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		99.95 1	99.95 1	99.95 1	99.99 1	99.99 1	99.95 2	99.97 21	99.99 3	100.00 1	99.98 13	99.78 23	100.00 1	99.92 30	100.00 1	99.87 45

ANet_high		99.88 6	99.87 11	99.91 3	99.99 1	99.91 4	99.65 62	100.00 1	99.90 49	100.00 1	99.97 14	99.61 41	99.97 44	99.75 56	100.00 1	99.84 55

test_fmvsmconf0.01_n		99.89 3	99.88 7	99.91 3	99.98 3	99.76 70	99.12 244	100.00 1	100.00 1	99.99 7	99.91 31	99.98 1	100.00 1	99.97 4	100.00 1	99.99 2

test_vis3_rt		99.89 3	99.90 4	99.87 26	99.98 3	99.75 79	99.70 38	100.00 1	99.73 112	100.00 1	99.89 41	99.79 22	99.88 240	99.98 1	100.00 1	99.98 5

Gipuma		99.57 102	99.59 96	99.49 244	99.98 3	99.71 101	99.72 33	99.84 105	99.81 91	99.94 48	99.78 133	98.91 167	99.71 441	98.41 282	99.95 116	99.05 427
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_fmvsmconf0.1_n		99.87 9	99.86 13	99.91 3	99.97 6	99.74 87	99.01 285	99.99 12	99.99 3	99.98 14	99.88 50	99.97 2	99.99 7	99.96 9	100.00 1	99.98 5

test_fmvs3		99.83 21	99.93 2	99.53 232	99.96 7	98.62 376	99.67 53	100.00 1	99.95 32	100.00 1	99.95 16	99.85 14	99.99 7	99.98 1	99.99 19	99.98 5

test_f		99.75 49	99.88 7	99.37 295	99.96 7	98.21 410	99.51 101	100.00 1	99.94 36	100.00 1	99.93 22	99.58 50	99.94 98	99.97 4	99.99 19	99.97 10

anonymousdsp		99.80 30	99.77 45	99.90 8	99.96 7	99.88 12	99.73 30	99.85 95	99.70 129	99.92 59	99.93 22	99.45 63	99.97 44	99.36 119	100.00 1	99.85 50

v7n		99.82 24	99.80 32	99.88 19	99.96 7	99.84 26	99.82 10	99.82 122	99.84 75	99.94 48	99.91 31	99.13 120	99.96 69	99.83 46	99.99 19	99.83 59

PS-MVSNAJss		99.84 17	99.82 25	99.89 11	99.96 7	99.77 63	99.68 48	99.85 95	99.95 32	99.98 14	99.92 27	99.28 93	99.98 26	99.75 56	100.00 1	99.94 18

jajsoiax		99.89 3	99.89 6	99.89 11	99.96 7	99.78 57	99.70 38	99.86 89	99.89 55	99.98 14	99.90 36	99.94 4	99.98 26	99.75 56	100.00 1	99.90 30

mvs_tets		99.90 2	99.90 4	99.90 8	99.96 7	99.79 54	99.72 33	99.88 74	99.92 45	99.98 14	99.93 22	99.94 4	99.98 26	99.77 55	100.00 1	99.92 25

OurMVSNet-221017-0		99.75 49	99.71 56	99.84 38	99.96 7	99.83 33	99.83 7	99.85 95	99.80 95	99.93 53	99.93 22	98.54 225	99.93 120	99.59 78	99.98 54	99.76 86

fmvsm_s_conf0.1_n_a		99.85 12	99.83 21	99.91 3	99.95 15	99.82 41	99.10 253	99.98 13	99.99 3	99.98 14	99.91 31	99.68 33	99.93 120	99.93 25	99.99 19	99.99 2

test_fmvs1_n		99.68 64	99.81 28	99.28 329	99.95 15	97.93 433	99.49 107	100.00 1	99.82 85	99.99 7	99.89 41	99.21 105	99.98 26	99.97 4	99.98 54	99.93 21

mvsany_test3		99.85 12	99.88 7	99.75 98	99.95 15	99.37 231	99.53 92	99.98 13	99.77 107	99.99 7	99.95 16	99.85 14	99.94 98	99.95 14	99.98 54	99.94 18

test_vis1_n		99.68 64	99.79 34	99.36 301	99.94 18	98.18 413	99.52 94	100.00 1	99.86 65	100.00 1	99.88 50	98.99 151	99.96 69	99.97 4	99.96 91	99.95 15

testf1		99.63 86	99.60 93	99.72 122	99.94 18	99.95 2	99.47 112	99.89 68	99.43 216	99.88 82	99.80 108	99.26 97	99.90 203	98.81 228	99.88 202	99.32 354

APD_test2		99.63 86	99.60 93	99.72 122	99.94 18	99.95 2	99.47 112	99.89 68	99.43 216	99.88 82	99.80 108	99.26 97	99.90 203	98.81 228	99.88 202	99.32 354

pmmvs6		99.86 10	99.86 13	99.83 41	99.94 18	99.90 7	99.83 7	99.91 57	99.85 71	99.94 48	99.95 16	99.73 27	99.90 203	99.65 70	99.97 77	99.69 119

test_djsdf		99.84 17	99.81 28	99.91 3	99.94 18	99.84 26	99.77 19	99.80 143	99.73 112	99.97 24	99.92 27	99.77 25	99.98 26	99.43 106	100.00 1	99.90 30

MIMVSNet1		99.66 77	99.62 85	99.80 64	99.94 18	99.87 15	99.69 45	99.77 170	99.78 102	99.93 53	99.89 41	97.94 302	99.92 153	99.65 70	99.98 54	99.62 188

fmvsm_s_conf0.1_n_2		99.81 28	99.78 39	99.89 11	99.93 24	99.76 70	98.92 317	99.98 13	99.99 3	99.99 7	99.88 50	99.43 67	99.94 98	99.94 20	99.99 19	99.99 2

fmvsm_s_conf0.1_n		99.86 10	99.85 17	99.89 11	99.93 24	99.78 57	99.07 266	99.98 13	99.99 3	99.98 14	99.90 36	99.88 11	99.92 153	99.93 25	99.99 19	99.98 5

test_cas_vis1_n_1920		99.76 46	99.86 13	99.45 259	99.93 24	98.40 398	99.30 167	99.98 13	99.94 36	99.99 7	99.89 41	99.80 21	99.97 44	99.96 9	99.97 77	99.97 10

test_vis1_n_1920		99.72 53	99.88 7	99.27 334	99.93 24	97.84 437	99.34 149	100.00 1	99.99 3	99.99 7	99.82 91	99.87 13	99.99 7	99.97 4	99.99 19	99.97 10

K. test v3		98.87 322	98.60 335	99.69 139	99.93 24	99.46 197	99.74 27	94.97 539	99.78 102	99.88 82	99.88 50	93.66 446	99.97 44	99.61 76	99.95 116	99.64 170

mvs5depth		99.88 6	99.91 3	99.80 64	99.92 29	99.42 212	99.94 3	100.00 1	99.97 25	99.89 72	99.99 12	99.63 37	99.97 44	99.87 44	99.99 19	100.00 1

SixPastTwentyTwo		99.42 163	99.30 188	99.76 87	99.92 29	99.67 120	99.70 38	99.14 440	99.65 155	99.89 72	99.90 36	96.20 397	99.94 98	99.42 111	99.92 158	99.67 135

test_fmvsmconf_n		99.85 12	99.84 20	99.88 19	99.91 31	99.73 90	98.97 304	99.98 13	99.99 3	99.96 34	99.85 68	99.93 7	99.99 7	99.94 20	99.99 19	99.93 21

test_fmvs2		99.72 53	99.85 17	99.34 309	99.91 31	98.08 424	99.48 109	100.00 1	99.90 49	99.99 7	99.91 31	99.50 62	99.98 26	99.98 1	99.99 19	99.96 13

pm-mvs1		99.79 34	99.79 34	99.78 76	99.91 31	99.83 33	99.76 23	99.87 80	99.73 112	99.89 72	99.87 56	99.63 37	99.87 256	99.54 87	99.92 158	99.63 176

TransMVSNet (Re)		99.78 37	99.77 45	99.81 54	99.91 31	99.85 21	99.75 25	99.86 89	99.70 129	99.91 62	99.89 41	99.60 44	99.87 256	99.59 78	99.74 310	99.71 104

Baseline_NR-MVSNet		99.49 132	99.37 164	99.82 46	99.91 31	99.84 26	98.83 334	99.86 89	99.68 135	99.65 227	99.88 50	97.67 323	99.87 256	99.03 191	99.86 224	99.76 86

LTVRE_ROB	99.19 1	99.88 6	99.87 11	99.88 19	99.91 31	99.90 7	99.96 1	99.92 47	99.90 49	99.97 24	99.87 56	99.81 20	99.95 81	99.54 87	99.99 19	99.80 67
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
dtuonlycased		99.24 220	99.47 132	98.56 435	99.90 37	96.17 495	97.62 479	99.85 95	99.66 150	99.86 96	99.50 345	99.39 71	99.93 120	99.55 85	99.85 231	99.59 215

PVSNet_Blended_VisFu		99.40 172	99.38 161	99.44 263	99.90 37	98.66 366	98.94 313	99.91 57	97.97 428	99.79 133	99.73 176	99.05 143	99.97 44	99.15 164	99.99 19	99.68 126

TDRefinement		99.72 53	99.70 57	99.77 80	99.90 37	99.85 21	99.86 6	99.92 47	99.69 132	99.78 139	99.92 27	99.37 78	99.88 240	98.93 213	99.95 116	99.60 208

KinetiMVS		99.66 77	99.63 82	99.76 87	99.89 40	99.57 168	99.37 140	99.82 122	99.95 32	99.90 67	99.63 265	98.57 216	99.97 44	99.65 70	99.94 135	99.74 91

APD_test1		99.36 189	99.28 197	99.61 191	99.89 40	99.89 10	99.32 158	99.74 189	99.18 262	99.69 201	99.75 163	98.41 249	99.84 312	97.85 335	99.70 332	99.10 407

EGC-MVSNET		89.05 512	85.52 515	99.64 167	99.89 40	99.78 57	99.56 87	99.52 336	24.19 549	49.96 551	99.83 83	99.15 115	99.92 153	97.71 351	99.85 231	99.21 378

Anonymous20240521		99.44 155	99.42 152	99.49 244	99.89 40	98.96 323	99.62 67	99.76 178	99.85 71	99.82 112	99.88 50	96.39 386	99.97 44	99.59 78	99.98 54	99.55 236

UniMVSNet_ETH3D		99.85 12	99.83 21	99.90 8	99.89 40	99.91 4	99.89 5	99.71 207	99.93 43	99.95 45	99.89 41	99.71 28	99.96 69	99.51 93	99.97 77	99.84 55

XXY-MVS		99.71 56	99.67 65	99.81 54	99.89 40	99.72 95	99.59 80	99.82 122	99.39 226	99.82 112	99.84 76	99.38 76	99.91 184	99.38 115	99.93 149	99.80 67

sc_t1		99.81 28	99.80 32	99.82 46	99.88 46	99.88 12	99.83 7	99.79 152	99.94 36	99.93 53	99.92 27	99.35 84	99.92 153	99.64 73	99.94 135	99.68 126

fmvsm_l_conf0.5_n_3		99.85 12	99.83 21	99.92 2	99.88 46	99.86 18	99.08 261	99.97 21	99.98 18	99.96 34	99.79 120	99.90 9	99.99 7	99.96 9	99.99 19	99.90 30

fmvsm_l_conf0.5_n_a		99.80 30	99.79 34	99.84 38	99.88 46	99.64 136	99.12 244	99.91 57	99.98 18	99.95 45	99.67 234	99.67 34	99.99 7	99.94 20	99.99 19	99.88 41

fmvsm_l_conf0.5_n		99.80 30	99.78 39	99.85 32	99.88 46	99.66 123	99.11 249	99.91 57	99.98 18	99.96 34	99.64 249	99.60 44	99.99 7	99.95 14	99.99 19	99.88 41

test_fmvsmvis_n_1920		99.84 17	99.86 13	99.81 54	99.88 46	99.55 173	99.17 219	99.98 13	99.99 3	99.96 34	99.84 76	99.96 3	99.99 7	99.96 9	99.99 19	99.88 41

FC-MVSNet-test		99.70 57	99.65 74	99.86 30	99.88 46	99.86 18	99.72 33	99.78 165	99.90 49	99.82 112	99.83 83	98.45 244	99.87 256	99.51 93	99.97 77	99.86 47

EU-MVSNet		99.39 176	99.62 85	98.72 421	99.88 46	96.44 487	99.56 87	99.85 95	99.90 49	99.90 67	99.85 68	98.09 290	99.83 335	99.58 81	99.95 116	99.90 30

CHOSEN 1792x2688		99.39 176	99.30 188	99.65 160	99.88 46	99.25 259	98.78 346	99.88 74	98.66 352	99.96 34	99.79 120	97.45 336	99.93 120	99.34 123	99.99 19	99.78 77

Vis-MVSNet		99.75 49	99.74 53	99.79 72	99.88 46	99.66 123	99.69 45	99.92 47	99.67 143	99.77 151	99.75 163	99.61 41	99.98 26	99.35 122	99.98 54	99.72 99
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
E5new		99.68 64	99.67 65	99.70 133	99.87 55	99.62 144	99.41 122	99.84 105	99.68 135	99.77 151	99.81 98	99.59 46	99.78 393	99.13 174	99.96 91	99.70 107

E5		99.68 64	99.67 65	99.70 133	99.87 55	99.62 144	99.41 122	99.84 105	99.68 135	99.77 151	99.81 98	99.59 46	99.78 393	99.13 174	99.96 91	99.70 107

tt0805		99.63 86	99.57 105	99.81 54	99.87 55	99.88 12	99.58 82	98.70 467	99.72 116	99.91 62	99.60 295	99.43 67	99.81 375	99.81 51	99.53 395	99.73 95

tfpnnormal		99.43 159	99.38 161	99.60 195	99.87 55	99.75 79	99.59 80	99.78 165	99.71 122	99.90 67	99.69 215	98.85 175	99.90 203	97.25 403	99.78 286	99.15 395

SteuartSystems-ACMMP		99.30 204	99.14 223	99.76 87	99.87 55	99.66 123	99.18 214	99.60 284	98.55 366	99.57 266	99.67 234	99.03 146	99.94 98	97.01 418	99.80 272	99.69 119
Skip Steuart: Steuart Systems R&D Blog.
ELoFTR		99.25 216	99.26 202	99.21 346	99.86 60	98.66 366	99.00 291	99.93 43	98.56 364	99.83 110	99.83 83	97.34 342	99.92 153	99.03 191	100.00 1	99.04 429

casdiffseed414692147		99.68 64	99.68 63	99.67 145	99.86 60	99.65 129	99.32 158	99.87 80	99.75 110	99.77 151	99.80 108	99.61 41	99.68 464	99.21 146	99.95 116	99.67 135

usedtu_dtu_shiyan2		99.44 155	99.33 180	99.78 76	99.86 60	99.76 70	99.54 90	99.79 152	99.66 150	99.66 223	99.79 120	96.76 370	99.96 69	99.15 164	99.72 325	99.62 188

E6new		99.68 64	99.67 65	99.70 133	99.86 60	99.62 144	99.41 122	99.84 105	99.68 135	99.77 151	99.81 98	99.59 46	99.78 393	99.13 174	99.96 91	99.70 107

E6		99.68 64	99.67 65	99.70 133	99.86 60	99.62 144	99.41 122	99.84 105	99.68 135	99.77 151	99.81 98	99.59 46	99.78 393	99.13 174	99.96 91	99.70 107

FE-MVSNET2		99.68 64	99.67 65	99.72 122	99.86 60	99.68 117	99.46 116	99.88 74	99.62 164	99.87 92	99.85 68	99.06 141	99.85 295	99.44 104	99.98 54	99.63 176

viewdifsd2359ckpt11		99.62 94	99.64 79	99.56 214	99.86 60	99.19 280	99.02 280	99.93 43	99.83 81	99.88 82	99.81 98	98.99 151	99.83 335	99.48 97	99.96 91	99.65 158

viewmsd2359difaftdt		99.62 94	99.64 79	99.56 214	99.86 60	99.19 280	99.02 280	99.93 43	99.83 81	99.88 82	99.81 98	98.99 151	99.83 335	99.48 97	99.96 91	99.65 158

fmvsm_l_conf0.5_n_9		99.83 21	99.81 28	99.89 11	99.86 60	99.80 51	98.94 313	99.96 30	99.98 18	99.96 34	99.78 133	99.88 11	99.98 26	99.96 9	99.99 19	99.90 30

