351	99.80 218	97.88 161	99.20 308	99.48 167

COLMAP_ROB	96.50 10	98.99 82	98.85 97	99.41 66	99.58 86	99.10 65	98.74 97	99.56 85	99.09 102	99.33 121	99.19 140	98.40 74	99.72 279	95.98 296	99.76 159	99.42 192
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_fmvsm_n_1920		99.33 31	99.45 23	98.99 147	99.57 91	97.73 189	97.93 207	99.83 25	99.22 76	99.93 6	99.30 112	99.42 11	99.96 14	99.85 5	99.99 5	99.29 243

ZNCC-MVS		98.68 133	98.40 162	99.54 31	99.57 91	99.21 33	98.46 138	99.29 205	97.28 264	98.11 289	98.39 306	98.00 112	99.87 128	96.86 232	99.64 210	99.55 129

MSP-MVS		98.40 174	98.00 215	99.61 13	99.57 91	99.25 29	98.57 117	99.35 170	97.55 235	99.31 129	97.71 356	94.61 287	99.88 109	96.14 290	99.19 311	99.70 64
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
testgi		98.32 187	98.39 165	98.13 271	99.57 91	95.54 290	97.78 229	99.49 110	97.37 255	99.19 147	97.65 360	98.96 28	99.49 372	96.50 268	98.99 336	99.34 227

MP-MVS		98.46 168	98.09 204	99.54 31	99.57 91	99.22 32	98.50 130	99.19 233	97.61 227	97.58 326	98.66 269	97.40 164	99.88 109	94.72 335	99.60 223	99.54 133
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 121	98.46 154	99.47 60	99.57 91	98.97 73	98.23 160	99.48 112	96.60 307	99.10 157	99.06 172	98.71 47	99.83 185	95.58 316	99.78 141	99.62 86

LGP-MVS_train				99.47 60	99.57 91	98.97 73		99.48 112	96.60 307	99.10 157	99.06 172	98.71 47	99.83 185	95.58 316	99.78 141	99.62 86

IS-MVSNet		98.19 205	97.90 228	99.08 129	99.57 91	97.97 159	99.31 30	98.32 343	99.01 112	98.98 175	99.03 183	91.59 339	99.79 231	95.49 318	99.80 131	99.48 167

dcpmvs_2		98.78 112	99.11 68	97.78 293	99.56 99	93.67 361	99.06 65	99.86 16	99.50 41	99.66 58	99.26 123	97.21 177	99.99 2	98.00 153	99.91 75	99.68 67

test_0402		98.76 116	98.71 113	98.93 158	99.56 99	98.14 137	98.45 140	99.34 176	99.28 70	98.95 183	98.91 215	98.34 81	99.79 231	95.63 313	99.91 75	98.86 322

EPP-MVSNet		98.30 190	98.04 211	99.07 131	99.56 99	97.83 174	99.29 36	98.07 354	99.03 110	98.59 244	99.13 159	92.16 333	99.90 78	96.87 230	99.68 194	99.49 156

ACMMP		98.75 117	98.50 145	99.52 44	99.56 99	99.16 48	98.87 88	99.37 160	97.16 279	98.82 212	99.01 193	97.71 135	99.87 128	96.29 281	99.69 189	99.54 133
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
fmvsm_s_conf0.5_n_a		99.10 68	99.20 55	98.78 181	99.55 103	96.59 254	97.79 228	99.82 29	98.21 178	99.81 35	99.53 63	98.46 70	99.84 167	99.70 30	99.97 20	99.90 15

fmvsm_s_conf0.5_n		99.09 69	99.26 48	98.61 211	99.55 103	96.09 271	97.74 238	99.81 30	98.55 155	99.85 26	99.55 57	98.60 58	99.84 167	99.69 32	99.98 12	99.89 16

FMVSNet1		99.17 51	99.17 57	99.17 111	99.55 103	98.24 126	99.20 48	99.44 133	99.21 78	99.43 98	99.55 57	97.82 128	99.86 136	98.42 125	99.89 88	99.41 195

Vis-MVSNet (Re-imp)		97.46 266	97.16 276	98.34 253	99.55 103	96.10 268	98.94 80	98.44 337	98.32 167	98.16 283	98.62 278	88.76 363	99.73 272	93.88 361	99.79 136	99.18 269

ACMM	96.08 12	98.91 93	98.73 108	99.48 56	99.55 103	99.14 57	98.07 183	99.37 160	97.62 224	99.04 168	98.96 206	98.84 35	99.79 231	97.43 188	99.65 208	99.49 156
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 125	98.97 85	97.89 286	99.54 108	94.05 341	98.55 119	99.92 7	96.78 300	99.72 45	99.78 13	96.60 214	99.67 300	99.91 2	99.90 82	99.94 10

mPP-MVS		98.64 140	98.34 172	99.54 31	99.54 108	99.17 44	98.63 110	99.24 223	97.47 242	98.09 291	98.68 264	97.62 144	99.89 93	96.22 284	99.62 216	99.57 116

XVG-ACMP-BASELINE		98.56 151	98.34 172	99.22 105	99.54 108	98.59 100	97.71 241	99.46 124	97.25 267	98.98 175	98.99 197	97.54 151	99.84 167	95.88 299	99.74 163	99.23 255

region2R		98.69 128	98.40 162	99.54 31	99.53 111	99.17 44	98.52 123	99.31 189	97.46 247	98.44 262	98.51 292	97.83 125	99.88 109	96.46 270	99.58 232	99.58 111

PGM-MVS		98.66 137	98.37 168	99.55 28	99.53 111	99.18 43	98.23 160	99.49 110	97.01 288	98.69 228	98.88 225	98.00 112	99.89 93	95.87 302	99.59 227	99.58 111

Patchmatch-RL test		97.26 283	97.02 284	97.99 283	99.52 113	95.53 291	96.13 362	99.71 45	97.47 242	99.27 133	99.16 150	84.30 397	99.62 325	97.89 158	99.77 147	98.81 330

ACMMPR		98.70 125	98.42 160	99.54 31	99.52 113	99.14 57	98.52 123	99.31 189	97.47 242	98.56 249	98.54 287	97.75 133	99.88 109	96.57 257	99.59 227	99.58 111

fmvsm_s_conf0.5_n_9		99.17 51	99.38 28	98.53 228	99.51 115	95.82 283	97.62 255	99.78 35	99.72 15	99.90 13	99.48 74	98.66 51	99.89 93	99.85 5	99.93 53	99.89 16

AstraMVS		98.16 210	98.07 209	98.41 243	99.51 115	95.86 280	98.00 196	95.14 417	98.97 116	99.43 98	99.24 130	93.25 311	99.84 167	99.21 68	99.87 94	99.54 133

fmvsm_s_conf0.5_n_8		99.13 63	99.26 48	98.74 192	99.51 115	96.44 260	97.65 250	99.65 59	99.66 24	99.78 38	99.48 74	97.92 119	99.93 52	99.72 27	99.95 37	99.87 21

GST-MVS		98.61 146	98.30 178	99.52 44	99.51 115	99.20 39	98.26 158	99.25 218	97.44 250	98.67 231	98.39 306	97.68 136	99.85 149	96.00 294	99.51 254	99.52 145

Anonymous20231206		98.21 203	98.21 189	98.20 265	99.51 115	95.43 298	98.13 172	99.32 184	96.16 325	98.93 191	98.82 239	96.00 240	99.83 185	97.32 193	99.73 166	99.36 221

ACMP	95.32 15	98.41 172	98.09 204	99.36 70	99.51 115	98.79 86	97.68 244	99.38 156	95.76 340	98.81 214	98.82 239	98.36 76	99.82 195	94.75 332	99.77 147	99.48 167
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LuminaMVS		98.39 180	98.20 190	98.98 151	99.50 121	97.49 201	97.78 229	97.69 363	98.75 133	99.49 87	99.25 128	92.30 331	99.94 41	99.14 73	99.88 90	99.50 151

DVP-MVS		98.77 115	98.52 142	99.52 44	99.50 121	99.21 33	98.02 192	98.84 302	97.97 197	99.08 159	99.02 184	97.61 145	99.88 109	96.99 216	99.63 213	99.48 167
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				99.60 15	99.50 121	99.23 31	98.02 192	99.32 184					99.88 109	96.99 216	99.63 213	99.68 67

test0726					99.50 121	99.21 33	98.17 168	99.35 170	97.97 197	99.26 137	99.06 172	97.61 145

AllTest		98.44 170	98.20 190	99.16 114	99.50 121	98.55 103	98.25 159	99.58 71	96.80 298	98.88 201	99.06 172	97.65 139	99.57 345	94.45 342	99.61 221	99.37 214

TestCases				99.16 114	99.50 121	98.55 103		99.58 71	96.80 298	98.88 201	99.06 172	97.65 139	99.57 345	94.45 342	99.61 221	99.37 214

XVG-OURS		98.53 159	98.34 172	99.11 122	99.50 121	98.82 85	95.97 368	99.50 103	97.30 262	99.05 166	98.98 201	99.35 13	99.32 402	95.72 309	99.68 194	99.18 269

EG-PatchMatch MVS		98.99 82	99.01 80	98.94 156	99.50 121	97.47 204	98.04 188	99.59 69	98.15 190	99.40 107	99.36 99	98.58 62	99.76 254	98.78 99	99.68 194	99.59 103

fmvsm_s_conf0.5_n_2		99.14 59	99.31 40	98.63 206	99.49 129	96.08 273	97.38 282	99.81 30	99.48 42	99.84 29	99.57 49	98.46 70	99.89 93	99.82 10	99.97 20	99.91 13

SED-MVS		98.91 93	98.72 110	99.49 54	99.49 129	99.17 44	98.10 178	99.31 189	98.03 193	99.66 58	99.02 184	98.36 76	99.88 109	96.91 222	99.62 216	99.41 195

IU-MVS					99.49 129	99.15 52		98.87 293	92.97 398	99.41 104				96.76 239	99.62 216	99.66 74

test_241102_ONE					99.49 129	99.17 44		99.31 189	97.98 196	99.66 58	98.90 218	98.36 76	99.48 375

UA-Net		99.47 16	99.40 26	99.70 2	99.49 129	99.29 24	99.80 4	99.72 43	99.82 8	99.04 168	99.81 8	98.05 109	99.96 14	98.85 95	99.99 5	99.86 27

HFP-MVS		98.71 121	98.44 157	99.51 48	99.49 129	99.16 48	98.52 123	99.31 189	97.47 242	98.58 246	98.50 296	97.97 116	99.85 149	96.57 257	99.59 227	99.53 142

VPA-MVSNet		99.30 33	99.30 43	99.28 92	99.49 129	98.36 120	99.00 72	99.45 128	99.63 29	99.52 80	99.44 84	98.25 87	99.88 109	99.09 77	99.84 105	99.62 86

XVG-OURS-SEG-HR		98.49 165	98.28 180	99.14 118	99.49 129	98.83 83	96.54 333	99.48 112	97.32 260	99.11 154	98.61 280	99.33 14	99.30 405	96.23 283	98.38 372	99.28 245

114514_t		96.50 323	95.77 332	98.69 196	99.48 137	97.43 208	97.84 222	99.55 89	81.42 445	96.51 385	98.58 284	95.53 260	99.67 300	93.41 374	99.58 232	98.98 300

