High-res multi-view results

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

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

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

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

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

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

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

LCM-MVSNet		99.93 1	99.92 1	99.94 1	99.99 1	99.97 1	99.90 1	99.89 13	99.98 1	99.99 1	99.96 1	99.77 2	100.00 1	99.81 16	100.00 1	99.85 30

Gipuma		99.03 84	99.16 63	98.64 222	99.94 2	98.51 112	99.32 26	99.75 42	99.58 39	98.60 272	99.62 40	98.22 108	99.51 404	97.70 193	99.73 184	97.89 437
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 29	99.31 42	99.53 39	99.91 3	98.98 72	99.63 7	99.58 93	99.44 53	99.78 40	99.76 15	96.39 253	99.92 65	99.44 55	99.92 69	99.68 71

pmmvs6		99.67 3	99.70 3	99.60 16	99.90 4	99.27 28	99.53 9	99.76 39	99.64 27	99.84 30	99.83 4	99.50 9	99.87 134	99.36 58	99.92 69	99.64 84

PS-MVSNAJss		99.46 17	99.49 16	99.35 80	99.90 4	98.15 139	99.20 48	99.65 69	99.48 45	99.92 8	99.71 22	98.07 123	99.96 14	99.53 48	100.00 1	99.93 11

testf1		99.25 41	99.16 63	99.51 49	99.89 6	99.63 4	98.71 105	99.69 54	98.90 133	99.43 106	99.35 108	98.86 34	99.67 327	97.81 180	99.81 133	99.24 282

APD_test2		99.25 41	99.16 63	99.51 49	99.89 6	99.63 4	98.71 105	99.69 54	98.90 133	99.43 106	99.35 108	98.86 34	99.67 327	97.81 180	99.81 133	99.24 282

ANet_high		99.57 10	99.67 6	99.28 96	99.89 6	98.09 146	99.14 57	99.93 5	99.82 8	99.93 6	99.81 8	99.17 20	99.94 42	99.31 62	100.00 1	99.82 36

anonymousdsp		99.51 14	99.47 21	99.62 10	99.88 9	99.08 70	99.34 23	99.69 54	98.93 129	99.65 64	99.72 21	98.93 32	99.95 26	99.11 78	100.00 1	99.82 36

v7n		99.53 12	99.57 13	99.41 70	99.88 9	98.54 110	99.45 14	99.61 81	99.66 24	99.68 58	99.66 32	98.44 81	99.95 26	99.73 28	99.96 28	99.75 60

mvs_tets		99.63 6	99.67 6	99.49 55	99.88 9	98.61 102	99.34 23	99.71 47	99.27 74	99.90 14	99.74 18	99.68 4	99.97 7	99.55 43	99.99 5	99.88 20

test_fmvsmconf0.01_n		99.57 10	99.63 10	99.36 74	99.87 12	98.13 142	98.08 191	99.95 1	99.45 51	99.98 2	99.75 16	99.80 1	99.97 7	99.82 12	99.99 5	99.99 2

jajsoiax		99.58 9	99.61 11	99.48 57	99.87 12	98.61 102	99.28 40	99.66 65	99.09 108	99.89 18	99.68 25	99.53 7	99.97 7	99.50 51	99.99 5	99.87 22

test_djsdf		99.52 13	99.51 15	99.53 39	99.86 14	98.74 92	99.39 20	99.56 109	99.11 98	99.70 52	99.73 20	99.00 27	99.97 7	99.26 66	99.98 12	99.89 16

MIMVSNet1		99.38 28	99.32 40	99.55 29	99.86 14	99.19 43	99.41 17	99.59 90	99.59 37	99.71 50	99.57 49	97.12 208	99.90 81	99.21 71	99.87 98	99.54 142

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 27	99.85 16	99.11 65	99.90 1	99.78 36	99.63 29	99.78 40	99.67 30	99.48 10	99.81 222	99.30 63	99.97 21	99.77 50
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 17	99.34 20	99.69 5	99.58 93	99.90 3	99.86 24	99.78 13	99.58 6	99.95 26	99.00 88	99.95 38	99.78 47

SixPastTwentyTwo		98.75 134	98.62 149	99.16 118	99.83 18	97.96 166	99.28 40	98.20 384	99.37 61	99.70 52	99.65 36	92.65 359	99.93 54	99.04 85	99.84 112	99.60 100

sc_t1		99.62 7	99.66 8	99.53 39	99.82 19	99.09 69	99.50 11	99.63 73	99.88 4	99.86 24	99.80 11	99.03 24	99.89 97	99.48 53	99.93 56	99.60 100

Baseline_NR-MVSNet		98.98 92	98.86 111	99.36 74	99.82 19	98.55 107	97.47 299	99.57 100	99.37 61	99.21 163	99.61 43	96.76 235	99.83 192	98.06 157	99.83 122	99.71 63

pm-mvs1		99.44 19	99.48 18	99.33 89	99.80 21	98.63 99	99.29 36	99.63 73	99.30 71	99.65 64	99.60 45	99.16 22	99.82 205	99.07 81	99.83 122	99.56 129

TransMVSNet (Re)		99.44 19	99.47 21	99.36 74	99.80 21	98.58 105	99.27 42	99.57 100	99.39 59	99.75 45	99.62 40	99.17 20	99.83 192	99.06 83	99.62 243	99.66 78

K. test v3		98.00 253	97.66 278	99.03 145	99.79 23	97.56 202	99.19 52	92.47 470	99.62 33	99.52 88	99.66 32	89.61 391	99.96 14	99.25 68	99.81 133	99.56 129

test_fmvsmconf0.1_n		99.49 15	99.54 14	99.34 83	99.78 24	98.11 143	97.77 248	99.90 11	99.33 66	99.97 3	99.66 32	99.71 3	99.96 14	99.79 19	99.99 5	99.96 8

APD_test1		98.83 118	98.66 142	99.34 83	99.78 24	99.47 9	98.42 150	99.45 158	98.28 191	98.98 200	99.19 153	97.76 155	99.58 378	96.57 293	99.55 270	98.97 339

test_vis3_rt		99.14 63	99.17 61	99.07 135	99.78 24	98.38 119	98.92 82	99.94 2	97.80 237	99.91 12	99.67 30	97.15 207	98.91 463	99.76 23	99.56 266	99.92 12

EGC-MVSNET		85.24 449	80.54 452	99.34 83	99.77 27	99.20 40	99.08 61	99.29 238	12.08 488	20.84 489	99.42 90	97.55 174	99.85 156	97.08 239	99.72 192	98.96 341

Anonymous20240521		98.69 147	98.87 107	98.16 299	99.77 27	95.11 341	99.08 61	99.44 166	99.34 65	99.33 130	99.55 57	94.10 334	99.94 42	99.25 68	99.96 28	99.42 211

FC-MVSNet-test		99.27 38	99.25 53	99.34 83	99.77 27	98.37 121	99.30 35	99.57 100	99.61 35	99.40 115	99.50 69	97.12 208	99.85 156	99.02 87	99.94 50	99.80 42

test_vis1_n		98.31 217	98.50 169	97.73 336	99.76 30	94.17 371	98.68 108	99.91 9	96.31 353	99.79 39	99.57 49	92.85 355	99.42 424	99.79 19	99.84 112	99.60 100

test_fmvs3		99.12 70	99.41 26	98.25 287	99.76 30	95.07 342	99.05 67	99.94 2	97.78 240	99.82 34	99.84 3	98.56 71	99.71 299	99.96 1	99.96 28	99.97 4

XXY-MVS		99.14 63	99.15 68	99.10 128	99.76 30	97.74 191	98.85 92	99.62 78	98.48 174	99.37 120	99.49 75	98.75 46	99.86 143	98.20 147	99.80 144	99.71 63

TDRefinement		99.42 24	99.38 29	99.55 29	99.76 30	99.33 21	99.68 6	99.71 47	99.38 60	99.53 83	99.61 43	98.64 59	99.80 231	98.24 142	99.84 112	99.52 157

fmvsm_s_conf0.1_n_a		99.17 53	99.30 45	98.80 187	99.75 34	96.59 273	97.97 221	99.86 16	98.22 194	99.88 21	99.71 22	98.59 65	99.84 174	99.73 28	99.98 12	99.98 3

tt0805		98.69 147	98.62 149	98.90 171	99.75 34	99.30 23	99.15 56	96.97 421	98.86 139	98.87 233	97.62 397	98.63 61	98.96 460	99.41 57	98.29 410	98.45 403

test_vis1_n_1920		98.40 200	98.92 99	96.81 398	99.74 36	90.76 449	98.15 179	99.91 9	98.33 182	99.89 18	99.55 57	95.07 305	99.88 115	99.76 23	99.93 56	99.79 44

FOURS1					99.73 37	99.67 3	99.43 15	99.54 118	99.43 55	99.26 148

PEN-MVS		99.41 25	99.34 36	99.62 10	99.73 37	99.14 58	99.29 36	99.54 118	99.62 33	99.56 74	99.42 90	98.16 117	99.96 14	98.78 103	99.93 56	99.77 50

lessismore_v0				98.97 157	99.73 37	97.53 204		86.71 485		99.37 120	99.52 68	89.93 387	99.92 65	98.99 89	99.72 192	99.44 202

SteuartSystems-ACMMP		98.79 127	98.54 162	99.54 32	99.73 37	99.16 49	98.23 169	99.31 222	97.92 228	98.90 222	98.90 240	98.00 129	99.88 115	96.15 325	99.72 192	99.58 115
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 238	98.15 230	98.22 293	99.73 37	95.15 338	97.36 313	99.68 60	94.45 411	98.99 199	99.27 128	96.87 224	99.94 42	97.13 236	99.91 78	99.57 123

Vis-MVSNet		99.34 30	99.36 33	99.27 99	99.73 37	98.26 128	99.17 53	99.78 36	99.11 98	99.27 144	99.48 76	98.82 37	99.95 26	98.94 92	99.93 56	99.59 107
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
tt0320-xc		99.64 5	99.68 5	99.50 54	99.72 43	98.98 72	99.51 10	99.85 18	99.86 6	99.88 21	99.82 5	99.02 26	99.90 81	99.54 44	99.95 38	99.61 98

SSC-MVS		98.71 138	98.74 122	98.62 228	99.72 43	96.08 298	98.74 98	98.64 363	99.74 13	99.67 60	99.24 141	94.57 320	99.95 26	99.11 78	99.24 334	99.82 36

test_f		98.67 156	98.87 107	98.05 309	99.72 43	95.59 313	98.51 134	99.81 31	96.30 355	99.78 40	99.82 5	96.14 264	98.63 470	99.82 12	99.93 56	99.95 9

ACMH	96.65 7	99.25 41	99.24 54	99.26 101	99.72 43	98.38 119	99.07 64	99.55 113	98.30 186	99.65 64	99.45 85	99.22 17	99.76 267	98.44 129	99.77 161	99.64 84
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0320		99.61 8	99.65 9	99.48 57	99.71 47	98.94 79	99.54 8	99.83 25	99.87 5	99.89 18	99.82 5	98.75 46	99.90 81	99.54 44	99.95 38	99.59 107

fmvsm_s_conf0.1_n		99.16 57	99.33 38	98.64 222	99.71 47	96.10 293	97.87 234	99.85 18	98.56 170	99.90 14	99.68 25	98.69 55	99.85 156	99.72 30	99.98 12	99.97 4

PS-CasMVS		99.40 26	99.33 38	99.62 10	99.71 47	99.10 66	99.29 36	99.53 122	99.53 42	99.46 101	99.41 94	98.23 105	99.95 26	98.89 97	99.95 38	99.81 40

DTE-MVSNet		99.43 23	99.35 34	99.66 7	99.71 47	99.30 23	99.31 30	99.51 128	99.64 27	99.56 74	99.46 81	98.23 105	99.97 7	98.78 103	99.93 56	99.72 62

WR-MVS_H		99.33 31	99.22 55	99.65 8	99.71 47	99.24 31	99.32 26	99.55 113	99.46 50	99.50 94	99.34 112	97.30 196	99.93 54	98.90 95	99.93 56	99.77 50

HPM-MVS_fast		99.01 86	98.82 115	99.57 22	99.71 47	99.35 17	99.00 72	99.50 131	97.33 286	98.94 217	98.86 250	98.75 46	99.82 205	97.53 205	99.71 201	99.56 129

ACMH+	96.62 9	99.08 77	99.00 91	99.33 89	99.71 47	98.83 87	98.60 120	99.58 93	99.11 98	99.53 83	99.18 157	98.81 38	99.67 327	96.71 277	99.77 161	99.50 165

PMVS	91.26 20	97.86 267	97.94 254	97.65 343	99.71 47	97.94 168	98.52 129	98.68 359	98.99 121	97.52 366	99.35 108	97.41 189	98.18 476	91.59 439	99.67 222	96.82 465
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FE-MVSNET2		99.15 58	99.22 55	98.94 161	99.70 55	97.49 205	98.62 117	99.67 64	98.85 142	99.34 127	99.54 63	98.47 75	99.81 222	98.93 93	99.91 78	99.51 161

KinetiMVS		99.03 84	99.02 87	99.03 145	99.70 55	97.48 208	98.43 147	99.29 238	99.70 16	99.60 71	99.07 186	96.13 265	99.94 42	99.42 56	99.87 98	99.68 71

FIs		99.14 63	99.09 79	99.29 95	99.70 55	98.28 127	99.13 58	99.52 127	99.48 45	99.24 157	99.41 94	96.79 232	99.82 205	98.69 113	99.88 94	99.76 56

VPNet		98.87 108	98.83 114	99.01 149	99.70 55	97.62 200	98.43 147	99.35 203	99.47 48	99.28 142	99.05 194	96.72 238	99.82 205	98.09 154	99.36 313	99.59 107

fmvsm_s_conf0.1_n_2		99.20 51	99.38 29	98.65 220	99.69 59	96.08 298	97.49 294	99.90 11	99.53 42	99.88 21	99.64 37	98.51 74	99.90 81	99.83 10	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 214	98.68 137	97.27 374	99.69 59	92.29 423	98.03 202	99.85 18	97.62 250	99.96 4	99.62 40	93.98 335	99.74 281	99.52 50	99.86 105	99.79 44

MP-MVS-pluss		98.57 173	98.23 218	99.60 16	99.69 59	99.35 17	97.16 335	99.38 189	94.87 401	98.97 204	98.99 216	98.01 128	99.88 115	97.29 223	99.70 208	99.58 115
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 46	99.32 40	98.96 158	99.68 62	97.35 216	98.84 94	99.48 141	99.69 18	99.63 67	99.68 25	99.03 24	99.96 14	97.97 168	99.92 69	99.57 123

sd_testset		99.28 37	99.31 42	99.19 112	99.68 62	98.06 155	99.41 17	99.30 230	99.69 18	99.63 67	99.68 25	99.25 16	99.96 14	97.25 226	99.92 69	99.57 123

test_fmvs1_n		98.09 244	98.28 209	97.52 360	99.68 62	93.47 402	98.63 115	99.93 5	95.41 389	99.68 58	99.64 37	91.88 370	99.48 411	99.82 12	99.87 98	99.62 90