Elysia		99.69 59	99.65 74	99.81 54	99.86 60	99.72 95	99.34 149	99.77 170	99.94 36	99.91 62	99.76 155	98.55 220	99.99 7	99.70 61	99.98 54	99.72 99

StellarMVS		99.69 59	99.65 74	99.81 54	99.86 60	99.72 95	99.34 149	99.77 170	99.94 36	99.91 62	99.76 155	98.55 220	99.99 7	99.70 61	99.98 54	99.72 99

SSC-MVS		99.52 122	99.42 152	99.83 41	99.86 60	99.65 129	99.52 94	99.81 135	99.87 62	99.81 119	99.79 120	96.78 369	99.99 7	99.83 46	99.51 399	99.86 47

lessismore_v0				99.64 167	99.86 60	99.38 226		90.66 549		99.89 72	99.83 83	94.56 433	99.97 44	99.56 83	99.92 158	99.57 228

ACMH+	98.40 8	99.50 127	99.43 149	99.71 128	99.86 60	99.76 70	99.32 158	99.77 170	99.53 186	99.77 151	99.76 155	99.26 97	99.78 393	97.77 342	99.88 202	99.60 208

ACMH	98.42 6	99.59 101	99.54 116	99.72 122	99.86 60	99.62 144	99.56 87	99.79 152	98.77 339	99.80 126	99.85 68	99.64 35	99.85 295	98.70 251	99.89 191	99.70 107
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
hybridcas		99.65 83	99.63 82	99.70 133	99.85 75	99.67 120	99.30 167	99.87 80	99.67 143	99.81 119	99.77 145	99.21 105	99.81 375	99.24 139	99.94 135	99.61 203

AstraMVS		99.15 257	99.06 251	99.42 270	99.85 75	98.59 379	99.13 239	97.26 521	99.84 75	99.87 92	99.77 145	96.11 399	99.93 120	99.71 60	99.96 91	99.74 91

mmtdpeth		99.78 37	99.83 21	99.66 153	99.85 75	99.05 308	99.79 15	99.97 21	100.00 1	99.43 318	99.94 19	99.64 35	99.94 98	99.83 46	99.99 19	99.98 5

fmvsm_s_conf0.5_n_a		99.82 24	99.79 34	99.89 11	99.85 75	99.82 41	99.03 276	99.96 30	99.99 3	99.97 24	99.84 76	99.58 50	99.93 120	99.92 30	99.98 54	99.93 21

fmvsm_s_conf0.5_n		99.83 21	99.81 28	99.87 26	99.85 75	99.78 57	99.03 276	99.96 30	99.99 3	99.97 24	99.84 76	99.78 23	99.92 153	99.92 30	99.99 19	99.92 25

HyFIR lowres test		98.91 314	98.64 331	99.73 113	99.85 75	99.47 189	98.07 441	99.83 115	98.64 355	99.89 72	99.60 295	92.57 460	100.00 1	99.33 126	99.97 77	99.72 99

Casviewmamba		99.63 86	99.60 93	99.73 113	99.84 81	99.72 95	99.36 144	99.87 80	99.67 143	99.74 176	99.73 176	99.07 134	99.83 335	99.14 171	99.93 149	99.62 188

E4		99.61 98	99.59 96	99.66 153	99.84 81	99.53 176	99.08 261	99.84 105	99.65 155	99.74 176	99.80 108	99.45 63	99.77 406	98.93 213	99.95 116	99.69 119

viewmacassd2359aftdt		99.63 86	99.61 89	99.68 141	99.84 81	99.61 154	99.14 232	99.87 80	99.71 122	99.75 165	99.77 145	99.54 55	99.72 436	98.91 216	99.96 91	99.70 107

FE-MVSNET		99.45 151	99.36 169	99.71 128	99.84 81	99.64 136	99.16 225	99.91 57	98.65 353	99.73 182	99.73 176	98.54 225	99.82 358	98.71 249	99.96 91	99.67 135

guyue		99.12 264	99.02 267	99.41 280	99.84 81	98.56 382	99.19 210	98.30 495	99.82 85	99.84 104	99.75 163	94.84 427	99.92 153	99.68 66	99.94 135	99.74 91

KD-MVS_self_test		99.63 86	99.59 96	99.76 87	99.84 81	99.90 7	99.37 140	99.79 152	99.83 81	99.88 82	99.85 68	98.42 248	99.90 203	99.60 77	99.73 317	99.49 282

FIs		99.65 83	99.58 100	99.84 38	99.84 81	99.85 21	99.66 57	99.75 183	99.86 65	99.74 176	99.79 120	98.27 269	99.85 295	99.37 118	99.93 149	99.83 59

XVG-OURS-SEG-HR		99.16 253	98.99 284	99.66 153	99.84 81	99.64 136	98.25 419	99.73 194	98.39 385	99.63 238	99.43 366	99.70 31	99.90 203	97.34 388	98.64 489	99.44 312

PMVS	92.94 21	98.82 328	98.81 315	98.85 406	99.84 81	97.99 427	99.20 204	99.47 353	99.71 122	99.42 321	99.82 91	98.09 290	99.47 511	93.88 522	99.85 231	99.07 425
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
fmvsm_s_conf0.5_n_9		99.82 24	99.82 25	99.82 46	99.83 90	99.59 160	98.97 304	99.92 47	99.99 3	99.97 24	99.84 76	99.90 9	99.94 98	99.94 20	99.99 19	99.92 25

LuminaMVS		99.39 176	99.28 197	99.73 113	99.83 90	99.49 184	99.00 291	99.05 447	99.81 91	99.89 72	99.79 120	96.54 379	99.97 44	99.64 73	99.98 54	99.73 95

FOURS1					99.83 90	99.89 10	99.74 27	99.71 207	99.69 132	99.63 238

MP-MVS-pluss		99.14 258	98.92 299	99.80 64	99.83 90	99.83 33	98.61 368	99.63 261	96.84 492	99.44 314	99.58 308	98.81 177	99.91 184	97.70 354	99.82 255	99.67 135
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
PM-MVS		99.36 189	99.29 194	99.58 202	99.83 90	99.66 123	98.95 311	99.86 89	98.85 321	99.81 119	99.73 176	98.40 253	99.92 153	98.36 285	99.83 245	99.17 391

PEN-MVS		99.66 77	99.59 96	99.89 11	99.83 90	99.87 15	99.66 57	99.73 194	99.70 129	99.84 104	99.73 176	98.56 219	99.96 69	99.29 134	99.94 135	99.83 59

HPM-MVS_fast		99.43 159	99.30 188	99.80 64	99.83 90	99.81 47	99.52 94	99.70 216	98.35 395	99.51 297	99.50 345	99.31 89	99.88 240	98.18 303	99.84 237	99.69 119

RPSCF		99.18 246	99.02 267	99.64 167	99.83 90	99.85 21	99.44 119	99.82 122	98.33 401	99.50 300	99.78 133	97.90 304	99.65 482	96.78 435	99.83 245	99.44 312

COLMAP_ROB	98.06 12	99.45 151	99.37 164	99.70 133	99.83 90	99.70 109	99.38 132	99.78 165	99.53 186	99.67 216	99.78 133	99.19 108	99.86 276	97.32 390	99.87 216	99.55 236
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
DKM-HiRes		98.95 309	98.73 321	99.62 184	99.82 99	99.47 189	98.50 392	99.81 135	99.41 221	97.76 505	99.58 308	95.04 424	99.83 335	98.89 217	99.76 295	99.58 221

tt0320-xc		99.82 24	99.82 25	99.82 46	99.82 99	99.84 26	99.82 10	99.92 47	99.94 36	99.94 48	99.93 22	99.34 85	99.92 153	99.70 61	99.96 91	99.70 107

tt0320		99.79 34	99.79 34	99.81 54	99.82 99	99.84 26	99.82 10	99.90 64	99.94 36	99.94 48	99.94 19	99.07 134	99.92 153	99.68 66	99.97 77	99.67 135

fmvsm_s_conf0.5_n_8		99.76 46	99.72 55	99.88 19	99.82 99	99.75 79	99.02 280	99.87 80	99.98 18	99.98 14	99.81 98	99.07 134	99.97 44	99.91 33	99.99 19	99.92 25

fmvsm_s_conf0.5_n_2		99.78 37	99.75 51	99.88 19	99.82 99	99.76 70	98.88 322	99.92 47	99.98 18	99.98 14	99.85 68	99.42 69	99.94 98	99.93 25	99.98 54	99.94 18

test_fmvsm_n_1920		99.84 17	99.85 17	99.83 41	99.82 99	99.70 109	99.17 219	99.97 21	99.99 3	99.96 34	99.82 91	99.94 4	100.00 1	99.95 14	100.00 1	99.80 67

TSAR-MVS + MP.		99.34 196	99.24 208	99.63 175	99.82 99	99.37 231	99.26 186	99.35 390	98.77 339	99.57 266	99.70 206	99.27 96	99.88 240	97.71 351	99.75 303	99.65 158
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
new-patchmatchnet		99.35 191	99.57 105	98.71 425	99.82 99	96.62 483	98.55 383	99.75 183	99.50 191	99.88 82	99.87 56	99.31 89	99.88 240	99.43 106	100.00 1	99.62 188

VPNet		99.46 147	99.37 164	99.71 128	99.82 99	99.59 160	99.48 109	99.70 216	99.81 91	99.69 201	99.58 308	97.66 327	99.86 276	99.17 159	99.44 411	99.67 135

XVG-OURS		99.21 237	99.06 251	99.65 160	99.82 99	99.62 144	97.87 463	99.74 189	98.36 389	99.66 223	99.68 228	99.71 28	99.90 203	96.84 432	99.88 202	99.43 318

XVG-ACMP-BASELINE		99.23 223	99.10 241	99.63 175	99.82 99	99.58 165	98.83 334	99.72 203	98.36 389	99.60 258	99.71 196	98.92 164	99.91 184	97.08 416	99.84 237	99.40 327

LPG-MVS_test		99.22 232	99.05 258	99.74 103	99.82 99	99.63 142	99.16 225	99.73 194	97.56 455	99.64 233	99.69 215	99.37 78	99.89 225	96.66 442	99.87 216	99.69 119

LGP-MVS_train				99.74 103	99.82 99	99.63 142		99.73 194	97.56 455	99.64 233	99.69 215	99.37 78	99.89 225	96.66 442	99.87 216	99.69 119

RoMa-HiRes		99.38 179	99.30 188	99.64 167	99.81 112	99.47 189	99.11 249	99.94 41	99.03 291	99.55 279	99.56 320	97.71 318	99.92 153	99.19 152	99.77 290	99.54 248

PMatch-Up-SfM		99.08 274	99.02 267	99.27 334	99.81 112	99.04 310	98.13 432	99.83 115	99.16 271	99.26 367	99.69 215	97.22 348	99.83 335	98.67 256	99.43 415	98.94 447

fmvsm_s_conf0.5_n_11		99.76 46	99.75 51	99.81 54	99.81 112	99.53 176	99.15 228	99.89 68	99.99 3	99.98 14	99.86 63	99.13 120	99.98 26	99.93 25	99.99 19	99.92 25

fmvsm_s_conf0.5_n_10		99.77 44	99.73 54	99.88 19	99.81 112	99.75 79	99.06 267	99.85 95	99.99 3	99.97 24	99.84 76	99.12 123	99.98 26	99.95 14	99.99 19	99.90 30

fmvsm_s_conf0.5_n_3		99.79 34	99.77 45	99.85 32	99.81 112	99.71 101	98.97 304	99.92 47	99.98 18	99.97 24	99.86 63	99.53 58	99.95 81	99.88 41	99.99 19	99.89 38

WB-MVS		99.44 155	99.32 181	99.80 64	99.81 112	99.61 154	99.47 112	99.81 135	99.82 85	99.71 193	99.72 186	96.60 375	99.98 26	99.75 56	99.23 444	99.82 66

MTAPA		99.35 191	99.20 213	99.80 64	99.81 112	99.81 47	99.33 155	99.53 331	99.27 245	99.42 321	99.63 265	98.21 277	99.95 81	97.83 341	99.79 278	99.65 158

v10		99.69 59	99.69 60	99.66 153	99.81 112	99.39 224	99.66 57	99.75 183	99.60 176	99.92 59	99.87 56	98.75 190	99.86 276	99.90 37	99.99 19	99.73 95

HPM-MVS		99.25 216	99.07 249	99.78 76	99.81 112	99.75 79	99.61 73	99.67 234	97.72 450	99.35 342	99.25 423	99.23 103	99.92 153	97.21 406	99.82 255	99.67 135
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
casdiffmvs_mvg		99.68 64	99.68 63	99.69 139	99.81 112	99.59 160	99.29 175	99.90 64	99.71 122	99.79 133	99.73 176	99.54 55	99.84 312	99.36 119	99.96 91	99.65 158
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
IterMVS-LS		99.41 170	99.47 132	99.25 341	99.81 112	98.09 421	98.85 328	99.76 178	99.62 164	99.83 110	99.64 249	98.54 225	99.97 44	99.15 164	99.99 19	99.68 126
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
viewdifsd2359ckpt07		99.51 124	99.50 125	99.52 234	99.80 123	99.19 280	98.92 317	99.88 74	99.72 116	99.64 233	99.62 275	99.06 141	99.81 375	98.96 204	99.94 135	99.56 232

diffmvs_AUTHOR		99.48 135	99.48 130	99.47 252	99.80 123	98.89 337	98.71 359	99.82 122	99.79 99	99.66 223	99.63 265	98.87 173	99.88 240	99.13 174	99.95 116	99.62 188

SDMVSNet		99.77 44	99.77 45	99.76 87	99.80 123	99.65 129	99.63 64	99.86 89	99.97 25	99.89 72	99.89 41	99.52 60	99.99 7	99.42 111	99.96 91	99.65 158

sd_testset		99.78 37	99.78 39	99.80 64	99.80 123	99.76 70	99.80 14	99.79 152	99.97 25	99.89 72	99.89 41	99.53 58	99.99 7	99.36 119	99.96 91	99.65 158

v1240		99.56 106	99.58 100	99.51 238	99.80 123	99.00 313	99.00 291	99.65 249	99.15 276	99.90 67	99.75 163	99.09 127	99.88 240	99.90 37	99.96 91	99.67 135

v8		99.68 64	99.69 60	99.65 160	99.80 123	99.40 220	99.66 57	99.76 178	99.64 159	99.93 53	99.85 68	98.66 204	99.84 312	99.88 41	99.99 19	99.71 104

MDA-MVSNet-bldmvs		99.06 279	99.05 258	99.07 371	99.80 123	97.83 438	98.89 320	99.72 203	99.29 241	99.63 238	99.70 206	96.47 381	99.89 225	98.17 305	99.82 255	99.50 277

PS-CasMVS		99.66 77	99.58 100	99.89 11	99.80 123	99.85 21	99.66 57	99.73 194	99.62 164	99.84 104	99.71 196	98.62 208	99.96 69	99.30 131	99.96 91	99.86 47

DTE-MVSNet		99.68 64	99.61 89	99.88 19	99.80 123	99.87 15	99.67 53	99.71 207	99.72 116	99.84 104	99.78 133	98.67 202	99.97 44	99.30 131	99.95 116	99.80 67

WR-MVS_H		99.61 98	99.53 120	99.87 26	99.80 123	99.83 33	99.67 53	99.75 183	99.58 180	99.85 101	99.69 215	98.18 282	99.94 98	99.28 136	99.95 116	99.83 59

baseline		99.63 86	99.62 85	99.66 153	99.80 123	99.62 144	99.44 119	99.80 143	99.71 122	99.72 188	99.69 215	99.15 115	99.83 335	99.32 128	99.94 135	99.53 257

IS-MVSNet		99.03 287	98.85 308	99.55 221	99.80 123	99.25 259	99.73 30	99.15 438	99.37 228	99.61 255	99.71 196	94.73 430	99.81 375	97.70 354	99.88 202	99.58 221

EPP-MVSNet		99.17 251	99.00 277	99.66 153	99.80 123	99.43 209	99.70 38	99.24 422	99.48 196	99.56 274	99.77 145	94.89 426	99.93 120	98.72 247	99.89 191	99.63 176

ACMM	98.09 11	99.46 147	99.38 161	99.72 122	99.80 123	99.69 114	99.13 239	99.65 249	98.99 296	99.64 233	99.72 186	99.39 71	99.86 276	98.23 296	99.81 265	99.60 208
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PMatch-SfM		98.91 314	98.81 315	99.22 345	99.79 137	98.89 337	98.18 423	99.61 272	99.18 262	99.03 407	99.61 285	96.13 398	99.80 385	98.71 249	99.04 459	98.99 440

fmvsm_s_conf0.5_n_5		99.78 37	99.76 49	99.85 32	99.79 137	99.72 95	98.84 331	99.96 30	99.96 28	99.96 34	99.72 186	99.71 28	99.99 7	99.93 25	99.98 54	99.85 50

dcpmvs_2		99.61 98	99.64 79	99.53 232	99.79 137	98.82 348	99.58 82	99.97 21	99.95 32	99.96 34	99.76 155	98.44 245	99.99 7	99.34 123	99.96 91	99.78 77

v1144		99.54 116	99.53 120	99.59 198	99.79 137	99.28 250	99.10 253	99.61 272	99.20 259	99.84 104	99.73 176	98.67 202	99.84 312	99.86 45	99.98 54	99.64 170

