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 82	99.16 63	98.64 220	99.94 2	98.51 112	99.32 26	99.75 42	99.58 39	98.60 270	99.62 40	98.22 106	99.51 401	97.70 191	99.73 182	97.89 434
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 90	99.44 53	99.78 40	99.76 15	96.39 251	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	98.07 121	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	98.71 104	99.69 54	98.90 133	99.43 106	99.35 106	98.86 34	99.67 324	97.81 178	99.81 131	99.24 280

APD_test2		99.25 41	99.16 63	99.51 49	99.89 6	99.63 4	98.71 104	99.69 54	98.90 133	99.43 106	99.35 106	98.86 34	99.67 324	97.81 178	99.81 131	99.24 280

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 79	99.66 24	99.68 58	99.66 32	98.44 79	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	98.08 188	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	99.56 106	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 88	99.59 37	99.71 50	99.57 49	97.12 206	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 90	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		98.75 132	98.62 147	99.16 118	99.83 18	97.96 166	99.28 40	98.20 381	99.37 61	99.70 52	99.65 36	92.65 357	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 90	98.86 109	99.36 74	99.82 19	98.55 107	97.47 296	99.57 97	99.37 61	99.21 161	99.61 43	96.76 233	99.83 192	98.06 155	99.83 120	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	99.83 120	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 97	99.39 59	99.75 45	99.62 40	99.17 20	99.83 192	99.06 83	99.62 241	99.66 78

K. test v3		98.00 251	97.66 276	99.03 145	99.79 23	97.56 202	99.19 52	92.47 467	99.62 33	99.52 88	99.66 32	89.61 389	99.96 14	99.25 68	99.81 131	99.56 129

test_fmvsmconf0.1_n		99.49 15	99.54 14	99.34 83	99.78 24	98.11 143	97.77 245	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		98.83 116	98.66 140	99.34 83	99.78 24	99.47 9	98.42 149	99.45 155	98.28 188	98.98 198	99.19 151	97.76 153	99.58 375	96.57 290	99.55 268	98.97 336

test_vis3_rt		99.14 63	99.17 61	99.07 135	99.78 24	98.38 119	98.92 82	99.94 2	97.80 234	99.91 12	99.67 30	97.15 205	98.91 460	99.76 23	99.56 264	99.92 12

EGC-MVSNET		85.24 446	80.54 449	99.34 83	99.77 27	99.20 40	99.08 61	99.29 235	12.08 485	20.84 486	99.42 90	97.55 172	99.85 156	97.08 237	99.72 190	98.96 338

Anonymous20240521		98.69 145	98.87 105	98.16 297	99.77 27	95.11 339	99.08 61	99.44 163	99.34 65	99.33 130	99.55 57	94.10 332	99.94 42	99.25 68	99.96 28	99.42 209

FC-MVSNet-test		99.27 38	99.25 53	99.34 83	99.77 27	98.37 121	99.30 35	99.57 97	99.61 35	99.40 115	99.50 69	97.12 206	99.85 156	99.02 87	99.94 50	99.80 42

test_vis1_n		98.31 215	98.50 167	97.73 333	99.76 30	94.17 368	98.68 107	99.91 9	96.31 350	99.79 39	99.57 49	92.85 353	99.42 421	99.79 19	99.84 112	99.60 100

test_fmvs3		99.12 70	99.41 26	98.25 285	99.76 30	95.07 340	99.05 67	99.94 2	97.78 237	99.82 34	99.84 3	98.56 69	99.71 298	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 76	98.48 171	99.37 120	99.49 75	98.75 46	99.86 143	98.20 145	99.80 142	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 57	99.80 231	98.24 140	99.84 112	99.52 155

fmvsm_s_conf0.1_n_a		99.17 53	99.30 45	98.80 185	99.75 34	96.59 271	97.97 218	99.86 16	98.22 191	99.88 21	99.71 22	98.59 63	99.84 174	99.73 28	99.98 12	99.98 3

tt0805		98.69 145	98.62 147	98.90 171	99.75 34	99.30 23	99.15 56	96.97 418	98.86 138	98.87 231	97.62 395	98.63 59	98.96 457	99.41 57	98.29 408	98.45 400

test_vis1_n_1920		98.40 198	98.92 97	96.81 395	99.74 36	90.76 446	98.15 176	99.91 9	98.33 179	99.89 18	99.55 57	95.07 303	99.88 115	99.76 23	99.93 56	99.79 44

FOURS1					99.73 37	99.67 3	99.43 15	99.54 115	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	99.54 115	99.62 33	99.56 74	99.42 90	98.16 115	99.96 14	98.78 103	99.93 56	99.77 50

lessismore_v0				98.97 157	99.73 37	97.53 204		86.71 482		99.37 120	99.52 68	89.93 385	99.92 65	98.99 89	99.72 190	99.44 200

SteuartSystems-ACMMP		98.79 125	98.54 160	99.54 32	99.73 37	99.16 49	98.23 166	99.31 219	97.92 225	98.90 220	98.90 238	98.00 127	99.88 115	96.15 322	99.72 190	99.58 115
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 236	98.15 228	98.22 291	99.73 37	95.15 336	97.36 310	99.68 60	94.45 408	98.99 197	99.27 126	96.87 222	99.94 42	97.13 234	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		98.71 136	98.74 120	98.62 226	99.72 43	96.08 296	98.74 97	98.64 360	99.74 13	99.67 60	99.24 139	94.57 318	99.95 26	99.11 78	99.24 332	99.82 36

test_f		98.67 154	98.87 105	98.05 307	99.72 43	95.59 311	98.51 133	99.81 31	96.30 352	99.78 40	99.82 5	96.14 262	98.63 467	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	99.55 110	98.30 183	99.65 64	99.45 85	99.22 17	99.76 267	98.44 129	99.77 159	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	98.64 220	99.71 47	96.10 291	97.87 231	99.85 18	98.56 167	99.90 14	99.68 25	98.69 53	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	99.53 119	99.53 42	99.46 101	99.41 94	98.23 103	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	99.51 125	99.64 27	99.56 74	99.46 81	98.23 103	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	99.55 110	99.46 50	99.50 94	99.34 110	97.30 194	99.93 54	98.90 95	99.93 56	99.77 50

HPM-MVS_fast		99.01 84	98.82 113	99.57 22	99.71 47	99.35 17	99.00 72	99.50 128	97.33 283	98.94 215	98.86 248	98.75 46	99.82 205	97.53 203	99.71 199	99.56 129

ACMH+	96.62 9	99.08 77	99.00 89	99.33 89	99.71 47	98.83 87	98.60 119	99.58 90	99.11 98	99.53 83	99.18 155	98.81 38	99.67 324	96.71 275	99.77 159	99.50 163

PMVS	91.26 20	97.86 265	97.94 252	97.65 340	99.71 47	97.94 168	98.52 128	98.68 356	98.99 121	97.52 364	99.35 106	97.41 187	98.18 473	91.59 436	99.67 220	96.82 462
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	98.62 116	99.67 64	98.85 141	99.34 127	99.54 63	98.47 73	99.81 222	98.93 93	99.91 78	99.51 159

KinetiMVS		99.03 82	99.02 85	99.03 145	99.70 55	97.48 208	98.43 146	99.29 235	99.70 16	99.60 71	99.07 184	96.13 263	99.94 42	99.42 56	99.87 98	99.68 71

FIs		99.14 63	99.09 77	99.29 95	99.70 55	98.28 127	99.13 58	99.52 124	99.48 45	99.24 155	99.41 94	96.79 230	99.82 205	98.69 113	99.88 94	99.76 56

VPNet		98.87 106	98.83 112	99.01 149	99.70 55	97.62 200	98.43 146	99.35 200	99.47 48	99.28 142	99.05 192	96.72 236	99.82 205	98.09 152	99.36 311	99.59 107

fmvsm_s_conf0.1_n_2		99.20 51	99.38 29	98.65 218	99.69 59	96.08 296	97.49 291	99.90 11	99.53 42	99.88 21	99.64 37	98.51 72	99.90 81	99.83 10	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 212	98.68 135	97.27 371	99.69 59	92.29 420	98.03 199	99.85 18	97.62 247	99.96 4	99.62 40	93.98 333	99.74 281	99.52 50	99.86 105	99.79 44

MP-MVS-pluss		98.57 171	98.23 216	99.60 16	99.69 59	99.35 17	97.16 332	99.38 186	94.87 398	98.97 202	98.99 214	98.01 126	99.88 115	97.29 221	99.70 206	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	99.48 138	99.69 18	99.63 67	99.68 25	99.03 24	99.96 14	97.97 166	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	99.30 227	99.69 18	99.63 67	99.68 25	99.25 16	99.96 14	97.25 224	99.92 69	99.57 123

test_fmvs1_n		98.09 242	98.28 207	97.52 357	99.68 62	93.47 399	98.63 114	99.93 5	95.41 386	99.68 58	99.64 37	91.88 368	99.48 408	99.82 12	99.87 98	99.62 90

CHOSEN 1792x2688		97.49 294	97.14 309	98.54 249	99.68 62	96.09 294	96.50 368	99.62 76	91.58 446	98.84 234	98.97 221	92.36 359	99.88 115	96.76 268	99.95 38	99.67 76

tfpnnormal		98.90 101	98.90 99	98.91 168	99.67 66	97.82 183	99.00 72	99.44 163	99.45 51	99.51 93	99.24 139	98.20 110	99.86 143	95.92 331	99.69 209	99.04 322

MTAPA		98.88 105	98.64 143	99.61 14	99.67 66	99.36 16	98.43 146	99.20 259	98.83 143	98.89 223	98.90 238	96.98 216	99.92 65	97.16 229	99.70 206	99.56 129

test_fmvsmvis_n_1920		99.26 40	99.49 16	98.54 249	99.66 68	96.97 250	98.00 206	99.85 18	99.24 76	99.92 8	99.50 69	99.39 12	99.95 26	99.89 3	99.98 12	98.71 377

mvs5depth		99.30 34	99.59 12	98.44 263	99.65 69	95.35 328	99.82 3	99.94 2	99.83 7	99.42 110	99.94 2	98.13 118	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	97.05 245	97.80 240	99.76 39	98.70 149	99.78 40	99.11 174	98.79 42	99.95 26	99.85 6	99.96 28	99.83 33

WB-MVS		98.52 185	98.55 158	98.43 264	99.65 69	95.59 311	98.52 128	98.77 345	99.65 26	99.52 88	99.00 212	94.34 324	99.93 54	98.65 115	98.83 380	99.76 56

CP-MVSNet		99.21 48	99.09 77	99.56 27	99.65 69	98.96 78	99.13 58	99.34 206	99.42 56	99.33 130	99.26 132	97.01 214	99.94 42	98.74 108	99.93 56	99.79 44

HPM-MVS		98.79 125	98.53 162	99.59 20	99.65 69	99.29 25	99.16 54	99.43 169	96.74 330	98.61 268	98.38 339	98.62 60	99.87 134	96.47 302	99.67 220	99.59 107
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 163	98.36 193	99.42 68	99.65 69	99.42 11	98.55 124	99.57 97	97.72 241	98.90 220	99.26 132	96.12 265	99.52 396	95.72 342	99.71 199	99.32 256

NormalMVS		98.26 222	97.97 249	99.15 121	99.64 75	97.83 178	98.28 160	99.43 169	99.24 76	98.80 242	98.85 251	89.76 387	99.94 42	98.04 157	99.67 220	99.68 71

lecture		99.25 41	99.12 71	99.62 10	99.64 75	99.40 12	98.89 87	99.51 125	99.19 88	99.37 120	99.25 137	98.36 84	99.88 115	98.23 142	99.67 220	99.59 107

fmvsm_l_conf0.5_n		99.21 48	99.28 47	99.02 148	99.64 75	97.28 224	97.82 236	99.76 39	98.73 145	99.82 34	99.09 182	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	97.68 259	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.		98.63 160	98.49 172	99.06 141	99.64 75	97.90 172	98.51 133	98.94 310	96.96 314	99.24 155	98.89 244	97.83 145	99.81 222	96.88 258	99.49 290	99.48 181
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 119	98.72 124	99.12 124	99.64 75	98.54 110	97.98 214	99.68 60	97.62 247	99.34 127	99.18 155	97.54 174	99.77 261	97.79 180	99.74 179	99.04 322

Elysia		99.15 58	99.14 69	99.18 113	99.63 81	97.92 169	98.50 135	99.43 169	99.67 21	99.70 52	99.13 170	96.66 239	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	98.50 135	99.43 169	99.67 21	99.70 52	99.13 170	96.66 239	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	98.69 106	99.54 115	99.31 69	99.62 70	99.53 65	97.36 191	99.86 143	99.24 70	99.71 199	99.39 222

EU-MVSNet		97.66 282	98.50 167	95.13 437	99.63 81	85.84 468	98.35 156	98.21 380	98.23 190	99.54 79	99.46 81	95.02 304	99.68 320	98.24 140	99.87 98	99.87 22

HyFIR lowres test		97.19 321	96.60 345	98.96 158	99.62 85	97.28 224	95.17 434	99.50 128	94.21 413	99.01 192	98.32 347	86.61 407	99.99 2	97.10 236	99.84 112	99.60 100

E6		99.05 80	99.11 72	98.85 175	99.60 86	97.30 221	98.42 149	99.63 73	98.73 145	99.26 148	99.39 100	98.71 50	99.70 305	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 87	97.18 236	97.44 300	99.83 25	99.56 40	99.91 12	99.34 110	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 87	98.21 136	97.82 236	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 89	98.93 80	98.68 107	99.60 81	96.46 343	99.53 83	98.77 271		99.83 192	96.67 279	99.64 231	99.58 115