CHOSEN 1792x2688		97.49 296	97.14 311	98.54 251	99.68 62	96.09 296	96.50 371	99.62 78	91.58 449	98.84 236	98.97 223	92.36 361	99.88 115	96.76 270	99.95 38	99.67 76

tfpnnormal		98.90 103	98.90 101	98.91 168	99.67 66	97.82 183	99.00 72	99.44 166	99.45 51	99.51 93	99.24 141	98.20 112	99.86 143	95.92 334	99.69 211	99.04 325

MTAPA		98.88 107	98.64 145	99.61 14	99.67 66	99.36 16	98.43 147	99.20 262	98.83 144	98.89 225	98.90 240	96.98 218	99.92 65	97.16 231	99.70 208	99.56 129

test_fmvsmvis_n_1920		99.26 40	99.49 16	98.54 251	99.66 68	96.97 252	98.00 209	99.85 18	99.24 76	99.92 8	99.50 69	99.39 12	99.95 26	99.89 3	99.98 12	98.71 380

mvs5depth		99.30 34	99.59 12	98.44 265	99.65 69	95.35 330	99.82 3	99.94 2	99.83 7	99.42 110	99.94 2	98.13 120	99.96 14	99.63 36	99.96 28	100.00 1

fmvsm_l_conf0.5_n_a		99.19 52	99.27 48	98.94 161	99.65 69	97.05 247	97.80 243	99.76 39	98.70 152	99.78 40	99.11 176	98.79 42	99.95 26	99.85 6	99.96 28	99.83 33

WB-MVS		98.52 187	98.55 160	98.43 266	99.65 69	95.59 313	98.52 129	98.77 348	99.65 26	99.52 88	99.00 214	94.34 326	99.93 54	98.65 115	98.83 382	99.76 56

CP-MVSNet		99.21 48	99.09 79	99.56 27	99.65 69	98.96 78	99.13 58	99.34 209	99.42 56	99.33 130	99.26 134	97.01 216	99.94 42	98.74 108	99.93 56	99.79 44

HPM-MVS		98.79 127	98.53 164	99.59 20	99.65 69	99.29 25	99.16 54	99.43 172	96.74 333	98.61 270	98.38 341	98.62 62	99.87 134	96.47 305	99.67 222	99.59 107
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 165	98.36 195	99.42 68	99.65 69	99.42 11	98.55 125	99.57 100	97.72 244	98.90 222	99.26 134	96.12 267	99.52 399	95.72 345	99.71 201	99.32 258

NormalMVS		98.26 224	97.97 251	99.15 121	99.64 75	97.83 178	98.28 163	99.43 172	99.24 76	98.80 244	98.85 253	89.76 389	99.94 42	98.04 159	99.67 222	99.68 71

lecture		99.25 41	99.12 71	99.62 10	99.64 75	99.40 12	98.89 87	99.51 128	99.19 88	99.37 120	99.25 139	98.36 86	99.88 115	98.23 144	99.67 222	99.59 107

fmvsm_l_conf0.5_n		99.21 48	99.28 47	99.02 148	99.64 75	97.28 226	97.82 239	99.76 39	98.73 146	99.82 34	99.09 184	98.81 38	99.95 26	99.86 4	99.96 28	99.83 33

test_fmvsmconf_n		99.44 19	99.48 18	99.31 94	99.64 75	98.10 145	97.68 262	99.84 22	99.29 72	99.92 8	99.57 49	99.60 5	99.96 14	99.74 27	99.98 12	99.89 16

TSAR-MVS + MP.		98.63 162	98.49 174	99.06 141	99.64 75	97.90 172	98.51 134	98.94 313	96.96 317	99.24 157	98.89 246	97.83 147	99.81 222	96.88 260	99.49 292	99.48 183
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 121	98.72 126	99.12 124	99.64 75	98.54 110	97.98 217	99.68 60	97.62 250	99.34 127	99.18 157	97.54 176	99.77 261	97.79 182	99.74 181	99.04 325

Elysia		99.15 58	99.14 69	99.18 113	99.63 81	97.92 169	98.50 136	99.43 172	99.67 21	99.70 52	99.13 172	96.66 241	99.98 4	99.54 44	99.96 28	99.64 84

StellarMVS		99.15 58	99.14 69	99.18 113	99.63 81	97.92 169	98.50 136	99.43 172	99.67 21	99.70 52	99.13 172	96.66 241	99.98 4	99.54 44	99.96 28	99.64 84

KD-MVS_self_test		99.25 41	99.18 60	99.44 66	99.63 81	99.06 71	98.69 107	99.54 118	99.31 69	99.62 70	99.53 65	97.36 193	99.86 143	99.24 70	99.71 201	99.39 224

EU-MVSNet		97.66 284	98.50 169	95.13 440	99.63 81	85.84 471	98.35 159	98.21 383	98.23 193	99.54 79	99.46 81	95.02 306	99.68 323	98.24 142	99.87 98	99.87 22

HyFIR lowres test		97.19 323	96.60 347	98.96 158	99.62 85	97.28 226	95.17 437	99.50 131	94.21 416	99.01 194	98.32 349	86.61 409	99.99 2	97.10 238	99.84 112	99.60 100

E6new		99.05 80	99.11 72	98.85 175	99.60 86	97.30 221	98.42 150	99.63 73	98.73 146	99.26 148	99.39 100	98.71 50	99.70 306	98.43 131	99.84 112	99.54 142

E6		99.05 80	99.11 72	98.85 175	99.60 86	97.30 221	98.42 150	99.63 73	98.73 146	99.26 148	99.39 100	98.71 50	99.70 306	98.43 131	99.84 112	99.54 142

E5		99.05 80	99.11 72	98.85 175	99.60 86	97.30 221	98.42 150	99.63 73	98.73 146	99.26 148	99.39 100	98.71 50	99.70 306	98.43 131	99.84 112	99.54 142

fmvsm_l_conf0.5_n_9		99.32 33	99.43 24	98.98 155	99.59 89	97.18 238	97.44 303	99.83 25	99.56 40	99.91 12	99.34 112	99.36 13	99.93 54	99.83 10	99.98 12	99.85 30

fmvsm_l_conf0.5_n_3		99.45 18	99.48 18	99.34 83	99.59 89	98.21 136	97.82 239	99.84 22	99.41 58	99.92 8	99.41 94	99.51 8	99.95 26	99.84 9	99.97 21	99.87 22

MED-MVS test				99.45 64	99.58 91	98.93 80	98.68 108	99.60 83	96.46 346	99.53 83	98.77 273		99.83 192	96.67 282	99.64 233	99.58 115

MED-MVS		98.90 103	98.72 126	99.45 64	99.58 91	98.93 80	98.68 108	99.60 83	98.14 212	99.53 83	98.77 273	97.87 144	99.83 192	96.67 282	99.64 233	99.58 115

TestfortrainingZip a		98.95 96	98.72 126	99.64 9	99.58 91	99.32 22	98.68 108	99.60 83	96.46 346	99.53 83	98.77 273	97.87 144	99.83 192	98.39 135	99.64 233	99.77 50

FE-MVSNET		98.59 170	98.50 169	98.87 172	99.58 91	97.30 221	98.08 191	99.74 43	96.94 319	98.97 204	99.10 179	96.94 220	99.74 281	97.33 221	99.86 105	99.55 136

mmtdpeth		99.30 34	99.42 25	98.92 167	99.58 91	96.89 260	99.48 13	99.92 7	99.92 2	98.26 308	99.80 11	98.33 92	99.91 74	99.56 41	99.95 38	99.97 4

ACMMP_NAP		98.75 134	98.48 175	99.57 22	99.58 91	99.29 25	97.82 239	99.25 251	96.94 319	98.78 246	99.12 175	98.02 127	99.84 174	97.13 236	99.67 222	99.59 107

nrg030		99.40 26	99.35 34	99.54 32	99.58 91	99.13 61	98.98 75	99.48 141	99.68 20	99.46 101	99.26 134	98.62 62	99.73 288	99.17 75	99.92 69	99.76 56

VDDNet		98.21 231	97.95 252	99.01 149	99.58 91	97.74 191	99.01 70	97.29 412	99.67 21	98.97 204	99.50 69	90.45 384	99.80 231	97.88 175	99.20 342	99.48 183

COLMAP_ROB	96.50 10	98.99 89	98.85 113	99.41 70	99.58 91	99.10 66	98.74 98	99.56 109	99.09 108	99.33 130	99.19 153	98.40 83	99.72 298	95.98 332	99.76 176	99.42 211
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_fmvsm_n_1920		99.33 31	99.45 23	98.99 151	99.57 100	97.73 193	97.93 223	99.83 25	99.22 79	99.93 6	99.30 122	99.42 11	99.96 14	99.85 6	99.99 5	99.29 268

ZNCC-MVS		98.68 153	98.40 187	99.54 32	99.57 100	99.21 34	98.46 144	99.29 238	97.28 292	98.11 320	98.39 339	98.00 129	99.87 134	96.86 263	99.64 233	99.55 136

MSP-MVS		98.40 200	98.00 246	99.61 14	99.57 100	99.25 30	98.57 123	99.35 203	97.55 261	99.31 138	97.71 390	94.61 319	99.88 115	96.14 326	99.19 345	99.70 68
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
testgi		98.32 215	98.39 190	98.13 300	99.57 100	95.54 316	97.78 245	99.49 139	97.37 283	99.19 165	97.65 394	98.96 29	99.49 408	96.50 304	98.99 370	99.34 249

MP-MVS		98.46 193	98.09 235	99.54 32	99.57 100	99.22 33	98.50 136	99.19 266	97.61 253	97.58 360	98.66 301	97.40 190	99.88 115	94.72 371	99.60 250	99.54 142
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 138	98.46 179	99.47 61	99.57 100	98.97 74	98.23 169	99.48 141	96.60 338	99.10 176	99.06 187	98.71 50	99.83 192	95.58 352	99.78 155	99.62 90

LGP-MVS_train				99.47 61	99.57 100	98.97 74		99.48 141	96.60 338	99.10 176	99.06 187	98.71 50	99.83 192	95.58 352	99.78 155	99.62 90

IS-MVSNet		98.19 234	97.90 260	99.08 133	99.57 100	97.97 163	99.31 30	98.32 379	99.01 120	98.98 200	99.03 198	91.59 372	99.79 244	95.49 354	99.80 144	99.48 183

viewdifsd2359ckpt11		98.84 115	99.04 84	98.24 289	99.56 108	95.51 318	97.38 308	99.70 52	99.16 93	99.57 72	99.40 97	98.26 101	99.71 299	98.55 124	99.82 127	99.50 165

viewmsd2359difaftdt		98.84 115	99.04 84	98.24 289	99.56 108	95.51 318	97.38 308	99.70 52	99.16 93	99.57 72	99.40 97	98.26 101	99.71 299	98.55 124	99.82 127	99.50 165

dcpmvs_2		98.78 129	99.11 72	97.78 326	99.56 108	93.67 397	99.06 65	99.86 16	99.50 44	99.66 61	99.26 134	97.21 204	99.99 2	98.00 164	99.91 78	99.68 71

test_0402		98.76 133	98.71 131	98.93 164	99.56 108	98.14 141	98.45 146	99.34 209	99.28 73	98.95 210	98.91 237	98.34 91	99.79 244	95.63 349	99.91 78	98.86 358

EPP-MVSNet		98.30 218	98.04 242	99.07 135	99.56 108	97.83 178	99.29 36	98.07 390	99.03 118	98.59 274	99.13 172	92.16 365	99.90 81	96.87 261	99.68 216	99.49 172

ACMMP		98.75 134	98.50 169	99.52 45	99.56 108	99.16 49	98.87 88	99.37 193	97.16 307	98.82 240	99.01 210	97.71 158	99.87 134	96.29 317	99.69 211	99.54 142
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
fmvsm_s_conf0.5_n_a		99.10 72	99.20 59	98.78 194	99.55 114	96.59 273	97.79 244	99.82 30	98.21 196	99.81 37	99.53 65	98.46 79	99.84 174	99.70 33	99.97 21	99.90 15

fmvsm_s_conf0.5_n		99.09 73	99.26 51	98.61 232	99.55 114	96.09 296	97.74 255	99.81 31	98.55 171	99.85 27	99.55 57	98.60 64	99.84 174	99.69 35	99.98 12	99.89 16

FMVSNet1		99.17 53	99.17 61	99.17 115	99.55 114	98.24 130	99.20 48	99.44 166	99.21 81	99.43 106	99.55 57	97.82 150	99.86 143	98.42 134	99.89 92	99.41 214

Vis-MVSNet (Re-imp)		97.46 298	97.16 308	98.34 278	99.55 114	96.10 293	98.94 80	98.44 373	98.32 184	98.16 314	98.62 310	88.76 396	99.73 288	93.88 397	99.79 150	99.18 302

ACMM	96.08 12	98.91 101	98.73 124	99.48 57	99.55 114	99.14 58	98.07 195	99.37 193	97.62 250	99.04 190	98.96 226	98.84 36	99.79 244	97.43 215	99.65 231	99.49 172
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 143	98.97 95	97.89 318	99.54 119	94.05 374	98.55 125	99.92 7	96.78 331	99.72 48	99.78 13	96.60 245	99.67 327	99.91 2	99.90 86	99.94 10

mPP-MVS		98.64 160	98.34 198	99.54 32	99.54 119	99.17 45	98.63 115	99.24 256	97.47 269	98.09 322	98.68 296	97.62 167	99.89 97	96.22 320	99.62 243	99.57 123

XVG-ACMP-BASELINE		98.56 174	98.34 198	99.22 109	99.54 119	98.59 104	97.71 258	99.46 154	97.25 295	98.98 200	98.99 216	97.54 176	99.84 174	95.88 335	99.74 181	99.23 284

viewmacassd2359aftdt		98.86 112	98.87 107	98.83 180	99.53 122	97.32 220	97.70 260	99.64 71	98.22 194	99.25 155	99.27 128	98.40 83	99.61 364	97.98 167	99.87 98	99.55 136

region2R		98.69 147	98.40 187	99.54 32	99.53 122	99.17 45	98.52 129	99.31 222	97.46 274	98.44 293	98.51 324	97.83 147	99.88 115	96.46 306	99.58 259	99.58 115

PGM-MVS		98.66 157	98.37 194	99.55 29	99.53 122	99.18 44	98.23 169	99.49 139	97.01 316	98.69 257	98.88 247	98.00 129	99.89 97	95.87 338	99.59 254	99.58 115

E4		98.87 108	98.88 104	98.81 184	99.52 125	97.23 229	97.62 273	99.61 81	98.58 165	99.18 169	99.33 115	98.29 95	99.69 313	97.99 166	99.83 122	99.52 157