V42		99.56 106	99.54 116	99.63 175	99.79 137	99.46 197	99.39 129	99.59 290	99.24 252	99.86 96	99.70 206	98.55 220	99.82 358	99.79 53	99.95 116	99.60 208

test20.03		99.55 111	99.54 116	99.58 202	99.79 137	99.37 231	99.02 280	99.89 68	99.60 176	99.82 112	99.62 275	98.81 177	99.89 225	99.43 106	99.86 224	99.47 290

casdiffmvs		99.63 86	99.61 89	99.67 145	99.79 137	99.59 160	99.13 239	99.85 95	99.79 99	99.76 160	99.72 186	99.33 87	99.82 358	99.21 146	99.94 135	99.59 215
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_0402		99.22 232	99.14 223	99.45 259	99.79 137	99.43 209	99.28 177	99.68 229	99.54 184	99.40 332	99.56 320	99.07 134	99.82 358	96.01 476	99.96 91	99.11 404

ACMMP		99.25 216	99.08 245	99.74 103	99.79 137	99.68 117	99.50 102	99.65 249	98.07 421	99.52 290	99.69 215	98.57 216	99.92 153	97.18 411	99.79 278	99.63 176
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
E2		99.54 116	99.51 122	99.62 184	99.78 146	99.47 189	99.01 285	99.82 122	99.55 182	99.69 201	99.77 145	99.26 97	99.76 413	98.82 224	99.93 149	99.62 188

E3		99.54 116	99.51 122	99.62 184	99.78 146	99.47 189	99.01 285	99.82 122	99.55 182	99.69 201	99.77 145	99.25 101	99.76 413	98.82 224	99.93 149	99.62 188

NormalMVS		99.09 273	98.91 303	99.62 184	99.78 146	99.11 295	99.36 144	99.77 170	99.82 85	99.68 208	99.53 334	93.30 449	99.99 7	99.24 139	99.76 295	99.74 91

lecture		99.56 106	99.48 130	99.81 54	99.78 146	99.86 18	99.50 102	99.70 216	99.59 178	99.75 165	99.71 196	98.94 160	99.92 153	98.59 264	99.76 295	99.66 149

fmvsm_s_conf0.5_n_6		99.80 30	99.78 39	99.85 32	99.78 146	99.78 57	99.00 291	99.97 21	99.96 28	99.97 24	99.56 320	99.92 8	99.93 120	99.91 33	99.99 19	99.83 59

MSP-MVS		99.04 286	98.79 319	99.81 54	99.78 146	99.73 90	99.35 148	99.57 302	98.54 369	99.54 283	98.99 466	96.81 368	99.93 120	96.97 421	99.53 395	99.77 81
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
v144192		99.55 111	99.54 116	99.58 202	99.78 146	99.20 277	99.11 249	99.62 264	99.18 262	99.89 72	99.72 186	98.66 204	99.87 256	99.88 41	99.97 77	99.66 149

AllTest		99.21 237	99.07 249	99.63 175	99.78 146	99.64 136	99.12 244	99.83 115	98.63 356	99.63 238	99.72 186	98.68 199	99.75 424	96.38 462	99.83 245	99.51 271

TestCases				99.63 175	99.78 146	99.64 136		99.83 115	98.63 356	99.63 238	99.72 186	98.68 199	99.75 424	96.38 462	99.83 245	99.51 271

v2v482		99.50 127	99.47 132	99.58 202	99.78 146	99.25 259	99.14 232	99.58 299	99.25 250	99.81 119	99.62 275	98.24 271	99.84 312	99.83 46	99.97 77	99.64 170

FMVSNet1		99.66 77	99.63 82	99.73 113	99.78 146	99.77 63	99.68 48	99.70 216	99.67 143	99.82 112	99.83 83	98.98 155	99.90 203	99.24 139	99.97 77	99.53 257

Vis-MVSNet (Re-imp)		98.77 334	98.58 340	99.34 309	99.78 146	98.88 339	99.61 73	99.56 307	99.11 282	99.24 372	99.56 320	93.00 456	99.78 393	97.43 383	99.89 191	99.35 343

ACMP	97.51 14	99.05 283	98.84 310	99.67 145	99.78 146	99.55 173	98.88 322	99.66 239	97.11 483	99.47 307	99.60 295	99.07 134	99.89 225	96.18 471	99.85 231	99.58 221
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
RoMa-SfM		99.32 201	99.23 211	99.59 198	99.77 159	99.53 176	98.89 320	99.88 74	98.78 336	99.65 227	99.52 338	97.78 314	99.90 203	98.96 204	99.86 224	99.35 343

pmmvs-eth3d		99.48 135	99.47 132	99.51 238	99.77 159	99.41 219	98.81 339	99.66 239	99.42 220	99.75 165	99.66 240	99.20 107	99.76 413	98.98 199	99.99 19	99.36 340

Patchmatch-RL test		98.60 353	98.36 372	99.33 312	99.77 159	99.07 305	98.27 416	99.87 80	98.91 313	99.74 176	99.72 186	90.57 494	99.79 389	98.55 269	99.85 231	99.11 404

v1192		99.57 102	99.57 105	99.57 210	99.77 159	99.22 270	99.04 273	99.60 284	99.18 262	99.87 92	99.72 186	99.08 131	99.85 295	99.89 40	99.98 54	99.66 149

EG-PatchMatch MVS		99.57 102	99.56 110	99.62 184	99.77 159	99.33 241	99.26 186	99.76 178	99.32 237	99.80 126	99.78 133	99.29 91	99.87 256	99.15 164	99.91 171	99.66 149

DenseAffine		99.17 251	99.06 251	99.49 244	99.76 164	99.33 241	98.43 404	99.97 21	99.11 282	99.17 386	99.61 285	97.05 358	99.76 413	98.56 268	99.88 202	99.38 333

dtuplus		99.52 122	99.55 112	99.43 267	99.76 164	98.90 334	98.71 359	99.89 68	99.67 143	99.79 133	99.77 145	99.25 101	99.81 375	99.18 155	99.96 91	99.57 228

MED-MVS test				99.74 103	99.76 164	99.65 129	99.38 132	99.78 165	99.58 180	99.81 119	99.66 240		99.90 203	97.69 360	99.79 278	99.67 135

MED-MVS		99.51 124	99.42 152	99.80 64	99.76 164	99.65 129	99.38 132	99.78 165	99.77 107	99.81 119	99.78 133	99.02 147	99.90 203	97.69 360	99.76 295	99.85 50

TestfortrainingZip a		99.55 111	99.45 141	99.85 32	99.76 164	99.82 41	99.38 132	99.62 264	99.77 107	99.87 92	99.78 133	98.12 287	99.88 240	98.96 204	99.77 290	99.85 50

SSM_0404		99.57 102	99.58 100	99.54 227	99.76 164	99.28 250	99.19 210	99.84 105	99.80 95	99.78 139	99.70 206	99.44 65	99.93 120	98.74 240	99.95 116	99.41 324

ttmdpeth		99.48 135	99.55 112	99.29 326	99.76 164	98.16 415	99.33 155	99.95 38	99.79 99	99.36 338	99.89 41	99.13 120	99.77 406	99.09 182	99.64 359	99.93 21

GeoE		99.69 59	99.66 72	99.78 76	99.76 164	99.76 70	99.60 79	99.82 122	99.46 204	99.75 165	99.56 320	99.63 37	99.95 81	99.43 106	99.88 202	99.62 188

ZNCC-MVS		99.22 232	99.04 264	99.77 80	99.76 164	99.73 90	99.28 177	99.56 307	98.19 411	99.14 392	99.29 413	98.84 176	99.92 153	97.53 377	99.80 272	99.64 170

tttt0517		97.62 433	97.20 447	98.90 401	99.76 164	97.40 460	99.48 109	94.36 541	99.06 288	99.70 197	99.49 350	84.55 523	99.94 98	98.73 245	99.65 357	99.36 340

pmmvs5		99.19 242	99.11 232	99.42 270	99.76 164	98.88 339	98.55 383	99.73 194	98.82 328	99.72 188	99.62 275	96.56 376	99.82 358	99.32 128	99.95 116	99.56 232

nrg030		99.70 57	99.66 72	99.82 46	99.76 164	99.84 26	99.61 73	99.70 216	99.93 43	99.78 139	99.68 228	99.10 125	99.78 393	99.45 103	99.96 91	99.83 59

v148		99.40 172	99.41 156	99.39 286	99.76 164	98.94 326	99.09 258	99.59 290	99.17 269	99.81 119	99.61 285	98.41 249	99.69 452	99.32 128	99.94 135	99.53 257

region2R		99.23 223	99.05 258	99.77 80	99.76 164	99.70 109	99.31 164	99.59 290	98.41 382	99.32 351	99.36 393	98.73 194	99.93 120	97.29 394	99.74 310	99.67 135

MP-MVS		99.06 279	98.83 312	99.76 87	99.76 164	99.71 101	99.32 158	99.50 345	98.35 395	98.97 412	99.48 354	98.37 255	99.92 153	95.95 482	99.75 303	99.63 176
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PMMVS2		99.48 135	99.45 141	99.57 210	99.76 164	98.99 315	98.09 438	99.90 64	98.95 303	99.78 139	99.58 308	99.57 52	99.93 120	99.48 97	99.95 116	99.79 75

CP-MVSNet		99.54 116	99.43 149	99.87 26	99.76 164	99.82 41	99.57 85	99.61 272	99.54 184	99.80 126	99.64 249	97.79 313	99.95 81	99.21 146	99.94 135	99.84 55

mPP-MVS		99.19 242	99.00 277	99.76 87	99.76 164	99.68 117	99.38 132	99.54 320	98.34 399	99.01 409	99.50 345	98.53 230	99.93 120	97.18 411	99.78 286	99.66 149

viewmamba		99.49 132	99.51 122	99.42 270	99.75 182	98.90 334	98.85 328	99.85 95	99.69 132	99.73 182	99.67 234	98.79 182	99.82 358	99.28 136	99.95 116	99.54 248

hybridnocas07		99.43 159	99.44 146	99.39 286	99.75 182	98.85 345	98.76 348	99.85 95	99.71 122	99.70 197	99.68 228	98.47 239	99.77 406	99.13 174	99.95 116	99.55 236

hybrid		99.42 163	99.43 149	99.37 295	99.75 182	98.77 355	98.72 356	99.84 105	99.61 169	99.65 227	99.68 228	98.53 230	99.79 389	99.16 163	99.94 135	99.54 248

fmvsm_s_conf0.5_n_4		99.78 37	99.78 39	99.79 72	99.75 182	99.56 169	98.98 302	99.94 41	99.92 45	99.97 24	99.72 186	99.84 16	99.92 153	99.91 33	99.98 54	99.89 38

SSC-MVS3.2		99.64 85	99.67 65	99.56 214	99.75 182	98.98 317	98.96 308	99.87 80	99.88 60	99.84 104	99.64 249	99.32 88	99.91 184	99.78 54	99.96 91	99.80 67

IterMVS-SCA-FT		99.00 299	99.16 218	98.51 436	99.75 182	95.90 501	98.07 441	99.84 105	99.84 75	99.89 72	99.73 176	96.01 402	99.99 7	99.33 126	100.00 1	99.63 176

ACMMP_NAP		99.28 208	99.11 232	99.79 72	99.75 182	99.81 47	98.95 311	99.53 331	98.27 406	99.53 288	99.73 176	98.75 190	99.87 256	97.70 354	99.83 245	99.68 126

v1921920		99.56 106	99.57 105	99.55 221	99.75 182	99.11 295	99.05 268	99.61 272	99.15 276	99.88 82	99.71 196	99.08 131	99.87 256	99.90 37	99.97 77	99.66 149

testgi		99.29 206	99.26 202	99.37 295	99.75 182	98.81 349	98.84 331	99.89 68	98.38 387	99.75 165	99.04 459	99.36 81	99.86 276	99.08 184	99.25 440	99.45 297

PGM-MVS		99.20 239	99.01 273	99.77 80	99.75 182	99.71 101	99.16 225	99.72 203	97.99 426	99.42 321	99.60 295	98.81 177	99.93 120	96.91 425	99.74 310	99.66 149

jason		99.16 253	99.11 232	99.32 317	99.75 182	98.44 395	98.26 418	99.39 379	98.70 347	99.74 176	99.30 409	98.54 225	99.97 44	98.48 274	99.82 255	99.55 236
jason: jason.
fmvsm_s_conf0.5_n_7		99.73 52	99.78 39	99.60 195	99.74 193	98.93 329	98.85 328	99.96 30	99.96 28	99.97 24	99.76 155	99.82 18	99.96 69	99.95 14	99.98 54	99.90 30

Anonymous20231206		99.35 191	99.31 183	99.47 252	99.74 193	99.06 307	99.28 177	99.74 189	99.23 254	99.72 188	99.53 334	97.63 331	99.88 240	99.11 180	99.84 237	99.48 286

ACMMPR		99.23 223	99.06 251	99.76 87	99.74 193	99.69 114	99.31 164	99.59 290	98.36 389	99.35 342	99.38 384	98.61 210	99.93 120	97.43 383	99.75 303	99.67 135

IterMVS		98.97 303	99.16 218	98.42 441	99.74 193	95.64 506	98.06 443	99.83 115	99.83 81	99.85 101	99.74 171	96.10 401	99.99 7	99.27 138	100.00 1	99.63 176
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
viewcassd2359sk11		99.48 135	99.45 141	99.58 202	99.73 197	99.42 212	98.96 308	99.80 143	99.44 209	99.63 238	99.74 171	99.09 127	99.76 413	98.72 247	99.91 171	99.57 228

viewmanbaseed2359cas		99.50 127	99.47 132	99.61 191	99.73 197	99.52 181	99.03 276	99.83 115	99.49 193	99.65 227	99.64 249	99.18 109	99.71 441	98.73 245	99.92 158	99.58 221

GST-MVS		99.16 253	98.96 291	99.75 98	99.73 197	99.73 90	99.20 204	99.55 314	98.22 408	99.32 351	99.35 398	98.65 206	99.91 184	96.86 428	99.74 310	99.62 188

HFP-MVS		99.25 216	99.08 245	99.76 87	99.73 197	99.70 109	99.31 164	99.59 290	98.36 389	99.36 338	99.37 388	98.80 181	99.91 184	97.43 383	99.75 303	99.68 126

114514_t		98.49 369	98.11 398	99.64 167	99.73 197	99.58 165	99.24 193	99.76 178	89.94 540	99.42 321	99.56 320	97.76 317	99.86 276	97.74 347	99.82 255	99.47 290

dtuonly		98.93 313	99.11 232	98.38 444	99.72 202	95.75 504	97.07 508	99.91 57	99.04 289	99.65 227	99.41 370	98.32 263	99.83 335	98.97 201	99.90 175	99.55 236

viewdifsd2359ckpt13		99.42 163	99.37 164	99.57 210	99.72 202	99.46 197	99.01 285	99.80 143	99.20 259	99.51 297	99.60 295	98.92 164	99.70 445	98.65 260	99.90 175	99.55 236

UA-Net		99.78 37	99.76 49	99.86 30	99.72 202	99.71 101	99.91 4	99.95 38	99.96 28	99.71 193	99.91 31	99.15 115	99.97 44	99.50 95	100.00 1	99.90 30

N_pmnet		98.73 339	98.53 347	99.35 305	99.72 202	98.67 363	98.34 409	94.65 540	98.35 395	99.79 133	99.68 228	98.03 294	99.93 120	98.28 291	99.92 158	99.44 312

DeepC-MVS	98.90 4	99.62 94	99.61 89	99.67 145	99.72 202	99.44 205	99.24 193	99.71 207	99.27 245	99.93 53	99.90 36	99.70 31	99.93 120	98.99 197	99.99 19	99.64 170
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DKM		99.12 264	98.98 287	99.54 227	99.71 207	99.48 188	98.53 388	99.88 74	99.18 262	98.99 411	99.64 249	96.25 394	99.75 424	98.66 257	99.93 149	99.40 327

mamba_0408		99.54 116	99.55 112	99.54 227	99.71 207	99.24 264	99.27 181	99.79 152	99.72 116	99.78 139	99.64 249	99.36 81	99.93 120	98.74 240	99.90 175	99.45 297

icg_test_0407_2		99.30 204	99.29 194	99.31 321	99.71 207	98.55 384	98.17 426	99.71 207	99.41 221	99.73 182	99.60 295	99.17 111	99.92 153	98.45 277	99.70 332	99.45 297