IterMVS-LS		98.55 155	98.70 116	98.09 272	99.48 137	94.73 321	97.22 299	99.39 154	98.97 116	99.38 110	99.31 111	96.00 240	99.93 52	98.58 114	99.97 20	99.60 96
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
fmvsm_s_conf0.5_n_5		99.07 75	99.10 70	98.99 147	99.47 139	97.22 220	97.40 280	99.83 25	97.61 227	99.85 26	99.30 112	98.80 39	99.95 26	99.71 29	99.90 82	99.78 44

v8		99.01 79	99.16 59	98.57 218	99.47 139	96.31 265	98.90 83	99.47 120	99.03 110	99.52 80	99.57 49	96.93 191	99.81 210	99.60 34	99.98 12	99.60 96

SSC-MVS3.2		98.53 159	98.79 102	97.74 300	99.46 141	93.62 364	96.45 339	99.34 176	99.33 63	98.93 191	98.70 260	97.90 120	99.90 78	99.12 74	99.92 66	99.69 66

fmvsm_s_conf0.5_n_3		99.22 46	99.37 31	98.78 181	99.46 141	96.58 256	97.65 250	99.72 43	99.47 45	99.86 23	99.50 67	98.94 29	99.89 93	99.75 23	99.97 20	99.86 27

XVS		98.72 120	98.45 155	99.53 38	99.46 141	99.21 33	98.65 108	99.34 176	98.62 144	97.54 330	98.63 276	97.50 157	99.83 185	96.79 235	99.53 249	99.56 122

X-MVStestdata		94.32 372	92.59 391	99.53 38	99.46 141	99.21 33	98.65 108	99.34 176	98.62 144	97.54 330	45.85 450	97.50 157	99.83 185	96.79 235	99.53 249	99.56 122

test20.03		98.78 112	98.77 105	98.78 181	99.46 141	97.20 223	97.78 229	99.24 223	99.04 109	99.41 104	98.90 218	97.65 139	99.76 254	97.70 173	99.79 136	99.39 205

guyue		98.01 220	97.93 225	98.26 260	99.45 146	95.48 294	98.08 180	96.24 400	98.89 125	99.34 119	99.14 157	91.32 343	99.82 195	99.07 78	99.83 112	99.48 167

CSCG		98.68 133	98.50 145	99.20 106	99.45 146	98.63 95	98.56 118	99.57 78	97.87 207	98.85 206	98.04 337	97.66 138	99.84 167	96.72 244	99.81 120	99.13 279

GeoE		99.05 76	98.99 83	99.25 100	99.44 148	98.35 121	98.73 101	99.56 85	98.42 161	98.91 194	98.81 241	98.94 29	99.91 71	98.35 127	99.73 166	99.49 156

v148		98.45 169	98.60 133	98.00 282	99.44 148	94.98 313	97.44 279	99.06 259	98.30 169	99.32 127	98.97 203	96.65 212	99.62 325	98.37 126	99.85 101	99.39 205

v10		98.97 86	99.11 68	98.55 223	99.44 148	96.21 267	98.90 83	99.55 89	98.73 134	99.48 88	99.60 45	96.63 213	99.83 185	99.70 30	99.99 5	99.61 94

V42		98.78 112	98.78 104	98.76 186	99.44 148	97.04 231	98.27 157	99.19 233	97.87 207	99.25 141	99.16 150	96.84 195	99.78 242	99.21 68	99.84 105	99.46 177

MDA-MVSNet-bldmvs		97.94 226	97.91 227	98.06 277	99.44 148	94.96 314	96.63 331	99.15 249	98.35 163	98.83 209	99.11 163	94.31 295	99.85 149	96.60 254	98.72 354	99.37 214

casdiffmvs_mvg		99.12 66	99.16 59	98.99 147	99.43 153	97.73 189	98.00 196	99.62 64	99.22 76	99.55 72	99.22 136	98.93 31	99.75 261	98.66 110	99.81 120	99.50 151
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test1111		96.49 324	96.82 298	95.52 397	99.42 154	87.08 432	99.22 45	87.14 448	99.11 92	99.46 93	99.58 47	88.69 364	99.86 136	98.80 97	99.95 37	99.62 86

v2v482		98.56 151	98.62 128	98.37 250	99.42 154	95.81 284	97.58 263	99.16 244	97.90 205	99.28 131	99.01 193	95.98 245	99.79 231	99.33 57	99.90 82	99.51 148

OPM-MVS		98.56 151	98.32 176	99.25 100	99.41 156	98.73 91	97.13 306	99.18 237	97.10 282	98.75 223	98.92 214	98.18 96	99.65 316	96.68 248	99.56 239	99.37 214
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 215	98.08 207	98.04 280	99.41 156	94.59 327	94.59 419	99.40 152	97.50 239	98.82 212	98.83 236	96.83 197	99.84 167	97.50 185	99.81 120	99.71 59

test_one_0601					99.39 158	99.20 39		99.31 189	98.49 157	98.66 233	99.02 184	97.64 142

mvsany_test3		98.87 98	98.92 88	98.74 192	99.38 159	96.94 238	98.58 116	99.10 254	96.49 312	99.96 4	99.81 8	98.18 96	99.45 383	98.97 87	99.79 136	99.83 31

patch_mono-2		98.51 164	98.63 126	98.17 268	99.38 159	94.78 318	97.36 285	99.69 49	98.16 188	98.49 258	99.29 115	97.06 183	99.97 7	98.29 131	99.91 75	99.76 52

test2506		92.39 403	91.89 405	93.89 418	99.38 159	82.28 449	99.32 26	66.03 456	99.08 104	98.77 220	99.57 49	66.26 444	99.84 167	98.71 107	99.95 37	99.54 133

ECVR-MVS		96.42 326	96.61 312	95.85 389	99.38 159	88.18 427	99.22 45	86.00 450	99.08 104	99.36 115	99.57 49	88.47 369	99.82 195	98.52 120	99.95 37	99.54 133

casdiffmvs		98.95 89	99.00 81	98.81 173	99.38 159	97.33 212	97.82 223	99.57 78	99.17 88	99.35 117	99.17 148	98.35 80	99.69 288	98.46 122	99.73 166	99.41 195
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		98.96 88	99.02 78	98.76 186	99.38 159	97.26 217	98.49 133	99.50 103	98.86 128	99.19 147	99.06 172	98.23 89	99.69 288	98.71 107	99.76 159	99.33 232

TranMVSNet+NR-MVSNet		99.17 51	99.07 75	99.46 62	99.37 165	98.87 81	98.39 146	99.42 145	99.42 53	99.36 115	99.06 172	98.38 75	99.95 26	98.34 128	99.90 82	99.57 116

fmvsm_s_conf0.5_n_6		99.08 73	99.21 54	98.69 196	99.36 166	96.51 258	97.62 255	99.68 54	98.43 160	99.85 26	99.10 166	99.12 22	99.88 109	99.77 20	99.92 66	99.67 72

tttt0517		95.64 351	94.98 361	97.64 310	99.36 166	93.81 356	98.72 102	90.47 442	98.08 192	98.67 231	98.34 313	73.88 430	99.92 62	97.77 168	99.51 254	99.20 261

test_part2					99.36 166	99.10 65				99.05 166

v1144		98.60 147	98.66 122	98.41 243	99.36 166	95.90 278	97.58 263	99.34 176	97.51 238	99.27 133	99.15 154	96.34 227	99.80 218	99.47 51	99.93 53	99.51 148

CP-MVS		98.70 125	98.42 160	99.52 44	99.36 166	99.12 62	98.72 102	99.36 164	97.54 236	98.30 271	98.40 305	97.86 124	99.89 93	96.53 266	99.72 174	99.56 122

Test_1112_low_res		96.99 305	96.55 316	98.31 256	99.35 171	95.47 296	95.84 380	99.53 96	91.51 415	96.80 372	98.48 299	91.36 342	99.83 185	96.58 255	99.53 249	99.62 86

DeepC-MVS	97.60 4	98.97 86	98.93 87	99.10 124	99.35 171	97.98 158	98.01 195	99.46 124	97.56 233	99.54 74	99.50 67	98.97 27	99.84 167	98.06 146	99.92 66	99.49 156
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 282	96.86 294	98.58 215	99.34 173	96.32 264	96.75 325	99.58 71	93.14 396	96.89 367	97.48 370	92.11 334	99.86 136	96.91 222	99.54 245	99.57 116

reproduce_model		99.15 56	98.97 85	99.67 4	99.33 174	99.44 10	98.15 170	99.47 120	99.12 91	99.52 80	99.32 110	98.31 83	99.90 78	97.78 167	99.73 166	99.66 74

MVSMamba_PlusPlus		98.83 103	98.98 84	98.36 251	99.32 175	96.58 256	98.90 83	99.41 149	99.75 11	98.72 226	99.50 67	96.17 231	99.94 41	99.27 62	99.78 141	98.57 360

fmvsm_s_conf0.5_n_4		99.01 79	99.22 52	98.38 247	99.31 176	95.48 294	97.56 265	99.73 42	98.87 126	99.75 43	99.27 118	98.80 39	99.86 136	99.80 15	99.90 82	99.81 37

SF-MVS		98.53 159	98.27 183	99.32 87	99.31 176	98.75 87	98.19 164	99.41 149	96.77 301	98.83 209	98.90 218	97.80 130	99.82 195	95.68 312	99.52 252	99.38 212

CPTT-MVS		97.84 241	97.36 265	99.27 95	99.31 176	98.46 111	98.29 153	99.27 212	94.90 364	97.83 310	98.37 309	94.90 276	99.84 167	93.85 363	99.54 245	99.51 148

UnsupCasMVSNet_eth		97.89 230	97.60 251	98.75 188	99.31 176	97.17 226	97.62 255	99.35 170	98.72 136	98.76 222	98.68 264	92.57 328	99.74 266	97.76 172	95.60 434	99.34 227

fmvsm_s_conf0.5_n_7		98.83 103	99.04 77	98.20 265	99.30 180	94.83 316	97.23 295	99.36 164	98.64 139	99.84 29	99.43 86	98.10 105	99.91 71	99.56 38	99.96 27	99.87 21

pmmvs-eth3d		98.47 167	98.34 172	98.86 167	99.30 180	97.76 185	97.16 304	99.28 209	95.54 346	99.42 102	99.19 140	97.27 172	99.63 322	97.89 158	99.97 20	99.20 261

mamv4		99.44 19	99.39 27	99.58 20	99.30 180	99.74 2	99.04 68	99.81 30	99.77 10	99.82 32	99.57 49	97.82 128	99.98 4	99.53 45	99.89 88	99.01 294

SymmetryMVS		98.05 216	97.71 241	99.09 128	99.29 183	97.83 174	98.28 154	97.64 368	99.24 73	98.80 215	98.85 231	89.76 356	99.94 41	98.04 148	99.50 261	99.49 156

Anonymous20231211		99.27 37	99.27 46	99.26 97	99.29 183	98.18 133	99.49 12	99.51 100	99.70 16	99.80 36	99.68 25	96.84 195	99.83 185	99.21 68	99.91 75	99.77 47

UnsupCasMVSNet_bld		97.30 280	96.92 290	98.45 238	99.28 185	96.78 248	96.20 356	99.27 212	95.42 350	98.28 275	98.30 317	93.16 314	99.71 280	94.99 326	97.37 410	98.87 321