Patchmatch-RL test		97.26 316	97.02 317	97.99 313	99.52 125	95.53 317	96.13 396	99.71 47	97.47 269	99.27 144	99.16 163	84.30 431	99.62 357	97.89 172	99.77 161	98.81 366

ACMMPR		98.70 143	98.42 185	99.54 32	99.52 125	99.14 58	98.52 129	99.31 222	97.47 269	98.56 280	98.54 319	97.75 156	99.88 115	96.57 293	99.59 254	99.58 115

fmvsm_s_conf0.5_n_9		99.17 53	99.38 29	98.53 253	99.51 128	95.82 308	97.62 273	99.78 36	99.72 15	99.90 14	99.48 76	98.66 57	99.89 97	99.85 6	99.93 56	99.89 16

AstraMVS		98.16 240	98.07 240	98.41 268	99.51 128	95.86 305	98.00 209	95.14 453	98.97 124	99.43 106	99.24 141	93.25 343	99.84 174	99.21 71	99.87 98	99.54 142

fmvsm_s_conf0.5_n_8		99.13 67	99.26 51	98.74 207	99.51 128	96.44 285	97.65 268	99.65 69	99.66 24	99.78 40	99.48 76	97.92 137	99.93 54	99.72 30	99.95 38	99.87 22

GST-MVS		98.61 166	98.30 206	99.52 45	99.51 128	99.20 40	98.26 167	99.25 251	97.44 277	98.67 260	98.39 339	97.68 159	99.85 156	96.00 330	99.51 282	99.52 157

Anonymous20231206		98.21 231	98.21 219	98.20 294	99.51 128	95.43 327	98.13 181	99.32 217	96.16 360	98.93 218	98.82 263	96.00 272	99.83 192	97.32 222	99.73 184	99.36 242

ACMP	95.32 15	98.41 197	98.09 235	99.36 74	99.51 128	98.79 90	97.68 262	99.38 189	95.76 376	98.81 242	98.82 263	98.36 86	99.82 205	94.75 368	99.77 161	99.48 183
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LuminaMVS		98.39 206	98.20 220	98.98 155	99.50 134	97.49 205	97.78 245	97.69 399	98.75 145	99.49 95	99.25 139	92.30 363	99.94 42	99.14 76	99.88 94	99.50 165

DVP-MVS		98.77 132	98.52 165	99.52 45	99.50 134	99.21 34	98.02 205	98.84 337	97.97 222	99.08 178	99.02 199	97.61 169	99.88 115	96.99 247	99.63 240	99.48 183
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				99.60 16	99.50 134	99.23 32	98.02 205	99.32 217					99.88 115	96.99 247	99.63 240	99.68 71

test0726					99.50 134	99.21 34	98.17 177	99.35 203	97.97 222	99.26 148	99.06 187	97.61 169

AllTest		98.44 195	98.20 220	99.16 118	99.50 134	98.55 107	98.25 168	99.58 93	96.80 329	98.88 229	99.06 187	97.65 162	99.57 380	94.45 378	99.61 248	99.37 235

TestCases				99.16 118	99.50 134	98.55 107		99.58 93	96.80 329	98.88 229	99.06 187	97.65 162	99.57 380	94.45 378	99.61 248	99.37 235

XVG-OURS		98.53 183	98.34 198	99.11 126	99.50 134	98.82 89	95.97 402	99.50 131	97.30 290	99.05 188	98.98 221	99.35 14	99.32 438	95.72 345	99.68 216	99.18 302

EG-PatchMatch MVS		98.99 89	99.01 89	98.94 161	99.50 134	97.47 209	98.04 200	99.59 90	98.15 211	99.40 115	99.36 107	98.58 70	99.76 267	98.78 103	99.68 216	99.59 107

fmvsm_s_conf0.5_n_2		99.14 63	99.31 42	98.63 226	99.49 142	96.08 298	97.38 308	99.81 31	99.48 45	99.84 30	99.57 49	98.46 79	99.89 97	99.82 12	99.97 21	99.91 13

SED-MVS		98.91 101	98.72 126	99.49 55	99.49 142	99.17 45	98.10 188	99.31 222	98.03 218	99.66 61	99.02 199	98.36 86	99.88 115	96.91 253	99.62 243	99.41 214

IU-MVS					99.49 142	99.15 53		98.87 328	92.97 434	99.41 112				96.76 270	99.62 243	99.66 78

test_241102_ONE					99.49 142	99.17 45		99.31 222	97.98 221	99.66 61	98.90 240	98.36 86	99.48 411

UA-Net		99.47 16	99.40 27	99.70 2	99.49 142	99.29 25	99.80 4	99.72 45	99.82 8	99.04 190	99.81 8	98.05 126	99.96 14	98.85 99	99.99 5	99.86 28

HFP-MVS		98.71 138	98.44 182	99.51 49	99.49 142	99.16 49	98.52 129	99.31 222	97.47 269	98.58 276	98.50 328	97.97 133	99.85 156	96.57 293	99.59 254	99.53 154

VPA-MVSNet		99.30 34	99.30 45	99.28 96	99.49 142	98.36 124	99.00 72	99.45 158	99.63 29	99.52 88	99.44 86	98.25 103	99.88 115	99.09 80	99.84 112	99.62 90

XVG-OURS-SEG-HR		98.49 190	98.28 209	99.14 122	99.49 142	98.83 87	96.54 367	99.48 141	97.32 288	99.11 173	98.61 312	99.33 15	99.30 441	96.23 319	98.38 406	99.28 271

fmvsm_s_conf0.5_n_11		99.21 48	99.34 36	98.80 187	99.48 150	96.56 278	97.97 221	99.69 54	99.63 29	99.84 30	99.54 63	98.21 110	99.94 42	99.76 23	99.95 38	99.88 20

114514_t		96.50 356	95.77 365	98.69 215	99.48 150	97.43 213	97.84 238	99.55 113	81.42 481	96.51 420	98.58 316	95.53 292	99.67 327	93.41 410	99.58 259	98.98 335

IterMVS-LS		98.55 178	98.70 134	98.09 302	99.48 150	94.73 354	97.22 329	99.39 187	98.97 124	99.38 118	99.31 121	96.00 272	99.93 54	98.58 118	99.97 21	99.60 100
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
fmvsm_s_conf0.5_n_10		99.15 58	99.27 48	98.78 194	99.47 153	96.56 278	97.75 254	99.71 47	99.60 36	99.74 47	99.44 86	97.96 134	99.95 26	99.86 4	99.94 50	99.82 36

fmvsm_s_conf0.5_n_5		99.07 79	99.10 77	98.99 151	99.47 153	97.22 232	97.40 305	99.83 25	97.61 253	99.85 27	99.30 122	98.80 40	99.95 26	99.71 32	99.90 86	99.78 47

v8		99.01 86	99.16 63	98.57 239	99.47 153	96.31 290	98.90 83	99.47 150	99.03 118	99.52 88	99.57 49	96.93 221	99.81 222	99.60 37	99.98 12	99.60 100

SSC-MVS3.2		98.53 183	98.79 118	97.74 333	99.46 156	93.62 400	96.45 373	99.34 209	99.33 66	98.93 218	98.70 292	97.90 138	99.90 81	99.12 77	99.92 69	99.69 70

fmvsm_s_conf0.5_n_3		99.22 47	99.37 32	98.78 194	99.46 156	96.58 276	97.65 268	99.72 45	99.47 48	99.86 24	99.50 69	98.94 30	99.89 97	99.75 26	99.97 21	99.86 28

XVS		98.72 137	98.45 180	99.53 39	99.46 156	99.21 34	98.65 113	99.34 209	98.62 159	97.54 364	98.63 308	97.50 182	99.83 192	96.79 266	99.53 276	99.56 129

X-MVStestdata		94.32 406	92.59 425	99.53 39	99.46 156	99.21 34	98.65 113	99.34 209	98.62 159	97.54 364	45.85 486	97.50 182	99.83 192	96.79 266	99.53 276	99.56 129

test20.03		98.78 129	98.77 121	98.78 194	99.46 156	97.20 235	97.78 245	99.24 256	99.04 117	99.41 112	98.90 240	97.65 162	99.76 267	97.70 193	99.79 150	99.39 224

guyue		98.01 252	97.93 256	98.26 285	99.45 161	95.48 322	98.08 191	96.24 436	98.89 135	99.34 127	99.14 170	91.32 376	99.82 205	99.07 81	99.83 122	99.48 183

CSCG		98.68 153	98.50 169	99.20 110	99.45 161	98.63 99	98.56 124	99.57 100	97.87 232	98.85 234	98.04 370	97.66 161	99.84 174	96.72 275	99.81 133	99.13 314

GeoE		99.05 80	98.99 93	99.25 104	99.44 163	98.35 125	98.73 102	99.56 109	98.42 177	98.91 221	98.81 266	98.94 30	99.91 74	98.35 137	99.73 184	99.49 172

v148		98.45 194	98.60 154	98.00 312	99.44 163	94.98 344	97.44 303	99.06 292	98.30 186	99.32 136	98.97 223	96.65 243	99.62 357	98.37 136	99.85 107	99.39 224

v10		98.97 93	99.11 72	98.55 246	99.44 163	96.21 292	98.90 83	99.55 113	98.73 146	99.48 96	99.60 45	96.63 244	99.83 192	99.70 33	99.99 5	99.61 98

V42		98.78 129	98.78 120	98.76 201	99.44 163	97.04 248	98.27 166	99.19 266	97.87 232	99.25 155	99.16 163	96.84 225	99.78 255	99.21 71	99.84 112	99.46 193

MDA-MVSNet-bldmvs		97.94 258	97.91 259	98.06 307	99.44 163	94.96 345	96.63 363	99.15 282	98.35 180	98.83 237	99.11 176	94.31 327	99.85 156	96.60 290	98.72 388	99.37 235

viewdifsd2359ckpt07		98.71 138	98.86 111	98.26 285	99.43 168	95.65 312	97.20 330	99.66 65	99.20 83	99.29 140	99.01 210	98.29 95	99.73 288	97.92 171	99.75 180	99.39 224

casdiffmvs_mvg		99.12 70	99.16 63	98.99 151	99.43 168	97.73 193	98.00 209	99.62 78	99.22 79	99.55 77	99.22 147	98.93 32	99.75 275	98.66 114	99.81 133	99.50 165
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SSM_0404		98.90 103	99.01 89	98.57 239	99.42 170	96.59 273	98.13 181	99.66 65	99.09 108	99.30 139	99.02 199	98.79 42	99.89 97	97.87 177	99.80 144	99.23 284

test1111		96.49 357	96.82 331	95.52 433	99.42 170	87.08 468	99.22 45	87.14 484	99.11 98	99.46 101	99.58 47	88.69 397	99.86 143	98.80 101	99.95 38	99.62 90

v2v482		98.56 174	98.62 149	98.37 275	99.42 170	95.81 309	97.58 282	99.16 277	97.90 230	99.28 142	99.01 210	95.98 277	99.79 244	99.33 60	99.90 86	99.51 161

OPM-MVS		98.56 174	98.32 204	99.25 104	99.41 173	98.73 95	97.13 337	99.18 270	97.10 310	98.75 252	98.92 234	98.18 113	99.65 347	96.68 281	99.56 266	99.37 235
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 246	98.08 238	98.04 310	99.41 173	94.59 360	94.59 455	99.40 185	97.50 266	98.82 240	98.83 260	96.83 227	99.84 174	97.50 208	99.81 133	99.71 63

E2		98.70 143	98.68 137	98.73 209	99.40 175	97.10 245	97.48 295	99.57 100	98.09 215	99.00 195	99.20 150	97.90 138	99.67 327	97.73 191	99.77 161	99.43 206

E3		98.69 147	98.68 137	98.73 209	99.40 175	97.10 245	97.48 295	99.57 100	98.09 215	99.00 195	99.20 150	97.90 138	99.67 327	97.73 191	99.77 161	99.43 206

test_one_0601					99.39 177	99.20 40		99.31 222	98.49 173	98.66 262	99.02 199	97.64 165

mvsany_test3		98.87 108	98.92 99	98.74 207	99.38 178	96.94 256	98.58 122	99.10 287	96.49 343	99.96 4	99.81 8	98.18 113	99.45 419	98.97 90	99.79 150	99.83 33

patch_mono-2		98.51 188	98.63 147	98.17 297	99.38 178	94.78 351	97.36 313	99.69 54	98.16 206	98.49 289	99.29 125	97.06 211	99.97 7	98.29 141	99.91 78	99.76 56

test2506		92.39 437	91.89 439	93.89 454	99.38 178	82.28 485	99.32 26	66.03 492	99.08 112	98.77 249	99.57 49	66.26 478	99.84 174	98.71 111	99.95 38	99.54 142

ECVR-MVS		96.42 359	96.61 345	95.85 425	99.38 178	88.18 463	99.22 45	86.00 486	99.08 112	99.36 123	99.57 49	88.47 402	99.82 205	98.52 126	99.95 38	99.54 142

casdiffmvs		98.95 96	99.00 91	98.81 184	99.38 178	97.33 218	97.82 239	99.57 100	99.17 92	99.35 125	99.17 161	98.35 90	99.69 313	98.46 128	99.73 184	99.41 214
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		98.96 95	99.02 87	98.76 201	99.38 178	97.26 228	98.49 139	99.50 131	98.86 139	99.19 165	99.06 187	98.23 105	99.69 313	98.71 111	99.76 176	99.33 255

TranMVSNet+NR-MVSNet		99.17 53	99.07 82	99.46 63	99.37 184	98.87 85	98.39 155	99.42 178	99.42 56	99.36 123	99.06 187	98.38 85	99.95 26	98.34 138	99.90 86	99.57 123

fmvsm_s_conf0.5_n_6		99.08 77	99.21 58	98.69 215	99.36 185	96.51 280	97.62 273	99.68 60	98.43 176	99.85 27	99.10 179	99.12 23	99.88 115	99.77 22	99.92 69	99.67 76

tttt0517		95.64 385	94.98 395	97.64 346	99.36 185	93.81 392	98.72 103	90.47 478	98.08 217	98.67 260	98.34 346	73.88 464	99.92 65	97.77 184	99.51 282	99.20 294

test_part2					99.36 185	99.10 66				99.05 188

v1144		98.60 168	98.66 142	98.41 268	99.36 185	95.90 303	97.58 282	99.34 209	97.51 265	99.27 144	99.15 167	96.34 258	99.80 231	99.47 54	99.93 56	99.51 161

CP-MVS		98.70 143	98.42 185	99.52 45	99.36 185	99.12 63	98.72 103	99.36 197	97.54 263	98.30 302	98.40 338	97.86 146	99.89 97	96.53 302	99.72 192	99.56 129

diffmvs_AUTHOR		98.50 189	98.59 156	98.23 292	99.35 190	95.48 322	96.61 364	99.60 83	98.37 178	98.90 222	99.00 214	97.37 192	99.76 267	98.22 145	99.85 107	99.46 193