SSM_04072		99.55 111	99.55 112	99.55 221	99.71 207	99.24 264	99.27 181	99.79 152	99.72 116	99.78 139	99.64 249	99.36 81	99.97 44	98.74 240	99.90 175	99.45 297

SSM_0407		99.56 106	99.56 110	99.54 227	99.71 207	99.24 264	99.15 228	99.84 105	99.80 95	99.78 139	99.70 206	99.44 65	99.93 120	98.74 240	99.90 175	99.45 297

IMVS_0407		99.38 179	99.42 152	99.28 329	99.71 207	98.55 384	99.27 181	99.71 207	99.41 221	99.73 182	99.60 295	99.17 111	99.83 335	98.45 277	99.70 332	99.45 297

IMVS_0404		99.23 223	99.20 213	99.32 317	99.71 207	98.55 384	98.57 379	99.71 207	99.41 221	99.52 290	99.60 295	98.12 287	99.95 81	98.45 277	99.70 332	99.45 297

IMVS_0403		99.37 184	99.39 158	99.28 329	99.71 207	98.55 384	99.19 210	99.71 207	99.41 221	99.67 216	99.60 295	99.12 123	99.84 312	98.45 277	99.70 332	99.45 297

test_vis1_rt		99.45 151	99.46 138	99.41 280	99.71 207	98.63 375	98.99 299	99.96 30	99.03 291	99.95 45	99.12 448	98.75 190	99.84 312	99.82 50	99.82 255	99.77 81

XVS		99.27 212	99.11 232	99.75 98	99.71 207	99.71 101	99.37 140	99.61 272	99.29 241	98.76 439	99.47 358	98.47 239	99.88 240	97.62 368	99.73 317	99.67 135

X-MVStestdata		96.09 486	94.87 501	99.75 98	99.71 207	99.71 101	99.37 140	99.61 272	99.29 241	98.76 439	61.30 558	98.47 239	99.88 240	97.62 368	99.73 317	99.67 135

VDDNet		98.97 303	98.82 313	99.42 270	99.71 207	98.81 349	99.62 67	98.68 468	99.81 91	99.38 335	99.80 108	94.25 437	99.85 295	98.79 231	99.32 429	99.59 215

DSMNet-mixed		99.48 135	99.65 74	98.95 384	99.71 207	97.27 465	99.50 102	99.82 122	99.59 178	99.41 327	99.85 68	99.62 40	100.00 1	99.53 90	99.89 191	99.59 215

EC-MVSNet		99.69 59	99.69 60	99.68 141	99.71 207	99.91 4	99.76 23	99.96 30	99.86 65	99.51 297	99.39 381	99.57 52	99.93 120	99.64 73	99.86 224	99.20 383

CSCG		99.37 184	99.29 194	99.60 195	99.71 207	99.46 197	99.43 121	99.85 95	98.79 334	99.41 327	99.60 295	98.92 164	99.92 153	98.02 314	99.92 158	99.43 318

LF4IMVS		99.01 296	98.92 299	99.27 334	99.71 207	99.28 250	98.59 373	99.77 170	98.32 402	99.39 334	99.41 370	98.62 208	99.84 312	96.62 448	99.84 237	98.69 472

LoFTR		99.29 206	99.26 202	99.36 301	99.70 223	99.05 308	98.66 364	99.95 38	98.85 321	99.86 96	99.75 163	98.14 284	99.93 120	98.54 271	99.91 171	99.10 407

SIFT-PointCN		98.28 388	98.47 354	97.71 477	99.70 223	98.91 333	96.98 512	99.70 216	97.90 436	99.36 338	99.35 398	95.51 415	99.83 335	97.84 340	99.89 191	94.39 532

viewdifsd2359ckpt09		99.24 220	99.16 218	99.49 244	99.70 223	99.22 270	98.88 322	99.81 135	98.70 347	99.38 335	99.37 388	98.22 276	99.76 413	98.48 274	99.88 202	99.51 271

viewmambaseed2359dif		99.47 145	99.50 125	99.37 295	99.70 223	98.80 352	98.67 362	99.92 47	99.49 193	99.77 151	99.71 196	99.08 131	99.78 393	99.20 150	99.94 135	99.54 248

patch_mono-2		99.51 124	99.46 138	99.64 167	99.70 223	99.11 295	99.04 273	99.87 80	99.71 122	99.47 307	99.79 120	98.24 271	99.98 26	99.38 115	99.96 91	99.83 59

test_0728_SECOND				99.83 41	99.70 223	99.79 54	99.14 232	99.61 272					99.92 153	97.88 328	99.72 325	99.77 81

OPM-MVS		99.26 214	99.13 225	99.63 175	99.70 223	99.61 154	98.58 375	99.48 350	98.50 374	99.52 290	99.63 265	99.14 118	99.76 413	97.89 327	99.77 290	99.51 271
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
new_pmnet		98.88 321	98.89 304	98.84 408	99.70 223	97.62 447	98.15 429	99.50 345	97.98 427	99.62 248	99.54 331	98.15 283	99.94 98	97.55 374	99.84 237	98.95 444

onestephybrid01		99.45 151	99.46 138	99.42 270	99.69 231	98.88 339	98.76 348	99.81 135	99.78 102	99.67 216	99.73 176	98.61 210	99.84 312	99.17 159	99.93 149	99.52 268

SED-MVS		99.40 172	99.28 197	99.77 80	99.69 231	99.82 41	99.20 204	99.54 320	99.13 278	99.82 112	99.63 265	98.91 167	99.92 153	97.85 335	99.70 332	99.58 221

IU-MVS					99.69 231	99.77 63		99.22 426	97.50 461	99.69 201				97.75 346	99.70 332	99.77 81

test_241102_ONE					99.69 231	99.82 41		99.54 320	99.12 281	99.82 112	99.49 350	98.91 167	99.52 507

D2MVS		99.22 232	99.19 215	99.29 326	99.69 231	98.74 358	98.81 339	99.41 369	98.55 366	99.68 208	99.69 215	98.13 285	99.87 256	98.82 224	99.98 54	99.24 370

DVP-MVS		99.32 201	99.17 217	99.77 80	99.69 231	99.80 51	99.14 232	99.31 405	99.16 271	99.62 248	99.61 285	98.35 257	99.91 184	97.88 328	99.72 325	99.61 203
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
test0726					99.69 231	99.80 51	99.24 193	99.57 302	99.16 271	99.73 182	99.65 247	98.35 257

wuyk23d		97.58 435	99.13 225	92.93 528	99.69 231	99.49 184	99.52 94	99.77 170	97.97 428	99.96 34	99.79 120	99.84 16	99.94 98	95.85 486	99.82 255	79.36 546

DeepMVS_CX				97.98 462	99.69 231	96.95 473		99.26 415	75.51 546	95.74 536	98.28 512	96.47 381	99.62 487	91.23 530	97.89 518	97.38 521

E3new		99.42 163	99.37 164	99.56 214	99.68 240	99.38 226	98.93 316	99.79 152	99.30 240	99.55 279	99.69 215	98.88 171	99.76 413	98.63 262	99.89 191	99.53 257

MVSMamba_PlusPlus		99.55 111	99.58 100	99.47 252	99.68 240	99.40 220	99.52 94	99.70 216	99.92 45	99.77 151	99.86 63	98.28 267	99.96 69	99.54 87	99.90 175	99.05 427

thisisatest0530		97.45 443	96.95 457	98.94 385	99.68 240	97.73 443	99.09 258	94.19 543	98.61 361	99.56 274	99.30 409	84.30 525	99.93 120	98.27 292	99.54 393	99.16 393

VPA-MVSNet		99.66 77	99.62 85	99.79 72	99.68 240	99.75 79	99.62 67	99.69 225	99.85 71	99.80 126	99.81 98	98.81 177	99.91 184	99.47 100	99.88 202	99.70 107

UnsupCasMVSNet_eth		98.83 327	98.57 341	99.59 198	99.68 240	99.45 203	98.99 299	99.67 234	99.48 196	99.55 279	99.36 393	94.92 425	99.86 276	98.95 211	96.57 531	99.45 297

Test_1112_low_res		98.95 309	98.73 321	99.63 175	99.68 240	99.15 289	98.09 438	99.80 143	97.14 481	99.46 311	99.40 376	96.11 399	99.89 225	99.01 196	99.84 237	99.84 55

MVE	92.54 22	96.66 468	96.11 475	98.31 450	99.68 240	97.55 449	97.94 457	95.60 538	99.37 228	90.68 546	98.70 495	96.56 376	98.61 537	86.94 543	99.55 388	98.77 468
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
SIFT-NCMNet		98.18 400	98.46 356	97.36 492	99.67 247	99.19 280	96.33 530	98.99 453	98.83 326	99.62 248	99.63 265	95.41 419	99.33 517	97.64 366	100.00 1	93.54 544

VortexMVS		99.13 261	99.24 208	98.79 414	99.67 247	96.60 485	99.24 193	99.80 143	99.85 71	99.93 53	99.84 76	95.06 423	99.89 225	99.80 52	99.98 54	99.89 38

diffmvs		99.34 196	99.32 181	99.39 286	99.67 247	98.77 355	98.57 379	99.81 135	99.61 169	99.48 305	99.41 370	98.47 239	99.86 276	98.97 201	99.90 175	99.53 257
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
our_test_3		98.85 326	99.09 243	98.13 458	99.66 250	94.90 519	97.72 471	99.58 299	99.07 286	99.64 233	99.62 275	98.19 280	99.93 120	98.41 282	99.95 116	99.55 236

ppachtmachnet_test		98.89 320	99.12 229	98.20 456	99.66 250	95.24 515	97.63 477	99.68 229	99.08 284	99.78 139	99.62 275	98.65 206	99.88 240	98.02 314	99.96 91	99.48 286

CP-MVS		99.23 223	99.05 258	99.75 98	99.66 250	99.66 123	99.38 132	99.62 264	98.38 387	99.06 404	99.27 417	98.79 182	99.94 98	97.51 378	99.82 255	99.66 149

1112_ss		99.05 283	98.84 310	99.67 145	99.66 250	99.29 248	98.52 390	99.82 122	97.65 453	99.43 318	99.16 441	96.42 383	99.91 184	99.07 187	99.84 237	99.80 67

SIFT-PCN-Cal		98.24 393	98.51 349	97.43 487	99.65 254	98.64 373	97.09 505	99.35 390	98.16 413	99.69 201	99.52 338	95.59 410	99.83 335	97.57 373	100.00 1	93.81 540

SymmetryMVS		99.01 296	98.82 313	99.58 202	99.65 254	99.11 295	99.36 144	99.20 432	99.82 85	99.68 208	99.53 334	93.30 449	99.99 7	99.24 139	99.63 362	99.64 170

test-260524					99.64 256	99.70 109		99.58 299		99.69 201		97.64 330	99.87 256	98.68 254	99.76 295

SIFT-NN-NCMNet		97.22 452	97.27 444	97.07 505	99.64 256	99.20 277	96.53 526	95.91 530	96.91 489	97.38 513	98.95 475	96.01 402	98.29 540	94.87 506	99.21 446	93.73 542

PDCNetPlus		98.55 360	98.50 352	98.69 426	99.64 256	96.12 496	97.67 476	100.00 1	98.34 399	99.79 133	99.75 163	92.45 466	99.98 26	98.92 215	99.99 19	99.96 13

YYNet1		98.95 309	98.99 284	98.84 408	99.64 256	97.14 470	98.22 421	99.32 401	98.92 312	99.59 261	99.66 240	97.40 338	99.83 335	98.27 292	99.90 175	99.55 236

MDA-MVSNet_test_wron		98.95 309	98.99 284	98.85 406	99.64 256	97.16 468	98.23 420	99.33 399	98.93 309	99.56 274	99.66 240	97.39 340	99.83 335	98.29 290	99.88 202	99.55 236

test_one_0601					99.63 261	99.76 70		99.55 314	99.23 254	99.31 356	99.61 285	98.59 213

thres100view900		96.39 476	96.03 477	97.47 484	99.63 261	95.93 500	99.18 214	97.57 514	98.75 343	98.70 445	97.31 533	87.04 512	99.67 470	87.62 539	98.51 494	96.81 525

thres600view7		96.60 470	96.16 474	97.93 465	99.63 261	96.09 499	99.18 214	97.57 514	98.77 339	98.72 442	97.32 532	87.04 512	99.72 436	88.57 535	98.62 490	97.98 511

ITE_SJBPF				99.38 290	99.63 261	99.44 205		99.73 194	98.56 364	99.33 348	99.53 334	98.88 171	99.68 464	96.01 476	99.65 357	99.02 437

ArgMatch-Sym		99.06 279	98.96 291	99.35 305	99.62 265	99.22 270	98.34 409	99.79 152	98.80 332	99.50 300	99.29 413	98.30 265	99.75 424	97.30 393	99.71 329	99.08 419

test_part2					99.62 265	99.67 120				99.55 279

SIFT-CM-Cal		97.96 418	98.15 395	97.39 489	99.61 267	99.15 289	96.75 521	98.41 489	98.04 423	99.03 407	99.54 331	95.24 422	99.41 514	96.97 421	99.80 272	93.61 543

Anonymous20231211		99.62 94	99.57 105	99.76 87	99.61 267	99.60 158	99.81 13	99.73 194	99.82 85	99.90 67	99.90 36	97.97 301	99.86 276	99.42 111	99.96 91	99.80 67

CPTT-MVS		98.74 337	98.44 361	99.64 167	99.61 267	99.38 226	99.18 214	99.55 314	96.49 497	99.27 363	99.37 388	97.11 356	99.92 153	95.74 492	99.67 352	99.62 188

ME-MVS		99.26 214	99.10 241	99.73 113	99.60 270	99.65 129	98.75 352	99.45 361	99.31 239	99.65 227	99.66 240	98.00 300	99.86 276	97.69 360	99.79 278	99.67 135

reproduce_model		99.50 127	99.40 157	99.83 41	99.60 270	99.83 33	99.12 244	99.68 229	99.49 193	99.80 126	99.79 120	99.01 148	99.93 120	98.24 295	99.82 255	99.73 95

test1111		97.74 427	98.16 394	96.49 517	99.60 270	89.86 552	99.71 37	91.21 548	99.89 55	99.88 82	99.87 56	93.73 445	99.90 203	99.56 83	99.99 19	99.70 107

h-mvs33		98.61 350	98.34 375	99.44 263	99.60 270	98.67 363	99.27 181	99.44 362	99.68 135	99.32 351	99.49 350	92.50 464	100.00 1	99.24 139	96.51 536	99.65 158

MSDG		99.08 274	98.98 287	99.37 295	99.60 270	99.13 292	97.54 482	99.74 189	98.84 325	99.53 288	99.55 329	99.10 125	99.79 389	97.07 417	99.86 224	99.18 388

FPMVS		96.32 479	95.50 488	98.79 414	99.60 270	98.17 414	98.46 401	98.80 463	97.16 480	96.28 531	99.63 265	82.19 526	99.09 527	88.45 536	98.89 473	99.10 407

ArgMatch-SfM		99.14 258	99.06 251	99.36 301	99.59 276	99.14 291	98.45 402	99.81 135	98.67 351	99.50 300	99.42 368	98.55 220	99.84 312	97.85 335	99.73 317	99.11 404

SIFT-UM-Cal		98.18 400	98.45 359	97.37 491	99.59 276	98.95 324	96.76 520	99.39 379	98.39 385	99.46 311	99.31 406	96.23 396	99.24 521	97.21 406	99.70 332	93.90 539

SIFT-NN-PointCN		97.97 416	98.24 385	97.14 503	99.59 276	98.71 360	96.75 521	99.56 307	97.02 486	97.91 495	99.27 417	96.85 367	98.39 539	97.47 380	99.76 295	94.31 533

usedtu_dtu_shiyan1		98.87 322	98.71 324	99.35 305	99.59 276	98.88 339	97.17 501	99.64 257	98.94 304	99.27 363	99.22 432	95.57 412	99.83 335	99.08 184	99.92 158	99.35 343

FE-MVSNET3		98.87 322	98.71 324	99.35 305	99.59 276	98.88 339	97.17 501	99.64 257	98.94 304	99.27 363	99.22 432	95.57 412	99.83 335	99.08 184	99.92 158	99.35 343

test2506		94.73 505	94.59 505	95.15 525	99.59 276	85.90 554	99.75 25	74.01 556	99.89 55	99.71 193	99.86 63	79.00 538	99.90 203	99.52 91	99.99 19	99.65 158