EC-MVSNet		99.09 69	99.05 76	99.20 106	99.28 185	98.93 79	99.24 44	99.84 22	99.08 104	98.12 288	98.37 309	98.72 46	99.90 78	99.05 81	99.77 147	98.77 338

reproduce-ours		99.09 69	98.90 90	99.67 4	99.27 187	99.49 6	98.00 196	99.42 145	99.05 107	99.48 88	99.27 118	98.29 85	99.89 93	97.61 177	99.71 179	99.62 86

our_new_method		99.09 69	98.90 90	99.67 4	99.27 187	99.49 6	98.00 196	99.42 145	99.05 107	99.48 88	99.27 118	98.29 85	99.89 93	97.61 177	99.71 179	99.62 86

DPE-MVS		98.59 149	98.26 184	99.57 21	99.27 187	99.15 52	97.01 309	99.39 154	97.67 220	99.44 97	98.99 197	97.53 153	99.89 93	95.40 320	99.68 194	99.66 74
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 240	98.18 194	96.87 358	99.27 187	91.16 407	95.53 389	99.25 218	99.10 99	99.41 104	99.35 100	93.10 316	99.96 14	98.65 111	99.94 48	99.49 156

v1192		98.60 147	98.66 122	98.41 243	99.27 187	95.88 279	97.52 270	99.36 164	97.41 251	99.33 121	99.20 139	96.37 225	99.82 195	99.57 36	99.92 66	99.55 129

N_pmnet		97.63 254	97.17 275	98.99 147	99.27 187	97.86 171	95.98 367	93.41 431	95.25 355	99.47 92	98.90 218	95.63 257	99.85 149	96.91 222	99.73 166	99.27 246

FPMVS		93.44 389	92.23 396	97.08 346	99.25 193	97.86 171	95.61 386	97.16 380	92.90 400	93.76 433	98.65 271	75.94 428	95.66 447	79.30 445	97.49 403	97.73 411

new-patchmatchnet		98.35 181	98.74 106	97.18 341	99.24 194	92.23 389	96.42 343	99.48 112	98.30 169	99.69 53	99.53 63	97.44 162	99.82 195	98.84 96	99.77 147	99.49 156

MCST-MVS		98.00 221	97.63 249	99.10 124	99.24 194	98.17 134	96.89 318	98.73 321	95.66 341	97.92 301	97.70 358	97.17 178	99.66 311	96.18 288	99.23 303	99.47 175

UniMVSNet (Re)		98.87 98	98.71 113	99.35 76	99.24 194	98.73 91	97.73 240	99.38 156	98.93 121	99.12 153	98.73 253	96.77 202	99.86 136	98.63 113	99.80 131	99.46 177

jason		97.45 268	97.35 266	97.76 297	99.24 194	93.93 350	95.86 377	98.42 339	94.24 379	98.50 257	98.13 327	94.82 280	99.91 71	97.22 198	99.73 166	99.43 189
jason: jason.
IterMVS		97.73 246	98.11 203	96.57 368	99.24 194	90.28 416	95.52 391	99.21 227	98.86 128	99.33 121	99.33 106	93.11 315	99.94 41	98.49 121	99.94 48	99.48 167
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 155	98.62 128	98.32 254	99.22 199	95.58 289	97.51 272	99.45 128	97.16 279	99.45 96	99.24 130	96.12 235	99.85 149	99.60 34	99.88 90	99.55 129

ITE_SJBPF				98.87 166	99.22 199	98.48 110		99.35 170	97.50 239	98.28 275	98.60 282	97.64 142	99.35 398	93.86 362	99.27 295	98.79 336

h-mvs33		97.77 244	97.33 268	99.10 124	99.21 201	97.84 173	98.35 150	98.57 331	99.11 92	98.58 246	99.02 184	88.65 367	99.96 14	98.11 141	96.34 426	99.49 156

v144192		98.54 157	98.57 136	98.45 238	99.21 201	95.98 276	97.63 254	99.36 164	97.15 281	99.32 127	99.18 144	95.84 252	99.84 167	99.50 48	99.91 75	99.54 133

APDe-MVS		98.99 82	98.79 102	99.60 15	99.21 201	99.15 52	98.87 88	99.48 112	97.57 231	99.35 117	99.24 130	97.83 125	99.89 93	97.88 161	99.70 186	99.75 56
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 91	98.81 101	99.28 92	99.21 201	98.45 112	98.46 138	99.33 182	99.63 29	99.48 88	99.15 154	97.23 175	99.75 261	97.17 200	99.66 207	99.63 85

SR-MVS-dyc-post		98.81 108	98.55 138	99.57 21	99.20 205	99.38 13	98.48 136	99.30 197	98.64 139	98.95 183	98.96 206	97.49 160	99.86 136	96.56 261	99.39 276	99.45 181

RE-MVS-def			98.58 135		99.20 205	99.38 13	98.48 136	99.30 197	98.64 139	98.95 183	98.96 206	97.75 133		96.56 261	99.39 276	99.45 181

v1921920		98.54 157	98.60 133	98.38 247	99.20 205	95.76 286	97.56 265	99.36 164	97.23 273	99.38 110	99.17 148	96.02 238	99.84 167	99.57 36	99.90 82	99.54 133

thisisatest0530		95.27 358	94.45 369	97.74 300	99.19 208	94.37 331	97.86 219	90.20 443	97.17 278	98.22 278	97.65 360	73.53 431	99.90 78	96.90 227	99.35 282	98.95 306

Anonymous20240529		98.93 91	98.87 93	99.12 120	99.19 208	98.22 131	99.01 70	98.99 276	99.25 72	99.54 74	99.37 95	97.04 184	99.80 218	97.89 158	99.52 252	99.35 225

APD-MVS_3200maxsize		98.84 102	98.61 132	99.53 38	99.19 208	99.27 27	98.49 133	99.33 182	98.64 139	99.03 171	98.98 201	97.89 122	99.85 149	96.54 265	99.42 273	99.46 177

HQP_MVS		97.99 224	97.67 243	98.93 158	99.19 208	97.65 193	97.77 232	99.27 212	98.20 182	97.79 313	97.98 341	94.90 276	99.70 284	94.42 344	99.51 254	99.45 181

plane_prior7					99.19 208	97.87 170

ab-mvs		98.41 172	98.36 169	98.59 214	99.19 208	97.23 218	99.32 26	98.81 307	97.66 221	98.62 238	99.40 94	96.82 198	99.80 218	95.88 299	99.51 254	98.75 341

F-COLMAP		97.30 280	96.68 307	99.14 118	99.19 208	98.39 114	97.27 294	99.30 197	92.93 399	96.62 378	98.00 339	95.73 255	99.68 297	92.62 390	98.46 371	99.35 225

SR-MVS		98.71 121	98.43 158	99.57 21	99.18 215	99.35 17	98.36 149	99.29 205	98.29 172	98.88 201	98.85 231	97.53 153	99.87 128	96.14 290	99.31 288	99.48 167

UniMVSNet_NR-MVSNet		98.86 101	98.68 119	99.40 68	99.17 216	98.74 88	97.68 244	99.40 152	99.14 90	99.06 161	98.59 283	96.71 208	99.93 52	98.57 116	99.77 147	99.53 142

LF4IMVS		97.90 228	97.69 242	98.52 229	99.17 216	97.66 192	97.19 303	99.47 120	96.31 320	97.85 309	98.20 324	96.71 208	99.52 363	94.62 336	99.72 174	98.38 377

SMA-MVS		98.40 174	98.03 212	99.51 48	99.16 218	99.21 33	98.05 186	99.22 226	94.16 381	98.98 175	99.10 166	97.52 155	99.79 231	96.45 271	99.64 210	99.53 142
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
DU-MVS		98.82 106	98.63 126	99.39 69	99.16 218	98.74 88	97.54 268	99.25 218	98.84 131	99.06 161	98.76 250	96.76 204	99.93 52	98.57 116	99.77 147	99.50 151

NR-MVSNet		98.95 89	98.82 99	99.36 70	99.16 218	98.72 93	99.22 45	99.20 229	99.10 99	99.72 45	98.76 250	96.38 224	99.86 136	98.00 153	99.82 116	99.50 151

MVS_111021_LR		98.30 190	98.12 202	98.83 170	99.16 218	98.03 153	96.09 364	99.30 197	97.58 230	98.10 290	98.24 320	98.25 87	99.34 399	96.69 247	99.65 208	99.12 280

DSMNet-mixed		97.42 271	97.60 251	96.87 358	99.15 222	91.46 396	98.54 121	99.12 251	92.87 401	97.58 326	99.63 39	96.21 230	99.90 78	95.74 308	99.54 245	99.27 246

D2MVS		97.84 241	97.84 232	97.83 289	99.14 223	94.74 320	96.94 313	98.88 291	95.84 338	98.89 197	98.96 206	94.40 292	99.69 288	97.55 180	99.95 37	99.05 286

pmmvs5		97.64 253	97.49 257	98.08 275	99.14 223	95.12 310	96.70 328	99.05 262	93.77 388	98.62 238	98.83 236	93.23 312	99.75 261	98.33 130	99.76 159	99.36 221

SPE-MVS-test		99.13 63	99.09 72	99.26 97	99.13 225	98.97 73	99.31 30	99.88 14	99.44 50	98.16 283	98.51 292	98.64 53	99.93 52	98.91 90	99.85 101	98.88 320

VDD-MVS		98.56 151	98.39 165	99.07 131	99.13 225	98.07 148	98.59 115	97.01 383	99.59 35	99.11 154	99.27 118	94.82 280	99.79 231	98.34 128	99.63 213	99.34 227

save fliter					99.11 227	97.97 159	96.53 335	99.02 270	98.24 175

APD-MVS		98.10 211	97.67 243	99.42 64	99.11 227	98.93 79	97.76 235	99.28 209	94.97 362	98.72 226	98.77 248	97.04 184	99.85 149	93.79 364	99.54 245	99.49 156
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 128	98.71 113	98.62 208	99.10 229	96.37 262	97.23 295	98.87 293	99.20 80	99.19 147	98.99 197	97.30 169	99.85 149	98.77 102	99.79 136	99.65 79

EI-MVSNet		98.40 174	98.51 143	98.04 280	99.10 229	94.73 321	97.20 300	98.87 293	98.97 116	99.06 161	99.02 184	96.00 240	99.80 218	98.58 114	99.82 116	99.60 96

CVMVSNet		96.25 332	97.21 274	93.38 425	99.10 229	80.56 453	97.20 300	98.19 350	96.94 291	99.00 173	99.02 184	89.50 360	99.80 218	96.36 277	99.59 227	99.78 44

EI-MVSNet-Vis-set		98.68 133	98.70 116	98.63 206	99.09 232	96.40 261	97.23 295	98.86 298	99.20 80	99.18 151	98.97 203	97.29 171	99.85 149	98.72 106	99.78 141	99.64 80

HPM-MVS++		98.10 211	97.64 248	99.48 56	99.09 232	99.13 60	97.52 270	98.75 318	97.46 247	96.90 366	97.83 351	96.01 239	99.84 167	95.82 306	99.35 282	99.46 177

DP-MVS Recon		97.33 278	96.92 290	98.57 218	99.09 232	97.99 155	96.79 321	99.35 170	93.18 395	97.71 317	98.07 335	95.00 275	99.31 403	93.97 357	99.13 319	98.42 374

MVS_111021_HR		98.25 199	98.08 207	98.75 188	99.09 232	97.46 205	95.97 368	99.27 212	97.60 229	97.99 299	98.25 319	98.15 102	99.38 394	96.87 230	99.57 236	99.42 192