Test_1112_low_res		96.99 338	96.55 349	98.31 281	99.35 190	95.47 325	95.84 414	99.53 122	91.51 451	96.80 406	98.48 331	91.36 375	99.83 192	96.58 291	99.53 276	99.62 90

DeepC-MVS	97.60 4	98.97 93	98.93 98	99.10 128	99.35 190	97.98 162	98.01 208	99.46 154	97.56 259	99.54 79	99.50 69	98.97 28	99.84 174	98.06 157	99.92 69	99.49 172
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 315	96.86 327	98.58 236	99.34 193	96.32 289	96.75 356	99.58 93	93.14 432	96.89 401	97.48 404	92.11 367	99.86 143	96.91 253	99.54 272	99.57 123

reproduce_model		99.15 58	98.97 95	99.67 4	99.33 194	99.44 10	98.15 179	99.47 150	99.12 97	99.52 88	99.32 120	98.31 93	99.90 81	97.78 183	99.73 184	99.66 78

MVSMamba_PlusPlus		98.83 118	98.98 94	98.36 276	99.32 195	96.58 276	98.90 83	99.41 182	99.75 11	98.72 255	99.50 69	96.17 263	99.94 42	99.27 65	99.78 155	98.57 396

fmvsm_s_conf0.5_n_4		99.01 86	99.22 55	98.38 272	99.31 196	95.48 322	97.56 284	99.73 44	98.87 137	99.75 45	99.27 128	98.80 40	99.86 143	99.80 17	99.90 86	99.81 40

SF-MVS		98.53 183	98.27 212	99.32 91	99.31 196	98.75 91	98.19 173	99.41 182	96.77 332	98.83 237	98.90 240	97.80 152	99.82 205	95.68 348	99.52 279	99.38 233

CPTT-MVS		97.84 273	97.36 297	99.27 99	99.31 196	98.46 115	98.29 162	99.27 245	94.90 400	97.83 344	98.37 342	94.90 308	99.84 174	93.85 399	99.54 272	99.51 161

UnsupCasMVSNet_eth		97.89 262	97.60 283	98.75 203	99.31 196	97.17 240	97.62 273	99.35 203	98.72 151	98.76 251	98.68 296	92.57 360	99.74 281	97.76 188	95.60 469	99.34 249

fmvsm_s_conf0.5_n_7		98.83 118	99.04 84	98.20 294	99.30 200	94.83 349	97.23 325	99.36 197	98.64 154	99.84 30	99.43 89	98.10 122	99.91 74	99.56 41	99.96 28	99.87 22

pmmvs-eth3d		98.47 192	98.34 198	98.86 174	99.30 200	97.76 189	97.16 335	99.28 242	95.54 382	99.42 110	99.19 153	97.27 199	99.63 354	97.89 172	99.97 21	99.20 294

mamv4		99.44 19	99.39 28	99.58 21	99.30 200	99.74 2	99.04 68	99.81 31	99.77 10	99.82 34	99.57 49	97.82 150	99.98 4	99.53 48	99.89 92	99.01 329

viewcassd2359sk11		98.55 178	98.51 166	98.67 218	99.29 203	96.99 251	97.39 306	99.54 118	97.73 242	98.81 242	99.08 185	97.55 174	99.66 340	97.52 207	99.67 222	99.36 242

SymmetryMVS		98.05 248	97.71 273	99.09 132	99.29 203	97.83 178	98.28 163	97.64 404	99.24 76	98.80 244	98.85 253	89.76 389	99.94 42	98.04 159	99.50 290	99.49 172

Anonymous20231211		99.27 38	99.27 48	99.26 101	99.29 203	98.18 137	99.49 12	99.51 128	99.70 16	99.80 38	99.68 25	96.84 225	99.83 192	99.21 71	99.91 78	99.77 50

viewmanbaseed2359cas		98.58 172	98.54 162	98.70 213	99.28 206	97.13 244	97.47 299	99.55 113	97.55 261	98.96 209	98.92 234	97.77 154	99.59 371	97.59 201	99.77 161	99.39 224

UnsupCasMVSNet_bld		97.30 313	96.92 323	98.45 263	99.28 206	96.78 267	96.20 390	99.27 245	95.42 386	98.28 306	98.30 350	93.16 346	99.71 299	94.99 362	97.37 444	98.87 357

EC-MVSNet		99.09 73	99.05 83	99.20 110	99.28 206	98.93 80	99.24 44	99.84 22	99.08 112	98.12 319	98.37 342	98.72 49	99.90 81	99.05 84	99.77 161	98.77 374

mamba_0408		98.80 125	98.88 104	98.55 246	99.27 209	96.50 281	98.00 209	99.60 83	98.93 129	99.22 160	98.84 258	98.59 65	99.89 97	97.74 189	99.72 192	99.27 272

SSM_04072		98.80 125	98.88 104	98.56 244	99.27 209	96.50 281	98.00 209	99.60 83	98.93 129	99.22 160	98.84 258	98.59 65	99.90 81	97.74 189	99.72 192	99.27 272

SSM_0407		98.86 112	98.96 97	98.55 246	99.27 209	96.50 281	98.04 200	99.66 65	99.09 108	99.22 160	99.02 199	98.79 42	99.87 134	97.87 177	99.72 192	99.27 272

reproduce-ours		99.09 73	98.90 101	99.67 4	99.27 209	99.49 6	98.00 209	99.42 178	99.05 115	99.48 96	99.27 128	98.29 95	99.89 97	97.61 198	99.71 201	99.62 90

our_new_method		99.09 73	98.90 101	99.67 4	99.27 209	99.49 6	98.00 209	99.42 178	99.05 115	99.48 96	99.27 128	98.29 95	99.89 97	97.61 198	99.71 201	99.62 90

DPE-MVS		98.59 170	98.26 213	99.57 22	99.27 209	99.15 53	97.01 340	99.39 187	97.67 246	99.44 105	98.99 216	97.53 178	99.89 97	95.40 356	99.68 216	99.66 78
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 272	98.18 225	96.87 394	99.27 209	91.16 443	95.53 424	99.25 251	99.10 105	99.41 112	99.35 108	93.10 348	99.96 14	98.65 115	99.94 50	99.49 172

v1192		98.60 168	98.66 142	98.41 268	99.27 209	95.88 304	97.52 289	99.36 197	97.41 278	99.33 130	99.20 150	96.37 256	99.82 205	99.57 39	99.92 69	99.55 136

N_pmnet		97.63 286	97.17 307	98.99 151	99.27 209	97.86 175	95.98 401	93.41 467	95.25 391	99.47 100	98.90 240	95.63 289	99.85 156	96.91 253	99.73 184	99.27 272

viewdifsd2359ckpt13		98.39 206	98.29 208	98.70 213	99.26 218	97.19 236	97.51 291	99.48 141	96.94 319	98.58 276	98.82 263	97.47 187	99.55 387	97.21 228	99.33 318	99.34 249

FPMVS		93.44 423	92.23 430	97.08 382	99.25 219	97.86 175	95.61 421	97.16 416	92.90 436	93.76 469	98.65 303	75.94 462	95.66 483	79.30 481	97.49 437	97.73 447

ME-MVS		98.61 166	98.33 203	99.44 66	99.24 220	98.93 80	97.45 301	99.06 292	98.14 212	99.06 180	98.77 273	96.97 219	99.82 205	96.67 282	99.64 233	99.58 115

new-patchmatchnet		98.35 209	98.74 122	97.18 377	99.24 220	92.23 425	96.42 377	99.48 141	98.30 186	99.69 56	99.53 65	97.44 188	99.82 205	98.84 100	99.77 161	99.49 172

MCST-MVS		98.00 253	97.63 281	99.10 128	99.24 220	98.17 138	96.89 349	98.73 356	95.66 377	97.92 335	97.70 392	97.17 206	99.66 340	96.18 324	99.23 337	99.47 191

UniMVSNet (Re)		98.87 108	98.71 131	99.35 80	99.24 220	98.73 95	97.73 257	99.38 189	98.93 129	99.12 172	98.73 282	96.77 233	99.86 143	98.63 117	99.80 144	99.46 193

jason		97.45 300	97.35 298	97.76 330	99.24 220	93.93 386	95.86 411	98.42 375	94.24 415	98.50 288	98.13 360	94.82 312	99.91 74	97.22 227	99.73 184	99.43 206
jason: jason.
IterMVS		97.73 278	98.11 234	96.57 404	99.24 220	90.28 452	95.52 426	99.21 260	98.86 139	99.33 130	99.33 115	93.11 347	99.94 42	98.49 127	99.94 50	99.48 183
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 178	98.62 149	98.32 279	99.22 226	95.58 315	97.51 291	99.45 158	97.16 307	99.45 104	99.24 141	96.12 267	99.85 156	99.60 37	99.88 94	99.55 136

ITE_SJBPF				98.87 172	99.22 226	98.48 114		99.35 203	97.50 266	98.28 306	98.60 314	97.64 165	99.35 434	93.86 398	99.27 329	98.79 372

h-mvs33		97.77 276	97.33 300	99.10 128	99.21 228	97.84 177	98.35 159	98.57 367	99.11 98	98.58 276	99.02 199	88.65 400	99.96 14	98.11 152	96.34 460	99.49 172

v144192		98.54 181	98.57 158	98.45 263	99.21 228	95.98 301	97.63 272	99.36 197	97.15 309	99.32 136	99.18 157	95.84 284	99.84 174	99.50 51	99.91 78	99.54 142

APDe-MVS		98.99 89	98.79 118	99.60 16	99.21 228	99.15 53	98.87 88	99.48 141	97.57 257	99.35 125	99.24 141	97.83 147	99.89 97	97.88 175	99.70 208	99.75 60
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 99	98.81 117	99.28 96	99.21 228	98.45 116	98.46 144	99.33 215	99.63 29	99.48 96	99.15 167	97.23 202	99.75 275	97.17 230	99.66 230	99.63 89

SR-MVS-dyc-post		98.81 123	98.55 160	99.57 22	99.20 232	99.38 13	98.48 142	99.30 230	98.64 154	98.95 210	98.96 226	97.49 185	99.86 143	96.56 297	99.39 309	99.45 198

RE-MVS-def			98.58 157		99.20 232	99.38 13	98.48 142	99.30 230	98.64 154	98.95 210	98.96 226	97.75 156		96.56 297	99.39 309	99.45 198

v1921920		98.54 181	98.60 154	98.38 272	99.20 232	95.76 311	97.56 284	99.36 197	97.23 301	99.38 118	99.17 161	96.02 270	99.84 174	99.57 39	99.90 86	99.54 142

E3new		98.41 197	98.34 198	98.62 228	99.19 235	96.90 259	97.32 316	99.50 131	97.40 280	98.63 265	98.92 234	97.21 204	99.65 347	97.34 219	99.52 279	99.31 262

thisisatest0530		95.27 392	94.45 403	97.74 333	99.19 235	94.37 364	97.86 235	90.20 479	97.17 306	98.22 309	97.65 394	73.53 465	99.90 81	96.90 258	99.35 315	98.95 342

Anonymous20240529		98.93 99	98.87 107	99.12 124	99.19 235	98.22 135	99.01 70	98.99 310	99.25 75	99.54 79	99.37 103	97.04 212	99.80 231	97.89 172	99.52 279	99.35 247

APD-MVS_3200maxsize		98.84 115	98.61 153	99.53 39	99.19 235	99.27 28	98.49 139	99.33 215	98.64 154	99.03 193	98.98 221	97.89 142	99.85 156	96.54 301	99.42 306	99.46 193

HQP_MVS		97.99 256	97.67 275	98.93 164	99.19 235	97.65 197	97.77 248	99.27 245	98.20 200	97.79 347	97.98 374	94.90 308	99.70 306	94.42 380	99.51 282	99.45 198

plane_prior7					99.19 235	97.87 174

ab-mvs		98.41 197	98.36 195	98.59 235	99.19 235	97.23 229	99.32 26	98.81 342	97.66 247	98.62 268	99.40 97	96.82 228	99.80 231	95.88 335	99.51 282	98.75 377

F-COLMAP		97.30 313	96.68 340	99.14 122	99.19 235	98.39 118	97.27 324	99.30 230	92.93 435	96.62 413	98.00 372	95.73 287	99.68 323	92.62 426	98.46 405	99.35 247

viewdifsd2359ckpt09		98.13 241	97.92 257	98.77 199	99.18 243	97.35 216	97.29 320	99.53 122	95.81 374	98.09 322	98.47 332	96.34 258	99.66 340	97.02 243	99.51 282	99.29 268

SR-MVS		98.71 138	98.43 183	99.57 22	99.18 243	99.35 17	98.36 158	99.29 238	98.29 189	98.88 229	98.85 253	97.53 178	99.87 134	96.14 326	99.31 322	99.48 183

UniMVSNet_NR-MVSNet		98.86 112	98.68 137	99.40 72	99.17 245	98.74 92	97.68 262	99.40 185	99.14 96	99.06 180	98.59 315	96.71 239	99.93 54	98.57 120	99.77 161	99.53 154

LF4IMVS		97.90 260	97.69 274	98.52 254	99.17 245	97.66 196	97.19 334	99.47 150	96.31 353	97.85 343	98.20 357	96.71 239	99.52 399	94.62 372	99.72 192	98.38 413

SMA-MVS		98.40 200	98.03 243	99.51 49	99.16 247	99.21 34	98.05 198	99.22 259	94.16 417	98.98 200	99.10 179	97.52 180	99.79 244	96.45 307	99.64 233	99.53 154
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
DU-MVS		98.82 121	98.63 147	99.39 73	99.16 247	98.74 92	97.54 287	99.25 251	98.84 143	99.06 180	98.76 279	96.76 235	99.93 54	98.57 120	99.77 161	99.50 165

NR-MVSNet		98.95 96	98.82 115	99.36 74	99.16 247	98.72 97	99.22 45	99.20 262	99.10 105	99.72 48	98.76 279	96.38 255	99.86 143	98.00 164	99.82 127	99.50 165

MVS_111021_LR		98.30 218	98.12 233	98.83 180	99.16 247	98.03 157	96.09 398	99.30 230	97.58 256	98.10 321	98.24 353	98.25 103	99.34 435	96.69 280	99.65 231	99.12 315

DSMNet-mixed		97.42 303	97.60 283	96.87 394	99.15 251	91.46 432	98.54 127	99.12 284	92.87 437	97.58 360	99.63 39	96.21 262	99.90 81	95.74 344	99.54 272	99.27 272