MED-MVS		98.90 101	98.72 124	99.45 64	99.58 89	98.93 80	98.68 107	99.60 81	98.14 209	99.53 83	98.77 271	97.87 142	99.83 192	96.67 279	99.64 231	99.58 115

TestfortrainingZip a		98.95 94	98.72 124	99.64 9	99.58 89	99.32 22	98.68 107	99.60 81	96.46 343	99.53 83	98.77 271	97.87 142	99.83 192	98.39 133	99.64 231	99.77 50

FE-MVSNET		98.59 168	98.50 167	98.87 172	99.58 89	97.30 221	98.08 188	99.74 43	96.94 316	98.97 202	99.10 177	96.94 218	99.74 281	97.33 219	99.86 105	99.55 136

mmtdpeth		99.30 34	99.42 25	98.92 167	99.58 89	96.89 258	99.48 13	99.92 7	99.92 2	98.26 306	99.80 11	98.33 90	99.91 74	99.56 41	99.95 38	99.97 4

ACMMP_NAP		98.75 132	98.48 173	99.57 22	99.58 89	99.29 25	97.82 236	99.25 248	96.94 316	98.78 244	99.12 173	98.02 125	99.84 174	97.13 234	99.67 220	99.59 107

nrg030		99.40 26	99.35 34	99.54 32	99.58 89	99.13 61	98.98 75	99.48 138	99.68 20	99.46 101	99.26 132	98.62 60	99.73 288	99.17 75	99.92 69	99.76 56

VDDNet		98.21 229	97.95 250	99.01 149	99.58 89	97.74 191	99.01 70	97.29 409	99.67 21	98.97 202	99.50 69	90.45 382	99.80 231	97.88 173	99.20 340	99.48 181

COLMAP_ROB	96.50 10	98.99 87	98.85 111	99.41 70	99.58 89	99.10 66	98.74 97	99.56 106	99.09 108	99.33 130	99.19 151	98.40 81	99.72 297	95.98 329	99.76 174	99.42 209
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 98	97.73 193	97.93 220	99.83 25	99.22 79	99.93 6	99.30 120	99.42 11	99.96 14	99.85 6	99.99 5	99.29 266

ZNCC-MVS		98.68 151	98.40 185	99.54 32	99.57 98	99.21 34	98.46 143	99.29 235	97.28 289	98.11 318	98.39 337	98.00 127	99.87 134	96.86 261	99.64 231	99.55 136

MSP-MVS		98.40 198	98.00 244	99.61 14	99.57 98	99.25 30	98.57 122	99.35 200	97.55 258	99.31 138	97.71 388	94.61 317	99.88 115	96.14 323	99.19 343	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		98.32 213	98.39 188	98.13 298	99.57 98	95.54 314	97.78 242	99.49 136	97.37 280	99.19 163	97.65 392	98.96 29	99.49 405	96.50 301	98.99 368	99.34 247

MP-MVS		98.46 191	98.09 233	99.54 32	99.57 98	99.22 33	98.50 135	99.19 263	97.61 250	97.58 358	98.66 299	97.40 188	99.88 115	94.72 368	99.60 248	99.54 142
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 136	98.46 177	99.47 61	99.57 98	98.97 74	98.23 166	99.48 138	96.60 335	99.10 174	99.06 185	98.71 50	99.83 192	95.58 349	99.78 153	99.62 90

LGP-MVS_train				99.47 61	99.57 98	98.97 74		99.48 138	96.60 335	99.10 174	99.06 185	98.71 50	99.83 192	95.58 349	99.78 153	99.62 90

IS-MVSNet		98.19 232	97.90 258	99.08 133	99.57 98	97.97 163	99.31 30	98.32 376	99.01 120	98.98 198	99.03 196	91.59 370	99.79 244	95.49 351	99.80 142	99.48 181

viewdifsd2359ckpt11		98.84 113	99.04 82	98.24 287	99.56 106	95.51 316	97.38 305	99.70 52	99.16 93	99.57 72	99.40 97	98.26 99	99.71 298	98.55 124	99.82 125	99.50 163

viewmsd2359difaftdt		98.84 113	99.04 82	98.24 287	99.56 106	95.51 316	97.38 305	99.70 52	99.16 93	99.57 72	99.40 97	98.26 99	99.71 298	98.55 124	99.82 125	99.50 163

dcpmvs_2		98.78 127	99.11 72	97.78 323	99.56 106	93.67 394	99.06 65	99.86 16	99.50 44	99.66 61	99.26 132	97.21 202	99.99 2	98.00 162	99.91 78	99.68 71

test_0402		98.76 131	98.71 129	98.93 164	99.56 106	98.14 141	98.45 145	99.34 206	99.28 73	98.95 208	98.91 235	98.34 89	99.79 244	95.63 346	99.91 78	98.86 355

EPP-MVSNet		98.30 216	98.04 240	99.07 135	99.56 106	97.83 178	99.29 36	98.07 387	99.03 118	98.59 272	99.13 170	92.16 363	99.90 81	96.87 259	99.68 214	99.49 170

ACMMP		98.75 132	98.50 167	99.52 45	99.56 106	99.16 49	98.87 88	99.37 190	97.16 304	98.82 238	99.01 208	97.71 156	99.87 134	96.29 314	99.69 209	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	98.78 192	99.55 112	96.59 271	97.79 241	99.82 30	98.21 193	99.81 37	99.53 65	98.46 77	99.84 174	99.70 33	99.97 21	99.90 15

fmvsm_s_conf0.5_n		99.09 73	99.26 51	98.61 230	99.55 112	96.09 294	97.74 252	99.81 31	98.55 168	99.85 27	99.55 57	98.60 62	99.84 174	99.69 35	99.98 12	99.89 16

FMVSNet1		99.17 53	99.17 61	99.17 115	99.55 112	98.24 130	99.20 48	99.44 163	99.21 81	99.43 106	99.55 57	97.82 148	99.86 143	98.42 132	99.89 92	99.41 212

Vis-MVSNet (Re-imp)		97.46 296	97.16 306	98.34 276	99.55 112	96.10 291	98.94 80	98.44 370	98.32 181	98.16 312	98.62 308	88.76 394	99.73 288	93.88 394	99.79 148	99.18 300

ACMM	96.08 12	98.91 99	98.73 122	99.48 57	99.55 112	99.14 58	98.07 192	99.37 190	97.62 247	99.04 188	98.96 224	98.84 36	99.79 244	97.43 213	99.65 229	99.49 170
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 141	98.97 93	97.89 315	99.54 117	94.05 371	98.55 124	99.92 7	96.78 328	99.72 48	99.78 13	96.60 243	99.67 324	99.91 2	99.90 86	99.94 10

mPP-MVS		98.64 158	98.34 196	99.54 32	99.54 117	99.17 45	98.63 114	99.24 253	97.47 266	98.09 320	98.68 294	97.62 165	99.89 97	96.22 317	99.62 241	99.57 123

XVG-ACMP-BASELINE		98.56 172	98.34 196	99.22 109	99.54 117	98.59 104	97.71 255	99.46 151	97.25 292	98.98 198	98.99 214	97.54 174	99.84 174	95.88 332	99.74 179	99.23 282

viewmacassd2359aftdt		98.86 110	98.87 105	98.83 178	99.53 120	97.32 220	97.70 257	99.64 71	98.22 191	99.25 153	99.27 126	98.40 81	99.61 361	97.98 165	99.87 98	99.55 136

region2R		98.69 145	98.40 185	99.54 32	99.53 120	99.17 45	98.52 128	99.31 219	97.46 271	98.44 291	98.51 322	97.83 145	99.88 115	96.46 303	99.58 257	99.58 115

PGM-MVS		98.66 155	98.37 192	99.55 29	99.53 120	99.18 44	98.23 166	99.49 136	97.01 313	98.69 255	98.88 245	98.00 127	99.89 97	95.87 335	99.59 252	99.58 115

E4		98.87 106	98.88 102	98.81 182	99.52 123	97.23 227	97.62 270	99.61 79	98.58 162	99.18 167	99.33 113	98.29 93	99.69 310	97.99 164	99.83 120	99.52 155

Patchmatch-RL test		97.26 314	97.02 315	97.99 311	99.52 123	95.53 315	96.13 393	99.71 47	97.47 266	99.27 144	99.16 161	84.30 428	99.62 354	97.89 170	99.77 159	98.81 363

ACMMPR		98.70 141	98.42 183	99.54 32	99.52 123	99.14 58	98.52 128	99.31 219	97.47 266	98.56 278	98.54 317	97.75 154	99.88 115	96.57 290	99.59 252	99.58 115

fmvsm_s_conf0.5_n_9		99.17 53	99.38 29	98.53 251	99.51 126	95.82 306	97.62 270	99.78 36	99.72 15	99.90 14	99.48 76	98.66 55	99.89 97	99.85 6	99.93 56	99.89 16

AstraMVS		98.16 238	98.07 238	98.41 266	99.51 126	95.86 303	98.00 206	95.14 450	98.97 124	99.43 106	99.24 139	93.25 341	99.84 174	99.21 71	99.87 98	99.54 142

fmvsm_s_conf0.5_n_8		99.13 67	99.26 51	98.74 205	99.51 126	96.44 283	97.65 265	99.65 69	99.66 24	99.78 40	99.48 76	97.92 135	99.93 54	99.72 30	99.95 38	99.87 22

GST-MVS		98.61 164	98.30 204	99.52 45	99.51 126	99.20 40	98.26 164	99.25 248	97.44 274	98.67 258	98.39 337	97.68 157	99.85 156	96.00 327	99.51 280	99.52 155

Anonymous20231206		98.21 229	98.21 217	98.20 292	99.51 126	95.43 325	98.13 178	99.32 214	96.16 357	98.93 216	98.82 261	96.00 270	99.83 192	97.32 220	99.73 182	99.36 240

ACMP	95.32 15	98.41 195	98.09 233	99.36 74	99.51 126	98.79 90	97.68 259	99.38 186	95.76 373	98.81 240	98.82 261	98.36 84	99.82 205	94.75 365	99.77 159	99.48 181
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LuminaMVS		98.39 204	98.20 218	98.98 155	99.50 132	97.49 205	97.78 242	97.69 396	98.75 144	99.49 95	99.25 137	92.30 361	99.94 42	99.14 76	99.88 94	99.50 163

DVP-MVS		98.77 130	98.52 163	99.52 45	99.50 132	99.21 34	98.02 202	98.84 334	97.97 219	99.08 176	99.02 197	97.61 167	99.88 115	96.99 245	99.63 238	99.48 181
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	99.50 132	99.23 32	98.02 202	99.32 214					99.88 115	96.99 245	99.63 238	99.68 71

test0726					99.50 132	99.21 34	98.17 174	99.35 200	97.97 219	99.26 148	99.06 185	97.61 167

AllTest		98.44 193	98.20 218	99.16 118	99.50 132	98.55 107	98.25 165	99.58 90	96.80 326	98.88 227	99.06 185	97.65 160	99.57 377	94.45 375	99.61 246	99.37 233

TestCases				99.16 118	99.50 132	98.55 107		99.58 90	96.80 326	98.88 227	99.06 185	97.65 160	99.57 377	94.45 375	99.61 246	99.37 233

XVG-OURS		98.53 181	98.34 196	99.11 126	99.50 132	98.82 89	95.97 399	99.50 128	97.30 287	99.05 186	98.98 219	99.35 14	99.32 435	95.72 342	99.68 214	99.18 300

EG-PatchMatch MVS		98.99 87	99.01 87	98.94 161	99.50 132	97.47 209	98.04 197	99.59 88	98.15 208	99.40 115	99.36 105	98.58 68	99.76 267	98.78 103	99.68 214	99.59 107

fmvsm_s_conf0.5_n_2		99.14 63	99.31 42	98.63 224	99.49 140	96.08 296	97.38 305	99.81 31	99.48 45	99.84 30	99.57 49	98.46 77	99.89 97	99.82 12	99.97 21	99.91 13

SED-MVS		98.91 99	98.72 124	99.49 55	99.49 140	99.17 45	98.10 185	99.31 219	98.03 215	99.66 61	99.02 197	98.36 84	99.88 115	96.91 251	99.62 241	99.41 212

IU-MVS					99.49 140	99.15 53		98.87 325	92.97 431	99.41 112				96.76 268	99.62 241	99.66 78

test_241102_ONE					99.49 140	99.17 45		99.31 219	97.98 218	99.66 61	98.90 238	98.36 84	99.48 408

UA-Net		99.47 16	99.40 27	99.70 2	99.49 140	99.29 25	99.80 4	99.72 45	99.82 8	99.04 188	99.81 8	98.05 124	99.96 14	98.85 99	99.99 5	99.86 28

HFP-MVS		98.71 136	98.44 180	99.51 49	99.49 140	99.16 49	98.52 128	99.31 219	97.47 266	98.58 274	98.50 326	97.97 131	99.85 156	96.57 290	99.59 252	99.53 152

VPA-MVSNet		99.30 34	99.30 45	99.28 96	99.49 140	98.36 124	99.00 72	99.45 155	99.63 29	99.52 88	99.44 86	98.25 101	99.88 115	99.09 80	99.84 112	99.62 90

XVG-OURS-SEG-HR		98.49 188	98.28 207	99.14 122	99.49 140	98.83 87	96.54 364	99.48 138	97.32 285	99.11 171	98.61 310	99.33 15	99.30 438	96.23 316	98.38 404	99.28 269

fmvsm_s_conf0.5_n_11		99.21 48	99.34 36	98.80 185	99.48 148	96.56 276	97.97 218	99.69 54	99.63 29	99.84 30	99.54 63	98.21 108	99.94 42	99.76 23	99.95 38	99.88 20