BP-MVS1		97.40 273	96.97 286	98.71 195	99.07 236	96.81 244	98.34 152	97.18 378	98.58 150	98.17 280	98.61 280	84.01 399	99.94 41	98.97 87	99.78 141	99.37 214

9.14			97.78 234		99.07 236		97.53 269	99.32 184	95.53 347	98.54 253	98.70 260	97.58 147	99.76 254	94.32 349	99.46 266

PAPM_NR		96.82 312	96.32 323	98.30 257	99.07 236	96.69 252	97.48 275	98.76 315	95.81 339	96.61 379	96.47 396	94.12 301	99.17 416	90.82 417	97.78 397	99.06 285

TAMVS		98.24 200	98.05 210	98.80 175	99.07 236	97.18 225	97.88 215	98.81 307	96.66 306	99.17 152	99.21 137	94.81 282	99.77 248	96.96 220	99.88 90	99.44 185

CLD-MVS		97.49 264	97.16 276	98.48 235	99.07 236	97.03 232	94.71 412	99.21 227	94.46 373	98.06 293	97.16 382	97.57 148	99.48 375	94.46 341	99.78 141	98.95 306
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CS-MVS		99.13 63	99.10 70	99.24 102	99.06 241	99.15 52	99.36 22	99.88 14	99.36 61	98.21 279	98.46 300	98.68 50	99.93 52	99.03 83	99.85 101	98.64 353

thres100view900		94.19 375	93.67 380	95.75 392	99.06 241	91.35 400	98.03 189	94.24 426	98.33 165	97.40 342	94.98 426	79.84 415	99.62 325	83.05 438	98.08 388	96.29 433

thres600view7		94.45 370	93.83 377	96.29 376	99.06 241	91.53 395	97.99 201	94.24 426	98.34 164	97.44 340	95.01 424	79.84 415	99.67 300	84.33 436	98.23 377	97.66 414

plane_prior1					99.05 244

YYNet1		97.60 255	97.67 243	97.39 334	99.04 245	93.04 373	95.27 398	98.38 342	97.25 267	98.92 193	98.95 210	95.48 264	99.73 272	96.99 216	98.74 352	99.41 195

MDA-MVSNet_test_wron		97.60 255	97.66 246	97.41 333	99.04 245	93.09 369	95.27 398	98.42 339	97.26 266	98.88 201	98.95 210	95.43 265	99.73 272	97.02 213	98.72 354	99.41 195

MIMVSNet		96.62 319	96.25 327	97.71 304	99.04 245	94.66 324	99.16 54	96.92 389	97.23 273	97.87 306	99.10 166	86.11 382	99.65 316	91.65 401	99.21 307	98.82 325

icg_test_0403		98.34 182	98.56 137	97.66 307	99.03 248	94.03 344	97.98 202	99.45 128	98.16 188	98.89 197	98.71 256	97.90 120	99.74 266	97.50 185	99.45 268	99.22 259

PatchMatch-RL		97.24 286	96.78 301	98.61 211	99.03 248	97.83 174	96.36 346	99.06 259	93.49 393	97.36 346	97.78 352	95.75 254	99.49 372	93.44 373	98.77 351	98.52 362

GDP-MVS		97.50 261	97.11 280	98.67 199	99.02 250	96.85 242	98.16 169	99.71 45	98.32 167	98.52 256	98.54 287	83.39 403	99.95 26	98.79 98	99.56 239	99.19 266

ZD-MVS					99.01 251	98.84 82		99.07 258	94.10 383	98.05 295	98.12 329	96.36 226	99.86 136	92.70 389	99.19 311

CDPH-MVS		97.26 283	96.66 310	99.07 131	99.00 252	98.15 135	96.03 366	99.01 273	91.21 419	97.79 313	97.85 350	96.89 193	99.69 288	92.75 387	99.38 279	99.39 205

diffmvs		98.22 201	98.24 187	98.17 268	99.00 252	95.44 297	96.38 345	99.58 71	97.79 214	98.53 254	98.50 296	96.76 204	99.74 266	97.95 157	99.64 210	99.34 227
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WR-MVS		98.40 174	98.19 193	99.03 141	99.00 252	97.65 193	96.85 319	98.94 278	98.57 151	98.89 197	98.50 296	95.60 258	99.85 149	97.54 182	99.85 101	99.59 103

plane_prior6					98.99 255	97.70 191						94.90 276

xiu_mvs_v1_base_debu		97.86 235	98.17 195	96.92 355	98.98 256	93.91 351	96.45 339	99.17 241	97.85 209	98.41 265	97.14 384	98.47 67	99.92 62	98.02 150	99.05 325	96.92 426

xiu_mvs_v1_base		97.86 235	98.17 195	96.92 355	98.98 256	93.91 351	96.45 339	99.17 241	97.85 209	98.41 265	97.14 384	98.47 67	99.92 62	98.02 150	99.05 325	96.92 426

xiu_mvs_v1_base_debi		97.86 235	98.17 195	96.92 355	98.98 256	93.91 351	96.45 339	99.17 241	97.85 209	98.41 265	97.14 384	98.47 67	99.92 62	98.02 150	99.05 325	96.92 426

MVP-Stereo		98.08 214	97.92 226	98.57 218	98.96 259	96.79 245	97.90 213	99.18 237	96.41 316	98.46 260	98.95 210	95.93 249	99.60 333	96.51 267	98.98 339	99.31 238
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 174	98.68 119	97.54 322	98.96 259	97.99 155	97.88 215	99.36 164	98.20 182	99.63 64	99.04 181	98.76 42	95.33 449	96.56 261	99.74 163	99.31 238
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
新几何1				98.91 162	98.94 261	97.76 185		98.76 315	87.58 436	96.75 374	98.10 331	94.80 283	99.78 242	92.73 388	99.00 334	99.20 261

USDC		97.41 272	97.40 261	97.44 331	98.94 261	93.67 361	95.17 401	99.53 96	94.03 385	98.97 179	99.10 166	95.29 267	99.34 399	95.84 305	99.73 166	99.30 241

tfpn200view9		94.03 379	93.44 382	95.78 391	98.93 263	91.44 398	97.60 260	94.29 424	97.94 201	97.10 352	94.31 433	79.67 417	99.62 325	83.05 438	98.08 388	96.29 433

testdata				98.09 272	98.93 263	95.40 299		98.80 309	90.08 427	97.45 339	98.37 309	95.26 268	99.70 284	93.58 369	98.95 342	99.17 273

thres400		94.14 377	93.44 382	96.24 379	98.93 263	91.44 398	97.60 260	94.29 424	97.94 201	97.10 352	94.31 433	79.67 417	99.62 325	83.05 438	98.08 388	97.66 414

TAPA-MVS	96.21 11	96.63 318	95.95 329	98.65 200	98.93 263	98.09 142	96.93 315	99.28 209	83.58 442	98.13 287	97.78 352	96.13 233	99.40 390	93.52 370	99.29 293	98.45 367
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 267	96.93 239	95.54 388	98.78 312	85.72 439	96.86 369	98.11 330	94.43 290			99.10 324	99.23 255

PVSNet_BlendedMVS		97.55 260	97.53 254	97.60 314	98.92 267	93.77 358	96.64 330	99.43 139	94.49 371	97.62 322	99.18 144	96.82 198	99.67 300	94.73 333	99.93 53	99.36 221

PVSNet_Blended		96.88 308	96.68 307	97.47 329	98.92 267	93.77 358	94.71 412	99.43 139	90.98 421	97.62 322	97.36 378	96.82 198	99.67 300	94.73 333	99.56 239	98.98 300

MSDG		97.71 248	97.52 255	98.28 259	98.91 270	96.82 243	94.42 422	99.37 160	97.65 222	98.37 270	98.29 318	97.40 164	99.33 401	94.09 355	99.22 304	98.68 351

Anonymous202405211		97.90 228	97.50 256	99.08 129	98.90 271	98.25 125	98.53 122	96.16 401	98.87 126	99.11 154	98.86 228	90.40 352	99.78 242	97.36 191	99.31 288	99.19 266

原ACMM1				98.35 252	98.90 271	96.25 266		98.83 306	92.48 405	96.07 396	98.10 331	95.39 266	99.71 280	92.61 391	98.99 336	99.08 282

GBi-Net		98.65 138	98.47 152	99.17 111	98.90 271	98.24 126	99.20 48	99.44 133	98.59 147	98.95 183	99.55 57	94.14 298	99.86 136	97.77 168	99.69 189	99.41 195

test1		98.65 138	98.47 152	99.17 111	98.90 271	98.24 126	99.20 48	99.44 133	98.59 147	98.95 183	99.55 57	94.14 298	99.86 136	97.77 168	99.69 189	99.41 195

FMVSNet2		98.49 165	98.40 162	98.75 188	98.90 271	97.14 229	98.61 113	99.13 250	98.59 147	99.19 147	99.28 116	94.14 298	99.82 195	97.97 155	99.80 131	99.29 243

OMC-MVS		97.88 232	97.49 257	99.04 140	98.89 276	98.63 95	96.94 313	99.25 218	95.02 360	98.53 254	98.51 292	97.27 172	99.47 378	93.50 372	99.51 254	99.01 294

VortexMVS		97.98 225	98.31 177	97.02 349	98.88 277	91.45 397	98.03 189	99.47 120	98.65 138	99.55 72	99.47 77	91.49 341	99.81 210	99.32 58	99.91 75	99.80 39

MVSFormer		98.26 196	98.43 158	97.77 294	98.88 277	93.89 354	99.39 20	99.56 85	99.11 92	98.16 283	98.13 327	93.81 306	99.97 7	99.26 63	99.57 236	99.43 189

lupinMVS		97.06 298	96.86 294	97.65 308	98.88 277	93.89 354	95.48 392	97.97 356	93.53 391	98.16 283	97.58 364	93.81 306	99.91 71	96.77 238	99.57 236	99.17 273

dmvs_re		95.98 340	95.39 350	97.74 300	98.86 280	97.45 206	98.37 148	95.69 413	97.95 199	96.56 380	95.95 405	90.70 349	97.68 443	88.32 426	96.13 430	98.11 389

DELS-MVS		98.27 194	98.20 190	98.48 235	98.86 280	96.70 251	95.60 387	99.20 229	97.73 217	98.45 261	98.71 256	97.50 157	99.82 195	98.21 135	99.59 227	98.93 311
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		97.89 230	97.98 217	97.60 314	98.86 280	94.35 332	96.21 355	99.44 133	97.45 249	99.06 161	98.88 225	97.99 115	99.28 409	94.38 348	99.58 232	99.18 269

LCM-MVSNet-Re		98.64 140	98.48 150	99.11 122	98.85 283	98.51 108	98.49 133	99.83 25	98.37 162	99.69 53	99.46 79	98.21 94	99.92 62	94.13 354	99.30 291	98.91 315

pmmvs4		97.58 258	97.28 269	98.51 230	98.84 284	96.93 239	95.40 396	98.52 334	93.60 390	98.61 240	98.65 271	95.10 272	99.60 333	96.97 219	99.79 136	98.99 299

NP-MVS					98.84 284	97.39 210					96.84 387

sss		97.21 288	96.93 288	98.06 277	98.83 286	95.22 306	96.75 325	98.48 336	94.49 371	97.27 348	97.90 347	92.77 324	99.80 218	96.57 257	99.32 286	99.16 276