D2MVS		97.84 273	97.84 264	97.83 322	99.14 252	94.74 353	96.94 344	98.88 326	95.84 373	98.89 225	98.96 226	94.40 324	99.69 313	97.55 202	99.95 38	99.05 321

pmmvs5		97.64 285	97.49 289	98.08 305	99.14 252	95.12 340	96.70 359	99.05 296	93.77 424	98.62 268	98.83 260	93.23 344	99.75 275	98.33 140	99.76 176	99.36 242

SPE-MVS-test		99.13 67	99.09 79	99.26 101	99.13 254	98.97 74	99.31 30	99.88 14	99.44 53	98.16 314	98.51 324	98.64 59	99.93 54	98.91 94	99.85 107	98.88 356

VDD-MVS		98.56 174	98.39 190	99.07 135	99.13 254	98.07 152	98.59 121	97.01 419	99.59 37	99.11 173	99.27 128	94.82 312	99.79 244	98.34 138	99.63 240	99.34 249

save fliter					99.11 256	97.97 163	96.53 369	99.02 304	98.24 192

APD-MVS		98.10 242	97.67 275	99.42 68	99.11 256	98.93 80	97.76 251	99.28 242	94.97 398	98.72 255	98.77 273	97.04 212	99.85 156	93.79 400	99.54 272	99.49 172
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 147	98.71 131	98.62 228	99.10 258	96.37 287	97.23 325	98.87 328	99.20 83	99.19 165	98.99 216	97.30 196	99.85 156	98.77 106	99.79 150	99.65 83

EI-MVSNet		98.40 200	98.51 166	98.04 310	99.10 258	94.73 354	97.20 330	98.87 328	98.97 124	99.06 180	99.02 199	96.00 272	99.80 231	98.58 118	99.82 127	99.60 100

CVMVSNet		96.25 365	97.21 306	93.38 461	99.10 258	80.56 489	97.20 330	98.19 386	96.94 319	99.00 195	99.02 199	89.50 393	99.80 231	96.36 313	99.59 254	99.78 47

EI-MVSNet-Vis-set		98.68 153	98.70 134	98.63 226	99.09 261	96.40 286	97.23 325	98.86 333	99.20 83	99.18 169	98.97 223	97.29 198	99.85 156	98.72 110	99.78 155	99.64 84

HPM-MVS++		98.10 242	97.64 280	99.48 57	99.09 261	99.13 61	97.52 289	98.75 353	97.46 274	96.90 400	97.83 384	96.01 271	99.84 174	95.82 342	99.35 315	99.46 193

DP-MVS Recon		97.33 311	96.92 323	98.57 239	99.09 261	97.99 159	96.79 352	99.35 203	93.18 431	97.71 351	98.07 368	95.00 307	99.31 439	93.97 393	99.13 353	98.42 410

MVS_111021_HR		98.25 227	98.08 238	98.75 203	99.09 261	97.46 210	95.97 402	99.27 245	97.60 255	97.99 332	98.25 352	98.15 119	99.38 430	96.87 261	99.57 263	99.42 211

BP-MVS1		97.40 305	96.97 319	98.71 212	99.07 265	96.81 263	98.34 161	97.18 414	98.58 165	98.17 311	98.61 312	84.01 433	99.94 42	98.97 90	99.78 155	99.37 235

9.14			97.78 266		99.07 265		97.53 288	99.32 217	95.53 383	98.54 284	98.70 292	97.58 171	99.76 267	94.32 385	99.46 295

PAPM_NR		96.82 345	96.32 356	98.30 282	99.07 265	96.69 271	97.48 295	98.76 350	95.81 374	96.61 414	96.47 430	94.12 333	99.17 452	90.82 453	97.78 431	99.06 320

TAMVS		98.24 228	98.05 241	98.80 187	99.07 265	97.18 238	97.88 231	98.81 342	96.66 337	99.17 171	99.21 148	94.81 314	99.77 261	96.96 251	99.88 94	99.44 202

CLD-MVS		97.49 296	97.16 308	98.48 260	99.07 265	97.03 249	94.71 448	99.21 260	94.46 409	98.06 325	97.16 416	97.57 172	99.48 411	94.46 377	99.78 155	98.95 342
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CS-MVS		99.13 67	99.10 77	99.24 106	99.06 270	99.15 53	99.36 22	99.88 14	99.36 64	98.21 310	98.46 333	98.68 56	99.93 54	99.03 86	99.85 107	98.64 389

thres100view900		94.19 409	93.67 414	95.75 428	99.06 270	91.35 436	98.03 202	94.24 462	98.33 182	97.40 376	94.98 460	79.84 449	99.62 357	83.05 474	98.08 422	96.29 469

thres600view7		94.45 404	93.83 411	96.29 412	99.06 270	91.53 431	97.99 216	94.24 462	98.34 181	97.44 374	95.01 458	79.84 449	99.67 327	84.33 472	98.23 411	97.66 450

plane_prior1					99.05 273

YYNet1		97.60 287	97.67 275	97.39 370	99.04 274	93.04 409	95.27 433	98.38 378	97.25 295	98.92 220	98.95 230	95.48 296	99.73 288	96.99 247	98.74 386	99.41 214

MDA-MVSNet_test_wron		97.60 287	97.66 278	97.41 369	99.04 274	93.09 405	95.27 433	98.42 375	97.26 294	98.88 229	98.95 230	95.43 297	99.73 288	97.02 243	98.72 388	99.41 214

MIMVSNet		96.62 352	96.25 360	97.71 337	99.04 274	94.66 357	99.16 54	96.92 425	97.23 301	97.87 340	99.10 179	86.11 415	99.65 347	91.65 437	99.21 341	98.82 361

FE-MVSNET3		97.37 307	97.13 312	98.11 301	99.03 277	95.40 328	94.47 458	98.99 310	96.87 325	97.97 333	97.81 385	92.12 366	99.75 275	97.49 213	99.43 305	99.16 310

icg_test_0407_2		98.20 233	98.38 192	97.65 343	99.03 277	94.03 377	95.78 416	99.45 158	98.16 206	99.06 180	98.71 285	98.27 99	99.68 323	97.50 208	99.45 297	99.22 289

IMVS_0407		98.39 206	98.64 145	97.66 341	99.03 277	94.03 377	98.10 188	99.45 158	98.16 206	99.06 180	98.71 285	98.27 99	99.71 299	97.50 208	99.45 297	99.22 289

IMVS_0404		98.07 246	98.20 220	97.69 338	99.03 277	94.03 377	96.67 360	99.45 158	98.16 206	98.03 329	98.71 285	96.80 231	99.82 205	97.50 208	99.45 297	99.22 289

IMVS_0403		98.34 210	98.56 159	97.66 341	99.03 277	94.03 377	97.98 217	99.45 158	98.16 206	98.89 225	98.71 285	97.90 138	99.74 281	97.50 208	99.45 297	99.22 289

PatchMatch-RL		97.24 319	96.78 334	98.61 232	99.03 277	97.83 178	96.36 380	99.06 292	93.49 429	97.36 380	97.78 386	95.75 286	99.49 408	93.44 409	98.77 385	98.52 398

viewmambaseed2359dif		98.19 234	98.26 213	97.99 313	99.02 283	95.03 343	96.59 366	99.53 122	96.21 357	99.00 195	98.99 216	97.62 167	99.61 364	97.62 197	99.72 192	99.33 255

GDP-MVS		97.50 293	97.11 313	98.67 218	99.02 283	96.85 261	98.16 178	99.71 47	98.32 184	98.52 287	98.54 319	83.39 437	99.95 26	98.79 102	99.56 266	99.19 299

ZD-MVS					99.01 285	98.84 86		99.07 291	94.10 419	98.05 327	98.12 362	96.36 257	99.86 143	92.70 425	99.19 345

CDPH-MVS		97.26 316	96.66 343	99.07 135	99.00 286	98.15 139	96.03 400	99.01 307	91.21 455	97.79 347	97.85 383	96.89 223	99.69 313	92.75 423	99.38 312	99.39 224

diffmvs		98.22 229	98.24 217	98.17 297	99.00 286	95.44 326	96.38 379	99.58 93	97.79 239	98.53 285	98.50 328	96.76 235	99.74 281	97.95 170	99.64 233	99.34 249
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WR-MVS		98.40 200	98.19 224	99.03 145	99.00 286	97.65 197	96.85 350	98.94 313	98.57 167	98.89 225	98.50 328	95.60 290	99.85 156	97.54 204	99.85 107	99.59 107

plane_prior6					98.99 289	97.70 195						94.90 308

xiu_mvs_v1_base_debu		97.86 267	98.17 226	96.92 391	98.98 290	93.91 387	96.45 373	99.17 274	97.85 234	98.41 296	97.14 418	98.47 75	99.92 65	98.02 161	99.05 359	96.92 462

xiu_mvs_v1_base		97.86 267	98.17 226	96.92 391	98.98 290	93.91 387	96.45 373	99.17 274	97.85 234	98.41 296	97.14 418	98.47 75	99.92 65	98.02 161	99.05 359	96.92 462

xiu_mvs_v1_base_debi		97.86 267	98.17 226	96.92 391	98.98 290	93.91 387	96.45 373	99.17 274	97.85 234	98.41 296	97.14 418	98.47 75	99.92 65	98.02 161	99.05 359	96.92 462

MVP-Stereo		98.08 245	97.92 257	98.57 239	98.96 293	96.79 264	97.90 229	99.18 270	96.41 349	98.46 291	98.95 230	95.93 281	99.60 367	96.51 303	98.98 373	99.31 262
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 200	98.68 137	97.54 358	98.96 293	97.99 159	97.88 231	99.36 197	98.20 200	99.63 67	99.04 196	98.76 45	95.33 485	96.56 297	99.74 181	99.31 262
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
新几何1				98.91 168	98.94 295	97.76 189		98.76 350	87.58 472	96.75 408	98.10 364	94.80 315	99.78 255	92.73 424	99.00 368	99.20 294

USDC		97.41 304	97.40 293	97.44 367	98.94 295	93.67 397	95.17 437	99.53 122	94.03 421	98.97 204	99.10 179	95.29 299	99.34 435	95.84 341	99.73 184	99.30 266

tfpn200view9		94.03 413	93.44 416	95.78 427	98.93 297	91.44 434	97.60 279	94.29 460	97.94 226	97.10 386	94.31 467	79.67 451	99.62 357	83.05 474	98.08 422	96.29 469

testdata				98.09 302	98.93 297	95.40 328		98.80 344	90.08 463	97.45 373	98.37 342	95.26 300	99.70 306	93.58 405	98.95 376	99.17 306

thres400		94.14 411	93.44 416	96.24 415	98.93 297	91.44 434	97.60 279	94.29 460	97.94 226	97.10 386	94.31 467	79.67 451	99.62 357	83.05 474	98.08 422	97.66 450

TAPA-MVS	96.21 11	96.63 351	95.95 362	98.65 220	98.93 297	98.09 146	96.93 346	99.28 242	83.58 478	98.13 318	97.78 386	96.13 265	99.40 426	93.52 406	99.29 327	98.45 403
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 301	96.93 257	95.54 423	98.78 347	85.72 475	96.86 403	98.11 363	94.43 322			99.10 358	99.23 284

PVSNet_BlendedMVS		97.55 292	97.53 286	97.60 350	98.92 301	93.77 394	96.64 362	99.43 172	94.49 407	97.62 356	99.18 157	96.82 228	99.67 327	94.73 369	99.93 56	99.36 242

PVSNet_Blended		96.88 341	96.68 340	97.47 365	98.92 301	93.77 394	94.71 448	99.43 172	90.98 457	97.62 356	97.36 412	96.82 228	99.67 327	94.73 369	99.56 266	98.98 335

MSDG		97.71 280	97.52 287	98.28 284	98.91 304	96.82 262	94.42 459	99.37 193	97.65 248	98.37 301	98.29 351	97.40 190	99.33 437	94.09 391	99.22 338	98.68 387

Anonymous202405211		97.90 260	97.50 288	99.08 133	98.90 305	98.25 129	98.53 128	96.16 437	98.87 137	99.11 173	98.86 250	90.40 385	99.78 255	97.36 218	99.31 322	99.19 299

原ACMM1				98.35 277	98.90 305	96.25 291		98.83 341	92.48 441	96.07 431	98.10 364	95.39 298	99.71 299	92.61 427	98.99 370	99.08 317

GBi-Net		98.65 158	98.47 177	99.17 115	98.90 305	98.24 130	99.20 48	99.44 166	98.59 162	98.95 210	99.55 57	94.14 330	99.86 143	97.77 184	99.69 211	99.41 214

test1		98.65 158	98.47 177	99.17 115	98.90 305	98.24 130	99.20 48	99.44 166	98.59 162	98.95 210	99.55 57	94.14 330	99.86 143	97.77 184	99.69 211	99.41 214

FMVSNet2		98.49 190	98.40 187	98.75 203	98.90 305	97.14 243	98.61 119	99.13 283	98.59 162	99.19 165	99.28 126	94.14 330	99.82 205	97.97 168	99.80 144	99.29 268

OMC-MVS		97.88 264	97.49 289	99.04 144	98.89 310	98.63 99	96.94 344	99.25 251	95.02 396	98.53 285	98.51 324	97.27 199	99.47 414	93.50 408	99.51 282	99.01 329

VortexMVS		97.98 257	98.31 205	97.02 385	98.88 311	91.45 433	98.03 202	99.47 150	98.65 153	99.55 77	99.47 79	91.49 374	99.81 222	99.32 61	99.91 78	99.80 42

MVSFormer		98.26 224	98.43 183	97.77 327	98.88 311	93.89 390	99.39 20	99.56 109	99.11 98	98.16 314	98.13 360	93.81 338	99.97 7	99.26 66	99.57 263	99.43 206

lupinMVS		97.06 331	96.86 327	97.65 343	98.88 311	93.89 390	95.48 427	97.97 392	93.53 427	98.16 314	97.58 398	93.81 338	99.91 74	96.77 269	99.57 263	99.17 306

dmvs_re		95.98 374	95.39 384	97.74 333	98.86 314	97.45 211	98.37 157	95.69 449	97.95 224	96.56 415	95.95 439	90.70 382	97.68 479	88.32 462	96.13 464	98.11 425

DELS-MVS		98.27 222	98.20 220	98.48 260	98.86 314	96.70 270	95.60 422	99.20 262	97.73 242	98.45 292	98.71 285	97.50 182	99.82 205	98.21 146	99.59 254	98.93 347
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
TinyColmap		97.89 262	97.98 248	97.60 350	98.86 314	94.35 365	96.21 389	99.44 166	97.45 276	99.06 180	98.88 247	97.99 132	99.28 445	94.38 384	99.58 259	99.18 302

LCM-MVSNet-Re		98.64 160	98.48 175	99.11 126	98.85 317	98.51 112	98.49 139	99.83 25	98.37 178	99.69 56	99.46 81	98.21 110	99.92 65	94.13 390	99.30 325	98.91 351

pmmvs4		97.58 290	97.28 301	98.51 255	98.84 318	96.93 257	95.40 431	98.52 370	93.60 426	98.61 270	98.65 303	95.10 304	99.60 367	96.97 250	99.79 150	98.99 334