114514_t		96.50 354	95.77 363	98.69 213	99.48 148	97.43 213	97.84 235	99.55 110	81.42 478	96.51 417	98.58 314	95.53 290	99.67 324	93.41 407	99.58 257	98.98 332

IterMVS-LS		98.55 176	98.70 132	98.09 300	99.48 148	94.73 351	97.22 326	99.39 184	98.97 124	99.38 118	99.31 119	96.00 270	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	98.78 192	99.47 151	96.56 276	97.75 251	99.71 47	99.60 36	99.74 47	99.44 86	97.96 132	99.95 26	99.86 4	99.94 50	99.82 36

fmvsm_s_conf0.5_n_5		99.07 79	99.10 75	98.99 151	99.47 151	97.22 230	97.40 302	99.83 25	97.61 250	99.85 27	99.30 120	98.80 40	99.95 26	99.71 32	99.90 86	99.78 47

v8		99.01 84	99.16 63	98.57 237	99.47 151	96.31 288	98.90 83	99.47 147	99.03 118	99.52 88	99.57 49	96.93 219	99.81 222	99.60 37	99.98 12	99.60 100

SSC-MVS3.2		98.53 181	98.79 116	97.74 330	99.46 154	93.62 397	96.45 370	99.34 206	99.33 66	98.93 216	98.70 290	97.90 136	99.90 81	99.12 77	99.92 69	99.69 70

fmvsm_s_conf0.5_n_3		99.22 47	99.37 32	98.78 192	99.46 154	96.58 274	97.65 265	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		98.72 135	98.45 178	99.53 39	99.46 154	99.21 34	98.65 112	99.34 206	98.62 156	97.54 362	98.63 306	97.50 180	99.83 192	96.79 264	99.53 274	99.56 129

X-MVStestdata		94.32 403	92.59 422	99.53 39	99.46 154	99.21 34	98.65 112	99.34 206	98.62 156	97.54 362	45.85 483	97.50 180	99.83 192	96.79 264	99.53 274	99.56 129

test20.03		98.78 127	98.77 119	98.78 192	99.46 154	97.20 233	97.78 242	99.24 253	99.04 117	99.41 112	98.90 238	97.65 160	99.76 267	97.70 191	99.79 148	99.39 222

guyue		98.01 250	97.93 254	98.26 283	99.45 159	95.48 320	98.08 188	96.24 433	98.89 135	99.34 127	99.14 168	91.32 374	99.82 205	99.07 81	99.83 120	99.48 181

CSCG		98.68 151	98.50 167	99.20 110	99.45 159	98.63 99	98.56 123	99.57 97	97.87 229	98.85 232	98.04 368	97.66 159	99.84 174	96.72 273	99.81 131	99.13 311

GeoE		99.05 80	98.99 91	99.25 104	99.44 161	98.35 125	98.73 101	99.56 106	98.42 174	98.91 219	98.81 264	98.94 30	99.91 74	98.35 135	99.73 182	99.49 170

v148		98.45 192	98.60 152	98.00 310	99.44 161	94.98 342	97.44 300	99.06 289	98.30 183	99.32 136	98.97 221	96.65 241	99.62 354	98.37 134	99.85 107	99.39 222

v10		98.97 91	99.11 72	98.55 244	99.44 161	96.21 290	98.90 83	99.55 110	98.73 145	99.48 96	99.60 45	96.63 242	99.83 192	99.70 33	99.99 5	99.61 98

V42		98.78 127	98.78 118	98.76 199	99.44 161	97.04 246	98.27 163	99.19 263	97.87 229	99.25 153	99.16 161	96.84 223	99.78 255	99.21 71	99.84 112	99.46 191

MDA-MVSNet-bldmvs		97.94 256	97.91 257	98.06 305	99.44 161	94.96 343	96.63 360	99.15 279	98.35 177	98.83 235	99.11 174	94.31 325	99.85 156	96.60 287	98.72 386	99.37 233

viewdifsd2359ckpt07		98.71 136	98.86 109	98.26 283	99.43 166	95.65 310	97.20 327	99.66 65	99.20 83	99.29 140	99.01 208	98.29 93	99.73 288	97.92 169	99.75 178	99.39 222

casdiffmvs_mvg		99.12 70	99.16 63	98.99 151	99.43 166	97.73 193	98.00 206	99.62 76	99.22 79	99.55 77	99.22 145	98.93 32	99.75 275	98.66 114	99.81 131	99.50 163
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SSM_0404		98.90 101	99.01 87	98.57 237	99.42 168	96.59 271	98.13 178	99.66 65	99.09 108	99.30 139	99.02 197	98.79 42	99.89 97	97.87 175	99.80 142	99.23 282

test1111		96.49 355	96.82 329	95.52 430	99.42 168	87.08 465	99.22 45	87.14 481	99.11 98	99.46 101	99.58 47	88.69 395	99.86 143	98.80 101	99.95 38	99.62 90

v2v482		98.56 172	98.62 147	98.37 273	99.42 168	95.81 307	97.58 279	99.16 274	97.90 227	99.28 142	99.01 208	95.98 275	99.79 244	99.33 60	99.90 86	99.51 159

OPM-MVS		98.56 172	98.32 202	99.25 104	99.41 171	98.73 95	97.13 334	99.18 267	97.10 307	98.75 250	98.92 232	98.18 111	99.65 344	96.68 278	99.56 264	99.37 233
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 244	98.08 236	98.04 308	99.41 171	94.59 357	94.59 452	99.40 182	97.50 263	98.82 238	98.83 258	96.83 225	99.84 174	97.50 206	99.81 131	99.71 63

E2		98.70 141	98.68 135	98.73 207	99.40 173	97.10 243	97.48 292	99.57 97	98.09 212	99.00 193	99.20 148	97.90 136	99.67 324	97.73 189	99.77 159	99.43 204

E3		98.69 145	98.68 135	98.73 207	99.40 173	97.10 243	97.48 292	99.57 97	98.09 212	99.00 193	99.20 148	97.90 136	99.67 324	97.73 189	99.77 159	99.43 204

test_one_0601					99.39 175	99.20 40		99.31 219	98.49 170	98.66 260	99.02 197	97.64 163

mvsany_test3		98.87 106	98.92 97	98.74 205	99.38 176	96.94 254	98.58 121	99.10 284	96.49 340	99.96 4	99.81 8	98.18 111	99.45 416	98.97 90	99.79 148	99.83 33

patch_mono-2		98.51 186	98.63 145	98.17 295	99.38 176	94.78 348	97.36 310	99.69 54	98.16 203	98.49 287	99.29 123	97.06 209	99.97 7	98.29 139	99.91 78	99.76 56

test2506		92.39 434	91.89 436	93.89 451	99.38 176	82.28 482	99.32 26	66.03 489	99.08 112	98.77 247	99.57 49	66.26 475	99.84 174	98.71 111	99.95 38	99.54 142

ECVR-MVS		96.42 357	96.61 343	95.85 422	99.38 176	88.18 460	99.22 45	86.00 483	99.08 112	99.36 123	99.57 49	88.47 400	99.82 205	98.52 126	99.95 38	99.54 142

casdiffmvs		98.95 94	99.00 89	98.81 182	99.38 176	97.33 218	97.82 236	99.57 97	99.17 92	99.35 125	99.17 159	98.35 88	99.69 310	98.46 128	99.73 182	99.41 212
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 93	99.02 85	98.76 199	99.38 176	97.26 226	98.49 138	99.50 128	98.86 138	99.19 163	99.06 185	98.23 103	99.69 310	98.71 111	99.76 174	99.33 253

TranMVSNet+NR-MVSNet		99.17 53	99.07 80	99.46 63	99.37 182	98.87 85	98.39 152	99.42 175	99.42 56	99.36 123	99.06 185	98.38 83	99.95 26	98.34 136	99.90 86	99.57 123

fmvsm_s_conf0.5_n_6		99.08 77	99.21 58	98.69 213	99.36 183	96.51 278	97.62 270	99.68 60	98.43 173	99.85 27	99.10 177	99.12 23	99.88 115	99.77 22	99.92 69	99.67 76

tttt0517		95.64 382	94.98 392	97.64 343	99.36 183	93.81 389	98.72 102	90.47 475	98.08 214	98.67 258	98.34 344	73.88 461	99.92 65	97.77 182	99.51 280	99.20 292

test_part2					99.36 183	99.10 66				99.05 186

v1144		98.60 166	98.66 140	98.41 266	99.36 183	95.90 301	97.58 279	99.34 206	97.51 262	99.27 144	99.15 165	96.34 256	99.80 231	99.47 54	99.93 56	99.51 159

CP-MVS		98.70 141	98.42 183	99.52 45	99.36 183	99.12 63	98.72 102	99.36 194	97.54 260	98.30 300	98.40 336	97.86 144	99.89 97	96.53 299	99.72 190	99.56 129

diffmvs_AUTHOR		98.50 187	98.59 154	98.23 290	99.35 188	95.48 320	96.61 361	99.60 81	98.37 175	98.90 220	99.00 212	97.37 190	99.76 267	98.22 143	99.85 107	99.46 191

Test_1112_low_res		96.99 336	96.55 347	98.31 279	99.35 188	95.47 323	95.84 411	99.53 119	91.51 448	96.80 404	98.48 329	91.36 373	99.83 192	96.58 288	99.53 274	99.62 90

DeepC-MVS	97.60 4	98.97 91	98.93 96	99.10 128	99.35 188	97.98 162	98.01 205	99.46 151	97.56 256	99.54 79	99.50 69	98.97 28	99.84 174	98.06 155	99.92 69	99.49 170
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 313	96.86 325	98.58 234	99.34 191	96.32 287	96.75 353	99.58 90	93.14 429	96.89 399	97.48 402	92.11 365	99.86 143	96.91 251	99.54 270	99.57 123

reproduce_model		99.15 58	98.97 93	99.67 4	99.33 192	99.44 10	98.15 176	99.47 147	99.12 97	99.52 88	99.32 118	98.31 91	99.90 81	97.78 181	99.73 182	99.66 78

MVSMamba_PlusPlus		98.83 116	98.98 92	98.36 274	99.32 193	96.58 274	98.90 83	99.41 179	99.75 11	98.72 253	99.50 69	96.17 261	99.94 42	99.27 65	99.78 153	98.57 393

fmvsm_s_conf0.5_n_4		99.01 84	99.22 55	98.38 270	99.31 194	95.48 320	97.56 281	99.73 44	98.87 136	99.75 45	99.27 126	98.80 40	99.86 143	99.80 17	99.90 86	99.81 40

SF-MVS		98.53 181	98.27 210	99.32 91	99.31 194	98.75 91	98.19 170	99.41 179	96.77 329	98.83 235	98.90 238	97.80 150	99.82 205	95.68 345	99.52 277	99.38 231

CPTT-MVS		97.84 271	97.36 295	99.27 99	99.31 194	98.46 115	98.29 159	99.27 242	94.90 397	97.83 342	98.37 340	94.90 306	99.84 174	93.85 396	99.54 270	99.51 159

UnsupCasMVSNet_eth		97.89 260	97.60 281	98.75 201	99.31 194	97.17 238	97.62 270	99.35 200	98.72 148	98.76 249	98.68 294	92.57 358	99.74 281	97.76 186	95.60 466	99.34 247

fmvsm_s_conf0.5_n_7		98.83 116	99.04 82	98.20 292	99.30 198	94.83 346	97.23 322	99.36 194	98.64 151	99.84 30	99.43 89	98.10 120	99.91 74	99.56 41	99.96 28	99.87 22

pmmvs-eth3d		98.47 190	98.34 196	98.86 174	99.30 198	97.76 189	97.16 332	99.28 239	95.54 379	99.42 110	99.19 151	97.27 197	99.63 351	97.89 170	99.97 21	99.20 292

mamv4		99.44 19	99.39 28	99.58 21	99.30 198	99.74 2	99.04 68	99.81 31	99.77 10	99.82 34	99.57 49	97.82 148	99.98 4	99.53 48	99.89 92	99.01 326

viewcassd2359sk11		98.55 176	98.51 164	98.67 216	99.29 201	96.99 249	97.39 303	99.54 115	97.73 239	98.81 240	99.08 183	97.55 172	99.66 337	97.52 205	99.67 220	99.36 240

SymmetryMVS		98.05 246	97.71 271	99.09 132	99.29 201	97.83 178	98.28 160	97.64 401	99.24 76	98.80 242	98.85 251	89.76 387	99.94 42	98.04 157	99.50 288	99.49 170

Anonymous20231211		99.27 38	99.27 48	99.26 101	99.29 201	98.18 137	99.49 12	99.51 125	99.70 16	99.80 38	99.68 25	96.84 223	99.83 192	99.21 71	99.91 78	99.77 50

viewmanbaseed2359cas		98.58 170	98.54 160	98.70 211	99.28 204	97.13 242	97.47 296	99.55 110	97.55 258	98.96 207	98.92 232	97.77 152	99.59 368	97.59 199	99.77 159	99.39 222

UnsupCasMVSNet_bld		97.30 311	96.92 321	98.45 261	99.28 204	96.78 265	96.20 387	99.27 242	95.42 383	98.28 304	98.30 348	93.16 344	99.71 298	94.99 359	97.37 442	98.87 354

EC-MVSNet		99.09 73	99.05 81	99.20 110	99.28 204	98.93 80	99.24 44	99.84 22	99.08 112	98.12 317	98.37 340	98.72 49	99.90 81	99.05 84	99.77 159	98.77 371

mamba_0408		98.80 123	98.88 102	98.55 244	99.27 207	96.50 279	98.00 206	99.60 81	98.93 129	99.22 158	98.84 256	98.59 63	99.89 97	97.74 187	99.72 190	99.27 270