PVSNet	93.40 17	95.67 349	95.70 335	95.57 396	98.83 286	88.57 423	92.50 439	97.72 361	92.69 403	96.49 388	96.44 397	93.72 309	99.43 386	93.61 367	99.28 294	98.71 344

MVE	83.40 22	92.50 402	91.92 404	94.25 412	98.83 286	91.64 394	92.71 438	83.52 452	95.92 336	86.46 450	95.46 418	95.20 269	95.40 448	80.51 443	98.64 363	95.73 441
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 383	93.91 375	93.39 424	98.82 289	81.72 451	97.76 235	95.28 415	98.60 146	96.54 381	96.66 391	65.85 447	99.62 325	96.65 250	98.99 336	98.82 325

ambc				98.24 263	98.82 289	95.97 277	98.62 112	99.00 275		99.27 133	99.21 137	96.99 189	99.50 369	96.55 264	99.50 261	99.26 249

旧先验1					98.82 289	97.45 206		98.76 315			98.34 313	95.50 263			99.01 333	99.23 255

test_vis1_rt		97.75 245	97.72 240	97.83 289	98.81 292	96.35 263	97.30 290	99.69 49	94.61 369	97.87 306	98.05 336	96.26 229	98.32 437	98.74 104	98.18 380	98.82 325

WTY-MVS		96.67 316	96.27 326	97.87 287	98.81 292	94.61 326	96.77 323	97.92 358	94.94 363	97.12 351	97.74 355	91.11 345	99.82 195	93.89 360	98.15 384	99.18 269

3Dnovator+	97.89 3	98.69 128	98.51 143	99.24 102	98.81 292	98.40 113	99.02 69	99.19 233	98.99 113	98.07 292	99.28 116	97.11 182	99.84 167	96.84 233	99.32 286	99.47 175

QAPM		97.31 279	96.81 300	98.82 171	98.80 295	97.49 201	99.06 65	99.19 233	90.22 425	97.69 319	99.16 150	96.91 192	99.90 78	90.89 416	99.41 274	99.07 284

VNet		98.42 171	98.30 178	98.79 178	98.79 296	97.29 214	98.23 160	98.66 325	99.31 66	98.85 206	98.80 242	94.80 283	99.78 242	98.13 140	99.13 319	99.31 238

DPM-MVS		96.32 328	95.59 341	98.51 230	98.76 297	97.21 222	94.54 421	98.26 345	91.94 410	96.37 389	97.25 380	93.06 318	99.43 386	91.42 406	98.74 352	98.89 317

3Dnovator	98.27 2	98.81 108	98.73 108	99.05 138	98.76 297	97.81 182	99.25 43	99.30 197	98.57 151	98.55 251	99.33 106	97.95 117	99.90 78	97.16 201	99.67 200	99.44 185

PLC	94.65 16	96.51 321	95.73 334	98.85 168	98.75 299	97.91 167	96.42 343	99.06 259	90.94 422	95.59 402	97.38 376	94.41 291	99.59 337	90.93 414	98.04 393	99.05 286
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 310	96.75 303	97.08 346	98.74 300	93.33 367	96.71 327	98.26 345	96.72 303	98.44 262	97.37 377	95.20 269	99.47 378	91.89 396	97.43 407	98.44 370

hse-mvs2		97.46 266	97.07 281	98.64 202	98.73 301	97.33 212	97.45 278	97.64 368	99.11 92	98.58 246	97.98 341	88.65 367	99.79 231	98.11 141	97.39 409	98.81 330

CDS-MVSNet		97.69 249	97.35 266	98.69 196	98.73 301	97.02 233	96.92 317	98.75 318	95.89 337	98.59 244	98.67 266	92.08 335	99.74 266	96.72 244	99.81 120	99.32 234
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SD_0403		96.28 330	95.83 331	97.64 310	98.72 303	94.30 333	98.87 88	98.77 313	97.80 212	96.53 382	98.02 338	97.34 167	99.47 378	76.93 447	99.48 264	99.16 276

EIA-MVS		98.00 221	97.74 237	98.80 175	98.72 303	98.09 142	98.05 186	99.60 68	97.39 253	96.63 377	95.55 413	97.68 136	99.80 218	96.73 243	99.27 295	98.52 362

LFMVS		97.20 289	96.72 304	98.64 202	98.72 303	96.95 237	98.93 81	94.14 428	99.74 13	98.78 217	99.01 193	84.45 394	99.73 272	97.44 187	99.27 295	99.25 250

new_pmnet		96.99 305	96.76 302	97.67 305	98.72 303	94.89 315	95.95 372	98.20 348	92.62 404	98.55 251	98.54 287	94.88 279	99.52 363	93.96 358	99.44 272	98.59 359

Fast-Effi-MVS+		97.67 251	97.38 263	98.57 218	98.71 307	97.43 208	97.23 295	99.45 128	94.82 366	96.13 393	96.51 393	98.52 65	99.91 71	96.19 286	98.83 348	98.37 379

TEST9					98.71 307	98.08 146	95.96 370	99.03 267	91.40 416	95.85 399	97.53 366	96.52 217	99.76 254

train_agg		97.10 295	96.45 320	99.07 131	98.71 307	98.08 146	95.96 370	99.03 267	91.64 411	95.85 399	97.53 366	96.47 219	99.76 254	93.67 366	99.16 314	99.36 221

TSAR-MVS + GP.		98.18 206	97.98 217	98.77 185	98.71 307	97.88 169	96.32 349	98.66 325	96.33 318	99.23 144	98.51 292	97.48 161	99.40 390	97.16 201	99.46 266	99.02 293

FA-MVS(test-final)		96.99 305	96.82 298	97.50 326	98.70 311	94.78 318	99.34 23	96.99 384	95.07 359	98.48 259	99.33 106	88.41 370	99.65 316	96.13 292	98.92 345	98.07 392

AUN-MVS		96.24 334	95.45 346	98.60 213	98.70 311	97.22 220	97.38 282	97.65 366	95.95 335	95.53 409	97.96 345	82.11 411	99.79 231	96.31 279	97.44 406	98.80 335

our_test_3		97.39 274	97.73 239	96.34 374	98.70 311	89.78 419	94.61 418	98.97 277	96.50 311	99.04 168	98.85 231	95.98 245	99.84 167	97.26 196	99.67 200	99.41 195

ppachtmachnet_test		97.50 261	97.74 237	96.78 364	98.70 311	91.23 406	94.55 420	99.05 262	96.36 317	99.21 145	98.79 244	96.39 222	99.78 242	96.74 241	99.82 116	99.34 227

PCF-MVS	92.86 18	94.36 371	93.00 389	98.42 242	98.70 311	97.56 198	93.16 437	99.11 253	79.59 446	97.55 329	97.43 373	92.19 332	99.73 272	79.85 444	99.45 268	97.97 398
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 227	98.02 213	97.58 316	98.69 316	94.10 340	98.13 172	98.90 287	97.95 199	97.32 347	99.58 47	95.95 248	98.75 432	96.41 273	99.22 304	99.87 21

ETV-MVS		98.03 217	97.86 231	98.56 222	98.69 316	98.07 148	97.51 272	99.50 103	98.10 191	97.50 334	95.51 414	98.41 73	99.88 109	96.27 282	99.24 300	97.71 413

test_prior				98.95 155	98.69 316	97.95 163		99.03 267					99.59 337			99.30 241

mvsmamba		97.57 259	97.26 270	98.51 230	98.69 316	96.73 250	98.74 97	97.25 377	97.03 287	97.88 305	99.23 135	90.95 346	99.87 128	96.61 253	99.00 334	98.91 315

agg_prior					98.68 320	97.99 155		99.01 273		95.59 402			99.77 248

test_8					98.67 321	98.01 154	95.91 376	99.02 270	91.64 411	95.79 401	97.50 369	96.47 219	99.76 254

HQP-NCC					98.67 321		96.29 351		96.05 328	95.55 405

ACMP_Plane					98.67 321		96.29 351		96.05 328	95.55 405

CNVR-MVS		98.17 208	97.87 230	99.07 131	98.67 321	98.24 126	97.01 309	98.93 281	97.25 267	97.62 322	98.34 313	97.27 172	99.57 345	96.42 272	99.33 285	99.39 205

HQP-MVS		97.00 304	96.49 319	98.55 223	98.67 321	96.79 245	96.29 351	99.04 265	96.05 328	95.55 405	96.84 387	93.84 304	99.54 357	92.82 384	99.26 298	99.32 234

MM		98.22 201	97.99 216	98.91 162	98.66 326	96.97 234	97.89 214	94.44 422	99.54 38	98.95 183	99.14 157	93.50 310	99.92 62	99.80 15	99.96 27	99.85 29

test_fmvs1		97.72 247	97.94 223	97.07 348	98.66 326	92.39 384	97.68 244	99.81 30	95.20 358	99.54 74	99.44 84	91.56 340	99.41 389	99.78 19	99.77 147	99.40 204

balanced_conf03		98.63 142	98.72 110	98.38 247	98.66 326	96.68 253	98.90 83	99.42 145	98.99 113	98.97 179	99.19 140	95.81 253	99.85 149	98.77 102	99.77 147	98.60 356

thres200		93.72 385	93.14 387	95.46 400	98.66 326	91.29 402	96.61 332	94.63 421	97.39 253	96.83 370	93.71 436	79.88 414	99.56 348	82.40 441	98.13 385	95.54 442

wuyk23d		96.06 336	97.62 250	91.38 429	98.65 330	98.57 102	98.85 92	96.95 387	96.86 296	99.90 13	99.16 150	99.18 18	98.40 436	89.23 424	99.77 147	77.18 449

NCCC		97.86 235	97.47 260	99.05 138	98.61 331	98.07 148	96.98 311	98.90 287	97.63 223	97.04 356	97.93 346	95.99 244	99.66 311	95.31 321	98.82 350	99.43 189

DeepC-MVS_fast	96.85 6	98.30 190	98.15 199	98.75 188	98.61 331	97.23 218	97.76 235	99.09 256	97.31 261	98.75 223	98.66 269	97.56 149	99.64 319	96.10 293	99.55 243	99.39 205
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 387	92.09 398	97.75 298	98.60 333	94.40 330	97.32 288	95.26 416	97.56 233	96.79 373	95.50 415	53.57 455	99.77 248	95.26 322	98.97 340	99.08 282

thisisatest0515		94.12 378	93.16 386	96.97 353	98.60 333	92.90 374	93.77 433	90.61 441	94.10 383	96.91 363	95.87 408	74.99 429	99.80 218	94.52 339	99.12 322	98.20 385

GA-MVS		95.86 343	95.32 353	97.49 327	98.60 333	94.15 339	93.83 432	97.93 357	95.49 348	96.68 375	97.42 374	83.21 404	99.30 405	96.22 284	98.55 369	99.01 294

dmvs_testset		92.94 397	92.21 397	95.13 404	98.59 336	90.99 409	97.65 250	92.09 437	96.95 290	94.00 429	93.55 437	92.34 330	96.97 446	72.20 448	92.52 444	97.43 421

OPU-MVS				98.82 171	98.59 336	98.30 122	98.10 178				98.52 291	98.18 96	98.75 432	94.62 336	99.48 264	99.41 195

MSLP-MVS++		98.02 218	98.14 201	97.64 310	98.58 338	95.19 307	97.48 275	99.23 225	97.47 242	97.90 303	98.62 278	97.04 184	98.81 430	97.55 180	99.41 274	98.94 310

test12				98.93 158	98.58 338	97.83 174		98.66 325		96.53 382		95.51 262	99.69 288		99.13 319	99.27 246