NP-MVS					98.84 318	97.39 215					96.84 421

sss		97.21 321	96.93 321	98.06 307	98.83 320	95.22 336	96.75 356	98.48 372	94.49 407	97.27 382	97.90 380	92.77 356	99.80 231	96.57 293	99.32 320	99.16 310

PVSNet	93.40 17	95.67 383	95.70 368	95.57 432	98.83 320	88.57 459	92.50 476	97.72 397	92.69 439	96.49 423	96.44 431	93.72 341	99.43 422	93.61 403	99.28 328	98.71 380

MVE	83.40 22	92.50 436	91.92 438	94.25 448	98.83 320	91.64 430	92.71 475	83.52 488	95.92 371	86.46 486	95.46 452	95.20 301	95.40 484	80.51 479	98.64 397	95.73 477
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 417	93.91 409	93.39 460	98.82 323	81.72 487	97.76 251	95.28 451	98.60 161	96.54 416	96.66 425	65.85 481	99.62 357	96.65 286	98.99 370	98.82 361

ambc				98.24 289	98.82 323	95.97 302	98.62 117	99.00 309		99.27 144	99.21 148	96.99 217	99.50 405	96.55 300	99.50 290	99.26 278

旧先验1					98.82 323	97.45 211		98.76 350			98.34 346	95.50 295			99.01 367	99.23 284

test_vis1_rt		97.75 277	97.72 272	97.83 322	98.81 326	96.35 288	97.30 319	99.69 54	94.61 405	97.87 340	98.05 369	96.26 261	98.32 473	98.74 108	98.18 414	98.82 361

WTY-MVS		96.67 349	96.27 359	97.87 320	98.81 326	94.61 359	96.77 354	97.92 394	94.94 399	97.12 385	97.74 389	91.11 378	99.82 205	93.89 396	98.15 418	99.18 302

3Dnovator+	97.89 3	98.69 147	98.51 166	99.24 106	98.81 326	98.40 117	99.02 69	99.19 266	98.99 121	98.07 324	99.28 126	97.11 210	99.84 174	96.84 264	99.32 320	99.47 191

QAPM		97.31 312	96.81 333	98.82 182	98.80 329	97.49 205	99.06 65	99.19 266	90.22 461	97.69 353	99.16 163	96.91 222	99.90 81	90.89 452	99.41 307	99.07 319

VNet		98.42 196	98.30 206	98.79 191	98.79 330	97.29 225	98.23 169	98.66 360	99.31 69	98.85 234	98.80 267	94.80 315	99.78 255	98.13 151	99.13 353	99.31 262

DPM-MVS		96.32 361	95.59 375	98.51 255	98.76 331	97.21 234	94.54 457	98.26 381	91.94 446	96.37 424	97.25 414	93.06 350	99.43 422	91.42 442	98.74 386	98.89 353

3Dnovator	98.27 2	98.81 123	98.73 124	99.05 142	98.76 331	97.81 186	99.25 43	99.30 230	98.57 167	98.55 282	99.33 115	97.95 135	99.90 81	97.16 231	99.67 222	99.44 202

PLC	94.65 16	96.51 354	95.73 367	98.85 175	98.75 333	97.91 171	96.42 377	99.06 292	90.94 458	95.59 438	97.38 410	94.41 323	99.59 371	90.93 450	98.04 427	99.05 321
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 343	96.75 336	97.08 382	98.74 334	93.33 403	96.71 358	98.26 381	96.72 334	98.44 293	97.37 411	95.20 301	99.47 414	91.89 432	97.43 441	98.44 406

hse-mvs2		97.46 298	97.07 314	98.64 222	98.73 335	97.33 218	97.45 301	97.64 404	99.11 98	98.58 276	97.98 374	88.65 400	99.79 244	98.11 152	97.39 443	98.81 366

CDS-MVSNet		97.69 281	97.35 298	98.69 215	98.73 335	97.02 250	96.92 348	98.75 353	95.89 372	98.59 274	98.67 298	92.08 368	99.74 281	96.72 275	99.81 133	99.32 258
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SD_0403		96.28 363	95.83 364	97.64 346	98.72 337	94.30 366	98.87 88	98.77 348	97.80 237	96.53 417	98.02 371	97.34 194	99.47 414	76.93 483	99.48 293	99.16 310

EIA-MVS		98.00 253	97.74 269	98.80 187	98.72 337	98.09 146	98.05 198	99.60 83	97.39 281	96.63 412	95.55 447	97.68 159	99.80 231	96.73 274	99.27 329	98.52 398

LFMVS		97.20 322	96.72 337	98.64 222	98.72 337	96.95 255	98.93 81	94.14 464	99.74 13	98.78 246	99.01 210	84.45 428	99.73 288	97.44 214	99.27 329	99.25 279

new_pmnet		96.99 338	96.76 335	97.67 339	98.72 337	94.89 348	95.95 406	98.20 384	92.62 440	98.55 282	98.54 319	94.88 311	99.52 399	93.96 394	99.44 304	98.59 395

Fast-Effi-MVS+		97.67 283	97.38 295	98.57 239	98.71 341	97.43 213	97.23 325	99.45 158	94.82 402	96.13 428	96.51 427	98.52 73	99.91 74	96.19 322	98.83 382	98.37 415

TEST9					98.71 341	98.08 150	95.96 404	99.03 301	91.40 452	95.85 435	97.53 400	96.52 248	99.76 267

train_agg		97.10 328	96.45 353	99.07 135	98.71 341	98.08 150	95.96 404	99.03 301	91.64 447	95.85 435	97.53 400	96.47 250	99.76 267	93.67 402	99.16 348	99.36 242

TSAR-MVS + GP.		98.18 236	97.98 248	98.77 199	98.71 341	97.88 173	96.32 383	98.66 360	96.33 351	99.23 159	98.51 324	97.48 186	99.40 426	97.16 231	99.46 295	99.02 328

FA-MVS(test-final)		96.99 338	96.82 331	97.50 362	98.70 345	94.78 351	99.34 23	96.99 420	95.07 395	98.48 290	99.33 115	88.41 403	99.65 347	96.13 328	98.92 379	98.07 428

AUN-MVS		96.24 367	95.45 380	98.60 234	98.70 345	97.22 232	97.38 308	97.65 402	95.95 370	95.53 445	97.96 378	82.11 445	99.79 244	96.31 315	97.44 440	98.80 371

our_test_3		97.39 306	97.73 271	96.34 410	98.70 345	89.78 455	94.61 454	98.97 312	96.50 342	99.04 190	98.85 253	95.98 277	99.84 174	97.26 225	99.67 222	99.41 214

ppachtmachnet_test		97.50 293	97.74 269	96.78 400	98.70 345	91.23 442	94.55 456	99.05 296	96.36 350	99.21 163	98.79 269	96.39 253	99.78 255	96.74 272	99.82 127	99.34 249

PCF-MVS	92.86 18	94.36 405	93.00 423	98.42 267	98.70 345	97.56 202	93.16 474	99.11 286	79.59 482	97.55 363	97.43 407	92.19 364	99.73 288	79.85 480	99.45 297	97.97 434
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 259	98.02 244	97.58 352	98.69 350	94.10 373	98.13 181	98.90 322	97.95 224	97.32 381	99.58 47	95.95 280	98.75 468	96.41 309	99.22 338	99.87 22

ETV-MVS		98.03 249	97.86 263	98.56 244	98.69 350	98.07 152	97.51 291	99.50 131	98.10 214	97.50 368	95.51 448	98.41 82	99.88 115	96.27 318	99.24 334	97.71 449

test_prior				98.95 160	98.69 350	97.95 167		99.03 301					99.59 371			99.30 266

mvsmamba		97.57 291	97.26 302	98.51 255	98.69 350	96.73 269	98.74 98	97.25 413	97.03 315	97.88 339	99.23 146	90.95 379	99.87 134	96.61 289	99.00 368	98.91 351

agg_prior					98.68 354	97.99 159		99.01 307		95.59 438			99.77 261

test_8					98.67 355	98.01 158	95.91 410	99.02 304	91.64 447	95.79 437	97.50 403	96.47 250	99.76 267

HQP-NCC					98.67 355		96.29 385		96.05 363	95.55 441

ACMP_Plane					98.67 355		96.29 385		96.05 363	95.55 441

CNVR-MVS		98.17 238	97.87 262	99.07 135	98.67 355	98.24 130	97.01 340	98.93 316	97.25 295	97.62 356	98.34 346	97.27 199	99.57 380	96.42 308	99.33 318	99.39 224

HQP-MVS		97.00 337	96.49 352	98.55 246	98.67 355	96.79 264	96.29 385	99.04 299	96.05 363	95.55 441	96.84 421	93.84 336	99.54 393	92.82 420	99.26 332	99.32 258

MM		98.22 229	97.99 247	98.91 168	98.66 360	96.97 252	97.89 230	94.44 458	99.54 41	98.95 210	99.14 170	93.50 342	99.92 65	99.80 17	99.96 28	99.85 30

test_fmvs1		97.72 279	97.94 254	97.07 384	98.66 360	92.39 420	97.68 262	99.81 31	95.20 394	99.54 79	99.44 86	91.56 373	99.41 425	99.78 21	99.77 161	99.40 223

balanced_conf03		98.63 162	98.72 126	98.38 272	98.66 360	96.68 272	98.90 83	99.42 178	98.99 121	98.97 204	99.19 153	95.81 285	99.85 156	98.77 106	99.77 161	98.60 392

thres200		93.72 419	93.14 421	95.46 436	98.66 360	91.29 438	96.61 364	94.63 457	97.39 281	96.83 404	93.71 470	79.88 448	99.56 383	82.40 477	98.13 419	95.54 478

wuyk23d		96.06 370	97.62 282	91.38 465	98.65 364	98.57 106	98.85 92	96.95 423	96.86 327	99.90 14	99.16 163	99.18 19	98.40 472	89.23 460	99.77 161	77.18 485

NCCC		97.86 267	97.47 292	99.05 142	98.61 365	98.07 152	96.98 342	98.90 322	97.63 249	97.04 390	97.93 379	95.99 276	99.66 340	95.31 357	98.82 384	99.43 206

DeepC-MVS_fast	96.85 6	98.30 218	98.15 230	98.75 203	98.61 365	97.23 229	97.76 251	99.09 289	97.31 289	98.75 252	98.66 301	97.56 173	99.64 351	96.10 329	99.55 270	99.39 224
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 421	92.09 432	97.75 331	98.60 367	94.40 363	97.32 316	95.26 452	97.56 259	96.79 407	95.50 449	53.57 490	99.77 261	95.26 358	98.97 374	99.08 317

thisisatest0515		94.12 412	93.16 420	96.97 389	98.60 367	92.90 410	93.77 470	90.61 477	94.10 419	96.91 397	95.87 442	74.99 463	99.80 231	94.52 375	99.12 356	98.20 421

GA-MVS		95.86 377	95.32 387	97.49 363	98.60 367	94.15 372	93.83 469	97.93 393	95.49 384	96.68 410	97.42 408	83.21 438	99.30 441	96.22 320	98.55 403	99.01 329

dmvs_testset		92.94 431	92.21 431	95.13 440	98.59 370	90.99 445	97.65 268	92.09 473	96.95 318	94.00 465	93.55 471	92.34 362	96.97 482	72.20 484	92.52 479	97.43 457

OPU-MVS				98.82 182	98.59 370	98.30 126	98.10 188				98.52 323	98.18 113	98.75 468	94.62 372	99.48 293	99.41 214

MSLP-MVS++		98.02 250	98.14 232	97.64 346	98.58 372	95.19 337	97.48 295	99.23 258	97.47 269	97.90 337	98.62 310	97.04 212	98.81 466	97.55 202	99.41 307	98.94 346

test12				98.93 164	98.58 372	97.83 178		98.66 360		96.53 417		95.51 294	99.69 313		99.13 353	99.27 272

CL-MVSNet_self_test		97.44 301	97.22 305	98.08 305	98.57 374	95.78 310	94.30 462	98.79 345	96.58 340	98.60 272	98.19 358	94.74 318	99.64 351	96.41 309	98.84 381	98.82 361

PS-MVSNAJ		97.08 330	97.39 294	96.16 421	98.56 375	92.46 418	95.24 435	98.85 336	97.25 295	97.49 369	95.99 438	98.07 123	99.90 81	96.37 311	98.67 396	96.12 474

CNLPA		97.17 325	96.71 338	98.55 246	98.56 375	98.05 156	96.33 382	98.93 316	96.91 323	97.06 389	97.39 409	94.38 325	99.45 419	91.66 436	99.18 347	98.14 424

xiu_mvs_v2_base		97.16 326	97.49 289	96.17 419	98.54 377	92.46 418	95.45 428	98.84 337	97.25 295	97.48 370	96.49 428	98.31 93	99.90 81	96.34 314	98.68 395	96.15 473

alignmvs		97.35 309	96.88 326	98.78 194	98.54 377	98.09 146	97.71 258	97.69 399	99.20 83	97.59 359	95.90 441	88.12 405	99.55 387	98.18 148	98.96 375	98.70 383

FE-MVS		95.66 384	94.95 397	97.77 327	98.53 379	95.28 333	99.40 19	96.09 440	93.11 433	97.96 334	99.26 134	79.10 455	99.77 261	92.40 429	98.71 390	98.27 419

Effi-MVS+		98.02 250	97.82 265	98.62 228	98.53 379	97.19 236	97.33 315	99.68 60	97.30 290	96.68 410	97.46 406	98.56 71	99.80 231	96.63 287	98.20 413	98.86 358

baseline1		95.96 375	95.44 381	97.52 360	98.51 381	93.99 384	98.39 155	96.09 440	98.21 196	98.40 300	97.76 388	86.88 407	99.63 354	95.42 355	89.27 482	98.95 342

MVS_Test		98.18 236	98.36 195	97.67 339	98.48 382	94.73 354	98.18 174	99.02 304	97.69 245	98.04 328	99.11 176	97.22 203	99.56 383	98.57 120	98.90 380	98.71 380

MGCFI-Net		98.34 210	98.28 209	98.51 255	98.47 383	97.59 201	98.96 77	99.48 141	99.18 91	97.40 376	95.50 449	98.66 57	99.50 405	98.18 148	98.71 390	98.44 406

BH-RMVSNet		96.83 343	96.58 348	97.58 352	98.47 383	94.05 374	96.67 360	97.36 408	96.70 336	97.87 340	97.98 374	95.14 303	99.44 421	90.47 455	98.58 402	99.25 279

sasdasda		98.34 210	98.26 213	98.58 236	98.46 385	97.82 183	98.96 77	99.46 154	99.19 88	97.46 371	95.46 452	98.59 65	99.46 417	98.08 155	98.71 390	98.46 400

canonicalmvs		98.34 210	98.26 213	98.58 236	98.46 385	97.82 183	98.96 77	99.46 154	99.19 88	97.46 371	95.46 452	98.59 65	99.46 417	98.08 155	98.71 390	98.46 400