SSM_04072		98.80 123	98.88 102	98.56 242	99.27 207	96.50 279	98.00 206	99.60 81	98.93 129	99.22 158	98.84 256	98.59 63	99.90 81	97.74 187	99.72 190	99.27 270

SSM_0407		98.86 110	98.96 95	98.55 244	99.27 207	96.50 279	98.04 197	99.66 65	99.09 108	99.22 158	99.02 197	98.79 42	99.87 134	97.87 175	99.72 190	99.27 270

reproduce-ours		99.09 73	98.90 99	99.67 4	99.27 207	99.49 6	98.00 206	99.42 175	99.05 115	99.48 96	99.27 126	98.29 93	99.89 97	97.61 196	99.71 199	99.62 90

our_new_method		99.09 73	98.90 99	99.67 4	99.27 207	99.49 6	98.00 206	99.42 175	99.05 115	99.48 96	99.27 126	98.29 93	99.89 97	97.61 196	99.71 199	99.62 90

DPE-MVS		98.59 168	98.26 211	99.57 22	99.27 207	99.15 53	97.01 337	99.39 184	97.67 243	99.44 105	98.99 214	97.53 176	99.89 97	95.40 353	99.68 214	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		97.85 270	98.18 223	96.87 391	99.27 207	91.16 440	95.53 421	99.25 248	99.10 105	99.41 112	99.35 106	93.10 346	99.96 14	98.65 115	99.94 50	99.49 170

v1192		98.60 166	98.66 140	98.41 266	99.27 207	95.88 302	97.52 286	99.36 194	97.41 275	99.33 130	99.20 148	96.37 254	99.82 205	99.57 39	99.92 69	99.55 136

N_pmnet		97.63 284	97.17 305	98.99 151	99.27 207	97.86 175	95.98 398	93.41 464	95.25 388	99.47 100	98.90 238	95.63 287	99.85 156	96.91 251	99.73 182	99.27 270

viewdifsd2359ckpt13		98.39 204	98.29 206	98.70 211	99.26 216	97.19 234	97.51 288	99.48 138	96.94 316	98.58 274	98.82 261	97.47 185	99.55 384	97.21 226	99.33 316	99.34 247

FPMVS		93.44 420	92.23 427	97.08 379	99.25 217	97.86 175	95.61 418	97.16 413	92.90 433	93.76 466	98.65 301	75.94 459	95.66 480	79.30 478	97.49 435	97.73 444

ME-MVS		98.61 164	98.33 201	99.44 66	99.24 218	98.93 80	97.45 298	99.06 289	98.14 209	99.06 178	98.77 271	96.97 217	99.82 205	96.67 279	99.64 231	99.58 115

new-patchmatchnet		98.35 207	98.74 120	97.18 374	99.24 218	92.23 422	96.42 374	99.48 138	98.30 183	99.69 56	99.53 65	97.44 186	99.82 205	98.84 100	99.77 159	99.49 170

MCST-MVS		98.00 251	97.63 279	99.10 128	99.24 218	98.17 138	96.89 346	98.73 353	95.66 374	97.92 333	97.70 390	97.17 204	99.66 337	96.18 321	99.23 335	99.47 189

UniMVSNet (Re)		98.87 106	98.71 129	99.35 80	99.24 218	98.73 95	97.73 254	99.38 186	98.93 129	99.12 170	98.73 280	96.77 231	99.86 143	98.63 117	99.80 142	99.46 191

jason		97.45 298	97.35 296	97.76 327	99.24 218	93.93 383	95.86 408	98.42 372	94.24 412	98.50 286	98.13 358	94.82 310	99.91 74	97.22 225	99.73 182	99.43 204
jason: jason.
IterMVS		97.73 276	98.11 232	96.57 401	99.24 218	90.28 449	95.52 423	99.21 257	98.86 138	99.33 130	99.33 113	93.11 345	99.94 42	98.49 127	99.94 50	99.48 181
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 176	98.62 147	98.32 277	99.22 224	95.58 313	97.51 288	99.45 155	97.16 304	99.45 104	99.24 139	96.12 265	99.85 156	99.60 37	99.88 94	99.55 136

ITE_SJBPF				98.87 172	99.22 224	98.48 114		99.35 200	97.50 263	98.28 304	98.60 312	97.64 163	99.35 431	93.86 395	99.27 327	98.79 369

h-mvs33		97.77 274	97.33 298	99.10 128	99.21 226	97.84 177	98.35 156	98.57 364	99.11 98	98.58 274	99.02 197	88.65 398	99.96 14	98.11 150	96.34 458	99.49 170

v144192		98.54 179	98.57 156	98.45 261	99.21 226	95.98 299	97.63 269	99.36 194	97.15 306	99.32 136	99.18 155	95.84 282	99.84 174	99.50 51	99.91 78	99.54 142

APDe-MVS		98.99 87	98.79 116	99.60 16	99.21 226	99.15 53	98.87 88	99.48 138	97.57 254	99.35 125	99.24 139	97.83 145	99.89 97	97.88 173	99.70 206	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 97	98.81 115	99.28 96	99.21 226	98.45 116	98.46 143	99.33 212	99.63 29	99.48 96	99.15 165	97.23 200	99.75 275	97.17 228	99.66 228	99.63 89

SR-MVS-dyc-post		98.81 121	98.55 158	99.57 22	99.20 230	99.38 13	98.48 141	99.30 227	98.64 151	98.95 208	98.96 224	97.49 183	99.86 143	96.56 294	99.39 307	99.45 196

RE-MVS-def			98.58 155		99.20 230	99.38 13	98.48 141	99.30 227	98.64 151	98.95 208	98.96 224	97.75 154		96.56 294	99.39 307	99.45 196

v1921920		98.54 179	98.60 152	98.38 270	99.20 230	95.76 309	97.56 281	99.36 194	97.23 298	99.38 118	99.17 159	96.02 268	99.84 174	99.57 39	99.90 86	99.54 142

E3new		98.41 195	98.34 196	98.62 226	99.19 233	96.90 257	97.32 313	99.50 128	97.40 277	98.63 263	98.92 232	97.21 202	99.65 344	97.34 217	99.52 277	99.31 260

thisisatest0530		95.27 389	94.45 400	97.74 330	99.19 233	94.37 361	97.86 232	90.20 476	97.17 303	98.22 307	97.65 392	73.53 462	99.90 81	96.90 256	99.35 313	98.95 339

Anonymous20240529		98.93 97	98.87 105	99.12 124	99.19 233	98.22 135	99.01 70	98.99 307	99.25 75	99.54 79	99.37 101	97.04 210	99.80 231	97.89 170	99.52 277	99.35 245

APD-MVS_3200maxsize		98.84 113	98.61 151	99.53 39	99.19 233	99.27 28	98.49 138	99.33 212	98.64 151	99.03 191	98.98 219	97.89 140	99.85 156	96.54 298	99.42 304	99.46 191

HQP_MVS		97.99 254	97.67 273	98.93 164	99.19 233	97.65 197	97.77 245	99.27 242	98.20 197	97.79 345	97.98 372	94.90 306	99.70 305	94.42 377	99.51 280	99.45 196

plane_prior7					99.19 233	97.87 174

ab-mvs		98.41 195	98.36 193	98.59 233	99.19 233	97.23 227	99.32 26	98.81 339	97.66 244	98.62 266	99.40 97	96.82 226	99.80 231	95.88 332	99.51 280	98.75 374

F-COLMAP		97.30 311	96.68 338	99.14 122	99.19 233	98.39 118	97.27 321	99.30 227	92.93 432	96.62 410	98.00 370	95.73 285	99.68 320	92.62 423	98.46 403	99.35 245

viewdifsd2359ckpt09		98.13 239	97.92 255	98.77 197	99.18 241	97.35 216	97.29 317	99.53 119	95.81 371	98.09 320	98.47 330	96.34 256	99.66 337	97.02 241	99.51 280	99.29 266

SR-MVS		98.71 136	98.43 181	99.57 22	99.18 241	99.35 17	98.36 155	99.29 235	98.29 186	98.88 227	98.85 251	97.53 176	99.87 134	96.14 323	99.31 320	99.48 181

UniMVSNet_NR-MVSNet		98.86 110	98.68 135	99.40 72	99.17 243	98.74 92	97.68 259	99.40 182	99.14 96	99.06 178	98.59 313	96.71 237	99.93 54	98.57 120	99.77 159	99.53 152

LF4IMVS		97.90 258	97.69 272	98.52 252	99.17 243	97.66 196	97.19 331	99.47 147	96.31 350	97.85 341	98.20 355	96.71 237	99.52 396	94.62 369	99.72 190	98.38 410

SMA-MVS		98.40 198	98.03 241	99.51 49	99.16 245	99.21 34	98.05 195	99.22 256	94.16 414	98.98 198	99.10 177	97.52 178	99.79 244	96.45 304	99.64 231	99.53 152
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		98.82 119	98.63 145	99.39 73	99.16 245	98.74 92	97.54 284	99.25 248	98.84 142	99.06 178	98.76 277	96.76 233	99.93 54	98.57 120	99.77 159	99.50 163

NR-MVSNet		98.95 94	98.82 113	99.36 74	99.16 245	98.72 97	99.22 45	99.20 259	99.10 105	99.72 48	98.76 277	96.38 253	99.86 143	98.00 162	99.82 125	99.50 163

MVS_111021_LR		98.30 216	98.12 231	98.83 178	99.16 245	98.03 157	96.09 395	99.30 227	97.58 253	98.10 319	98.24 351	98.25 101	99.34 432	96.69 277	99.65 229	99.12 312

DSMNet-mixed		97.42 301	97.60 281	96.87 391	99.15 249	91.46 429	98.54 126	99.12 281	92.87 434	97.58 358	99.63 39	96.21 260	99.90 81	95.74 341	99.54 270	99.27 270

D2MVS		97.84 271	97.84 262	97.83 319	99.14 250	94.74 350	96.94 341	98.88 323	95.84 370	98.89 223	98.96 224	94.40 322	99.69 310	97.55 200	99.95 38	99.05 318

pmmvs5		97.64 283	97.49 287	98.08 303	99.14 250	95.12 338	96.70 356	99.05 293	93.77 421	98.62 266	98.83 258	93.23 342	99.75 275	98.33 138	99.76 174	99.36 240

SPE-MVS-test		99.13 67	99.09 77	99.26 101	99.13 252	98.97 74	99.31 30	99.88 14	99.44 53	98.16 312	98.51 322	98.64 57	99.93 54	98.91 94	99.85 107	98.88 353

VDD-MVS		98.56 172	98.39 188	99.07 135	99.13 252	98.07 152	98.59 120	97.01 416	99.59 37	99.11 171	99.27 126	94.82 310	99.79 244	98.34 136	99.63 238	99.34 247

save fliter					99.11 254	97.97 163	96.53 366	99.02 301	98.24 189

APD-MVS		98.10 240	97.67 273	99.42 68	99.11 254	98.93 80	97.76 248	99.28 239	94.97 395	98.72 253	98.77 271	97.04 210	99.85 156	93.79 397	99.54 270	99.49 170
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 145	98.71 129	98.62 226	99.10 256	96.37 285	97.23 322	98.87 325	99.20 83	99.19 163	98.99 214	97.30 194	99.85 156	98.77 106	99.79 148	99.65 83

EI-MVSNet		98.40 198	98.51 164	98.04 308	99.10 256	94.73 351	97.20 327	98.87 325	98.97 124	99.06 178	99.02 197	96.00 270	99.80 231	98.58 118	99.82 125	99.60 100

CVMVSNet		96.25 363	97.21 304	93.38 458	99.10 256	80.56 486	97.20 327	98.19 383	96.94 316	99.00 193	99.02 197	89.50 391	99.80 231	96.36 310	99.59 252	99.78 47

EI-MVSNet-Vis-set		98.68 151	98.70 132	98.63 224	99.09 259	96.40 284	97.23 322	98.86 330	99.20 83	99.18 167	98.97 221	97.29 196	99.85 156	98.72 110	99.78 153	99.64 84

HPM-MVS++		98.10 240	97.64 278	99.48 57	99.09 259	99.13 61	97.52 286	98.75 350	97.46 271	96.90 398	97.83 382	96.01 269	99.84 174	95.82 339	99.35 313	99.46 191

DP-MVS Recon		97.33 309	96.92 321	98.57 237	99.09 259	97.99 159	96.79 349	99.35 200	93.18 428	97.71 349	98.07 366	95.00 305	99.31 436	93.97 390	99.13 351	98.42 407

MVS_111021_HR		98.25 225	98.08 236	98.75 201	99.09 259	97.46 210	95.97 399	99.27 242	97.60 252	97.99 330	98.25 350	98.15 117	99.38 427	96.87 259	99.57 261	99.42 209

BP-MVS1		97.40 303	96.97 317	98.71 210	99.07 263	96.81 261	98.34 158	97.18 411	98.58 162	98.17 309	98.61 310	84.01 430	99.94 42	98.97 90	99.78 153	99.37 233

9.14			97.78 264		99.07 263		97.53 285	99.32 214	95.53 380	98.54 282	98.70 290	97.58 169	99.76 267	94.32 382	99.46 293

PAPM_NR		96.82 343	96.32 354	98.30 280	99.07 263	96.69 269	97.48 292	98.76 347	95.81 371	96.61 411	96.47 428	94.12 331	99.17 449	90.82 450	97.78 429	99.06 317