ECVR-MVS		97.73 428	98.04 402	96.78 509	99.59 276	90.81 546	99.72 33	90.43 550	99.89 55	99.86 96	99.86 63	93.60 447	99.89 225	99.46 101	99.99 19	99.65 158

xiu_mvs_v1_base_debu		99.23 223	99.34 175	98.91 395	99.59 276	98.23 407	98.47 397	99.66 239	99.61 169	99.68 208	98.94 476	99.39 71	99.97 44	99.18 155	99.55 388	98.51 484

xiu_mvs_v1_base		99.23 223	99.34 175	98.91 395	99.59 276	98.23 407	98.47 397	99.66 239	99.61 169	99.68 208	98.94 476	99.39 71	99.97 44	99.18 155	99.55 388	98.51 484

xiu_mvs_v1_base_debi		99.23 223	99.34 175	98.91 395	99.59 276	98.23 407	98.47 397	99.66 239	99.61 169	99.68 208	98.94 476	99.39 71	99.97 44	99.18 155	99.55 388	98.51 484

SF-MVS		99.10 272	98.93 295	99.62 184	99.58 286	99.51 182	99.13 239	99.65 249	97.97 428	99.42 321	99.61 285	98.86 174	99.87 256	96.45 459	99.68 346	99.49 282

tfpn200view9		96.30 480	95.89 479	97.53 479	99.58 286	96.11 497	99.00 291	97.54 517	98.43 379	98.52 460	96.98 538	86.85 514	99.67 470	87.62 539	98.51 494	96.81 525

EI-MVSNet		99.38 179	99.44 146	99.21 346	99.58 286	98.09 421	99.26 186	99.46 356	99.62 164	99.75 165	99.67 234	98.54 225	99.85 295	99.15 164	99.92 158	99.68 126

CVMVSNet		98.61 350	98.88 305	97.80 471	99.58 286	93.60 529	99.26 186	99.64 257	99.66 150	99.72 188	99.67 234	93.26 451	99.93 120	99.30 131	99.81 265	99.87 45

thres400		96.40 475	95.89 479	97.92 466	99.58 286	96.11 497	99.00 291	97.54 517	98.43 379	98.52 460	96.98 538	86.85 514	99.67 470	87.62 539	98.51 494	97.98 511

MCST-MVS		99.02 290	98.81 315	99.65 160	99.58 286	99.49 184	98.58 375	99.07 444	98.40 384	99.04 406	99.25 423	98.51 236	99.80 385	97.31 391	99.51 399	99.65 158

HQP_MVS		98.90 317	98.68 329	99.55 221	99.58 286	99.24 264	98.80 342	99.54 320	98.94 304	99.14 392	99.25 423	97.24 346	99.82 358	95.84 487	99.78 286	99.60 208

plane_prior7					99.58 286	99.38 226

TranMVSNet+NR-MVSNet		99.54 116	99.47 132	99.76 87	99.58 286	99.64 136	99.30 167	99.63 261	99.61 169	99.71 193	99.56 320	98.76 188	99.96 69	99.14 171	99.92 158	99.68 126

MVS_111021_LR		99.13 261	99.03 266	99.42 270	99.58 286	99.32 244	97.91 461	99.73 194	98.68 349	99.31 356	99.48 354	99.09 127	99.66 475	97.70 354	99.77 290	99.29 364

SIFT-NCM-Cal		98.18 400	98.41 365	97.48 482	99.57 296	99.28 250	97.26 497	98.08 500	98.30 404	99.23 373	99.39 381	97.13 354	99.04 530	96.86 428	99.86 224	94.12 536

SIFT-NN-UMatch		97.18 454	97.24 446	97.01 506	99.57 296	98.65 370	96.33 530	97.31 520	97.07 484	97.48 512	98.73 492	94.39 435	98.87 533	95.75 491	98.50 497	93.50 545

SIFT-UMatch		98.07 409	98.27 383	97.46 486	99.57 296	98.99 315	96.93 516	99.02 449	98.53 370	99.26 367	99.23 431	95.43 418	99.31 518	96.51 452	99.91 171	94.09 537

DPE-MVS		99.14 258	98.92 299	99.82 46	99.57 296	99.77 63	98.74 353	99.60 284	98.55 366	99.76 160	99.69 215	98.23 275	99.92 153	96.39 461	99.75 303	99.76 86
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SPE-MVS-test		99.68 64	99.70 57	99.64 167	99.57 296	99.83 33	99.78 17	99.97 21	99.92 45	99.50 300	99.38 384	99.57 52	99.95 81	99.69 64	99.90 175	99.15 395

EI-MVSNet-UG-set		99.48 135	99.50 125	99.42 270	99.57 296	98.65 370	99.24 193	99.46 356	99.68 135	99.80 126	99.66 240	98.99 151	99.89 225	99.19 152	99.90 175	99.72 99

EI-MVSNet-Vis-set		99.47 145	99.49 129	99.42 270	99.57 296	98.66 366	99.24 193	99.46 356	99.67 143	99.79 133	99.65 247	98.97 157	99.89 225	99.15 164	99.89 191	99.71 104

pmmvs4		99.13 261	99.06 251	99.36 301	99.57 296	99.10 302	98.01 447	99.25 418	98.78 336	99.58 263	99.44 365	98.24 271	99.76 413	98.74 240	99.93 149	99.22 375

MVSFormer		99.41 170	99.44 146	99.31 321	99.57 296	98.40 398	99.77 19	99.80 143	99.73 112	99.63 238	99.30 409	98.02 295	99.98 26	99.43 106	99.69 341	99.55 236

lupinMVS		98.96 306	98.87 306	99.24 343	99.57 296	98.40 398	98.12 434	99.18 434	98.28 405	99.63 238	99.13 444	98.02 295	99.97 44	98.22 297	99.69 341	99.35 343

ab-mvs		99.33 199	99.28 197	99.47 252	99.57 296	99.39 224	99.78 17	99.43 366	98.87 318	99.57 266	99.82 91	98.06 293	99.87 256	98.69 253	99.73 317	99.15 395

DP-MVS		99.48 135	99.39 158	99.74 103	99.57 296	99.62 144	99.29 175	99.61 272	99.87 62	99.74 176	99.76 155	98.69 198	99.87 256	98.20 299	99.80 272	99.75 89

F-COLMAP		98.74 337	98.45 359	99.62 184	99.57 296	99.47 189	98.84 331	99.65 249	96.31 501	98.93 416	99.19 440	97.68 322	99.87 256	96.52 451	99.37 422	99.53 257

CLD-MVS		98.76 335	98.57 341	99.33 312	99.57 296	98.97 320	97.53 484	99.55 314	96.41 498	99.27 363	99.13 444	99.07 134	99.78 393	96.73 438	99.89 191	99.23 373
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MatchFormer		99.03 287	99.02 267	99.08 370	99.56 310	98.47 391	98.57 379	99.90 64	98.13 415	99.80 126	99.75 163	98.34 259	99.84 312	97.18 411	99.90 175	98.92 450

reproduce-ours		99.46 147	99.35 173	99.82 46	99.56 310	99.83 33	99.05 268	99.65 249	99.45 207	99.78 139	99.78 133	98.93 161	99.93 120	98.11 309	99.81 265	99.70 107

our_new_method		99.46 147	99.35 173	99.82 46	99.56 310	99.83 33	99.05 268	99.65 249	99.45 207	99.78 139	99.78 133	98.93 161	99.93 120	98.11 309	99.81 265	99.70 107

UnsupCasMVSNet_bld		98.55 360	98.27 383	99.40 283	99.56 310	99.37 231	97.97 455	99.68 229	97.49 462	99.08 400	99.35 398	95.41 419	99.82 358	97.70 354	98.19 508	99.01 438

dmvs_re		98.69 344	98.48 353	99.31 321	99.55 314	99.42 212	99.54 90	98.38 491	99.32 237	98.72 442	98.71 493	96.76 370	99.21 522	96.01 476	99.35 425	99.31 359

APDe-MVS		99.48 135	99.36 169	99.85 32	99.55 314	99.81 47	99.50 102	99.69 225	98.99 296	99.75 165	99.71 196	98.79 182	99.93 120	98.46 276	99.85 231	99.80 67
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SIFT-NN-CMatch		97.30 450	97.34 440	97.18 499	99.54 316	98.85 345	96.02 532	95.77 537	97.05 485	97.55 511	98.70 495	96.35 389	98.75 535	95.82 489	99.26 438	93.95 538

SIFT-ConvMatch		98.16 404	98.37 370	97.52 480	99.54 316	99.20 277	96.97 513	98.47 483	98.09 419	99.14 392	99.40 376	95.93 405	99.05 529	97.87 331	99.92 158	94.31 533

SD_0403		97.42 445	96.90 461	98.98 380	99.54 316	97.90 435	99.52 94	99.54 320	99.34 233	97.87 498	98.85 483	98.72 195	99.64 484	78.93 547	99.83 245	99.40 327

test_fmvs1		99.48 135	99.65 74	98.97 381	99.54 316	97.16 468	99.11 249	99.98 13	99.78 102	99.96 34	99.81 98	98.72 195	99.97 44	99.95 14	99.97 77	99.79 75

SR-MVS-dyc-post		99.27 212	99.11 232	99.73 113	99.54 316	99.74 87	99.26 186	99.62 264	99.16 271	99.52 290	99.64 249	98.41 249	99.91 184	97.27 397	99.61 372	99.54 248

RE-MVS-def			99.13 225		99.54 316	99.74 87	99.26 186	99.62 264	99.16 271	99.52 290	99.64 249	98.57 216		97.27 397	99.61 372	99.54 248

PVSNet_BlendedMVS		99.03 287	99.01 273	99.09 365	99.54 316	97.99 427	98.58 375	99.82 122	97.62 454	99.34 346	99.71 196	98.52 234	99.77 406	97.98 319	99.97 77	99.52 268

PVSNet_Blended		98.70 343	98.59 337	99.02 376	99.54 316	97.99 427	97.58 481	99.82 122	95.70 510	99.34 346	98.98 469	98.52 234	99.77 406	97.98 319	99.83 245	99.30 361

USDC		98.96 306	98.93 295	99.05 374	99.54 316	97.99 427	97.07 508	99.80 143	98.21 409	99.75 165	99.77 145	98.43 246	99.64 484	97.90 326	99.88 202	99.51 271

GDP-MVS		98.81 330	98.57 341	99.50 240	99.53 325	99.12 294	99.28 177	99.86 89	99.53 186	99.57 266	99.32 403	90.88 487	99.98 26	99.46 101	99.74 310	99.42 323

BP-MVS1		98.72 340	98.46 356	99.50 240	99.53 325	99.00 313	99.34 149	98.53 478	99.65 155	99.73 182	99.38 384	90.62 492	99.96 69	99.50 95	99.86 224	99.55 236

save fliter					99.53 325	99.25 259	98.29 415	99.38 384	99.07 286

CS-MVS		99.67 76	99.70 57	99.58 202	99.53 325	99.84 26	99.79 15	99.96 30	99.90 49	99.61 255	99.41 370	99.51 61	99.95 81	99.66 69	99.89 191	98.96 442

Anonymous20240529		99.42 163	99.34 175	99.65 160	99.53 325	99.60 158	99.63 64	99.39 379	99.47 201	99.76 160	99.78 133	98.13 285	99.86 276	98.70 251	99.68 346	99.49 282

APD-MVS_3200maxsize		99.31 203	99.16 218	99.74 103	99.53 325	99.75 79	99.27 181	99.61 272	99.19 261	99.57 266	99.64 249	98.76 188	99.90 203	97.29 394	99.62 364	99.56 232

MIMVSNet		98.43 376	98.20 389	99.11 362	99.53 325	98.38 402	99.58 82	98.61 473	98.96 300	99.33 348	99.76 155	90.92 484	99.81 375	97.38 386	99.76 295	99.15 395

HPM-MVS++		98.96 306	98.70 328	99.74 103	99.52 332	99.71 101	98.86 326	99.19 433	98.47 378	98.59 454	99.06 456	98.08 292	99.91 184	96.94 423	99.60 375	99.60 208

GA-MVS		97.99 415	97.68 429	98.93 389	99.52 332	98.04 425	97.19 500	99.05 447	98.32 402	98.81 432	98.97 471	89.89 502	99.41 514	98.33 288	99.05 457	99.34 349

SR-MVS		99.19 242	99.00 277	99.74 103	99.51 334	99.72 95	99.18 214	99.60 284	98.85 321	99.47 307	99.58 308	98.38 254	99.92 153	96.92 424	99.54 393	99.57 228

test222					99.51 334	99.08 304	97.83 465	99.29 409	95.21 517	98.68 446	99.31 406	97.28 345			99.38 420	99.43 318

testdata				99.42 270	99.51 334	98.93 329		99.30 408	96.20 502	98.87 426	99.40 376	98.33 262	99.89 225	96.29 465	99.28 434	99.44 312

plane_prior1					99.51 334

UniMVSNet (Re)		99.37 184	99.26 202	99.68 141	99.51 334	99.58 165	98.98 302	99.60 284	99.43 216	99.70 197	99.36 393	97.70 319	99.88 240	99.20 150	99.87 216	99.59 215

DELS-MVS		99.34 196	99.30 188	99.48 250	99.51 334	99.36 235	98.12 434	99.53 331	99.36 232	99.41 327	99.61 285	99.22 104	99.87 256	99.21 146	99.68 346	99.20 383
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
新几何1				99.52 234	99.50 340	99.22 270		99.26 415	95.66 511	98.60 453	99.28 415	97.67 323	99.89 225	95.95 482	99.32 429	99.45 297

SD-MVS		99.01 296	99.30 188	98.15 457	99.50 340	99.40 220	98.94 313	99.61 272	99.22 258	99.75 165	99.82 91	99.54 55	95.51 548	97.48 379	99.87 216	99.54 248
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
CDPH-MVS		98.56 359	98.20 389	99.61 191	99.50 340	99.46 197	98.32 413	99.41 369	95.22 516	99.21 379	99.10 452	98.34 259	99.82 358	95.09 505	99.66 355	99.56 232

APD-MVS		98.87 322	98.59 337	99.71 128	99.50 340	99.62 144	99.01 285	99.57 302	96.80 494	99.54 283	99.63 265	98.29 266	99.91 184	95.24 501	99.71 329	99.61 203
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_HR		99.12 264	99.02 267	99.40 283	99.50 340	99.11 295	97.92 459	99.71 207	98.76 342	99.08 400	99.47 358	99.17 111	99.54 501	97.85 335	99.76 295	99.54 248

旧先验1					99.49 345	99.29 248		99.26 415			99.39 381	97.67 323			99.36 423	99.46 295

GBi-Net		99.42 163	99.31 183	99.73 113	99.49 345	99.77 63	99.68 48	99.70 216	99.44 209	99.62 248	99.83 83	97.21 349	99.90 203	98.96 204	99.90 175	99.53 257

test1		99.42 163	99.31 183	99.73 113	99.49 345	99.77 63	99.68 48	99.70 216	99.44 209	99.62 248	99.83 83	97.21 349	99.90 203	98.96 204	99.90 175	99.53 257

FMVSNet2		99.35 191	99.28 197	99.55 221	99.49 345	99.35 238	99.45 117	99.57 302	99.44 209	99.70 197	99.74 171	97.21 349	99.87 256	99.03 191	99.94 135	99.44 312

DP-MVS Recon		98.50 367	98.23 386	99.31 321	99.49 345	99.46 197	98.56 382	99.63 261	94.86 523	98.85 428	99.37 388	97.81 311	99.59 494	96.08 473	99.44 411	98.88 456

FA-MVS(test-final)		98.52 364	98.32 377	99.10 364	99.48 350	98.67 363	99.77 19	98.60 476	97.35 470	99.63 238	99.80 108	93.07 454	99.84 312	97.92 324	99.30 431	98.78 466

MVP-Stereo		99.16 253	99.08 245	99.43 267	99.48 350	99.07 305	99.08 261	99.55 314	98.63 356	99.31 356	99.68 228	98.19 280	99.78 393	98.18 303	99.58 381	99.45 297
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
thres200		96.09 486	95.68 486	97.33 495	99.48 350	96.22 494	98.53 388	97.57 514	98.06 422	98.37 468	96.73 546	86.84 516	99.61 492	86.99 542	98.57 491	96.16 529

sss		98.90 317	98.77 320	99.27 334	99.48 350	98.44 395	98.72 356	99.32 401	97.94 434	99.37 337	99.35 398	96.31 390	99.91 184	98.85 220	99.63 362	99.47 290

PAPM_NR		98.36 382	98.04 402	99.33 312	99.48 350	98.93 329	98.79 345	99.28 412	97.54 458	98.56 459	98.57 502	97.12 355	99.69 452	94.09 518	98.90 472	99.38 333

TAMVS		99.49 132	99.45 141	99.63 175	99.48 350	99.42 212	99.45 117	99.57 302	99.66 150	99.78 139	99.83 83	97.85 309	99.86 276	99.44 104	99.96 91	99.61 203