CL-MVSNet_self_test		97.44 269	97.22 273	98.08 275	98.57 340	95.78 285	94.30 425	98.79 310	96.58 309	98.60 242	98.19 325	94.74 286	99.64 319	96.41 273	98.84 347	98.82 325

PS-MVSNAJ		97.08 297	97.39 262	96.16 385	98.56 341	92.46 382	95.24 400	98.85 301	97.25 267	97.49 335	95.99 404	98.07 106	99.90 78	96.37 275	98.67 362	96.12 438

CNLPA		97.17 292	96.71 305	98.55 223	98.56 341	98.05 152	96.33 348	98.93 281	96.91 293	97.06 355	97.39 375	94.38 293	99.45 383	91.66 400	99.18 313	98.14 388

xiu_mvs_v2_base		97.16 293	97.49 257	96.17 383	98.54 343	92.46 382	95.45 393	98.84 302	97.25 267	97.48 336	96.49 394	98.31 83	99.90 78	96.34 278	98.68 361	96.15 437

alignmvs		97.35 276	96.88 293	98.78 181	98.54 343	98.09 142	97.71 241	97.69 363	99.20 80	97.59 325	95.90 407	88.12 372	99.55 352	98.18 137	98.96 341	98.70 347

FE-MVS		95.66 350	94.95 363	97.77 294	98.53 345	95.28 303	99.40 19	96.09 404	93.11 397	97.96 300	99.26 123	79.10 421	99.77 248	92.40 393	98.71 356	98.27 383

Effi-MVS+		98.02 218	97.82 233	98.62 208	98.53 345	97.19 224	97.33 287	99.68 54	97.30 262	96.68 375	97.46 372	98.56 63	99.80 218	96.63 251	98.20 379	98.86 322

baseline1		95.96 341	95.44 347	97.52 324	98.51 347	93.99 348	98.39 146	96.09 404	98.21 178	98.40 269	97.76 354	86.88 374	99.63 322	95.42 319	89.27 447	98.95 306

MVS_Test		98.18 206	98.36 169	97.67 305	98.48 348	94.73 321	98.18 165	99.02 270	97.69 219	98.04 296	99.11 163	97.22 176	99.56 348	98.57 116	98.90 346	98.71 344

MGCFI-Net		98.34 182	98.28 180	98.51 230	98.47 349	97.59 197	98.96 77	99.48 112	99.18 87	97.40 342	95.50 415	98.66 51	99.50 369	98.18 137	98.71 356	98.44 370

BH-RMVSNet		96.83 310	96.58 315	97.58 316	98.47 349	94.05 341	96.67 329	97.36 372	96.70 305	97.87 306	97.98 341	95.14 271	99.44 385	90.47 419	98.58 368	99.25 250

sasdasda		98.34 182	98.26 184	98.58 215	98.46 351	97.82 179	98.96 77	99.46 124	99.19 84	97.46 337	95.46 418	98.59 59	99.46 381	98.08 144	98.71 356	98.46 364

canonicalmvs		98.34 182	98.26 184	98.58 215	98.46 351	97.82 179	98.96 77	99.46 124	99.19 84	97.46 337	95.46 418	98.59 59	99.46 381	98.08 144	98.71 356	98.46 364

MVS-HIRNet		94.32 372	95.62 338	90.42 430	98.46 351	75.36 454	96.29 351	89.13 445	95.25 355	95.38 411	99.75 16	92.88 321	99.19 415	94.07 356	99.39 276	96.72 431

PHI-MVS		98.29 193	97.95 221	99.34 79	98.44 354	99.16 48	98.12 175	99.38 156	96.01 332	98.06 293	98.43 303	97.80 130	99.67 300	95.69 311	99.58 232	99.20 261

DVP-MVS++		98.90 95	98.70 116	99.51 48	98.43 355	99.15 52	99.43 15	99.32 184	98.17 185	99.26 137	99.02 184	98.18 96	99.88 109	97.07 210	99.45 268	99.49 156

MSC_two_6792asdad				99.32 87	98.43 355	98.37 117		98.86 298					99.89 93	97.14 204	99.60 223	99.71 59

No_MVS				99.32 87	98.43 355	98.37 117		98.86 298					99.89 93	97.14 204	99.60 223	99.71 59

Fast-Effi-MVS+-dtu		98.27 194	98.09 204	98.81 173	98.43 355	98.11 139	97.61 259	99.50 103	98.64 139	97.39 344	97.52 368	98.12 104	99.95 26	96.90 227	98.71 356	98.38 377

OpenMVS_ROB	95.38 14	95.84 345	95.18 358	97.81 291	98.41 359	97.15 228	97.37 284	98.62 329	83.86 441	98.65 234	98.37 309	94.29 296	99.68 297	88.41 425	98.62 366	96.60 432

DeepPCF-MVS	96.93 5	98.32 187	98.01 214	99.23 104	98.39 360	98.97 73	95.03 405	99.18 237	96.88 294	99.33 121	98.78 246	98.16 100	99.28 409	96.74 241	99.62 216	99.44 185

Patchmatch-test		96.55 320	96.34 322	97.17 343	98.35 361	93.06 370	98.40 145	97.79 359	97.33 258	98.41 265	98.67 266	83.68 402	99.69 288	95.16 324	99.31 288	98.77 338

AdaColmap		97.14 294	96.71 305	98.46 237	98.34 362	97.80 183	96.95 312	98.93 281	95.58 345	96.92 361	97.66 359	95.87 251	99.53 359	90.97 413	99.14 317	98.04 393

OpenMVS	96.65 7	97.09 296	96.68 307	98.32 254	98.32 363	97.16 227	98.86 91	99.37 160	89.48 429	96.29 391	99.15 154	96.56 215	99.90 78	92.90 381	99.20 308	97.89 401

MG-MVS		96.77 313	96.61 312	97.26 339	98.31 364	93.06 370	95.93 373	98.12 353	96.45 315	97.92 301	98.73 253	93.77 308	99.39 392	91.19 411	99.04 328	99.33 232

test_yl		96.69 314	96.29 324	97.90 284	98.28 365	95.24 304	97.29 291	97.36 372	98.21 178	98.17 280	97.86 348	86.27 378	99.55 352	94.87 330	98.32 373	98.89 317

DCV-MVSNet		96.69 314	96.29 324	97.90 284	98.28 365	95.24 304	97.29 291	97.36 372	98.21 178	98.17 280	97.86 348	86.27 378	99.55 352	94.87 330	98.32 373	98.89 317

CHOSEN 280x420		95.51 355	95.47 344	95.65 395	98.25 367	88.27 426	93.25 436	98.88 291	93.53 391	94.65 420	97.15 383	86.17 380	99.93 52	97.41 189	99.93 53	98.73 343

SCA		96.41 327	96.66 310	95.67 393	98.24 368	88.35 425	95.85 379	96.88 390	96.11 326	97.67 320	98.67 266	93.10 316	99.85 149	94.16 350	99.22 304	98.81 330

DeepMVS_CX				93.44 423	98.24 368	94.21 336		94.34 423	64.28 449	91.34 443	94.87 430	89.45 361	92.77 450	77.54 446	93.14 443	93.35 445

MS-PatchMatch		97.68 250	97.75 236	97.45 330	98.23 370	93.78 357	97.29 291	98.84 302	96.10 327	98.64 235	98.65 271	96.04 237	99.36 395	96.84 233	99.14 317	99.20 261

BH-w/o		95.13 361	94.89 365	95.86 388	98.20 371	91.31 401	95.65 385	97.37 371	93.64 389	96.52 384	95.70 411	93.04 319	99.02 421	88.10 427	95.82 433	97.24 424

mvs_anonymous		97.83 243	98.16 198	96.87 358	98.18 372	91.89 391	97.31 289	98.90 287	97.37 255	98.83 209	99.46 79	96.28 228	99.79 231	98.90 91	98.16 383	98.95 306

miper_lstm_enhance		97.18 291	97.16 276	97.25 340	98.16 373	92.85 375	95.15 403	99.31 189	97.25 267	98.74 225	98.78 246	90.07 353	99.78 242	97.19 199	99.80 131	99.11 281

RRT-MVS		97.88 232	97.98 217	97.61 313	98.15 374	93.77 358	98.97 76	99.64 61	99.16 89	98.69 228	99.42 87	91.60 338	99.89 93	97.63 176	98.52 370	99.16 276

ET-MVSNet_ETH3D		94.30 374	93.21 385	97.58 316	98.14 375	94.47 329	94.78 411	93.24 433	94.72 367	89.56 445	95.87 408	78.57 424	99.81 210	96.91 222	97.11 418	98.46 364

ADS-MVSNet2		95.43 356	94.98 361	96.76 365	98.14 375	91.74 392	97.92 210	97.76 360	90.23 423	96.51 385	98.91 215	85.61 385	99.85 149	92.88 382	96.90 419	98.69 348

ADS-MVSNet		95.24 359	94.93 364	96.18 382	98.14 375	90.10 418	97.92 210	97.32 375	90.23 423	96.51 385	98.91 215	85.61 385	99.74 266	92.88 382	96.90 419	98.69 348

c3_l		97.36 275	97.37 264	97.31 335	98.09 378	93.25 368	95.01 406	99.16 244	97.05 284	98.77 220	98.72 255	92.88 321	99.64 319	96.93 221	99.76 159	99.05 286

FMVSNet3		97.50 261	97.24 272	98.29 258	98.08 379	95.83 282	97.86 219	98.91 286	97.89 206	98.95 183	98.95 210	87.06 373	99.81 210	97.77 168	99.69 189	99.23 255

PAPM		91.88 411	90.34 414	96.51 369	98.06 380	92.56 380	92.44 440	97.17 379	86.35 437	90.38 444	96.01 403	86.61 376	99.21 414	70.65 450	95.43 435	97.75 410

Effi-MVS+-dtu		98.26 196	97.90 228	99.35 76	98.02 381	99.49 6	98.02 192	99.16 244	98.29 172	97.64 321	97.99 340	96.44 221	99.95 26	96.66 249	98.93 344	98.60 356

eth_miper_zixun_eth		97.23 287	97.25 271	97.17 343	98.00 382	92.77 377	94.71 412	99.18 237	97.27 265	98.56 249	98.74 252	91.89 336	99.69 288	97.06 212	99.81 120	99.05 286

HY-MVS	95.94 13	95.90 342	95.35 352	97.55 321	97.95 383	94.79 317	98.81 96	96.94 388	92.28 408	95.17 413	98.57 285	89.90 355	99.75 261	91.20 410	97.33 414	98.10 390

UGNet		98.53 159	98.45 155	98.79 178	97.94 384	96.96 236	99.08 61	98.54 332	99.10 99	96.82 371	99.47 77	96.55 216	99.84 167	98.56 119	99.94 48	99.55 129
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
MAR-MVS		96.47 325	95.70 335	98.79 178	97.92 385	99.12 62	98.28 154	98.60 330	92.16 409	95.54 408	96.17 401	94.77 285	99.52 363	89.62 422	98.23 377	97.72 412
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		96.86 309	96.55 316	97.79 292	97.91 386	94.21 336	97.56 265	98.87 293	97.49 241	99.06 161	99.05 179	80.72 412	99.80 218	98.44 123	99.82 116	99.37 214