TAMVS		98.24 226	98.05 239	98.80 185	99.07 263	97.18 236	97.88 228	98.81 339	96.66 334	99.17 169	99.21 146	94.81 312	99.77 261	96.96 249	99.88 94	99.44 200

CLD-MVS		97.49 294	97.16 306	98.48 258	99.07 263	97.03 247	94.71 445	99.21 257	94.46 406	98.06 323	97.16 414	97.57 170	99.48 408	94.46 374	99.78 153	98.95 339
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 75	99.24 106	99.06 268	99.15 53	99.36 22	99.88 14	99.36 64	98.21 308	98.46 331	98.68 54	99.93 54	99.03 86	99.85 107	98.64 386

thres100view900		94.19 406	93.67 411	95.75 425	99.06 268	91.35 433	98.03 199	94.24 459	98.33 179	97.40 374	94.98 458	79.84 446	99.62 354	83.05 471	98.08 420	96.29 466

thres600view7		94.45 401	93.83 408	96.29 409	99.06 268	91.53 428	97.99 213	94.24 459	98.34 178	97.44 372	95.01 456	79.84 446	99.67 324	84.33 469	98.23 409	97.66 447

plane_prior1					99.05 271

YYNet1		97.60 285	97.67 273	97.39 367	99.04 272	93.04 406	95.27 430	98.38 375	97.25 292	98.92 218	98.95 228	95.48 294	99.73 288	96.99 245	98.74 384	99.41 212

MDA-MVSNet_test_wron		97.60 285	97.66 276	97.41 366	99.04 272	93.09 402	95.27 430	98.42 372	97.26 291	98.88 227	98.95 228	95.43 295	99.73 288	97.02 241	98.72 386	99.41 212

MIMVSNet		96.62 350	96.25 358	97.71 334	99.04 272	94.66 354	99.16 54	96.92 422	97.23 298	97.87 338	99.10 177	86.11 413	99.65 344	91.65 434	99.21 339	98.82 358

FE-MVSNET3		97.37 305	97.13 310	98.11 299	99.03 275	95.40 326	94.47 455	98.99 307	96.87 322	97.97 331	97.81 383	92.12 364	99.75 275	97.49 211	99.43 303	99.16 307

icg_test_0407_2		98.20 231	98.38 190	97.65 340	99.03 275	94.03 374	95.78 413	99.45 155	98.16 203	99.06 178	98.71 283	98.27 97	99.68 320	97.50 206	99.45 295	99.22 287

IMVS_0407		98.39 204	98.64 143	97.66 338	99.03 275	94.03 374	98.10 185	99.45 155	98.16 203	99.06 178	98.71 283	98.27 97	99.71 298	97.50 206	99.45 295	99.22 287

IMVS_0404		98.07 244	98.20 218	97.69 335	99.03 275	94.03 374	96.67 357	99.45 155	98.16 203	98.03 327	98.71 283	96.80 229	99.82 205	97.50 206	99.45 295	99.22 287

IMVS_0403		98.34 208	98.56 157	97.66 338	99.03 275	94.03 374	97.98 214	99.45 155	98.16 203	98.89 223	98.71 283	97.90 136	99.74 281	97.50 206	99.45 295	99.22 287

PatchMatch-RL		97.24 317	96.78 332	98.61 230	99.03 275	97.83 178	96.36 377	99.06 289	93.49 426	97.36 378	97.78 384	95.75 284	99.49 405	93.44 406	98.77 383	98.52 395

viewmambaseed2359dif		98.19 232	98.26 211	97.99 311	99.02 281	95.03 341	96.59 363	99.53 119	96.21 354	99.00 193	98.99 214	97.62 165	99.61 361	97.62 195	99.72 190	99.33 253

GDP-MVS		97.50 291	97.11 311	98.67 216	99.02 281	96.85 259	98.16 175	99.71 47	98.32 181	98.52 285	98.54 317	83.39 434	99.95 26	98.79 102	99.56 264	99.19 297

ZD-MVS					99.01 283	98.84 86		99.07 288	94.10 416	98.05 325	98.12 360	96.36 255	99.86 143	92.70 422	99.19 343

CDPH-MVS		97.26 314	96.66 341	99.07 135	99.00 284	98.15 139	96.03 397	99.01 304	91.21 452	97.79 345	97.85 381	96.89 221	99.69 310	92.75 420	99.38 310	99.39 222

diffmvs		98.22 227	98.24 215	98.17 295	99.00 284	95.44 324	96.38 376	99.58 90	97.79 236	98.53 283	98.50 326	96.76 233	99.74 281	97.95 168	99.64 231	99.34 247
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		98.40 198	98.19 222	99.03 145	99.00 284	97.65 197	96.85 347	98.94 310	98.57 164	98.89 223	98.50 326	95.60 288	99.85 156	97.54 202	99.85 107	99.59 107

plane_prior6					98.99 287	97.70 195						94.90 306

xiu_mvs_v1_base_debu		97.86 265	98.17 224	96.92 388	98.98 288	93.91 384	96.45 370	99.17 271	97.85 231	98.41 294	97.14 416	98.47 73	99.92 65	98.02 159	99.05 357	96.92 459

xiu_mvs_v1_base		97.86 265	98.17 224	96.92 388	98.98 288	93.91 384	96.45 370	99.17 271	97.85 231	98.41 294	97.14 416	98.47 73	99.92 65	98.02 159	99.05 357	96.92 459

xiu_mvs_v1_base_debi		97.86 265	98.17 224	96.92 388	98.98 288	93.91 384	96.45 370	99.17 271	97.85 231	98.41 294	97.14 416	98.47 73	99.92 65	98.02 159	99.05 357	96.92 459

MVP-Stereo		98.08 243	97.92 255	98.57 237	98.96 291	96.79 262	97.90 226	99.18 267	96.41 346	98.46 289	98.95 228	95.93 279	99.60 364	96.51 300	98.98 371	99.31 260
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 198	98.68 135	97.54 355	98.96 291	97.99 159	97.88 228	99.36 194	98.20 197	99.63 67	99.04 194	98.76 45	95.33 482	96.56 294	99.74 179	99.31 260
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	98.94 293	97.76 189		98.76 347	87.58 469	96.75 406	98.10 362	94.80 313	99.78 255	92.73 421	99.00 366	99.20 292

USDC		97.41 302	97.40 291	97.44 364	98.94 293	93.67 394	95.17 434	99.53 119	94.03 418	98.97 202	99.10 177	95.29 297	99.34 432	95.84 338	99.73 182	99.30 264

tfpn200view9		94.03 410	93.44 413	95.78 424	98.93 295	91.44 431	97.60 276	94.29 457	97.94 223	97.10 384	94.31 465	79.67 448	99.62 354	83.05 471	98.08 420	96.29 466

testdata				98.09 300	98.93 295	95.40 326		98.80 341	90.08 460	97.45 371	98.37 340	95.26 298	99.70 305	93.58 402	98.95 374	99.17 304

thres400		94.14 408	93.44 413	96.24 412	98.93 295	91.44 431	97.60 276	94.29 457	97.94 223	97.10 384	94.31 465	79.67 448	99.62 354	83.05 471	98.08 420	97.66 447

TAPA-MVS	96.21 11	96.63 349	95.95 360	98.65 218	98.93 295	98.09 146	96.93 343	99.28 239	83.58 475	98.13 316	97.78 384	96.13 263	99.40 423	93.52 403	99.29 325	98.45 400
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 299	96.93 255	95.54 420	98.78 344	85.72 472	96.86 401	98.11 361	94.43 320			99.10 356	99.23 282

PVSNet_BlendedMVS		97.55 290	97.53 284	97.60 347	98.92 299	93.77 391	96.64 359	99.43 169	94.49 404	97.62 354	99.18 155	96.82 226	99.67 324	94.73 366	99.93 56	99.36 240

PVSNet_Blended		96.88 339	96.68 338	97.47 362	98.92 299	93.77 391	94.71 445	99.43 169	90.98 454	97.62 354	97.36 410	96.82 226	99.67 324	94.73 366	99.56 264	98.98 332

MSDG		97.71 278	97.52 285	98.28 282	98.91 302	96.82 260	94.42 456	99.37 190	97.65 245	98.37 299	98.29 349	97.40 188	99.33 434	94.09 388	99.22 336	98.68 384

Anonymous202405211		97.90 258	97.50 286	99.08 133	98.90 303	98.25 129	98.53 127	96.16 434	98.87 136	99.11 171	98.86 248	90.40 383	99.78 255	97.36 216	99.31 320	99.19 297

原ACMM1				98.35 275	98.90 303	96.25 289		98.83 338	92.48 438	96.07 428	98.10 362	95.39 296	99.71 298	92.61 424	98.99 368	99.08 314

GBi-Net		98.65 156	98.47 175	99.17 115	98.90 303	98.24 130	99.20 48	99.44 163	98.59 159	98.95 208	99.55 57	94.14 328	99.86 143	97.77 182	99.69 209	99.41 212

test1		98.65 156	98.47 175	99.17 115	98.90 303	98.24 130	99.20 48	99.44 163	98.59 159	98.95 208	99.55 57	94.14 328	99.86 143	97.77 182	99.69 209	99.41 212

FMVSNet2		98.49 188	98.40 185	98.75 201	98.90 303	97.14 241	98.61 118	99.13 280	98.59 159	99.19 163	99.28 124	94.14 328	99.82 205	97.97 166	99.80 142	99.29 266

OMC-MVS		97.88 262	97.49 287	99.04 144	98.89 308	98.63 99	96.94 341	99.25 248	95.02 393	98.53 283	98.51 322	97.27 197	99.47 411	93.50 405	99.51 280	99.01 326

VortexMVS		97.98 255	98.31 203	97.02 382	98.88 309	91.45 430	98.03 199	99.47 147	98.65 150	99.55 77	99.47 79	91.49 372	99.81 222	99.32 61	99.91 78	99.80 42

MVSFormer		98.26 222	98.43 181	97.77 324	98.88 309	93.89 387	99.39 20	99.56 106	99.11 98	98.16 312	98.13 358	93.81 336	99.97 7	99.26 66	99.57 261	99.43 204

lupinMVS		97.06 329	96.86 325	97.65 340	98.88 309	93.89 387	95.48 424	97.97 389	93.53 424	98.16 312	97.58 396	93.81 336	99.91 74	96.77 267	99.57 261	99.17 304

dmvs_re		95.98 371	95.39 381	97.74 330	98.86 312	97.45 211	98.37 154	95.69 446	97.95 221	96.56 412	95.95 437	90.70 380	97.68 476	88.32 459	96.13 462	98.11 422

DELS-MVS		98.27 220	98.20 218	98.48 258	98.86 312	96.70 268	95.60 419	99.20 259	97.73 239	98.45 290	98.71 283	97.50 180	99.82 205	98.21 144	99.59 252	98.93 344
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		97.89 260	97.98 246	97.60 347	98.86 312	94.35 362	96.21 386	99.44 163	97.45 273	99.06 178	98.88 245	97.99 130	99.28 442	94.38 381	99.58 257	99.18 300

LCM-MVSNet-Re		98.64 158	98.48 173	99.11 126	98.85 315	98.51 112	98.49 138	99.83 25	98.37 175	99.69 56	99.46 81	98.21 108	99.92 65	94.13 387	99.30 323	98.91 348

pmmvs4		97.58 288	97.28 299	98.51 253	98.84 316	96.93 255	95.40 428	98.52 367	93.60 423	98.61 268	98.65 301	95.10 302	99.60 364	96.97 248	99.79 148	98.99 331

NP-MVS					98.84 316	97.39 215					96.84 419

sss		97.21 319	96.93 319	98.06 305	98.83 318	95.22 334	96.75 353	98.48 369	94.49 404	97.27 380	97.90 378	92.77 354	99.80 231	96.57 290	99.32 318	99.16 307

PVSNet	93.40 17	95.67 380	95.70 366	95.57 429	98.83 318	88.57 456	92.50 473	97.72 394	92.69 436	96.49 420	96.44 429	93.72 339	99.43 419	93.61 400	99.28 326	98.71 377

MVE	83.40 22	92.50 433	91.92 435	94.25 445	98.83 318	91.64 427	92.71 472	83.52 485	95.92 368	86.46 483	95.46 450	95.20 299	95.40 481	80.51 476	98.64 395	95.73 474
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 414	93.91 406	93.39 457	98.82 321	81.72 484	97.76 248	95.28 448	98.60 158	96.54 413	96.66 423	65.85 478	99.62 354	96.65 283	98.99 368	98.82 358

ambc				98.24 287	98.82 321	95.97 300	98.62 116	99.00 306		99.27 144	99.21 146	96.99 215	99.50 402	96.55 297	99.50 288	99.26 276

旧先验1					98.82 321	97.45 211		98.76 347			98.34 344	95.50 293			99.01 365	99.23 282

test_vis1_rt		97.75 275	97.72 270	97.83 319	98.81 324	96.35 286	97.30 316	99.69 54	94.61 402	97.87 338	98.05 367	96.26 259	98.32 470	98.74 108	98.18 412	98.82 358

WTY-MVS		96.67 347	96.27 357	97.87 317	98.81 324	94.61 356	96.77 351	97.92 391	94.94 396	97.12 383	97.74 387	91.11 376	99.82 205	93.89 393	98.15 416	99.18 300

3Dnovator+	97.89 3	98.69 145	98.51 164	99.24 106	98.81 324	98.40 117	99.02 69	99.19 263	98.99 121	98.07 322	99.28 124	97.11 208	99.84 174	96.84 262	99.32 318	99.47 189