原ACMM1				99.37 295	99.47 356	98.87 344		99.27 413	96.74 496	98.26 472	99.32 403	97.93 303	99.82 358	95.96 481	99.38 420	99.43 318

plane_prior6					99.47 356	99.26 256						97.24 346

UniMVSNet_NR-MVSNet		99.37 184	99.25 206	99.72 122	99.47 356	99.56 169	98.97 304	99.61 272	99.43 216	99.67 216	99.28 415	97.85 309	99.95 81	99.17 159	99.81 265	99.65 158

TAPA-MVS	97.92 13	98.03 411	97.55 433	99.46 256	99.47 356	99.44 205	98.50 392	99.62 264	86.79 541	99.07 403	99.26 421	98.26 270	99.62 487	97.28 396	99.73 317	99.31 359
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
dmvs_testset		97.27 451	96.83 463	98.59 431	99.46 360	97.55 449	99.25 192	96.84 525	98.78 336	97.24 518	97.67 524	97.11 356	98.97 531	86.59 544	98.54 493	99.27 365

SMA-MVS		99.19 242	99.00 277	99.73 113	99.46 360	99.73 90	99.13 239	99.52 336	97.40 467	99.57 266	99.64 249	98.93 161	99.83 335	97.61 370	99.79 278	99.63 176
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
PVSNet	97.47 15	98.42 377	98.44 361	98.35 445	99.46 360	96.26 492	96.70 524	99.34 394	97.68 452	99.00 410	99.13 444	97.40 338	99.72 436	97.59 372	99.68 346	99.08 419

TinyColmap		98.97 303	98.93 295	99.07 371	99.46 360	98.19 411	97.75 468	99.75 183	98.79 334	99.54 283	99.70 206	98.97 157	99.62 487	96.63 446	99.83 245	99.41 324

9.14			98.64 331		99.45 364		98.81 339	99.60 284	97.52 460	99.28 362	99.56 320	98.53 230	99.83 335	95.36 500	99.64 359

FE-MVS		97.85 421	97.42 438	99.15 355	99.44 365	98.75 357	99.77 19	98.20 498	95.85 506	99.33 348	99.80 108	88.86 505	99.88 240	96.40 460	99.12 450	98.81 463

PatchMatch-RL		98.68 345	98.47 354	99.30 325	99.44 365	99.28 250	98.14 431	99.54 320	97.12 482	99.11 397	99.25 423	97.80 312	99.70 445	96.51 452	99.30 431	98.93 448

PCF-MVS	96.03 18	96.73 465	95.86 481	99.33 312	99.44 365	99.16 287	96.87 518	99.44 362	86.58 542	98.95 414	99.40 376	94.38 436	99.88 240	87.93 538	99.80 272	98.95 444
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ZD-MVS					99.43 368	99.61 154		99.43 366	96.38 499	99.11 397	99.07 455	97.86 307	99.92 153	94.04 519	99.49 404

VDD-MVS		99.20 239	99.11 232	99.44 263	99.43 368	98.98 317	99.50 102	98.32 494	99.80 95	99.56 274	99.69 215	96.99 362	99.85 295	98.99 197	99.73 317	99.50 277

DU-MVS		99.33 199	99.21 212	99.71 128	99.43 368	99.56 169	98.83 334	99.53 331	99.38 227	99.67 216	99.36 393	97.67 323	99.95 81	99.17 159	99.81 265	99.63 176

NR-MVSNet		99.40 172	99.31 183	99.68 141	99.43 368	99.55 173	99.73 30	99.50 345	99.46 204	99.88 82	99.36 393	97.54 332	99.87 256	98.97 201	99.87 216	99.63 176

WTY-MVS		98.59 356	98.37 370	99.26 338	99.43 368	98.40 398	98.74 353	99.13 442	98.10 417	99.21 379	99.24 429	94.82 428	99.90 203	97.86 333	98.77 477	99.49 282

BridgeMVS		99.50 127	99.50 125	99.50 240	99.42 373	99.49 184	99.52 94	99.75 183	99.86 65	99.78 139	99.71 196	98.20 279	99.90 203	99.39 114	99.88 202	99.10 407

thisisatest0515		96.98 459	96.42 468	98.66 427	99.42 373	97.47 453	97.27 496	94.30 542	97.24 475	99.15 390	98.86 482	85.01 521	99.87 256	97.10 414	99.39 419	98.63 473

pmmvs3		98.08 408	97.80 421	98.91 395	99.41 375	97.69 445	97.87 463	99.66 239	95.87 505	99.50 300	99.51 342	90.35 496	99.97 44	98.55 269	99.47 407	99.08 419

NP-MVS					99.40 376	99.13 292					98.83 485

QAPM		98.40 380	97.99 405	99.65 160	99.39 377	99.47 189	99.67 53	99.52 336	91.70 537	98.78 438	99.80 108	98.55 220	99.95 81	94.71 510	99.75 303	99.53 257

OMC-MVS		98.90 317	98.72 323	99.44 263	99.39 377	99.42 212	98.58 375	99.64 257	97.31 472	99.44 314	99.62 275	98.59 213	99.69 452	96.17 472	99.79 278	99.22 375

3Dnovator	99.15 2	99.43 159	99.36 169	99.65 160	99.39 377	99.42 212	99.70 38	99.56 307	99.23 254	99.35 342	99.80 108	99.17 111	99.95 81	98.21 298	99.84 237	99.59 215

SIFT-MNN		97.55 438	97.74 426	96.98 507	99.38 380	98.85 345	96.92 517	98.61 473	98.36 389	98.63 450	99.10 452	92.51 463	97.85 542	96.63 446	99.48 406	94.25 535

Fast-Effi-MVS+		99.02 290	98.87 306	99.46 256	99.38 380	99.50 183	99.04 273	99.79 152	97.17 479	98.62 451	98.74 491	99.34 85	99.95 81	98.32 289	99.41 417	98.92 450

BH-untuned		98.22 397	98.09 399	98.58 434	99.38 380	97.24 466	98.55 383	98.98 454	97.81 446	99.20 384	98.76 490	97.01 360	99.65 482	94.83 507	98.33 501	98.86 458

mvsany_test1		99.44 155	99.45 141	99.40 283	99.37 383	98.64 373	97.90 462	99.59 290	99.27 245	99.92 59	99.82 91	99.74 26	99.93 120	99.55 85	99.87 216	99.63 176

xiu_mvs_v2_base		99.02 290	99.11 232	98.77 417	99.37 383	98.09 421	98.13 432	99.51 341	99.47 201	99.42 321	98.54 505	99.38 76	99.97 44	98.83 222	99.33 427	98.24 498

PS-MVSNAJ		99.00 299	99.08 245	98.76 418	99.37 383	98.10 420	98.00 450	99.51 341	99.47 201	99.41 327	98.50 507	99.28 93	99.97 44	98.83 222	99.34 426	98.20 502

testing3-2		96.51 473	96.43 467	96.74 513	99.36 386	91.38 543	99.10 253	97.87 510	99.48 196	98.57 457	98.71 493	76.65 543	99.66 475	98.87 219	99.26 438	99.18 388

EIA-MVS		99.12 264	99.01 273	99.45 259	99.36 386	99.62 144	99.34 149	99.79 152	98.41 382	98.84 429	98.89 480	98.75 190	99.84 312	98.15 307	99.51 399	98.89 455

DPM-MVS		98.28 388	97.94 413	99.32 317	99.36 386	99.11 295	97.31 495	98.78 464	96.88 490	98.84 429	99.11 451	97.77 315	99.61 492	94.03 520	99.36 423	99.23 373

mvsmamba		99.08 274	98.95 293	99.45 259	99.36 386	99.18 286	99.39 129	98.81 462	99.37 228	99.35 342	99.70 206	96.36 388	99.94 98	98.66 257	99.59 379	99.22 375

MM		99.18 246	99.05 258	99.55 221	99.35 390	98.81 349	99.05 268	97.79 512	99.99 3	99.48 305	99.59 305	96.29 393	99.95 81	99.94 20	99.98 54	99.88 41

ambc				99.20 349	99.35 390	98.53 388	99.17 219	99.46 356		99.67 216	99.80 108	98.46 243	99.70 445	97.92 324	99.70 332	99.38 333

TEST9					99.35 390	99.35 238	98.11 436	99.41 369	94.83 524	97.92 493	98.99 466	98.02 295	99.85 295

train_agg		98.35 385	97.95 409	99.57 210	99.35 390	99.35 238	98.11 436	99.41 369	94.90 521	97.92 493	98.99 466	98.02 295	99.85 295	95.38 499	99.44 411	99.50 277

agg_prior					99.35 390	99.36 235		99.39 379		97.76 505			99.85 295

test_prior				99.46 256	99.35 390	99.22 270		99.39 379					99.69 452			99.48 286

MVS_Test		99.28 208	99.31 183	99.19 350	99.35 390	98.79 353	99.36 144	99.49 349	99.17 269	99.21 379	99.67 234	98.78 185	99.66 475	99.09 182	99.66 355	99.10 407

CDS-MVSNet		99.22 232	99.13 225	99.50 240	99.35 390	99.11 295	98.96 308	99.54 320	99.46 204	99.61 255	99.70 206	96.31 390	99.83 335	99.34 123	99.88 202	99.55 236
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
3Dnovator+	98.92 3	99.35 191	99.24 208	99.67 145	99.35 390	99.47 189	99.62 67	99.50 345	99.44 209	99.12 396	99.78 133	98.77 187	99.94 98	97.87 331	99.72 325	99.62 188

ETV-MVS		99.18 246	99.18 216	99.16 353	99.34 399	99.28 250	99.12 244	99.79 152	99.48 196	98.93 416	98.55 504	99.40 70	99.93 120	98.51 273	99.52 398	98.28 494

Anonymous202405211		98.75 336	98.46 356	99.63 175	99.34 399	99.66 123	99.47 112	97.65 513	99.28 244	99.56 274	99.50 345	93.15 452	99.84 312	98.62 263	99.58 381	99.40 327

CHOSEN 280x420		98.41 378	98.41 365	98.40 442	99.34 399	95.89 502	96.94 515	99.44 362	98.80 332	99.25 369	99.52 338	93.51 448	99.98 26	98.94 212	99.98 54	99.32 354

test_8					99.34 399	99.31 245	98.08 440	99.40 376	94.90 521	97.87 498	98.97 471	98.02 295	99.84 312

TSAR-MVS + GP.		99.12 264	99.04 264	99.38 290	99.34 399	99.16 287	98.15 429	99.29 409	98.18 412	99.63 238	99.62 275	99.18 109	99.68 464	98.20 299	99.74 310	99.30 361

LCM-MVSNet-Re		99.28 208	99.15 222	99.67 145	99.33 404	99.76 70	99.34 149	99.97 21	98.93 309	99.91 62	99.79 120	98.68 199	99.93 120	96.80 434	99.56 384	99.30 361

MASt3R-SfM		98.45 374	98.51 349	98.26 455	99.32 405	97.43 459	97.43 490	99.69 225	94.97 520	99.75 165	99.41 370	98.49 238	99.75 424	97.73 348	99.79 278	97.61 518

PLC	97.35 16	98.36 382	97.99 405	99.48 250	99.32 405	99.24 264	98.50 392	99.51 341	95.19 518	98.58 455	98.96 473	96.95 363	99.83 335	95.63 493	99.25 440	99.37 337
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
Effi-MVS+		99.06 279	98.97 289	99.34 309	99.31 407	98.98 317	98.31 414	99.91 57	98.81 330	98.79 436	98.94 476	99.14 118	99.84 312	98.79 231	98.74 482	99.20 383

HQP-NCC					99.31 407		97.98 452		97.45 463	98.15 482

ACMP_Plane					99.31 407		97.98 452		97.45 463	98.15 482

HQP-MVS		98.36 382	98.02 404	99.39 286	99.31 407	98.94 326	97.98 452	99.37 385	97.45 463	98.15 482	98.83 485	96.67 372	99.70 445	94.73 508	99.67 352	99.53 257

baseline1		97.73 428	97.33 441	98.96 382	99.30 411	97.73 443	99.40 127	98.42 486	99.33 236	99.46 311	99.21 436	91.18 480	99.82 358	98.35 286	91.26 544	99.32 354

WR-MVS		99.11 269	98.93 295	99.66 153	99.30 411	99.42 212	98.42 405	99.37 385	99.04 289	99.57 266	99.20 438	96.89 365	99.86 276	98.66 257	99.87 216	99.70 107

hse-mvs2		98.52 364	98.30 380	99.16 353	99.29 413	98.60 377	98.77 347	99.02 449	99.68 135	99.32 351	99.04 459	92.50 464	99.85 295	99.24 139	97.87 519	99.03 432

test12				99.54 227	99.29 413	99.33 241		99.16 437		98.43 465		97.54 332	99.82 358		99.47 407	99.48 286

OpenMVS_ROB	97.31 17	97.36 449	96.84 462	98.89 402	99.29 413	99.45 203	98.87 325	99.48 350	86.54 543	99.44 314	99.74 171	97.34 342	99.86 276	91.61 528	99.28 434	97.37 522

MVS-HIRNet		97.86 420	98.22 387	96.76 511	99.28 416	91.53 541	98.38 407	92.60 547	99.13 278	99.31 356	99.96 15	97.18 353	99.68 464	98.34 287	99.83 245	99.07 425

DeepC-MVS_fast	98.47 5	99.23 223	99.12 229	99.56 214	99.28 416	99.22 270	98.99 299	99.40 376	99.08 284	99.58 263	99.64 249	98.90 170	99.83 335	97.44 382	99.75 303	99.63 176
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
AUN-MVS		97.82 422	97.38 439	99.14 358	99.27 418	98.53 388	98.72 356	99.02 449	98.10 417	97.18 520	99.03 463	89.26 504	99.85 295	97.94 323	97.91 517	99.03 432

Patchmatch-test		98.10 407	97.98 407	98.48 438	99.27 418	96.48 486	99.40 127	99.07 444	98.81 330	99.23 373	99.57 316	90.11 499	99.87 256	96.69 439	99.64 359	99.09 413

RRT-MVS		99.08 274	99.00 277	99.33 312	99.27 418	98.65 370	99.62 67	99.93 43	99.66 150	99.67 216	99.82 91	95.27 421	99.93 120	98.64 261	99.09 454	99.41 324

ET-MVSNet_ETH3D		96.78 463	96.07 476	98.91 395	99.26 421	97.92 434	97.70 474	96.05 529	97.96 431	92.37 545	98.43 508	87.06 511	99.90 203	98.27 292	97.56 522	98.91 452

Fast-Effi-MVS+-dtu		99.20 239	99.12 229	99.43 267	99.25 422	99.69 114	99.05 268	99.82 122	99.50 191	98.97 412	99.05 457	98.98 155	99.98 26	98.20 299	99.24 442	98.62 474

CNVR-MVS		98.99 302	98.80 318	99.56 214	99.25 422	99.43 209	98.54 386	99.27 413	98.58 363	98.80 434	99.43 366	98.53 230	99.70 445	97.22 405	99.59 379	99.54 248

LFMVS		98.46 373	98.19 392	99.26 338	99.24 424	98.52 390	99.62 67	96.94 524	99.87 62	99.31 356	99.58 308	91.04 482	99.81 375	98.68 254	99.42 416	99.45 297

VNet		99.18 246	99.06 251	99.56 214	99.24 424	99.36 235	99.33 155	99.31 405	99.67 143	99.47 307	99.57 316	96.48 380	99.84 312	99.15 164	99.30 431	99.47 290

testing3		96.48 474	95.63 487	99.01 377	99.23 426	97.81 439	98.90 319	99.10 443	98.72 344	97.84 501	97.92 520	72.44 550	99.85 295	97.21 406	99.33 427	99.35 343

CL-MVSNet_self_test		98.71 342	98.56 345	99.15 355	99.22 427	98.66 366	97.14 504	99.51 341	98.09 419	99.54 283	99.27 417	96.87 366	99.74 431	98.43 281	98.96 464	99.03 432

DeepPCF-MVS	98.42 6	99.18 246	99.02 267	99.67 145	99.22 427	99.75 79	97.25 498	99.47 353	98.72 344	99.66 223	99.70 206	99.29 91	99.63 486	98.07 313	99.81 265	99.62 188

MSLP-MVS++		99.05 283	99.09 243	98.91 395	99.21 429	98.36 403	98.82 338	99.47 353	98.85 321	98.90 422	99.56 320	98.78 185	99.09 527	98.57 267	99.68 346	99.26 367

NCCC		98.82 328	98.57 341	99.58 202	99.21 429	99.31 245	98.61 368	99.25 418	98.65 353	98.43 465	99.26 421	97.86 307	99.81 375	96.55 449	99.27 437	99.61 203