MVS-HIRNet		94.32 406	95.62 371	90.42 466	98.46 385	75.36 490	96.29 385	89.13 481	95.25 391	95.38 447	99.75 16	92.88 353	99.19 451	94.07 392	99.39 309	96.72 467

PHI-MVS		98.29 221	97.95 252	99.34 83	98.44 388	99.16 49	98.12 185	99.38 189	96.01 367	98.06 325	98.43 336	97.80 152	99.67 327	95.69 347	99.58 259	99.20 294

DVP-MVS++		98.90 103	98.70 134	99.51 49	98.43 389	99.15 53	99.43 15	99.32 217	98.17 203	99.26 148	99.02 199	98.18 113	99.88 115	97.07 240	99.45 297	99.49 172

MSC_two_6792asdad				99.32 91	98.43 389	98.37 121		98.86 333					99.89 97	97.14 234	99.60 250	99.71 63

No_MVS				99.32 91	98.43 389	98.37 121		98.86 333					99.89 97	97.14 234	99.60 250	99.71 63

Fast-Effi-MVS+-dtu		98.27 222	98.09 235	98.81 184	98.43 389	98.11 143	97.61 278	99.50 131	98.64 154	97.39 378	97.52 402	98.12 121	99.95 26	96.90 258	98.71 390	98.38 413

OpenMVS_ROB	95.38 14	95.84 379	95.18 392	97.81 324	98.41 393	97.15 242	97.37 312	98.62 364	83.86 477	98.65 263	98.37 342	94.29 328	99.68 323	88.41 461	98.62 400	96.60 468

DeepPCF-MVS	96.93 5	98.32 215	98.01 245	99.23 108	98.39 394	98.97 74	95.03 441	99.18 270	96.88 324	99.33 130	98.78 271	98.16 117	99.28 445	96.74 272	99.62 243	99.44 202

Patchmatch-test		96.55 353	96.34 355	97.17 379	98.35 395	93.06 406	98.40 154	97.79 395	97.33 286	98.41 296	98.67 298	83.68 436	99.69 313	95.16 360	99.31 322	98.77 374

AdaColmap		97.14 327	96.71 338	98.46 262	98.34 396	97.80 187	96.95 343	98.93 316	95.58 381	96.92 395	97.66 393	95.87 283	99.53 395	90.97 449	99.14 351	98.04 429

OpenMVS	96.65 7	97.09 329	96.68 340	98.32 279	98.32 397	97.16 241	98.86 91	99.37 193	89.48 465	96.29 426	99.15 167	96.56 246	99.90 81	92.90 417	99.20 342	97.89 437

MG-MVS		96.77 346	96.61 345	97.26 375	98.31 398	93.06 406	95.93 407	98.12 389	96.45 348	97.92 335	98.73 282	93.77 340	99.39 428	91.19 447	99.04 362	99.33 255

test_yl		96.69 347	96.29 357	97.90 316	98.28 399	95.24 334	97.29 320	97.36 408	98.21 196	98.17 311	97.86 381	86.27 411	99.55 387	94.87 366	98.32 407	98.89 353

DCV-MVSNet		96.69 347	96.29 357	97.90 316	98.28 399	95.24 334	97.29 320	97.36 408	98.21 196	98.17 311	97.86 381	86.27 411	99.55 387	94.87 366	98.32 407	98.89 353

CHOSEN 280x420		95.51 389	95.47 378	95.65 431	98.25 401	88.27 462	93.25 473	98.88 326	93.53 427	94.65 456	97.15 417	86.17 413	99.93 54	97.41 216	99.93 56	98.73 379

SCA		96.41 360	96.66 343	95.67 429	98.24 402	88.35 461	95.85 413	96.88 426	96.11 361	97.67 354	98.67 298	93.10 348	99.85 156	94.16 386	99.22 338	98.81 366

DeepMVS_CX				93.44 459	98.24 402	94.21 369		94.34 459	64.28 485	91.34 479	94.87 464	89.45 394	92.77 486	77.54 482	93.14 478	93.35 481

MS-PatchMatch		97.68 282	97.75 268	97.45 366	98.23 404	93.78 393	97.29 320	98.84 337	96.10 362	98.64 264	98.65 303	96.04 269	99.36 431	96.84 264	99.14 351	99.20 294

BH-w/o		95.13 395	94.89 399	95.86 424	98.20 405	91.31 437	95.65 420	97.37 407	93.64 425	96.52 419	95.70 445	93.04 351	99.02 457	88.10 463	95.82 468	97.24 460

mvs_anonymous		97.83 275	98.16 229	96.87 394	98.18 406	91.89 427	97.31 318	98.90 322	97.37 283	98.83 237	99.46 81	96.28 260	99.79 244	98.90 95	98.16 417	98.95 342

miper_lstm_enhance		97.18 324	97.16 308	97.25 376	98.16 407	92.85 411	95.15 439	99.31 222	97.25 295	98.74 254	98.78 271	90.07 386	99.78 255	97.19 229	99.80 144	99.11 316

RRT-MVS		97.88 264	97.98 248	97.61 349	98.15 408	93.77 394	98.97 76	99.64 71	99.16 93	98.69 257	99.42 90	91.60 371	99.89 97	97.63 196	98.52 404	99.16 310

ET-MVSNet_ETH3D		94.30 408	93.21 419	97.58 352	98.14 409	94.47 362	94.78 447	93.24 469	94.72 403	89.56 481	95.87 442	78.57 458	99.81 222	96.91 253	97.11 452	98.46 400

ADS-MVSNet2		95.43 390	94.98 395	96.76 401	98.14 409	91.74 428	97.92 226	97.76 396	90.23 459	96.51 420	98.91 237	85.61 419	99.85 156	92.88 418	96.90 453	98.69 384

ADS-MVSNet		95.24 393	94.93 398	96.18 418	98.14 409	90.10 454	97.92 226	97.32 411	90.23 459	96.51 420	98.91 237	85.61 419	99.74 281	92.88 418	96.90 453	98.69 384

c3_l		97.36 308	97.37 296	97.31 371	98.09 412	93.25 404	95.01 442	99.16 277	97.05 312	98.77 249	98.72 284	92.88 353	99.64 351	96.93 252	99.76 176	99.05 321

FMVSNet3		97.50 293	97.24 304	98.29 283	98.08 413	95.83 307	97.86 235	98.91 321	97.89 231	98.95 210	98.95 230	87.06 406	99.81 222	97.77 184	99.69 211	99.23 284

PAPM		91.88 446	90.34 448	96.51 405	98.06 414	92.56 416	92.44 477	97.17 415	86.35 473	90.38 480	96.01 437	86.61 409	99.21 450	70.65 486	95.43 470	97.75 446

Effi-MVS+-dtu		98.26 224	97.90 260	99.35 80	98.02 415	99.49 6	98.02 205	99.16 277	98.29 189	97.64 355	97.99 373	96.44 252	99.95 26	96.66 285	98.93 378	98.60 392

eth_miper_zixun_eth		97.23 320	97.25 303	97.17 379	98.00 416	92.77 413	94.71 448	99.18 270	97.27 293	98.56 280	98.74 281	91.89 369	99.69 313	97.06 242	99.81 133	99.05 321

HY-MVS	95.94 13	95.90 376	95.35 386	97.55 357	97.95 417	94.79 350	98.81 97	96.94 424	92.28 444	95.17 449	98.57 317	89.90 388	99.75 275	91.20 446	97.33 448	98.10 426

UGNet		98.53 183	98.45 180	98.79 191	97.94 418	96.96 254	99.08 61	98.54 368	99.10 105	96.82 405	99.47 79	96.55 247	99.84 174	98.56 123	99.94 50	99.55 136
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
MAR-MVS		96.47 358	95.70 368	98.79 191	97.92 419	99.12 63	98.28 163	98.60 365	92.16 445	95.54 444	96.17 435	94.77 317	99.52 399	89.62 458	98.23 411	97.72 448
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
MVSTER		96.86 342	96.55 349	97.79 325	97.91 420	94.21 369	97.56 284	98.87 328	97.49 268	99.06 180	99.05 194	80.72 446	99.80 231	98.44 129	99.82 127	99.37 235

API-MVS		97.04 333	96.91 325	97.42 368	97.88 421	98.23 134	98.18 174	98.50 371	97.57 257	97.39 378	96.75 423	96.77 233	99.15 454	90.16 456	99.02 366	94.88 479

myMVS_eth3d28		92.92 432	92.31 428	94.77 443	97.84 422	87.59 466	96.19 391	96.11 439	97.08 311	94.27 459	93.49 473	66.07 480	98.78 467	91.78 434	97.93 430	97.92 436

miper_ehance_all_eth		97.06 331	97.03 316	97.16 381	97.83 423	93.06 406	94.66 451	99.09 289	95.99 368	98.69 257	98.45 334	92.73 358	99.61 364	96.79 266	99.03 363	98.82 361

cl____		97.02 334	96.83 330	97.58 352	97.82 424	94.04 376	94.66 451	99.16 277	97.04 313	98.63 265	98.71 285	88.68 399	99.69 313	97.00 245	99.81 133	99.00 333

DIV-MVS_self_test		97.02 334	96.84 329	97.58 352	97.82 424	94.03 377	94.66 451	99.16 277	97.04 313	98.63 265	98.71 285	88.69 397	99.69 313	97.00 245	99.81 133	99.01 329

CANet		97.87 266	97.76 267	98.19 296	97.75 426	95.51 318	96.76 355	99.05 296	97.74 241	96.93 394	98.21 356	95.59 291	99.89 97	97.86 179	99.93 56	99.19 299

UBG		93.25 426	92.32 427	96.04 423	97.72 427	90.16 453	95.92 409	95.91 444	96.03 366	93.95 467	93.04 476	69.60 470	99.52 399	90.72 454	97.98 428	98.45 403

mvsany_test1		97.60 287	97.54 285	97.77 327	97.72 427	95.35 330	95.36 432	97.13 417	94.13 418	99.71 50	99.33 115	97.93 136	99.30 441	97.60 200	98.94 377	98.67 388

PVSNet_0	89.98 21	91.15 447	90.30 449	93.70 456	97.72 427	84.34 480	90.24 480	97.42 406	90.20 462	93.79 468	93.09 475	90.90 381	98.89 465	86.57 469	72.76 486	97.87 439

CR-MVSNet		96.28 363	95.95 362	97.28 373	97.71 430	94.22 367	98.11 186	98.92 319	92.31 443	96.91 397	99.37 103	85.44 422	99.81 222	97.39 217	97.36 446	97.81 442

RPMNet		97.02 334	96.93 321	97.30 372	97.71 430	94.22 367	98.11 186	99.30 230	99.37 61	96.91 397	99.34 112	86.72 408	99.87 134	97.53 205	97.36 446	97.81 442

ETVMVS		92.60 435	91.08 444	97.18 377	97.70 432	93.65 399	96.54 367	95.70 447	96.51 341	94.68 455	92.39 479	61.80 487	99.50 405	86.97 466	97.41 442	98.40 411

pmmvs3		95.03 397	94.40 404	96.93 390	97.70 432	92.53 417	95.08 440	97.71 398	88.57 469	97.71 351	98.08 367	79.39 453	99.82 205	96.19 322	99.11 357	98.43 408

baseline2		93.73 418	92.83 424	96.42 408	97.70 432	91.28 439	96.84 351	89.77 480	93.96 423	92.44 475	95.93 440	79.14 454	99.77 261	92.94 416	96.76 457	98.21 420

WBMVS		95.18 394	94.78 400	96.37 409	97.68 435	89.74 456	95.80 415	98.73 356	97.54 263	98.30 302	98.44 335	70.06 468	99.82 205	96.62 288	99.87 98	99.54 142

tpm		94.67 402	94.34 406	95.66 430	97.68 435	88.42 460	97.88 231	94.90 454	94.46 409	96.03 434	98.56 318	78.66 456	99.79 244	95.88 335	95.01 472	98.78 373

CANet_DTU		97.26 316	97.06 315	97.84 321	97.57 437	94.65 358	96.19 391	98.79 345	97.23 301	95.14 450	98.24 353	93.22 345	99.84 174	97.34 219	99.84 112	99.04 325

testing11		93.08 429	92.02 434	96.26 414	97.56 438	90.83 448	96.32 383	95.70 447	96.47 345	92.66 474	93.73 469	64.36 484	99.59 371	93.77 401	97.57 435	98.37 415

tpm2		93.09 428	92.58 426	94.62 445	97.56 438	86.53 469	97.66 266	95.79 446	86.15 474	94.07 464	98.23 355	75.95 461	99.53 395	90.91 451	96.86 456	97.81 442

testing91		93.32 424	92.27 429	96.47 407	97.54 440	91.25 440	96.17 395	96.76 428	97.18 305	93.65 470	93.50 472	65.11 483	99.63 354	93.04 415	97.45 439	98.53 397

TR-MVS		95.55 387	95.12 393	96.86 397	97.54 440	93.94 385	96.49 372	96.53 433	94.36 414	97.03 392	96.61 426	94.26 329	99.16 453	86.91 468	96.31 461	97.47 456

testing99		93.04 430	91.98 437	96.23 416	97.53 442	90.70 450	96.35 381	95.94 443	96.87 325	93.41 471	93.43 474	63.84 485	99.59 371	93.24 413	97.19 449	98.40 411

1314		95.74 381	95.60 373	96.17 419	97.53 442	92.75 414	98.07 195	98.31 380	91.22 454	94.25 460	96.68 424	95.53 292	99.03 456	91.64 438	97.18 450	96.74 466

CostFormer		93.97 414	93.78 412	94.51 446	97.53 442	85.83 472	97.98 217	95.96 442	89.29 467	94.99 452	98.63 308	78.63 457	99.62 357	94.54 374	96.50 458	98.09 427

FMVSNet5		96.01 372	95.20 391	98.41 268	97.53 442	96.10 293	98.74 98	99.50 131	97.22 304	98.03 329	99.04 196	69.80 469	99.88 115	97.27 224	99.71 201	99.25 279

PMMVS		96.51 354	95.98 361	98.09 302	97.53 442	95.84 306	94.92 444	98.84 337	91.58 449	96.05 433	95.58 446	95.68 288	99.66 340	95.59 351	98.09 421	98.76 376

reproduce_monomvs		95.00 399	95.25 388	94.22 449	97.51 447	83.34 481	97.86 235	98.44 373	98.51 172	99.29 140	99.30 122	67.68 474	99.56 383	98.89 97	99.81 133	99.77 50