QAPM		97.31 310	96.81 331	98.82 180	98.80 327	97.49 205	99.06 65	99.19 263	90.22 458	97.69 351	99.16 161	96.91 220	99.90 81	90.89 449	99.41 305	99.07 316

VNet		98.42 194	98.30 204	98.79 189	98.79 328	97.29 223	98.23 166	98.66 357	99.31 69	98.85 232	98.80 265	94.80 313	99.78 255	98.13 149	99.13 351	99.31 260

DPM-MVS		96.32 359	95.59 372	98.51 253	98.76 329	97.21 232	94.54 454	98.26 378	91.94 443	96.37 421	97.25 412	93.06 348	99.43 419	91.42 439	98.74 384	98.89 350

3Dnovator	98.27 2	98.81 121	98.73 122	99.05 142	98.76 329	97.81 186	99.25 43	99.30 227	98.57 164	98.55 280	99.33 113	97.95 133	99.90 81	97.16 229	99.67 220	99.44 200

PLC	94.65 16	96.51 352	95.73 365	98.85 175	98.75 331	97.91 171	96.42 374	99.06 289	90.94 455	95.59 435	97.38 408	94.41 321	99.59 368	90.93 447	98.04 425	99.05 318
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 341	96.75 334	97.08 379	98.74 332	93.33 400	96.71 355	98.26 378	96.72 331	98.44 291	97.37 409	95.20 299	99.47 411	91.89 429	97.43 439	98.44 403

hse-mvs2		97.46 296	97.07 312	98.64 220	98.73 333	97.33 218	97.45 298	97.64 401	99.11 98	98.58 274	97.98 372	88.65 398	99.79 244	98.11 150	97.39 441	98.81 363

CDS-MVSNet		97.69 279	97.35 296	98.69 213	98.73 333	97.02 248	96.92 345	98.75 350	95.89 369	98.59 272	98.67 296	92.08 366	99.74 281	96.72 273	99.81 131	99.32 256
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SD_0403		96.28 361	95.83 362	97.64 343	98.72 335	94.30 363	98.87 88	98.77 345	97.80 234	96.53 414	98.02 369	97.34 192	99.47 411	76.93 480	99.48 291	99.16 307

EIA-MVS		98.00 251	97.74 267	98.80 185	98.72 335	98.09 146	98.05 195	99.60 81	97.39 278	96.63 409	95.55 445	97.68 157	99.80 231	96.73 272	99.27 327	98.52 395

LFMVS		97.20 320	96.72 335	98.64 220	98.72 335	96.95 253	98.93 81	94.14 461	99.74 13	98.78 244	99.01 208	84.45 425	99.73 288	97.44 212	99.27 327	99.25 277

new_pmnet		96.99 336	96.76 333	97.67 336	98.72 335	94.89 345	95.95 403	98.20 381	92.62 437	98.55 280	98.54 317	94.88 309	99.52 396	93.96 391	99.44 302	98.59 392

Fast-Effi-MVS+		97.67 281	97.38 293	98.57 237	98.71 339	97.43 213	97.23 322	99.45 155	94.82 399	96.13 425	96.51 425	98.52 71	99.91 74	96.19 319	98.83 380	98.37 412

TEST9					98.71 339	98.08 150	95.96 401	99.03 298	91.40 449	95.85 432	97.53 398	96.52 246	99.76 267

train_agg		97.10 326	96.45 351	99.07 135	98.71 339	98.08 150	95.96 401	99.03 298	91.64 444	95.85 432	97.53 398	96.47 248	99.76 267	93.67 399	99.16 346	99.36 240

TSAR-MVS + GP.		98.18 234	97.98 246	98.77 197	98.71 339	97.88 173	96.32 380	98.66 357	96.33 348	99.23 157	98.51 322	97.48 184	99.40 423	97.16 229	99.46 293	99.02 325

FA-MVS(test-final)		96.99 336	96.82 329	97.50 359	98.70 343	94.78 348	99.34 23	96.99 417	95.07 392	98.48 288	99.33 113	88.41 401	99.65 344	96.13 325	98.92 377	98.07 425

AUN-MVS		96.24 365	95.45 377	98.60 232	98.70 343	97.22 230	97.38 305	97.65 399	95.95 367	95.53 442	97.96 376	82.11 442	99.79 244	96.31 312	97.44 438	98.80 368

our_test_3		97.39 304	97.73 269	96.34 407	98.70 343	89.78 452	94.61 451	98.97 309	96.50 339	99.04 188	98.85 251	95.98 275	99.84 174	97.26 223	99.67 220	99.41 212

ppachtmachnet_test		97.50 291	97.74 267	96.78 397	98.70 343	91.23 439	94.55 453	99.05 293	96.36 347	99.21 161	98.79 267	96.39 251	99.78 255	96.74 270	99.82 125	99.34 247

PCF-MVS	92.86 18	94.36 402	93.00 420	98.42 265	98.70 343	97.56 202	93.16 471	99.11 283	79.59 479	97.55 361	97.43 405	92.19 362	99.73 288	79.85 477	99.45 295	97.97 431
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 257	98.02 242	97.58 349	98.69 348	94.10 370	98.13 178	98.90 319	97.95 221	97.32 379	99.58 47	95.95 278	98.75 465	96.41 306	99.22 336	99.87 22

ETV-MVS		98.03 247	97.86 261	98.56 242	98.69 348	98.07 152	97.51 288	99.50 128	98.10 211	97.50 366	95.51 446	98.41 80	99.88 115	96.27 315	99.24 332	97.71 446

test_prior				98.95 160	98.69 348	97.95 167		99.03 298					99.59 368			99.30 264

mvsmamba		97.57 289	97.26 300	98.51 253	98.69 348	96.73 267	98.74 97	97.25 410	97.03 312	97.88 337	99.23 144	90.95 377	99.87 134	96.61 286	99.00 366	98.91 348

agg_prior					98.68 352	97.99 159		99.01 304		95.59 435			99.77 261

test_8					98.67 353	98.01 158	95.91 407	99.02 301	91.64 444	95.79 434	97.50 401	96.47 248	99.76 267

HQP-NCC					98.67 353		96.29 382		96.05 360	95.55 438

ACMP_Plane					98.67 353		96.29 382		96.05 360	95.55 438

CNVR-MVS		98.17 236	97.87 260	99.07 135	98.67 353	98.24 130	97.01 337	98.93 313	97.25 292	97.62 354	98.34 344	97.27 197	99.57 377	96.42 305	99.33 316	99.39 222

HQP-MVS		97.00 335	96.49 350	98.55 244	98.67 353	96.79 262	96.29 382	99.04 296	96.05 360	95.55 438	96.84 419	93.84 334	99.54 390	92.82 417	99.26 330	99.32 256

MM		98.22 227	97.99 245	98.91 168	98.66 358	96.97 250	97.89 227	94.44 455	99.54 41	98.95 208	99.14 168	93.50 340	99.92 65	99.80 17	99.96 28	99.85 30

test_fmvs1		97.72 277	97.94 252	97.07 381	98.66 358	92.39 417	97.68 259	99.81 31	95.20 391	99.54 79	99.44 86	91.56 371	99.41 422	99.78 21	99.77 159	99.40 221

balanced_conf03		98.63 160	98.72 124	98.38 270	98.66 358	96.68 270	98.90 83	99.42 175	98.99 121	98.97 202	99.19 151	95.81 283	99.85 156	98.77 106	99.77 159	98.60 389

thres200		93.72 416	93.14 418	95.46 433	98.66 358	91.29 435	96.61 361	94.63 454	97.39 278	96.83 402	93.71 468	79.88 445	99.56 380	82.40 474	98.13 417	95.54 475

wuyk23d		96.06 367	97.62 280	91.38 462	98.65 362	98.57 106	98.85 92	96.95 420	96.86 324	99.90 14	99.16 161	99.18 19	98.40 469	89.23 457	99.77 159	77.18 482

NCCC		97.86 265	97.47 290	99.05 142	98.61 363	98.07 152	96.98 339	98.90 319	97.63 246	97.04 388	97.93 377	95.99 274	99.66 337	95.31 354	98.82 382	99.43 204

DeepC-MVS_fast	96.85 6	98.30 216	98.15 228	98.75 201	98.61 363	97.23 227	97.76 248	99.09 286	97.31 286	98.75 250	98.66 299	97.56 171	99.64 348	96.10 326	99.55 268	99.39 222
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 418	92.09 429	97.75 328	98.60 365	94.40 360	97.32 313	95.26 449	97.56 256	96.79 405	95.50 447	53.57 487	99.77 261	95.26 355	98.97 372	99.08 314

thisisatest0515		94.12 409	93.16 417	96.97 386	98.60 365	92.90 407	93.77 467	90.61 474	94.10 416	96.91 395	95.87 440	74.99 460	99.80 231	94.52 372	99.12 354	98.20 418

GA-MVS		95.86 374	95.32 384	97.49 360	98.60 365	94.15 369	93.83 466	97.93 390	95.49 381	96.68 407	97.42 406	83.21 435	99.30 438	96.22 317	98.55 401	99.01 326

dmvs_testset		92.94 428	92.21 428	95.13 437	98.59 368	90.99 442	97.65 265	92.09 470	96.95 315	94.00 462	93.55 469	92.34 360	96.97 479	72.20 481	92.52 476	97.43 454

OPU-MVS				98.82 180	98.59 368	98.30 126	98.10 185				98.52 321	98.18 111	98.75 465	94.62 369	99.48 291	99.41 212

MSLP-MVS++		98.02 248	98.14 230	97.64 343	98.58 370	95.19 335	97.48 292	99.23 255	97.47 266	97.90 335	98.62 308	97.04 210	98.81 463	97.55 200	99.41 305	98.94 343

test12				98.93 164	98.58 370	97.83 178		98.66 357		96.53 414		95.51 292	99.69 310		99.13 351	99.27 270

CL-MVSNet_self_test		97.44 299	97.22 303	98.08 303	98.57 372	95.78 308	94.30 459	98.79 342	96.58 337	98.60 270	98.19 356	94.74 316	99.64 348	96.41 306	98.84 379	98.82 358

PS-MVSNAJ		97.08 328	97.39 292	96.16 418	98.56 373	92.46 415	95.24 432	98.85 333	97.25 292	97.49 367	95.99 436	98.07 121	99.90 81	96.37 308	98.67 394	96.12 471

CNLPA		97.17 323	96.71 336	98.55 244	98.56 373	98.05 156	96.33 379	98.93 313	96.91 320	97.06 387	97.39 407	94.38 323	99.45 416	91.66 433	99.18 345	98.14 421

xiu_mvs_v2_base		97.16 324	97.49 287	96.17 416	98.54 375	92.46 415	95.45 425	98.84 334	97.25 292	97.48 368	96.49 426	98.31 91	99.90 81	96.34 311	98.68 393	96.15 470

alignmvs		97.35 307	96.88 324	98.78 192	98.54 375	98.09 146	97.71 255	97.69 396	99.20 83	97.59 357	95.90 439	88.12 403	99.55 384	98.18 146	98.96 373	98.70 380

FE-MVS		95.66 381	94.95 394	97.77 324	98.53 377	95.28 331	99.40 19	96.09 437	93.11 430	97.96 332	99.26 132	79.10 452	99.77 261	92.40 426	98.71 388	98.27 416

Effi-MVS+		98.02 248	97.82 263	98.62 226	98.53 377	97.19 234	97.33 312	99.68 60	97.30 287	96.68 407	97.46 404	98.56 69	99.80 231	96.63 284	98.20 411	98.86 355

baseline1		95.96 372	95.44 378	97.52 357	98.51 379	93.99 381	98.39 152	96.09 437	98.21 193	98.40 298	97.76 386	86.88 405	99.63 351	95.42 352	89.27 479	98.95 339

MVS_Test		98.18 234	98.36 193	97.67 336	98.48 380	94.73 351	98.18 171	99.02 301	97.69 242	98.04 326	99.11 174	97.22 201	99.56 380	98.57 120	98.90 378	98.71 377

MGCFI-Net		98.34 208	98.28 207	98.51 253	98.47 381	97.59 201	98.96 77	99.48 138	99.18 91	97.40 374	95.50 447	98.66 55	99.50 402	98.18 146	98.71 388	98.44 403

BH-RMVSNet		96.83 341	96.58 346	97.58 349	98.47 381	94.05 371	96.67 357	97.36 405	96.70 333	97.87 338	97.98 372	95.14 301	99.44 418	90.47 452	98.58 400	99.25 277

sasdasda		98.34 208	98.26 211	98.58 234	98.46 383	97.82 183	98.96 77	99.46 151	99.19 88	97.46 369	95.46 450	98.59 63	99.46 414	98.08 153	98.71 388	98.46 397

canonicalmvs		98.34 208	98.26 211	98.58 234	98.46 383	97.82 183	98.96 77	99.46 151	99.19 88	97.46 369	95.46 450	98.59 63	99.46 414	98.08 153	98.71 388	98.46 397

MVS-HIRNet		94.32 403	95.62 369	90.42 463	98.46 383	75.36 487	96.29 382	89.13 478	95.25 388	95.38 444	99.75 16	92.88 351	99.19 448	94.07 389	99.39 307	96.72 464

PHI-MVS		98.29 219	97.95 250	99.34 83	98.44 386	99.16 49	98.12 182	99.38 186	96.01 364	98.06 323	98.43 334	97.80 150	99.67 324	95.69 344	99.58 257	99.20 292

DVP-MVS++		98.90 101	98.70 132	99.51 49	98.43 387	99.15 53	99.43 15	99.32 214	98.17 200	99.26 148	99.02 197	98.18 111	99.88 115	97.07 238	99.45 295	99.49 170