API-MVS		97.04 300	96.91 292	97.42 332	97.88 387	98.23 130	98.18 165	98.50 335	97.57 231	97.39 344	96.75 389	96.77 202	99.15 418	90.16 420	99.02 332	94.88 443

myMVS_eth3d28		92.92 398	92.31 394	94.77 407	97.84 388	87.59 430	96.19 357	96.11 403	97.08 283	94.27 423	93.49 439	66.07 446	98.78 431	91.78 398	97.93 396	97.92 400

miper_ehance_all_eth		97.06 298	97.03 283	97.16 345	97.83 389	93.06 370	94.66 415	99.09 256	95.99 333	98.69 228	98.45 301	92.73 326	99.61 332	96.79 235	99.03 329	98.82 325

cl____		97.02 301	96.83 297	97.58 316	97.82 390	94.04 343	94.66 415	99.16 244	97.04 285	98.63 236	98.71 256	88.68 366	99.69 288	97.00 214	99.81 120	99.00 298

DIV-MVS_self_test		97.02 301	96.84 296	97.58 316	97.82 390	94.03 344	94.66 415	99.16 244	97.04 285	98.63 236	98.71 256	88.69 364	99.69 288	97.00 214	99.81 120	99.01 294

CANet		97.87 234	97.76 235	98.19 267	97.75 392	95.51 292	96.76 324	99.05 262	97.74 216	96.93 360	98.21 323	95.59 259	99.89 93	97.86 163	99.93 53	99.19 266

UBG		93.25 392	92.32 393	96.04 387	97.72 393	90.16 417	95.92 375	95.91 408	96.03 331	93.95 431	93.04 442	69.60 436	99.52 363	90.72 418	97.98 394	98.45 367

mvsany_test1		97.60 255	97.54 253	97.77 294	97.72 393	95.35 300	95.36 397	97.13 381	94.13 382	99.71 47	99.33 106	97.93 118	99.30 405	97.60 179	98.94 343	98.67 352

PVSNet_0	89.98 21	91.15 412	90.30 415	93.70 420	97.72 393	84.34 444	90.24 443	97.42 370	90.20 426	93.79 432	93.09 441	90.90 348	98.89 429	86.57 433	72.76 450	97.87 403

CR-MVSNet		96.28 330	95.95 329	97.28 337	97.71 396	94.22 334	98.11 176	98.92 284	92.31 407	96.91 363	99.37 95	85.44 388	99.81 210	97.39 190	97.36 412	97.81 406

RPMNet		97.02 301	96.93 288	97.30 336	97.71 396	94.22 334	98.11 176	99.30 197	99.37 58	96.91 363	99.34 104	86.72 375	99.87 128	97.53 183	97.36 412	97.81 406

ETVMVS		92.60 401	91.08 410	97.18 341	97.70 398	93.65 363	96.54 333	95.70 411	96.51 310	94.68 419	92.39 445	61.80 452	99.50 369	86.97 430	97.41 408	98.40 375

pmmvs3		95.03 363	94.40 370	96.93 354	97.70 398	92.53 381	95.08 404	97.71 362	88.57 433	97.71 317	98.08 334	79.39 419	99.82 195	96.19 286	99.11 323	98.43 372

baseline2		93.73 384	92.83 390	96.42 372	97.70 398	91.28 403	96.84 320	89.77 444	93.96 387	92.44 439	95.93 406	79.14 420	99.77 248	92.94 380	96.76 423	98.21 384

WBMVS		95.18 360	94.78 366	96.37 373	97.68 401	89.74 420	95.80 381	98.73 321	97.54 236	98.30 271	98.44 302	70.06 434	99.82 195	96.62 252	99.87 94	99.54 133

tpm		94.67 368	94.34 372	95.66 394	97.68 401	88.42 424	97.88 215	94.90 418	94.46 373	96.03 398	98.56 286	78.66 422	99.79 231	95.88 299	95.01 437	98.78 337

CANet_DTU		97.26 283	97.06 282	97.84 288	97.57 403	94.65 325	96.19 357	98.79 310	97.23 273	95.14 414	98.24 320	93.22 313	99.84 167	97.34 192	99.84 105	99.04 290

testing11		93.08 395	92.02 400	96.26 378	97.56 404	90.83 412	96.32 349	95.70 411	96.47 314	92.66 438	93.73 435	64.36 450	99.59 337	93.77 365	97.57 401	98.37 379

tpm2		93.09 394	92.58 392	94.62 409	97.56 404	86.53 433	97.66 248	95.79 410	86.15 438	94.07 428	98.23 322	75.95 427	99.53 359	90.91 415	96.86 422	97.81 406

testing91		93.32 390	92.27 395	96.47 371	97.54 406	91.25 404	96.17 361	96.76 392	97.18 277	93.65 434	93.50 438	65.11 449	99.63 322	93.04 379	97.45 405	98.53 361

TR-MVS		95.55 353	95.12 359	96.86 361	97.54 406	93.94 349	96.49 338	96.53 397	94.36 378	97.03 358	96.61 392	94.26 297	99.16 417	86.91 432	96.31 427	97.47 420

testing99		93.04 396	91.98 403	96.23 380	97.53 408	90.70 414	96.35 347	95.94 407	96.87 295	93.41 435	93.43 440	63.84 451	99.59 337	93.24 377	97.19 415	98.40 375

1314		95.74 347	95.60 339	96.17 383	97.53 408	92.75 378	98.07 183	98.31 344	91.22 418	94.25 424	96.68 390	95.53 260	99.03 420	91.64 402	97.18 416	96.74 430

CostFormer		93.97 380	93.78 378	94.51 410	97.53 408	85.83 436	97.98 202	95.96 406	89.29 431	94.99 416	98.63 276	78.63 423	99.62 325	94.54 338	96.50 424	98.09 391

FMVSNet5		96.01 338	95.20 357	98.41 243	97.53 408	96.10 268	98.74 97	99.50 103	97.22 276	98.03 297	99.04 181	69.80 435	99.88 109	97.27 195	99.71 179	99.25 250

PMMVS		96.51 321	95.98 328	98.09 272	97.53 408	95.84 281	94.92 408	98.84 302	91.58 413	96.05 397	95.58 412	95.68 256	99.66 311	95.59 315	98.09 387	98.76 340

reproduce_monomvs		95.00 365	95.25 354	94.22 413	97.51 413	83.34 445	97.86 219	98.44 337	98.51 156	99.29 130	99.30 112	67.68 440	99.56 348	98.89 93	99.81 120	99.77 47

PAPR		95.29 357	94.47 368	97.75 298	97.50 414	95.14 309	94.89 409	98.71 323	91.39 417	95.35 412	95.48 417	94.57 288	99.14 419	84.95 435	97.37 410	98.97 303

testing222		91.96 409	90.37 413	96.72 366	97.47 415	92.59 379	96.11 363	94.76 419	96.83 297	92.90 437	92.87 443	57.92 453	99.55 352	86.93 431	97.52 402	98.00 397

PatchT		96.65 317	96.35 321	97.54 322	97.40 416	95.32 302	97.98 202	96.64 394	99.33 63	96.89 367	99.42 87	84.32 396	99.81 210	97.69 175	97.49 403	97.48 419

tpm cat1		93.29 391	93.13 388	93.75 419	97.39 417	84.74 439	97.39 281	97.65 366	83.39 443	94.16 425	98.41 304	82.86 407	99.39 392	91.56 404	95.35 436	97.14 425

PatchmatchNet		95.58 352	95.67 337	95.30 403	97.34 418	87.32 431	97.65 250	96.65 393	95.30 354	97.07 354	98.69 262	84.77 391	99.75 261	94.97 328	98.64 363	98.83 324
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 276	96.97 286	98.50 234	97.31 419	96.47 259	98.18 165	98.92 284	98.95 120	98.78 217	99.37 95	85.44 388	99.85 149	95.96 297	99.83 112	99.17 273

LS3D		98.63 142	98.38 167	99.36 70	97.25 420	99.38 13	99.12 60	99.32 184	99.21 78	98.44 262	98.88 225	97.31 168	99.80 218	96.58 255	99.34 284	98.92 312

IB-MVS	91.63 19	92.24 407	90.90 411	96.27 377	97.22 421	91.24 405	94.36 424	93.33 432	92.37 406	92.24 441	94.58 432	66.20 445	99.89 93	93.16 378	94.63 439	97.66 414
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		92.38 404	91.76 407	94.21 414	97.16 422	84.65 440	95.42 395	88.45 446	95.96 334	96.17 392	95.84 410	66.36 443	99.71 280	91.87 397	98.64 363	98.28 382

tpmrst		95.07 362	95.46 345	93.91 417	97.11 423	84.36 443	97.62 255	96.96 386	94.98 361	96.35 390	98.80 242	85.46 387	99.59 337	95.60 314	96.23 428	97.79 409

Syy-MVS		96.04 337	95.56 343	97.49 327	97.10 424	94.48 328	96.18 359	96.58 395	95.65 342	94.77 417	92.29 446	91.27 344	99.36 395	98.17 139	98.05 391	98.63 354

myMVS_eth3d		91.92 410	90.45 412	96.30 375	97.10 424	90.90 410	96.18 359	96.58 395	95.65 342	94.77 417	92.29 446	53.88 454	99.36 395	89.59 423	98.05 391	98.63 354

MDTV_nov1_ep13			95.22 356		97.06 426	83.20 446	97.74 238	96.16 401	94.37 377	96.99 359	98.83 236	83.95 400	99.53 359	93.90 359	97.95 395

MVS		93.19 393	92.09 398	96.50 370	96.91 427	94.03 344	98.07 183	98.06 355	68.01 448	94.56 422	96.48 395	95.96 247	99.30 405	83.84 437	96.89 421	96.17 435

E-PMN		94.17 376	94.37 371	93.58 421	96.86 428	85.71 437	90.11 445	97.07 382	98.17 185	97.82 312	97.19 381	84.62 393	98.94 425	89.77 421	97.68 400	96.09 439

JIA-IIPM		95.52 354	95.03 360	97.00 350	96.85 429	94.03 344	96.93 315	95.82 409	99.20 80	94.63 421	99.71 22	83.09 405	99.60 333	94.42 344	94.64 438	97.36 423

EMVS		93.83 382	94.02 374	93.23 426	96.83 430	84.96 438	89.77 446	96.32 399	97.92 203	97.43 341	96.36 400	86.17 380	98.93 426	87.68 428	97.73 399	95.81 440

cl22		95.79 346	95.39 350	96.98 352	96.77 431	92.79 376	94.40 423	98.53 333	94.59 370	97.89 304	98.17 326	82.82 408	99.24 411	96.37 275	99.03 329	98.92 312

WB-MVSnew		95.73 348	95.57 342	96.23 380	96.70 432	90.70 414	96.07 365	93.86 429	95.60 344	97.04 356	95.45 421	96.00 240	99.55 352	91.04 412	98.31 375	98.43 372

dp		93.47 388	93.59 381	93.13 427	96.64 433	81.62 452	97.66 248	96.42 398	92.80 402	96.11 394	98.64 274	78.55 425	99.59 337	93.31 375	92.18 446	98.16 387