PAPR		95.29 391	94.47 402	97.75 331	97.50 448	95.14 339	94.89 445	98.71 358	91.39 453	95.35 448	95.48 451	94.57 320	99.14 455	84.95 471	97.37 444	98.97 339

testing222		91.96 444	90.37 447	96.72 402	97.47 449	92.59 415	96.11 397	94.76 455	96.83 328	92.90 473	92.87 477	57.92 488	99.55 387	86.93 467	97.52 436	98.00 433

PatchT		96.65 350	96.35 354	97.54 358	97.40 450	95.32 332	97.98 217	96.64 430	99.33 66	96.89 401	99.42 90	84.32 430	99.81 222	97.69 195	97.49 437	97.48 455

tpm cat1		93.29 425	93.13 422	93.75 455	97.39 451	84.74 475	97.39 306	97.65 402	83.39 479	94.16 461	98.41 337	82.86 441	99.39 428	91.56 440	95.35 471	97.14 461

PatchmatchNet		95.58 386	95.67 370	95.30 439	97.34 452	87.32 467	97.65 268	96.65 429	95.30 390	97.07 388	98.69 294	84.77 425	99.75 275	94.97 364	98.64 397	98.83 360
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 309	96.97 319	98.50 259	97.31 453	96.47 284	98.18 174	98.92 319	98.95 128	98.78 246	99.37 103	85.44 422	99.85 156	95.96 333	99.83 122	99.17 306

LS3D		98.63 162	98.38 192	99.36 74	97.25 454	99.38 13	99.12 60	99.32 217	99.21 81	98.44 293	98.88 247	97.31 195	99.80 231	96.58 291	99.34 317	98.92 348

IB-MVS	91.63 19	92.24 441	90.90 445	96.27 413	97.22 455	91.24 441	94.36 461	93.33 468	92.37 442	92.24 477	94.58 466	66.20 479	99.89 97	93.16 414	94.63 474	97.66 450
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
UWE-MVS		92.38 438	91.76 441	94.21 450	97.16 456	84.65 476	95.42 430	88.45 482	95.96 369	96.17 427	95.84 444	66.36 477	99.71 299	91.87 433	98.64 397	98.28 418

tpmrst		95.07 396	95.46 379	93.91 453	97.11 457	84.36 479	97.62 273	96.96 422	94.98 397	96.35 425	98.80 267	85.46 421	99.59 371	95.60 350	96.23 462	97.79 445

Syy-MVS		96.04 371	95.56 377	97.49 363	97.10 458	94.48 361	96.18 393	96.58 431	95.65 378	94.77 453	92.29 480	91.27 377	99.36 431	98.17 150	98.05 425	98.63 390

myMVS_eth3d		91.92 445	90.45 446	96.30 411	97.10 458	90.90 446	96.18 393	96.58 431	95.65 378	94.77 453	92.29 480	53.88 489	99.36 431	89.59 459	98.05 425	98.63 390

MDTV_nov1_ep13			95.22 390		97.06 460	83.20 482	97.74 255	96.16 437	94.37 413	96.99 393	98.83 260	83.95 434	99.53 395	93.90 395	97.95 429

MVS		93.19 427	92.09 432	96.50 406	96.91 461	94.03 377	98.07 195	98.06 391	68.01 484	94.56 458	96.48 429	95.96 279	99.30 441	83.84 473	96.89 455	96.17 471

E-PMN		94.17 410	94.37 405	93.58 457	96.86 462	85.71 473	90.11 482	97.07 418	98.17 203	97.82 346	97.19 415	84.62 427	98.94 461	89.77 457	97.68 434	96.09 475

JIA-IIPM		95.52 388	95.03 394	97.00 386	96.85 463	94.03 377	96.93 346	95.82 445	99.20 83	94.63 457	99.71 22	83.09 439	99.60 367	94.42 380	94.64 473	97.36 459

EMVS		93.83 416	94.02 408	93.23 462	96.83 464	84.96 474	89.77 483	96.32 435	97.92 228	97.43 375	96.36 434	86.17 413	98.93 462	87.68 464	97.73 433	95.81 476

blend_shiyan4		92.09 443	90.16 450	97.88 319	96.78 465	94.93 346	95.24 435	98.58 366	96.22 356	96.07 431	91.42 482	63.46 486	99.73 288	96.70 278	76.98 485	98.98 335

cl22		95.79 380	95.39 384	96.98 388	96.77 466	92.79 412	94.40 460	98.53 369	94.59 406	97.89 338	98.17 359	82.82 442	99.24 447	96.37 311	99.03 363	98.92 348

WB-MVSnew		95.73 382	95.57 376	96.23 416	96.70 467	90.70 450	96.07 399	93.86 465	95.60 380	97.04 390	95.45 455	96.00 272	99.55 387	91.04 448	98.31 409	98.43 408

dp		93.47 422	93.59 415	93.13 463	96.64 468	81.62 488	97.66 266	96.42 434	92.80 438	96.11 429	98.64 306	78.55 459	99.59 371	93.31 411	92.18 481	98.16 423

MonoMVSNet		96.25 365	96.53 351	95.39 437	96.57 469	91.01 444	98.82 96	97.68 401	98.57 167	98.03 329	99.37 103	90.92 380	97.78 478	94.99 362	93.88 477	97.38 458

usedtu_blend_shiyan5		96.20 368	95.62 371	97.94 315	96.53 470	94.93 346	98.83 95	99.59 90	98.89 135	96.71 409	91.16 483	86.05 416	99.73 288	96.70 278	96.09 465	99.17 306

test-LLR		93.90 415	93.85 410	94.04 451	96.53 470	84.62 477	94.05 466	92.39 471	96.17 358	94.12 462	95.07 456	82.30 443	99.67 327	95.87 338	98.18 414	97.82 440

test-mter		92.33 440	91.76 441	94.04 451	96.53 470	84.62 477	94.05 466	92.39 471	94.00 422	94.12 462	95.07 456	65.63 482	99.67 327	95.87 338	98.18 414	97.82 440

TESTMET0.1,1		92.19 442	91.77 440	93.46 458	96.48 473	82.80 484	94.05 466	91.52 476	94.45 411	94.00 465	94.88 462	66.65 476	99.56 383	95.78 343	98.11 420	98.02 430

MGCNet		97.44 301	97.01 318	98.72 211	96.42 474	96.74 268	97.20 330	91.97 474	98.46 175	98.30 302	98.79 269	92.74 357	99.91 74	99.30 63	99.94 50	99.52 157

miper_enhance_ethall		96.01 372	95.74 366	96.81 398	96.41 475	92.27 424	93.69 471	98.89 325	91.14 456	98.30 302	97.35 413	90.58 383	99.58 378	96.31 315	99.03 363	98.60 392

tpmvs		95.02 398	95.25 388	94.33 447	96.39 476	85.87 470	98.08 191	96.83 427	95.46 385	95.51 446	98.69 294	85.91 417	99.53 395	94.16 386	96.23 462	97.58 453

CMPMVS	75.91 23	96.29 362	95.44 381	98.84 179	96.25 477	98.69 98	97.02 339	99.12 284	88.90 468	97.83 344	98.86 250	89.51 392	98.90 464	91.92 431	99.51 282	98.92 348
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 403	93.69 413	96.99 387	96.05 478	93.61 401	94.97 443	93.49 466	96.17 358	97.57 362	94.88 462	82.30 443	99.01 459	93.60 404	94.17 476	98.37 415

EPMVS		93.72 419	93.27 418	95.09 442	96.04 479	87.76 464	98.13 181	85.01 487	94.69 404	96.92 395	98.64 306	78.47 460	99.31 439	95.04 361	96.46 459	98.20 421

cascas		94.79 401	94.33 407	96.15 422	96.02 480	92.36 422	92.34 478	99.26 250	85.34 476	95.08 451	94.96 461	92.96 352	98.53 471	94.41 383	98.59 401	97.56 454

MVStest1		95.86 377	95.60 373	96.63 403	95.87 481	91.70 429	97.93 223	98.94 313	98.03 218	99.56 74	99.66 32	71.83 466	98.26 474	99.35 59	99.24 334	99.91 13

gg-mvs-nofinetune		92.37 439	91.20 443	95.85 425	95.80 482	92.38 421	99.31 30	81.84 489	99.75 11	91.83 478	99.74 18	68.29 471	99.02 457	87.15 465	97.12 451	96.16 472

gm-plane-assit					94.83 483	81.97 486			88.07 471		94.99 459		99.60 367	91.76 435

GG-mvs-BLEND				94.76 444	94.54 484	92.13 426	99.31 30	80.47 490		88.73 484	91.01 484	67.59 475	98.16 477	82.30 478	94.53 475	93.98 480

UWE-MVS-28		90.22 448	89.28 451	93.02 464	94.50 485	82.87 483	96.52 370	87.51 483	95.21 393	92.36 476	96.04 436	71.57 467	98.25 475	72.04 485	97.77 432	97.94 435

EPNet_dtu		94.93 400	94.78 400	95.38 438	93.58 486	87.68 465	96.78 353	95.69 449	97.35 285	89.14 483	98.09 366	88.15 404	99.49 408	94.95 365	99.30 325	98.98 335
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 452	75.95 455	77.12 469	92.39 487	67.91 493	90.16 481	59.44 494	82.04 480	89.42 482	94.67 465	49.68 491	81.74 487	48.06 487	77.66 484	81.72 483

KD-MVS_2432*1600		92.87 433	91.99 435	95.51 434	91.37 488	89.27 457	94.07 464	98.14 387	95.42 386	97.25 383	96.44 431	67.86 472	99.24 447	91.28 444	96.08 466	98.02 430

miper_refine_blended		92.87 433	91.99 435	95.51 434	91.37 488	89.27 457	94.07 464	98.14 387	95.42 386	97.25 383	96.44 431	67.86 472	99.24 447	91.28 444	96.08 466	98.02 430

EPNet		96.14 369	95.44 381	98.25 287	90.76 490	95.50 321	97.92 226	94.65 456	98.97 124	92.98 472	98.85 253	89.12 395	99.87 134	95.99 331	99.68 216	99.39 224
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 453	68.95 456	70.34 470	87.68 491	65.00 494	91.11 479	59.90 493	69.02 483	74.46 488	88.89 485	48.58 492	68.03 489	28.61 488	72.33 487	77.99 484

test_method		79.78 450	79.50 453	80.62 467	80.21 492	45.76 495	70.82 484	98.41 377	31.08 487	80.89 487	97.71 390	84.85 424	97.37 480	91.51 441	80.03 483	98.75 377

tmp_tt		78.77 451	78.73 454	78.90 468	58.45 493	74.76 492	94.20 463	78.26 491	39.16 486	86.71 485	92.82 478	80.50 447	75.19 488	86.16 470	92.29 480	86.74 482

testmvs		17.12 455	20.53 458	6.87 472	12.05 494	4.20 497	93.62 472	6.73 495	4.62 490	10.41 490	24.33 487	8.28 494	3.56 491	9.69 490	15.07 488	12.86 487

test123		17.04 456	20.11 459	7.82 471	10.25 495	4.91 496	94.80 446	4.47 496	4.93 489	10.00 491	24.28 488	9.69 493	3.64 490	10.14 489	12.43 489	14.92 486

mmdepth		0.00 459	0.00 462	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	0.00 491	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

monomultidepth		0.00 459	0.00 462	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	0.00 491	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

test_blank		0.00 459	0.00 462	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	0.00 491	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

eth-test2					0.00 496

eth-test					0.00 496

uanet_test		0.00 459	0.00 462	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	0.00 491	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

DCPMVS		0.00 459	0.00 462	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	0.00 491	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

cdsmvs_eth3d_5k		24.66 454	32.88 457	0.00 473	0.00 496	0.00 498	0.00 485	99.10 287	0.00 491	0.00 492	97.58 398	99.21 18	0.00 492	0.00 491	0.00 490	0.00 488

pcd_1.5k_mvsjas		8.17 457	10.90 460	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	0.00 491	98.07 123	0.00 492	0.00 491	0.00 490	0.00 488

sosnet-low-res		0.00 459	0.00 462	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	0.00 491	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

sosnet		0.00 459	0.00 462	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	0.00 491	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

uncertanet		0.00 459	0.00 462	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	0.00 491	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

Regformer		0.00 459	0.00 462	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	0.00 491	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

ab-mvs-re		8.12 458	10.83 461	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	97.48 404	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

uanet		0.00 459	0.00 462	0.00 473	0.00 496	0.00 498	0.00 485	0.00 497	0.00 491	0.00 492	0.00 491	0.00 495	0.00 492	0.00 491	0.00 490	0.00 488

TestfortrainingZip							98.68 108

WAC-MVS						90.90 446								91.37 443

PC_three_1452									93.27 430	99.40 115	98.54 319	98.22 108	97.00 481	95.17 359	99.45 297	99.49 172

test_241102_TWO								99.30 230	98.03 218	99.26 148	99.02 199	97.51 181	99.88 115	96.91 253	99.60 250	99.66 78

test_0728_THIRD									98.17 203	99.08 178	99.02 199	97.89 142	99.88 115	97.07 240	99.71 201	99.70 68

GSMVS																98.81 366

sam_mvs1												84.74 426				98.81 366

sam_mvs												84.29 432

MTGPA								99.20 262

test_post1							97.59 281				20.48 490	83.07 440	99.66 340	94.16 386

test_post											21.25 489	83.86 435	99.70 306

patchmatchnet-post											98.77 273	84.37 429	99.85 156

MTMP							97.93 223	91.91 475

test9_res														93.28 412	99.15 350	99.38 233

agg_prior2														92.50 428	99.16 348	99.37 235

test_prior4						97.97 163	95.86 411

test_prior2							95.74 418		96.48 344	96.11 429	97.63 396	95.92 282		94.16 386	99.20 342

旧先验2							95.76 417		88.56 470	97.52 366			99.66 340	94.48 376

新几何2							95.93 407

无先验							95.74 418	98.74 355	89.38 466				99.73 288	92.38 430		99.22 289

原ACMM2							95.53 424

testdata2													99.79 244	92.80 422

segment_acmp												97.02 215

testdata1							95.44 429		96.32 352

plane_prior5								99.27 245					99.70 306	94.42 380	99.51 282	99.45 198

plane_prior4											97.98 374

plane_prior3						97.78 188			97.41 278	97.79 347

plane_prior2							97.77 248		98.20 200

plane_prior						97.65 197	97.07 338		96.72 334						99.36 313

n2								0.00 497

nn								0.00 497

door-mid								99.57 100

test11								98.87 328

door								99.41 182

HQP5-MVS						96.79 264

BP-MVS														92.82 420

HQP4-MVS										95.56 440			99.54 393			99.32 258

HQP3-MVS								99.04 299							99.26 332

HQP2-MVS												93.84 336

MDTV_nov1_ep13_2view						74.92 491	97.69 261		90.06 464	97.75 350		85.78 418		93.52 406		98.69 384

ACMMP++_ref															99.77 161

ACMMP++															99.68 216

Test By Simon												96.52 248

High-resolution multi-view benchmark