MSC_two_6792asdad				99.32 91	98.43 387	98.37 121		98.86 330					99.89 97	97.14 232	99.60 248	99.71 63

No_MVS				99.32 91	98.43 387	98.37 121		98.86 330					99.89 97	97.14 232	99.60 248	99.71 63

Fast-Effi-MVS+-dtu		98.27 220	98.09 233	98.81 182	98.43 387	98.11 143	97.61 275	99.50 128	98.64 151	97.39 376	97.52 400	98.12 119	99.95 26	96.90 256	98.71 388	98.38 410

OpenMVS_ROB	95.38 14	95.84 376	95.18 389	97.81 321	98.41 391	97.15 240	97.37 309	98.62 361	83.86 474	98.65 261	98.37 340	94.29 326	99.68 320	88.41 458	98.62 398	96.60 465

DeepPCF-MVS	96.93 5	98.32 213	98.01 243	99.23 108	98.39 392	98.97 74	95.03 438	99.18 267	96.88 321	99.33 130	98.78 269	98.16 115	99.28 442	96.74 270	99.62 241	99.44 200

Patchmatch-test		96.55 351	96.34 353	97.17 376	98.35 393	93.06 403	98.40 151	97.79 392	97.33 283	98.41 294	98.67 296	83.68 433	99.69 310	95.16 357	99.31 320	98.77 371

AdaColmap		97.14 325	96.71 336	98.46 260	98.34 394	97.80 187	96.95 340	98.93 313	95.58 378	96.92 393	97.66 391	95.87 281	99.53 392	90.97 446	99.14 349	98.04 426

OpenMVS	96.65 7	97.09 327	96.68 338	98.32 277	98.32 395	97.16 239	98.86 91	99.37 190	89.48 462	96.29 423	99.15 165	96.56 244	99.90 81	92.90 414	99.20 340	97.89 434

MG-MVS		96.77 344	96.61 343	97.26 372	98.31 396	93.06 403	95.93 404	98.12 386	96.45 345	97.92 333	98.73 280	93.77 338	99.39 425	91.19 444	99.04 360	99.33 253

test_yl		96.69 345	96.29 355	97.90 313	98.28 397	95.24 332	97.29 317	97.36 405	98.21 193	98.17 309	97.86 379	86.27 409	99.55 384	94.87 363	98.32 405	98.89 350

DCV-MVSNet		96.69 345	96.29 355	97.90 313	98.28 397	95.24 332	97.29 317	97.36 405	98.21 193	98.17 309	97.86 379	86.27 409	99.55 384	94.87 363	98.32 405	98.89 350

CHOSEN 280x420		95.51 386	95.47 375	95.65 428	98.25 399	88.27 459	93.25 470	98.88 323	93.53 424	94.65 453	97.15 415	86.17 411	99.93 54	97.41 214	99.93 56	98.73 376

SCA		96.41 358	96.66 341	95.67 426	98.24 400	88.35 458	95.85 410	96.88 423	96.11 358	97.67 352	98.67 296	93.10 346	99.85 156	94.16 383	99.22 336	98.81 363

DeepMVS_CX				93.44 456	98.24 400	94.21 366		94.34 456	64.28 482	91.34 476	94.87 462	89.45 392	92.77 483	77.54 479	93.14 475	93.35 478

MS-PatchMatch		97.68 280	97.75 266	97.45 363	98.23 402	93.78 390	97.29 317	98.84 334	96.10 359	98.64 262	98.65 301	96.04 267	99.36 428	96.84 262	99.14 349	99.20 292

BH-w/o		95.13 392	94.89 396	95.86 421	98.20 403	91.31 434	95.65 417	97.37 404	93.64 422	96.52 416	95.70 443	93.04 349	99.02 454	88.10 460	95.82 465	97.24 457

mvs_anonymous		97.83 273	98.16 227	96.87 391	98.18 404	91.89 424	97.31 315	98.90 319	97.37 280	98.83 235	99.46 81	96.28 258	99.79 244	98.90 95	98.16 415	98.95 339

miper_lstm_enhance		97.18 322	97.16 306	97.25 373	98.16 405	92.85 408	95.15 436	99.31 219	97.25 292	98.74 252	98.78 269	90.07 384	99.78 255	97.19 227	99.80 142	99.11 313

RRT-MVS		97.88 262	97.98 246	97.61 346	98.15 406	93.77 391	98.97 76	99.64 71	99.16 93	98.69 255	99.42 90	91.60 369	99.89 97	97.63 194	98.52 402	99.16 307

ET-MVSNet_ETH3D		94.30 405	93.21 416	97.58 349	98.14 407	94.47 359	94.78 444	93.24 466	94.72 400	89.56 478	95.87 440	78.57 455	99.81 222	96.91 251	97.11 450	98.46 397

ADS-MVSNet2		95.43 387	94.98 392	96.76 398	98.14 407	91.74 425	97.92 223	97.76 393	90.23 456	96.51 417	98.91 235	85.61 416	99.85 156	92.88 415	96.90 451	98.69 381

ADS-MVSNet		95.24 390	94.93 395	96.18 415	98.14 407	90.10 451	97.92 223	97.32 408	90.23 456	96.51 417	98.91 235	85.61 416	99.74 281	92.88 415	96.90 451	98.69 381

c3_l		97.36 306	97.37 294	97.31 368	98.09 410	93.25 401	95.01 439	99.16 274	97.05 309	98.77 247	98.72 282	92.88 351	99.64 348	96.93 250	99.76 174	99.05 318

FMVSNet3		97.50 291	97.24 302	98.29 281	98.08 411	95.83 305	97.86 232	98.91 318	97.89 228	98.95 208	98.95 228	87.06 404	99.81 222	97.77 182	99.69 209	99.23 282

PAPM		91.88 443	90.34 445	96.51 402	98.06 412	92.56 413	92.44 474	97.17 412	86.35 470	90.38 477	96.01 435	86.61 407	99.21 447	70.65 483	95.43 467	97.75 443

Effi-MVS+-dtu		98.26 222	97.90 258	99.35 80	98.02 413	99.49 6	98.02 202	99.16 274	98.29 186	97.64 353	97.99 371	96.44 250	99.95 26	96.66 282	98.93 376	98.60 389

eth_miper_zixun_eth		97.23 318	97.25 301	97.17 376	98.00 414	92.77 410	94.71 445	99.18 267	97.27 290	98.56 278	98.74 279	91.89 367	99.69 310	97.06 240	99.81 131	99.05 318

HY-MVS	95.94 13	95.90 373	95.35 383	97.55 354	97.95 415	94.79 347	98.81 96	96.94 421	92.28 441	95.17 446	98.57 315	89.90 386	99.75 275	91.20 443	97.33 446	98.10 423

UGNet		98.53 181	98.45 178	98.79 189	97.94 416	96.96 252	99.08 61	98.54 365	99.10 105	96.82 403	99.47 79	96.55 245	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		96.47 356	95.70 366	98.79 189	97.92 417	99.12 63	98.28 160	98.60 362	92.16 442	95.54 441	96.17 433	94.77 315	99.52 396	89.62 455	98.23 409	97.72 445
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		96.86 340	96.55 347	97.79 322	97.91 418	94.21 366	97.56 281	98.87 325	97.49 265	99.06 178	99.05 192	80.72 443	99.80 231	98.44 129	99.82 125	99.37 233

API-MVS		97.04 331	96.91 323	97.42 365	97.88 419	98.23 134	98.18 171	98.50 368	97.57 254	97.39 376	96.75 421	96.77 231	99.15 451	90.16 453	99.02 364	94.88 476

myMVS_eth3d28		92.92 429	92.31 425	94.77 440	97.84 420	87.59 463	96.19 388	96.11 436	97.08 308	94.27 456	93.49 471	66.07 477	98.78 464	91.78 431	97.93 428	97.92 433

miper_ehance_all_eth		97.06 329	97.03 314	97.16 378	97.83 421	93.06 403	94.66 448	99.09 286	95.99 365	98.69 255	98.45 332	92.73 356	99.61 361	96.79 264	99.03 361	98.82 358

cl____		97.02 332	96.83 328	97.58 349	97.82 422	94.04 373	94.66 448	99.16 274	97.04 310	98.63 263	98.71 283	88.68 397	99.69 310	97.00 243	99.81 131	99.00 330

DIV-MVS_self_test		97.02 332	96.84 327	97.58 349	97.82 422	94.03 374	94.66 448	99.16 274	97.04 310	98.63 263	98.71 283	88.69 395	99.69 310	97.00 243	99.81 131	99.01 326

CANet		97.87 264	97.76 265	98.19 294	97.75 424	95.51 316	96.76 352	99.05 293	97.74 238	96.93 392	98.21 354	95.59 289	99.89 97	97.86 177	99.93 56	99.19 297

UBG		93.25 423	92.32 424	96.04 420	97.72 425	90.16 450	95.92 406	95.91 441	96.03 363	93.95 464	93.04 474	69.60 467	99.52 396	90.72 451	97.98 426	98.45 400

mvsany_test1		97.60 285	97.54 283	97.77 324	97.72 425	95.35 328	95.36 429	97.13 414	94.13 415	99.71 50	99.33 113	97.93 134	99.30 438	97.60 198	98.94 375	98.67 385

PVSNet_0	89.98 21	91.15 444	90.30 446	93.70 453	97.72 425	84.34 477	90.24 477	97.42 403	90.20 459	93.79 465	93.09 473	90.90 379	98.89 462	86.57 466	72.76 483	97.87 436

CR-MVSNet		96.28 361	95.95 360	97.28 370	97.71 428	94.22 364	98.11 183	98.92 316	92.31 440	96.91 395	99.37 101	85.44 419	99.81 222	97.39 215	97.36 444	97.81 439

RPMNet		97.02 332	96.93 319	97.30 369	97.71 428	94.22 364	98.11 183	99.30 227	99.37 61	96.91 395	99.34 110	86.72 406	99.87 134	97.53 203	97.36 444	97.81 439

ETVMVS		92.60 432	91.08 441	97.18 374	97.70 430	93.65 396	96.54 364	95.70 444	96.51 338	94.68 452	92.39 477	61.80 484	99.50 402	86.97 463	97.41 440	98.40 408

pmmvs3		95.03 394	94.40 401	96.93 387	97.70 430	92.53 414	95.08 437	97.71 395	88.57 466	97.71 349	98.08 365	79.39 450	99.82 205	96.19 319	99.11 355	98.43 405

baseline2		93.73 415	92.83 421	96.42 405	97.70 430	91.28 436	96.84 348	89.77 477	93.96 420	92.44 472	95.93 438	79.14 451	99.77 261	92.94 413	96.76 455	98.21 417

WBMVS		95.18 391	94.78 397	96.37 406	97.68 433	89.74 453	95.80 412	98.73 353	97.54 260	98.30 300	98.44 333	70.06 465	99.82 205	96.62 285	99.87 98	99.54 142

tpm		94.67 399	94.34 403	95.66 427	97.68 433	88.42 457	97.88 228	94.90 451	94.46 406	96.03 431	98.56 316	78.66 453	99.79 244	95.88 332	95.01 469	98.78 370

CANet_DTU		97.26 314	97.06 313	97.84 318	97.57 435	94.65 355	96.19 388	98.79 342	97.23 298	95.14 447	98.24 351	93.22 343	99.84 174	97.34 217	99.84 112	99.04 322

testing11		93.08 426	92.02 431	96.26 411	97.56 436	90.83 445	96.32 380	95.70 444	96.47 342	92.66 471	93.73 467	64.36 481	99.59 368	93.77 398	97.57 433	98.37 412

tpm2		93.09 425	92.58 423	94.62 442	97.56 436	86.53 466	97.66 263	95.79 443	86.15 471	94.07 461	98.23 353	75.95 458	99.53 392	90.91 448	96.86 454	97.81 439

testing91		93.32 421	92.27 426	96.47 404	97.54 438	91.25 437	96.17 392	96.76 425	97.18 302	93.65 467	93.50 470	65.11 480	99.63 351	93.04 412	97.45 437	98.53 394

TR-MVS		95.55 384	95.12 390	96.86 394	97.54 438	93.94 382	96.49 369	96.53 430	94.36 411	97.03 390	96.61 424	94.26 327	99.16 450	86.91 465	96.31 459	97.47 453

testing99		93.04 427	91.98 434	96.23 413	97.53 440	90.70 447	96.35 378	95.94 440	96.87 322	93.41 468	93.43 472	63.84 482	99.59 368	93.24 410	97.19 447	98.40 408

1314		95.74 378	95.60 370	96.17 416	97.53 440	92.75 411	98.07 192	98.31 377	91.22 451	94.25 457	96.68 422	95.53 290	99.03 453	91.64 435	97.18 448	96.74 463

CostFormer		93.97 411	93.78 409	94.51 443	97.53 440	85.83 469	97.98 214	95.96 439	89.29 464	94.99 449	98.63 306	78.63 454	99.62 354	94.54 371	96.50 456	98.09 424

FMVSNet5		96.01 369	95.20 388	98.41 266	97.53 440	96.10 291	98.74 97	99.50 128	97.22 301	98.03 327	99.04 194	69.80 466	99.88 115	97.27 222	99.71 199	99.25 277

PMMVS		96.51 352	95.98 359	98.09 300	97.53 440	95.84 304	94.92 441	98.84 334	91.58 446	96.05 430	95.58 444	95.68 286	99.66 337	95.59 348	98.09 419	98.76 373

reproduce_monomvs		95.00 396	95.25 385	94.22 446	97.51 445	83.34 478	97.86 232	98.44 370	98.51 169	99.29 140	99.30 120	67.68 471	99.56 380	98.89 97	99.81 131	99.77 50