BH-RMVSNet		98.41 378	98.14 396	99.21 346	99.21 429	98.47 391	98.60 370	98.26 496	98.35 395	98.93 416	99.31 406	97.20 352	99.66 475	94.32 513	99.10 452	99.51 271

miper_lstm_enhance		98.65 348	98.60 335	98.82 413	99.20 432	97.33 463	97.78 467	99.66 239	99.01 294	99.59 261	99.50 345	94.62 432	99.85 295	98.12 308	99.90 175	99.26 367

SCA		98.11 406	98.36 372	97.36 492	99.20 432	92.99 531	98.17 426	98.49 482	98.24 407	99.10 399	99.57 316	96.01 402	99.94 98	96.86 428	99.62 364	99.14 400

dongtai		89.37 511	88.91 514	90.76 529	99.19 434	77.46 555	95.47 535	87.82 554	92.28 535	94.17 542	98.82 487	71.22 552	95.54 547	63.85 548	97.34 525	99.27 365

mvs_anonymous		99.28 208	99.39 158	98.94 385	99.19 434	97.81 439	99.02 280	99.55 314	99.78 102	99.85 101	99.80 108	98.24 271	99.86 276	99.57 82	99.50 402	99.15 395

OpenMVS	98.12 10	98.23 395	97.89 418	99.26 338	99.19 434	99.26 256	99.65 62	99.69 225	91.33 538	98.14 486	99.77 145	98.28 267	99.96 69	95.41 498	99.55 388	98.58 479

CNLPA		98.57 358	98.34 375	99.28 329	99.18 437	99.10 302	98.34 409	99.41 369	98.48 377	98.52 460	98.98 469	97.05 358	99.78 393	95.59 494	99.50 402	98.96 442

TestfortrainingZip				99.38 290	99.17 438	99.25 259	99.38 132	98.82 460	98.93 309	99.68 208	99.49 350	98.11 289	99.56 500		98.44 499	99.32 354

test_yl		98.25 391	97.95 409	99.13 360	99.17 438	98.47 391	99.00 291	98.67 470	98.97 298	99.22 377	99.02 464	91.31 478	99.69 452	97.26 399	98.93 466	99.24 370

DCV-MVSNet		98.25 391	97.95 409	99.13 360	99.17 438	98.47 391	99.00 291	98.67 470	98.97 298	99.22 377	99.02 464	91.31 478	99.69 452	97.26 399	98.93 466	99.24 370

MG-MVS		98.52 364	98.39 368	98.94 385	99.15 441	97.39 461	98.18 423	99.21 429	98.89 317	99.23 373	99.63 265	97.37 341	99.74 431	94.22 515	99.61 372	99.69 119

ADS-MVSNet2		97.78 426	97.66 431	98.12 459	99.14 442	95.36 511	99.22 201	98.75 465	96.97 487	98.25 473	99.64 249	90.90 485	99.94 98	96.51 452	99.56 384	99.08 419

ADS-MVSNet		97.72 431	97.67 430	97.86 469	99.14 442	94.65 520	99.22 201	98.86 457	96.97 487	98.25 473	99.64 249	90.90 485	99.84 312	96.51 452	99.56 384	99.08 419

FMVSNet3		98.80 331	98.63 333	99.32 317	99.13 444	98.72 359	99.10 253	99.48 350	99.23 254	99.62 248	99.64 249	92.57 460	99.86 276	98.96 204	99.90 175	99.39 331

PHI-MVS		99.11 269	98.95 293	99.59 198	99.13 444	99.59 160	99.17 219	99.65 249	97.88 440	99.25 369	99.46 361	98.97 157	99.80 385	97.26 399	99.82 255	99.37 337

OPU-MVS				99.29 326	99.12 446	99.44 205	99.20 204				99.40 376	99.00 149	98.84 534	96.54 450	99.60 375	99.58 221

c3_l		98.72 340	98.71 324	98.72 421	99.12 446	97.22 467	97.68 475	99.56 307	98.90 314	99.54 283	99.48 354	96.37 387	99.73 434	97.88 328	99.88 202	99.21 378

alignmvs		98.28 388	97.96 408	99.25 341	99.12 446	98.93 329	99.03 276	98.42 486	99.64 159	98.72 442	97.85 521	90.86 488	99.62 487	98.88 218	99.13 449	99.19 386

PAPM		95.61 499	94.71 503	98.31 450	99.12 446	96.63 482	96.66 525	98.46 484	90.77 539	96.25 532	98.68 497	93.01 455	99.69 452	81.60 546	97.86 520	98.62 474

AdaColmap		98.60 353	98.35 374	99.38 290	99.12 446	99.22 270	98.67 362	99.42 368	97.84 445	98.81 432	99.27 417	97.32 344	99.81 375	95.14 503	99.53 395	99.10 407

MGCFI-Net		99.02 290	99.01 273	99.06 373	99.11 451	98.60 377	99.63 64	99.67 234	99.63 161	98.58 455	97.65 525	99.07 134	99.57 496	98.85 220	98.92 468	99.03 432

MS-PatchMatch		99.00 299	98.97 289	99.09 365	99.11 451	98.19 411	98.76 348	99.33 399	98.49 376	99.44 314	99.58 308	98.21 277	99.69 452	98.20 299	99.62 364	99.39 331

sasdasda		99.02 290	99.00 277	99.09 365	99.10 453	98.70 361	99.61 73	99.66 239	99.63 161	98.64 448	97.65 525	99.04 144	99.54 501	98.79 231	98.92 468	99.04 429

eth_miper_zixun_eth		98.68 345	98.71 324	98.60 430	99.10 453	96.84 480	97.52 486	99.54 320	98.94 304	99.58 263	99.48 354	96.25 394	99.76 413	98.01 317	99.93 149	99.21 378

canonicalmvs		99.02 290	99.00 277	99.09 365	99.10 453	98.70 361	99.61 73	99.66 239	99.63 161	98.64 448	97.65 525	99.04 144	99.54 501	98.79 231	98.92 468	99.04 429

balanced_ft_v1		99.37 184	99.36 169	99.38 290	99.10 453	99.38 226	99.68 48	99.72 203	99.72 116	99.36 338	99.77 145	97.66 327	99.94 98	99.52 91	99.73 317	98.83 461

baseline2		96.83 462	96.28 470	98.46 440	99.09 457	96.91 476	98.83 334	93.87 546	97.23 476	96.23 534	98.36 510	88.12 508	99.90 203	96.68 440	98.14 511	98.57 481

BH-w/o		97.20 453	97.01 455	97.76 472	99.08 458	95.69 505	98.03 446	98.52 479	95.76 509	97.96 492	98.02 517	95.62 409	99.47 511	92.82 525	97.25 528	98.12 505

MVSTER		98.47 371	98.22 387	99.24 343	99.06 459	98.35 404	99.08 261	99.46 356	99.27 245	99.75 165	99.66 240	88.61 506	99.85 295	99.14 171	99.92 158	99.52 268

reproduce_monomvs		97.40 446	97.46 434	97.20 498	99.05 460	91.91 537	99.20 204	99.18 434	99.84 75	99.86 96	99.75 163	80.67 528	99.83 335	99.69 64	99.95 116	99.85 50

CR-MVSNet		98.35 385	98.20 389	98.83 410	99.05 460	98.12 417	99.30 167	99.67 234	97.39 468	99.16 387	99.79 120	91.87 473	99.91 184	98.78 237	98.77 477	98.44 489

RPMNet		98.60 353	98.53 347	98.83 410	99.05 460	98.12 417	99.30 167	99.62 264	99.86 65	99.16 387	99.74 171	92.53 462	99.92 153	98.75 239	98.77 477	98.44 489

MVStest1		98.22 397	98.09 399	98.62 428	99.04 463	96.23 493	99.20 204	99.92 47	99.44 209	99.98 14	99.87 56	85.87 520	99.67 470	99.91 33	99.57 383	99.95 15

DVP-MVS++		99.38 179	99.25 206	99.77 80	99.03 464	99.77 63	99.74 27	99.61 272	99.18 262	99.76 160	99.61 285	99.00 149	99.92 153	97.72 349	99.60 375	99.62 188

MSC_two_6792asdad				99.74 103	99.03 464	99.53 176		99.23 423					99.92 153	97.77 342	99.69 341	99.78 77

No_MVS				99.74 103	99.03 464	99.53 176		99.23 423					99.92 153	97.77 342	99.69 341	99.78 77

cl____		98.54 362	98.41 365	98.92 390	99.03 464	97.80 441	97.46 488	99.59 290	98.90 314	99.60 258	99.46 361	93.85 442	99.78 393	97.97 321	99.89 191	99.17 391

DIV-MVS_self_test		98.54 362	98.42 364	98.92 390	99.03 464	97.80 441	97.46 488	99.59 290	98.90 314	99.60 258	99.46 361	93.87 441	99.78 393	97.97 321	99.89 191	99.18 388

HY-MVS	98.23 9	98.21 399	97.95 409	98.99 378	99.03 464	98.24 406	99.61 73	98.72 466	96.81 493	98.73 441	99.51 342	94.06 439	99.86 276	96.91 425	98.20 506	98.86 458

ALIKED-LG		98.78 332	98.66 330	99.14 358	99.02 470	99.40 220	98.74 353	99.79 152	98.62 360	99.18 385	99.38 384	97.54 332	99.77 406	95.94 484	99.74 310	98.25 497

miper_ehance_all_eth		98.59 356	98.59 337	98.59 431	98.98 471	97.07 471	97.49 487	99.52 336	98.50 374	99.52 290	99.37 388	96.41 385	99.71 441	97.86 333	99.62 364	99.00 439

MonoMVSNet		98.23 395	98.32 377	97.99 461	98.97 472	96.62 483	99.49 107	98.42 486	99.62 164	99.40 332	99.79 120	95.51 415	98.58 538	97.68 365	95.98 540	98.76 469

PMMVS		98.49 369	98.29 382	99.11 362	98.96 473	98.42 397	97.54 482	99.32 401	97.53 459	98.47 463	98.15 516	97.88 306	99.82 358	97.46 381	99.24 442	99.09 413

PatchT		98.45 374	98.32 377	98.83 410	98.94 474	98.29 405	99.24 193	98.82 460	99.84 75	99.08 400	99.76 155	91.37 477	99.94 98	98.82 224	99.00 462	98.26 496

tpm		97.15 455	96.95 457	97.75 473	98.91 475	94.24 523	99.32 158	97.96 505	97.71 451	98.29 471	99.32 403	86.72 517	99.92 153	98.10 312	96.24 539	99.09 413

1314		98.00 414	97.90 417	98.27 454	98.90 476	97.45 456	99.30 167	99.06 446	94.98 519	97.21 519	99.12 448	98.43 246	99.67 470	95.58 495	98.56 492	97.71 516

CostFormer		96.71 466	96.79 465	96.46 518	98.90 476	90.71 547	99.41 122	98.68 468	94.69 525	98.14 486	99.34 402	86.32 519	99.80 385	97.60 371	98.07 515	98.88 456

UGNet		99.38 179	99.34 175	99.49 244	98.90 476	98.90 334	99.70 38	99.35 390	99.86 65	98.57 457	99.81 98	98.50 237	99.93 120	99.38 115	99.98 54	99.66 149
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
Effi-MVS+-dtu		99.07 278	98.92 299	99.52 234	98.89 479	99.78 57	99.15 228	99.66 239	99.34 233	98.92 419	99.24 429	97.69 321	99.98 26	98.11 309	99.28 434	98.81 463

Patchmtry		98.78 332	98.54 346	99.49 244	98.89 479	99.19 280	99.32 158	99.67 234	99.65 155	99.72 188	99.79 120	91.87 473	99.95 81	98.00 318	99.97 77	99.33 350

tpm2		96.35 478	96.22 473	96.73 514	98.88 481	91.75 539	99.21 203	98.51 480	93.27 530	97.89 496	99.21 436	84.83 522	99.70 445	96.04 475	98.18 509	98.75 470

UBG		96.53 471	95.95 478	98.29 453	98.87 482	96.31 491	98.48 396	98.07 501	98.83 326	97.32 515	96.54 549	79.81 533	99.62 487	96.84 432	98.74 482	98.95 444

myMVS_eth3d28		96.23 482	95.74 484	97.70 478	98.86 483	95.59 509	98.66 364	98.14 499	98.96 300	97.67 509	97.06 537	76.78 542	98.92 532	97.10 414	98.41 500	98.58 479

WBMVS		97.50 442	97.18 448	98.48 438	98.85 484	95.89 502	98.44 403	99.52 336	99.53 186	99.52 290	99.42 368	80.10 531	99.86 276	99.24 139	99.95 116	99.68 126

tpm cat1		96.78 463	96.98 456	96.16 521	98.85 484	90.59 548	99.08 261	99.32 401	92.37 533	97.73 507	99.46 361	91.15 481	99.69 452	96.07 474	98.80 474	98.21 500

ALIKED-MNN		98.03 411	97.78 424	98.78 416	98.84 486	98.97 320	98.16 428	99.74 189	97.31 472	96.60 528	98.85 483	96.61 374	99.48 510	94.16 516	99.77 290	97.91 515

CANet		99.11 269	99.05 258	99.28 329	98.83 487	98.56 382	98.71 359	99.41 369	99.25 250	99.23 373	99.22 432	97.66 327	99.94 98	99.19 152	99.97 77	99.33 350

FMVSNet5		97.80 425	97.25 445	99.42 270	98.83 487	98.97 320	99.38 132	99.80 143	98.87 318	99.25 369	99.69 215	80.60 530	99.91 184	98.96 204	99.90 175	99.38 333

API-MVS		98.38 381	98.39 368	98.35 445	98.83 487	99.26 256	99.14 232	99.18 434	98.59 362	98.66 447	98.78 489	98.61 210	99.57 496	94.14 517	99.56 384	96.21 527

PatchmatchNet		97.65 432	97.80 421	97.18 499	98.82 490	92.49 534	99.17 219	98.39 490	98.12 416	98.79 436	99.58 308	90.71 491	99.89 225	97.23 404	99.41 417	99.16 393
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ETVMVS		96.14 485	95.22 496	98.89 402	98.80 491	98.01 426	98.66 364	98.35 493	98.71 346	97.18 520	96.31 554	74.23 549	99.75 424	96.64 445	98.13 514	98.90 453

PAPR		97.56 436	97.07 452	99.04 375	98.80 491	98.11 419	97.63 477	99.25 418	94.56 527	98.02 491	98.25 513	97.43 337	99.68 464	90.90 531	98.74 482	99.33 350

CANet_DTU		98.91 314	98.85 308	99.09 365	98.79 493	98.13 416	98.18 423	99.31 405	99.48 196	98.86 427	99.51 342	96.56 376	99.95 81	99.05 188	99.95 116	99.19 386

E-PMN		97.14 457	97.43 437	96.27 519	98.79 493	91.62 540	95.54 534	99.01 452	99.44 209	98.88 423	99.12 448	92.78 457	99.68 464	94.30 514	99.03 460	97.50 519

testing11		96.05 488	95.41 491	97.97 463	98.78 495	95.27 514	98.59 373	98.23 497	98.86 320	96.56 529	96.91 541	75.20 546	99.69 452	97.26 399	98.29 503	98.93 448

PVSNet_0	95.53 19	95.85 494	95.31 495	97.47 484	98.78 495	93.48 530	95.72 533	99.40 376	96.18 503	97.37 514	97.73 523	95.73 407	99.58 495	95.49 496	81.40 548	99.36 340

MAR-MVS		98.24 393	97.92 415	99.19 350	98.78 495	99.65 129	99.17 219	99.14 440	95.36 514	98.04 489	98.81 488	97.47 335	99.72 436	95.47 497	99.06 455	98.21 500
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
testing91		96.00 489	95.32 494	98.02 460	98.76 498	95.39 510	98.38 407	98.65 472	98.82 328	96.84 524	96.71 547	75.06 547	99.71 441	96.46 458	98.23 505	98.98 441

testing99		95.86 493	95.19 497	97.87 468	98.76 498	95.03 516	98.62 367	98.44 485	98.68 349	96.67 527	96.66 548	74.31 548	99.69 452	96.51 452	98.03 516	98.90 453

EMVS		96.96 460	97.28 442	95.99 523	98.76 498	91.03 544	95.26 537	98.61 473	99.34 233	98.92 419	98.88 481	93.79 443	99.66 475	92.87 524	99.05 457	97.30 523

IB-MVS	95.41 20	95.30 501	94.46 507	97.84 470	98.76 498	95.33 512	97.33 494	96.07 528	96.02 504	95.37 538	97.41 529	76.17 544	99.96 69	97.54 375	95.44 543	98.22 499
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
tpmrst		97.73 428	98.07 401	96.73 514	98.71 502	92.00 536	99.10 253	98.86 457	98.52 372	98.92 419	99.54 331	91.90 471	99.82 358	98.02 314	99.03 460	98.37 491