MonoMVSNet		96.25 332	96.53 318	95.39 401	96.57 434	91.01 408	98.82 95	97.68 365	98.57 151	98.03 297	99.37 95	90.92 347	97.78 442	94.99 326	93.88 442	97.38 422

test-LLR		93.90 381	93.85 376	94.04 415	96.53 435	84.62 441	94.05 429	92.39 435	96.17 323	94.12 426	95.07 422	82.30 409	99.67 300	95.87 302	98.18 380	97.82 404

test-mter		92.33 406	91.76 407	94.04 415	96.53 435	84.62 441	94.05 429	92.39 435	94.00 386	94.12 426	95.07 422	65.63 448	99.67 300	95.87 302	98.18 380	97.82 404

TESTMET0.1,1		92.19 408	91.77 406	93.46 422	96.48 437	82.80 448	94.05 429	91.52 440	94.45 375	94.00 429	94.88 428	66.65 442	99.56 348	95.78 307	98.11 386	98.02 394

MVS_0304		97.44 269	97.01 285	98.72 194	96.42 438	96.74 249	97.20 300	91.97 438	98.46 159	98.30 271	98.79 244	92.74 325	99.91 71	99.30 60	99.94 48	99.52 145

miper_enhance_ethall		96.01 338	95.74 333	96.81 362	96.41 439	92.27 388	93.69 434	98.89 290	91.14 420	98.30 271	97.35 379	90.58 350	99.58 343	96.31 279	99.03 329	98.60 356

tpmvs		95.02 364	95.25 354	94.33 411	96.39 440	85.87 434	98.08 180	96.83 391	95.46 349	95.51 410	98.69 262	85.91 383	99.53 359	94.16 350	96.23 428	97.58 417

CMPMVS	75.91 23	96.29 329	95.44 347	98.84 169	96.25 441	98.69 94	97.02 308	99.12 251	88.90 432	97.83 310	98.86 228	89.51 359	98.90 428	91.92 395	99.51 254	98.92 312
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 369	93.69 379	96.99 351	96.05 442	93.61 365	94.97 407	93.49 430	96.17 323	97.57 328	94.88 428	82.30 409	99.01 423	93.60 368	94.17 441	98.37 379

EPMVS		93.72 385	93.27 384	95.09 406	96.04 443	87.76 428	98.13 172	85.01 451	94.69 368	96.92 361	98.64 274	78.47 426	99.31 403	95.04 325	96.46 425	98.20 385

cascas		94.79 367	94.33 373	96.15 386	96.02 444	92.36 386	92.34 441	99.26 217	85.34 440	95.08 415	94.96 427	92.96 320	98.53 435	94.41 347	98.59 367	97.56 418

MVStest1		95.86 343	95.60 339	96.63 367	95.87 445	91.70 393	97.93 207	98.94 278	98.03 193	99.56 69	99.66 32	71.83 432	98.26 438	99.35 56	99.24 300	99.91 13

gg-mvs-nofinetune		92.37 405	91.20 409	95.85 389	95.80 446	92.38 385	99.31 30	81.84 453	99.75 11	91.83 442	99.74 18	68.29 437	99.02 421	87.15 429	97.12 417	96.16 436

gm-plane-assit					94.83 447	81.97 450			88.07 435		94.99 425		99.60 333	91.76 399

GG-mvs-BLEND				94.76 408	94.54 448	92.13 390	99.31 30	80.47 454		88.73 448	91.01 448	67.59 441	98.16 441	82.30 442	94.53 440	93.98 444

UWE-MVS-28		90.22 413	89.28 416	93.02 428	94.50 449	82.87 447	96.52 336	87.51 447	95.21 357	92.36 440	96.04 402	71.57 433	98.25 439	72.04 449	97.77 398	97.94 399

EPNet_dtu		94.93 366	94.78 366	95.38 402	93.58 450	87.68 429	96.78 322	95.69 413	97.35 257	89.14 447	98.09 333	88.15 371	99.49 372	94.95 329	99.30 291	98.98 300
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 417	75.95 420	77.12 433	92.39 451	67.91 457	90.16 444	59.44 458	82.04 444	89.42 446	94.67 431	49.68 456	81.74 451	48.06 451	77.66 449	81.72 447

KD-MVS_2432*1600		92.87 399	91.99 401	95.51 398	91.37 452	89.27 421	94.07 427	98.14 351	95.42 350	97.25 349	96.44 397	67.86 438	99.24 411	91.28 408	96.08 431	98.02 394

miper_refine_blended		92.87 399	91.99 401	95.51 398	91.37 452	89.27 421	94.07 427	98.14 351	95.42 350	97.25 349	96.44 397	67.86 438	99.24 411	91.28 408	96.08 431	98.02 394

EPNet		96.14 335	95.44 347	98.25 261	90.76 454	95.50 293	97.92 210	94.65 420	98.97 116	92.98 436	98.85 231	89.12 362	99.87 128	95.99 295	99.68 194	99.39 205
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 418	68.95 421	70.34 434	87.68 455	65.00 458	91.11 442	59.90 457	69.02 447	74.46 452	88.89 449	48.58 457	68.03 453	28.61 452	72.33 451	77.99 448

test_method		79.78 415	79.50 418	80.62 431	80.21 456	45.76 459	70.82 447	98.41 341	31.08 451	80.89 451	97.71 356	84.85 390	97.37 444	91.51 405	80.03 448	98.75 341

tmp_tt		78.77 416	78.73 419	78.90 432	58.45 457	74.76 456	94.20 426	78.26 455	39.16 450	86.71 449	92.82 444	80.50 413	75.19 452	86.16 434	92.29 445	86.74 446

testmvs		17.12 420	20.53 423	6.87 436	12.05 458	4.20 461	93.62 435	6.73 459	4.62 454	10.41 454	24.33 451	8.28 459	3.56 455	9.69 454	15.07 452	12.86 451

test123		17.04 421	20.11 424	7.82 435	10.25 459	4.91 460	94.80 410	4.47 460	4.93 453	10.00 455	24.28 452	9.69 458	3.64 454	10.14 453	12.43 453	14.92 450

mmdepth		0.00 424	0.00 427	0.00 437	0.00 460	0.00 462	0.00 448	0.00 461	0.00 455	0.00 456	0.00 455	0.00 460	0.00 456	0.00 455	0.00 454	0.00 452

monomultidepth		0.00 424	0.00 427	0.00 437	0.00 460	0.00 462	0.00 448	0.00 461	0.00 455	0.00 456	0.00 455	0.00 460	0.00 456	0.00 455	0.00 454	0.00 452

test_blank		0.00 424	0.00 427	0.00 437	0.00 460	0.00 462	0.00 448	0.00 461	0.00 455	0.00 456	0.00 455	0.00 460	0.00 456	0.00 455	0.00 454	0.00 452

eth-test2					0.00 460

eth-test					0.00 460

uanet_test		0.00 424	0.00 427	0.00 437	0.00 460	0.00 462	0.00 448	0.00 461	0.00 455	0.00 456	0.00 455	0.00 460	0.00 456	0.00 455	0.00 454	0.00 452

DCPMVS		0.00 424	0.00 427	0.00 437	0.00 460	0.00 462	0.00 448	0.00 461	0.00 455	0.00 456	0.00 455	0.00 460	0.00 456	0.00 455	0.00 454	0.00 452

cdsmvs_eth3d_5k		24.66 419	32.88 422	0.00 437	0.00 460	0.00 462	0.00 448	99.10 254	0.00 455	0.00 456	97.58 364	99.21 17	0.00 456	0.00 455	0.00 454	0.00 452

pcd_1.5k_mvsjas		8.17 422	10.90 425	0.00 437	0.00 460	0.00 462	0.00 448	0.00 461	0.00 455	0.00 456	0.00 455	98.07 106	0.00 456	0.00 455	0.00 454	0.00 452

sosnet-low-res		0.00 424	0.00 427	0.00 437	0.00 460	0.00 462	0.00 448	0.00 461	0.00 455	0.00 456	0.00 455	0.00 460	0.00 456	0.00 455	0.00 454	0.00 452

sosnet		0.00 424	0.00 427	0.00 437	0.00 460	0.00 462	0.00 448	0.00 461	0.00 455	0.00 456	0.00 455	0.00 460	0.00 456	0.00 455	0.00 454	0.00 452

uncertanet		0.00 424	0.00 427	0.00 437	0.00 460	0.00 462	0.00 448	0.00 461	0.00 455	0.00 456	0.00 455	0.00 460	0.00 456	0.00 455	0.00 454	0.00 452

Regformer		0.00 424	0.00 427	0.00 437	0.00 460	0.00 462	0.00 448	0.00 461	0.00 455	0.00 456	0.00 455	0.00 460	0.00 456	0.00 455	0.00 454	0.00 452

ab-mvs-re		8.12 423	10.83 426	0.00 437	0.00 460	0.00 462	0.00 448	0.00 461	0.00 455	0.00 456	97.48 370	0.00 460	0.00 456	0.00 455	0.00 454	0.00 452

uanet		0.00 424	0.00 427	0.00 437	0.00 460	0.00 462	0.00 448	0.00 461	0.00 455	0.00 456	0.00 455	0.00 460	0.00 456	0.00 455	0.00 454	0.00 452

WAC-MVS						90.90 410								91.37 407

PC_three_1452									93.27 394	99.40 107	98.54 287	98.22 92	97.00 445	95.17 323	99.45 268	99.49 156

test_241102_TWO								99.30 197	98.03 193	99.26 137	99.02 184	97.51 156	99.88 109	96.91 222	99.60 223	99.66 74

test_0728_THIRD									98.17 185	99.08 159	99.02 184	97.89 122	99.88 109	97.07 210	99.71 179	99.70 64

GSMVS																98.81 330

sam_mvs1												84.74 392				98.81 330

sam_mvs												84.29 398

MTGPA								99.20 229

test_post1							97.59 262				20.48 454	83.07 406	99.66 311	94.16 350

test_post											21.25 453	83.86 401	99.70 284

patchmatchnet-post											98.77 248	84.37 395	99.85 149

MTMP							97.93 207	91.91 439

test9_res														93.28 376	99.15 316	99.38 212

agg_prior2														92.50 392	99.16 314	99.37 214

test_prior4						97.97 159	95.86 377

test_prior2							95.74 383		96.48 313	96.11 394	97.63 362	95.92 250		94.16 350	99.20 308

旧先验2							95.76 382		88.56 434	97.52 332			99.66 311	94.48 340

新几何2							95.93 373

无先验							95.74 383	98.74 320	89.38 430				99.73 272	92.38 394		99.22 259

原ACMM2							95.53 389

testdata2													99.79 231	92.80 386

segment_acmp												97.02 187

testdata1							95.44 394		96.32 319

plane_prior5								99.27 212					99.70 284	94.42 344	99.51 254	99.45 181

plane_prior4											97.98 341

plane_prior3						97.78 184			97.41 251	97.79 313

plane_prior2							97.77 232		98.20 182

plane_prior						97.65 193	97.07 307		96.72 303						99.36 280

n2								0.00 461

nn								0.00 461

door-mid								99.57 78

test11								98.87 293

door								99.41 149

HQP5-MVS						96.79 245

BP-MVS														92.82 384

HQP4-MVS										95.56 404			99.54 357			99.32 234

HQP3-MVS								99.04 265							99.26 298

HQP2-MVS												93.84 304

MDTV_nov1_ep13_2view						74.92 455	97.69 243		90.06 428	97.75 316		85.78 384		93.52 370		98.69 348

ACMMP++_ref															99.77 147

ACMMP++															99.68 194

Test By Simon												96.52 217

High-resolution multi-view benchmark