MDTV_nov1_ep13			97.73 427		98.70 503	90.83 545	99.15 228	98.02 503	98.51 373	98.82 431	99.61 285	90.98 483	99.66 475	96.89 427	98.92 468

SP-LightGlue		98.62 349	98.51 349	98.94 385	98.69 504	99.01 312	98.34 409	99.54 320	99.27 245	97.72 508	99.15 443	95.88 406	99.54 501	98.53 272	99.47 407	98.27 495

dp		96.86 461	97.07 452	96.24 520	98.68 505	90.30 551	99.19 210	98.38 491	97.35 470	98.23 475	99.59 305	87.23 510	99.82 358	96.27 466	98.73 485	98.59 477

testing222		95.60 500	94.59 505	98.61 429	98.66 506	97.45 456	98.54 386	97.90 509	98.53 370	96.54 530	96.47 551	70.62 553	99.81 375	95.91 485	98.15 510	98.56 482

JIA-IIPM		98.06 410	97.92 415	98.50 437	98.59 507	97.02 472	98.80 342	98.51 480	99.88 60	97.89 496	99.87 56	91.89 472	99.90 203	98.16 306	97.68 521	98.59 477

MVS		95.72 496	94.63 504	98.99 378	98.56 508	97.98 432	99.30 167	98.86 457	72.71 547	97.30 516	99.08 454	98.34 259	99.74 431	89.21 532	98.33 501	99.26 367

UWE-MVS		96.21 484	95.78 483	97.49 481	98.53 509	93.83 527	98.04 444	93.94 545	98.96 300	98.46 464	98.17 515	79.86 532	99.87 256	96.99 419	99.06 455	98.78 466

TR-MVS		97.44 444	97.15 449	98.32 448	98.53 509	97.46 454	98.47 397	97.91 508	96.85 491	98.21 476	98.51 506	96.42 383	99.51 508	92.16 526	97.29 527	97.98 511

Syy-MVS		98.17 403	97.85 419	99.15 355	98.50 511	98.79 353	98.60 370	99.21 429	97.89 438	96.76 525	96.37 552	95.47 417	99.57 496	99.10 181	98.73 485	99.09 413

myMVS_eth3d		95.63 498	94.73 502	98.34 447	98.50 511	96.36 489	98.60 370	99.21 429	97.89 438	96.76 525	96.37 552	72.10 551	99.57 496	94.38 512	98.73 485	99.09 413

SP-SuperGlue		98.66 347	98.63 333	98.73 420	98.44 513	99.02 311	98.22 421	99.44 362	99.37 228	98.17 481	99.30 409	96.95 363	99.12 524	98.59 264	99.20 447	98.06 506

tpmvs		97.39 447	97.69 428	96.52 516	98.41 514	91.76 538	99.30 167	98.94 455	97.74 447	97.85 500	99.55 329	92.40 467	99.73 434	96.25 467	98.73 485	98.06 506

LS3D		99.24 220	99.11 232	99.61 191	98.38 515	99.79 54	99.57 85	99.68 229	99.61 169	99.15 390	99.71 196	98.70 197	99.91 184	97.54 375	99.68 346	99.13 403

cl22		97.56 436	97.28 442	98.40 442	98.37 516	96.75 481	97.24 499	99.37 385	97.31 472	99.41 327	99.22 432	87.30 509	99.37 516	97.70 354	99.62 364	99.08 419

CMPMVS	77.52 23	98.50 367	98.19 392	99.41 280	98.33 517	99.56 169	99.01 285	99.59 290	95.44 513	99.57 266	99.80 108	95.64 408	99.46 513	96.47 457	99.92 158	99.21 378
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
SP-MNN		97.94 419	97.82 420	98.31 450	98.30 518	97.67 446	97.81 466	97.93 507	98.14 414	97.16 522	98.64 499	96.31 390	99.21 522	97.34 388	98.75 481	98.05 508

miper_enhance_ethall		98.03 411	97.94 413	98.32 448	98.27 519	96.43 488	96.95 514	99.41 369	96.37 500	99.43 318	98.96 473	94.74 429	99.69 452	97.71 351	99.62 364	98.83 461

TESTMET0.1,1		96.24 481	95.84 482	97.41 488	98.24 520	93.84 526	97.38 491	95.84 534	98.43 379	97.81 502	98.56 503	79.77 534	99.89 225	97.77 342	98.77 477	98.52 483

SIFT-NN		94.78 504	94.89 500	94.45 526	98.23 521	97.29 464	94.93 538	95.84 534	95.82 508	94.78 540	97.12 535	90.26 497	92.28 550	88.91 533	98.14 511	93.77 541

gg-mvs-nofinetune		95.87 492	95.17 498	97.97 463	98.19 522	96.95 473	99.69 45	89.23 552	99.89 55	96.24 533	99.94 19	81.19 527	99.51 508	93.99 521	98.20 506	97.44 520

test-LLR		97.15 455	96.95 457	97.74 474	98.18 523	95.02 517	97.38 491	96.10 526	98.00 424	97.81 502	98.58 500	90.04 500	99.91 184	97.69 360	98.78 475	98.31 492

test-mter		96.23 482	95.73 485	97.74 474	98.18 523	95.02 517	97.38 491	96.10 526	97.90 436	97.81 502	98.58 500	79.12 537	99.91 184	97.69 360	98.78 475	98.31 492

EPMVS		96.53 471	96.32 469	97.17 501	98.18 523	92.97 532	99.39 129	89.95 551	98.21 409	98.61 452	99.59 305	86.69 518	99.72 436	96.99 419	99.23 444	98.81 463

WB-MVSnew		98.34 387	98.14 396	98.96 382	98.14 526	97.90 435	98.27 416	97.26 521	98.63 356	98.80 434	98.00 519	97.77 315	99.90 203	97.37 387	98.98 463	99.09 413

blended_shiyan6		97.82 422	97.46 434	98.92 390	98.08 527	97.46 454	97.73 469	99.34 394	97.96 431	98.33 470	97.35 530	92.78 457	99.84 312	99.04 189	96.53 532	99.46 295

blended_shiyan8		97.82 422	97.45 436	98.92 390	98.06 528	97.45 456	97.73 469	99.35 390	97.96 431	98.35 469	97.34 531	92.76 459	99.84 312	99.04 189	96.49 538	99.47 290

UWE-MVS-28		95.64 497	95.47 489	96.14 522	97.98 529	90.39 549	98.49 395	95.81 536	99.02 293	98.03 490	98.19 514	84.49 524	99.28 519	88.75 534	98.47 498	98.75 470

blend_shiyan4		95.04 503	93.76 509	98.88 404	97.92 530	97.49 451	97.72 471	99.34 394	97.93 435	97.65 510	97.11 536	77.69 541	99.83 335	98.79 231	79.72 549	99.33 350

kuosan		85.65 513	84.57 516	88.90 531	97.91 531	77.11 556	96.37 529	87.62 555	85.24 544	85.45 550	96.83 542	69.94 554	90.98 551	45.90 549	95.83 542	98.62 474

MGCNet		98.61 350	98.30 380	99.52 234	97.88 532	98.95 324	98.76 348	94.11 544	99.84 75	99.32 351	99.57 316	95.57 412	99.95 81	99.68 66	99.98 54	99.68 126

test0.0.03 1		97.37 448	96.91 460	98.74 419	97.72 533	97.57 448	97.60 480	97.36 519	98.00 424	99.21 379	98.02 517	90.04 500	99.79 389	98.37 284	95.89 541	98.86 458

wanda-best-256-512		97.53 439	97.14 450	98.72 421	97.71 534	96.86 478	97.00 510	99.34 394	97.73 448	98.18 477	96.82 543	91.92 468	99.84 312	99.02 194	96.53 532	99.45 297

FE-blended-shiyan7		97.53 439	97.14 450	98.72 421	97.71 534	96.86 478	97.00 510	99.34 394	97.73 448	98.18 477	96.82 543	91.92 468	99.84 312	99.02 194	96.53 532	99.45 297

usedtu_blend_shiyan5		97.97 416	97.65 432	98.92 390	97.71 534	97.49 451	99.53 92	99.81 135	99.52 190	98.18 477	96.82 543	91.92 468	99.83 335	98.79 231	96.53 532	99.45 297

GG-mvs-BLEND				97.36 492	97.59 537	96.87 477	99.70 38	88.49 553		94.64 541	97.26 534	80.66 529	99.12 524	91.50 529	96.50 537	96.08 530

gm-plane-assit					97.59 537	89.02 553			93.47 529		98.30 511		99.84 312	96.38 462

cascas		96.99 458	96.82 464	97.48 482	97.57 539	95.64 506	96.43 528	99.56 307	91.75 536	97.13 523	97.61 528	95.58 411	98.63 536	96.68 440	99.11 451	98.18 503

ALIKED-NN		96.66 468	96.26 471	97.88 467	97.49 540	98.59 379	96.71 523	99.15 438	95.50 512	93.58 543	98.39 509	94.52 434	97.74 543	92.05 527	98.94 465	97.29 524

SP-DiffGlue		98.47 371	98.43 363	98.59 431	97.44 541	98.59 379	98.01 447	99.36 389	99.00 295	99.06 404	99.20 438	97.01 360	99.25 520	97.64 366	99.15 448	97.92 514

gbinet_0.2-2-1-0.02		97.52 441	97.07 452	98.88 404	97.35 542	97.35 462	97.17 501	99.25 418	97.86 443	98.41 467	96.54 549	90.74 490	99.85 295	98.80 230	97.51 523	99.43 318

SP-NN		96.37 477	96.23 472	96.77 510	96.83 543	96.95 473	96.47 527	97.07 523	96.75 495	93.41 544	97.75 522	94.13 438	95.69 546	96.25 467	97.43 524	97.68 517

XFeat-MNN		96.67 467	96.56 466	96.98 507	96.73 544	95.62 508	94.54 539	98.93 456	97.42 466	98.18 477	98.67 498	91.60 476	99.12 524	93.88 522	99.10 452	96.21 527

EPNet_dtu		97.62 433	97.79 423	97.11 504	96.67 545	92.31 535	98.51 391	98.04 502	99.24 252	95.77 535	99.47 358	93.78 444	99.66 475	98.98 199	99.62 364	99.37 337
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
0.4-1-1-0.1		93.18 507	91.66 511	97.73 476	95.83 546	95.29 513	95.30 536	95.90 532	93.59 528	90.58 547	94.40 555	77.87 539	99.77 406	97.31 391	84.20 545	98.15 504

XFeat-NN		93.89 506	93.91 508	93.83 527	95.49 547	92.69 533	90.85 542	97.98 504	94.69 525	95.08 539	96.98 538	88.36 507	94.23 549	88.42 537	97.34 525	94.57 531

KD-MVS_2432*1600		95.89 490	95.41 491	97.31 496	94.96 548	93.89 524	97.09 505	99.22 426	97.23 476	98.88 423	99.04 459	79.23 535	99.54 501	96.24 469	96.81 529	98.50 487

miper_refine_blended		95.89 490	95.41 491	97.31 496	94.96 548	93.89 524	97.09 505	99.22 426	97.23 476	98.88 423	99.04 459	79.23 535	99.54 501	96.24 469	96.81 529	98.50 487

0.3-1-1-0.015		92.36 509	90.68 513	97.39 489	94.94 550	94.41 522	94.21 540	95.89 533	92.87 531	88.87 549	93.49 557	75.30 545	99.76 413	97.19 409	83.41 547	98.02 509

GLUNet-SfM		95.26 502	95.06 499	95.87 524	94.84 551	90.39 549	90.24 544	99.92 47	92.30 534	99.16 387	99.25 423	94.69 431	98.01 541	85.55 545	99.62 364	99.21 378

0.4-1-1-0.2		92.59 508	91.07 512	97.15 502	94.73 552	93.68 528	93.50 541	95.91 530	92.68 532	90.48 548	93.52 556	77.77 540	99.75 424	97.19 409	83.88 546	98.01 510

EPNet		98.13 405	97.77 425	99.18 352	94.57 553	97.99 427	99.24 193	97.96 505	99.74 111	97.29 517	99.62 275	93.13 453	99.97 44	98.59 264	99.83 245	99.58 221
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_method		91.72 510	92.32 510	89.91 530	93.49 554	70.18 557	90.28 543	99.56 307	61.71 548	95.39 537	99.52 338	93.90 440	99.94 98	98.76 238	98.27 504	99.62 188

tmp_tt		95.75 495	95.42 490	96.76 511	89.90 555	94.42 521	98.86 326	97.87 510	78.01 545	99.30 361	99.69 215	97.70 319	95.89 545	99.29 134	98.14 511	99.95 15

testmvs		28.94 515	33.33 517	15.79 533	26.03 556	9.81 559	96.77 519	15.67 557	11.55 551	23.87 553	50.74 561	19.03 556	8.53 553	23.21 551	33.07 550	29.03 548

test123		29.31 514	33.05 519	18.08 532	25.93 557	12.24 558	97.53 484	10.93 558	11.78 550	24.21 552	50.08 562	21.04 555	8.60 552	23.51 550	32.43 551	33.39 547

mmdepth		8.33 518	11.11 521	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	100.00 1	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

monomultidepth		8.33 518	11.11 521	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	100.00 1	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

test_blank		8.33 518	11.11 521	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	100.00 1	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

eth-test2					0.00 558

eth-test					0.00 558

uanet_test		8.33 518	11.11 521	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	100.00 1	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

DCPMVS		8.33 518	11.11 521	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	100.00 1	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

cdsmvs_eth3d_5k		24.88 516	33.17 518	0.00 534	0.00 558	0.00 560	0.00 545	99.62 264	0.00 552	0.00 554	99.13 444	99.82 18	0.00 554	0.00 552	0.00 552	0.00 549

pcd_1.5k_mvsjas		16.61 517	22.14 520	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	100.00 1	99.28 93	0.00 554	0.00 552	0.00 552	0.00 549

sosnet-low-res		8.33 518	11.11 521	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	100.00 1	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

sosnet		8.33 518	11.11 521	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	100.00 1	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

uncertanet		8.33 518	11.11 521	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	100.00 1	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

Regformer		8.33 518	11.11 521	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	100.00 1	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

ab-mvs-re		8.26 528	11.02 531	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	99.16 441	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

uanet		8.33 518	11.11 521	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	100.00 1	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

WAC-MVS						96.36 489								95.20 502

PC_three_1452									97.56 455	99.68 208	99.41 370	99.09 127	97.09 544	96.66 442	99.60 375	99.62 188

test_241102_TWO								99.54 320	99.13 278	99.76 160	99.63 265	98.32 263	99.92 153	97.85 335	99.69 341	99.75 89

test_0728_THIRD									99.18 262	99.62 248	99.61 285	98.58 215	99.91 184	97.72 349	99.80 272	99.77 81

GSMVS																99.14 400

sam_mvs1												90.81 489				99.14 400

sam_mvs												90.52 495

MTGPA								99.53 331

test_post1							99.14 232				51.63 560	89.54 503	99.82 358	96.86 428

test_post											52.41 559	90.25 498	99.86 276

patchmatchnet-post											99.62 275	90.58 493	99.94 98

MTMP							99.09 258	98.59 477

test9_res														95.10 504	99.44 411	99.50 277

agg_prior2														94.58 511	99.46 410	99.50 277

test_prior4						99.19 280	98.00 450

test_prior2							97.95 456		97.87 441	98.05 488	99.05 457	97.90 304		95.99 479	99.49 404

旧先验2							97.94 457		95.33 515	98.94 415			99.88 240	96.75 436

新几何2							98.04 444

无先验							98.01 447	99.23 423	95.83 507				99.85 295	95.79 490		99.44 312

原ACMM2							97.92 459

testdata2													99.89 225	95.99 479

segment_acmp												98.37 255

testdata1							97.72 471		97.86 443

plane_prior5								99.54 320					99.82 358	95.84 487	99.78 286	99.60 208

plane_prior4											99.25 423

plane_prior3						99.31 245			98.36 389	99.14 392

plane_prior2							98.80 342		98.94 304

plane_prior						99.24 264	98.42 405		97.87 441						99.71 329

n2								0.00 559

nn								0.00 559

door-mid								99.83 115

test11								99.29 409

door								99.77 170

HQP5-MVS						98.94 326

BP-MVS														94.73 508

HQP4-MVS										98.15 482			99.70 445			99.53 257

HQP3-MVS								99.37 385							99.67 352

HQP2-MVS												96.67 372

MDTV_nov1_ep13_2view						91.44 542	99.14 232		97.37 469	99.21 379		91.78 475		96.75 436		99.03 432

ACMMP++_ref															99.94 135

ACMMP++															99.79 278

Test By Simon												98.41 249

High-resolution multi-view benchmark