PAPR		95.29 388	94.47 399	97.75 328	97.50 446	95.14 337	94.89 442	98.71 355	91.39 450	95.35 445	95.48 449	94.57 318	99.14 452	84.95 468	97.37 442	98.97 336

testing222		91.96 441	90.37 444	96.72 399	97.47 447	92.59 412	96.11 394	94.76 452	96.83 325	92.90 470	92.87 475	57.92 485	99.55 384	86.93 464	97.52 434	98.00 430

PatchT		96.65 348	96.35 352	97.54 355	97.40 448	95.32 330	97.98 214	96.64 427	99.33 66	96.89 399	99.42 90	84.32 427	99.81 222	97.69 193	97.49 435	97.48 452

tpm cat1		93.29 422	93.13 419	93.75 452	97.39 449	84.74 472	97.39 303	97.65 399	83.39 476	94.16 458	98.41 335	82.86 438	99.39 425	91.56 437	95.35 468	97.14 458

PatchmatchNet		95.58 383	95.67 368	95.30 436	97.34 450	87.32 464	97.65 265	96.65 426	95.30 387	97.07 386	98.69 292	84.77 422	99.75 275	94.97 361	98.64 395	98.83 357
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 307	96.97 317	98.50 257	97.31 451	96.47 282	98.18 171	98.92 316	98.95 128	98.78 244	99.37 101	85.44 419	99.85 156	95.96 330	99.83 120	99.17 304

LS3D		98.63 160	98.38 190	99.36 74	97.25 452	99.38 13	99.12 60	99.32 214	99.21 81	98.44 291	98.88 245	97.31 193	99.80 231	96.58 288	99.34 315	98.92 345

IB-MVS	91.63 19	92.24 438	90.90 442	96.27 410	97.22 453	91.24 438	94.36 458	93.33 465	92.37 439	92.24 474	94.58 464	66.20 476	99.89 97	93.16 411	94.63 471	97.66 447
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		92.38 435	91.76 438	94.21 447	97.16 454	84.65 473	95.42 427	88.45 479	95.96 366	96.17 424	95.84 442	66.36 474	99.71 298	91.87 430	98.64 395	98.28 415

tpmrst		95.07 393	95.46 376	93.91 450	97.11 455	84.36 476	97.62 270	96.96 419	94.98 394	96.35 422	98.80 265	85.46 418	99.59 368	95.60 347	96.23 460	97.79 442

Syy-MVS		96.04 368	95.56 374	97.49 360	97.10 456	94.48 358	96.18 390	96.58 428	95.65 375	94.77 450	92.29 478	91.27 375	99.36 428	98.17 148	98.05 423	98.63 387

myMVS_eth3d		91.92 442	90.45 443	96.30 408	97.10 456	90.90 443	96.18 390	96.58 428	95.65 375	94.77 450	92.29 478	53.88 486	99.36 428	89.59 456	98.05 423	98.63 387

MDTV_nov1_ep13			95.22 387		97.06 458	83.20 479	97.74 252	96.16 434	94.37 410	96.99 391	98.83 258	83.95 431	99.53 392	93.90 392	97.95 427

MVS		93.19 424	92.09 429	96.50 403	96.91 459	94.03 374	98.07 192	98.06 388	68.01 481	94.56 455	96.48 427	95.96 277	99.30 438	83.84 470	96.89 453	96.17 468

E-PMN		94.17 407	94.37 402	93.58 454	96.86 460	85.71 470	90.11 479	97.07 415	98.17 200	97.82 344	97.19 413	84.62 424	98.94 458	89.77 454	97.68 432	96.09 472

JIA-IIPM		95.52 385	95.03 391	97.00 383	96.85 461	94.03 374	96.93 343	95.82 442	99.20 83	94.63 454	99.71 22	83.09 436	99.60 364	94.42 377	94.64 470	97.36 456

EMVS		93.83 413	94.02 405	93.23 459	96.83 462	84.96 471	89.77 480	96.32 432	97.92 225	97.43 373	96.36 432	86.17 411	98.93 459	87.68 461	97.73 431	95.81 473

blend_shiyan4		92.09 440	90.16 447	97.88 316	96.78 463	94.93 344	95.24 432	98.58 363	96.22 353	96.07 428	91.42 480	63.46 483	99.73 288	96.70 276	76.98 482	98.98 332

cl22		95.79 377	95.39 381	96.98 385	96.77 464	92.79 409	94.40 457	98.53 366	94.59 403	97.89 336	98.17 357	82.82 439	99.24 444	96.37 308	99.03 361	98.92 345

WB-MVSnew		95.73 379	95.57 373	96.23 413	96.70 465	90.70 447	96.07 396	93.86 462	95.60 377	97.04 388	95.45 453	96.00 270	99.55 384	91.04 445	98.31 407	98.43 405

dp		93.47 419	93.59 412	93.13 460	96.64 466	81.62 485	97.66 263	96.42 431	92.80 435	96.11 426	98.64 304	78.55 456	99.59 368	93.31 408	92.18 478	98.16 420

MonoMVSNet		96.25 363	96.53 349	95.39 434	96.57 467	91.01 441	98.82 95	97.68 398	98.57 164	98.03 327	99.37 101	90.92 378	97.78 475	94.99 359	93.88 474	97.38 455

test-LLR		93.90 412	93.85 407	94.04 448	96.53 468	84.62 474	94.05 463	92.39 468	96.17 355	94.12 459	95.07 454	82.30 440	99.67 324	95.87 335	98.18 412	97.82 437

test-mter		92.33 437	91.76 438	94.04 448	96.53 468	84.62 474	94.05 463	92.39 468	94.00 419	94.12 459	95.07 454	65.63 479	99.67 324	95.87 335	98.18 412	97.82 437

TESTMET0.1,1		92.19 439	91.77 437	93.46 455	96.48 470	82.80 481	94.05 463	91.52 473	94.45 408	94.00 462	94.88 460	66.65 473	99.56 380	95.78 340	98.11 418	98.02 427

MGCNet		97.44 299	97.01 316	98.72 209	96.42 471	96.74 266	97.20 327	91.97 471	98.46 172	98.30 300	98.79 267	92.74 355	99.91 74	99.30 63	99.94 50	99.52 155

miper_enhance_ethall		96.01 369	95.74 364	96.81 395	96.41 472	92.27 421	93.69 468	98.89 322	91.14 453	98.30 300	97.35 411	90.58 381	99.58 375	96.31 312	99.03 361	98.60 389

tpmvs		95.02 395	95.25 385	94.33 444	96.39 473	85.87 467	98.08 188	96.83 424	95.46 382	95.51 443	98.69 292	85.91 414	99.53 392	94.16 383	96.23 460	97.58 450

CMPMVS	75.91 23	96.29 360	95.44 378	98.84 177	96.25 474	98.69 98	97.02 336	99.12 281	88.90 465	97.83 342	98.86 248	89.51 390	98.90 461	91.92 428	99.51 280	98.92 345
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 400	93.69 410	96.99 384	96.05 475	93.61 398	94.97 440	93.49 463	96.17 355	97.57 360	94.88 460	82.30 440	99.01 456	93.60 401	94.17 473	98.37 412

EPMVS		93.72 416	93.27 415	95.09 439	96.04 476	87.76 461	98.13 178	85.01 484	94.69 401	96.92 393	98.64 304	78.47 457	99.31 436	95.04 358	96.46 457	98.20 418

cascas		94.79 398	94.33 404	96.15 419	96.02 477	92.36 419	92.34 475	99.26 247	85.34 473	95.08 448	94.96 459	92.96 350	98.53 468	94.41 380	98.59 399	97.56 451

MVStest1		95.86 374	95.60 370	96.63 400	95.87 478	91.70 426	97.93 220	98.94 310	98.03 215	99.56 74	99.66 32	71.83 463	98.26 471	99.35 59	99.24 332	99.91 13

gg-mvs-nofinetune		92.37 436	91.20 440	95.85 422	95.80 479	92.38 418	99.31 30	81.84 486	99.75 11	91.83 475	99.74 18	68.29 468	99.02 454	87.15 462	97.12 449	96.16 469

gm-plane-assit					94.83 480	81.97 483			88.07 468		94.99 457		99.60 364	91.76 432

GG-mvs-BLEND				94.76 441	94.54 481	92.13 423	99.31 30	80.47 487		88.73 481	91.01 481	67.59 472	98.16 474	82.30 475	94.53 472	93.98 477

UWE-MVS-28		90.22 445	89.28 448	93.02 461	94.50 482	82.87 480	96.52 367	87.51 480	95.21 390	92.36 473	96.04 434	71.57 464	98.25 472	72.04 482	97.77 430	97.94 432

EPNet_dtu		94.93 397	94.78 397	95.38 435	93.58 483	87.68 462	96.78 350	95.69 446	97.35 282	89.14 480	98.09 364	88.15 402	99.49 405	94.95 362	99.30 323	98.98 332
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 449	75.95 452	77.12 466	92.39 484	67.91 490	90.16 478	59.44 491	82.04 477	89.42 479	94.67 463	49.68 488	81.74 484	48.06 484	77.66 481	81.72 480

KD-MVS_2432*1600		92.87 430	91.99 432	95.51 431	91.37 485	89.27 454	94.07 461	98.14 384	95.42 383	97.25 381	96.44 429	67.86 469	99.24 444	91.28 441	96.08 463	98.02 427

miper_refine_blended		92.87 430	91.99 432	95.51 431	91.37 485	89.27 454	94.07 461	98.14 384	95.42 383	97.25 381	96.44 429	67.86 469	99.24 444	91.28 441	96.08 463	98.02 427

EPNet		96.14 366	95.44 378	98.25 285	90.76 487	95.50 319	97.92 223	94.65 453	98.97 124	92.98 469	98.85 251	89.12 393	99.87 134	95.99 328	99.68 214	99.39 222
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 450	68.95 453	70.34 467	87.68 488	65.00 491	91.11 476	59.90 490	69.02 480	74.46 485	88.89 482	48.58 489	68.03 486	28.61 485	72.33 484	77.99 481

test_method		79.78 447	79.50 450	80.62 464	80.21 489	45.76 492	70.82 481	98.41 374	31.08 484	80.89 484	97.71 388	84.85 421	97.37 477	91.51 438	80.03 480	98.75 374

tmp_tt		78.77 448	78.73 451	78.90 465	58.45 490	74.76 489	94.20 460	78.26 488	39.16 483	86.71 482	92.82 476	80.50 444	75.19 485	86.16 467	92.29 477	86.74 479

testmvs		17.12 452	20.53 455	6.87 469	12.05 491	4.20 494	93.62 469	6.73 492	4.62 487	10.41 487	24.33 484	8.28 491	3.56 488	9.69 487	15.07 485	12.86 484

test123		17.04 453	20.11 456	7.82 468	10.25 492	4.91 493	94.80 443	4.47 493	4.93 486	10.00 488	24.28 485	9.69 490	3.64 487	10.14 486	12.43 486	14.92 483

mmdepth		0.00 456	0.00 459	0.00 470	0.00 493	0.00 495	0.00 482	0.00 494	0.00 488	0.00 489	0.00 488	0.00 492	0.00 489	0.00 488	0.00 487	0.00 485

monomultidepth		0.00 456	0.00 459	0.00 470	0.00 493	0.00 495	0.00 482	0.00 494	0.00 488	0.00 489	0.00 488	0.00 492	0.00 489	0.00 488	0.00 487	0.00 485

test_blank		0.00 456	0.00 459	0.00 470	0.00 493	0.00 495	0.00 482	0.00 494	0.00 488	0.00 489	0.00 488	0.00 492	0.00 489	0.00 488	0.00 487	0.00 485

eth-test2					0.00 493

eth-test					0.00 493

uanet_test		0.00 456	0.00 459	0.00 470	0.00 493	0.00 495	0.00 482	0.00 494	0.00 488	0.00 489	0.00 488	0.00 492	0.00 489	0.00 488	0.00 487	0.00 485

DCPMVS		0.00 456	0.00 459	0.00 470	0.00 493	0.00 495	0.00 482	0.00 494	0.00 488	0.00 489	0.00 488	0.00 492	0.00 489	0.00 488	0.00 487	0.00 485

cdsmvs_eth3d_5k		24.66 451	32.88 454	0.00 470	0.00 493	0.00 495	0.00 482	99.10 284	0.00 488	0.00 489	97.58 396	99.21 18	0.00 489	0.00 488	0.00 487	0.00 485

pcd_1.5k_mvsjas		8.17 454	10.90 457	0.00 470	0.00 493	0.00 495	0.00 482	0.00 494	0.00 488	0.00 489	0.00 488	98.07 121	0.00 489	0.00 488	0.00 487	0.00 485

sosnet-low-res		0.00 456	0.00 459	0.00 470	0.00 493	0.00 495	0.00 482	0.00 494	0.00 488	0.00 489	0.00 488	0.00 492	0.00 489	0.00 488	0.00 487	0.00 485

sosnet		0.00 456	0.00 459	0.00 470	0.00 493	0.00 495	0.00 482	0.00 494	0.00 488	0.00 489	0.00 488	0.00 492	0.00 489	0.00 488	0.00 487	0.00 485

uncertanet		0.00 456	0.00 459	0.00 470	0.00 493	0.00 495	0.00 482	0.00 494	0.00 488	0.00 489	0.00 488	0.00 492	0.00 489	0.00 488	0.00 487	0.00 485

Regformer		0.00 456	0.00 459	0.00 470	0.00 493	0.00 495	0.00 482	0.00 494	0.00 488	0.00 489	0.00 488	0.00 492	0.00 489	0.00 488	0.00 487	0.00 485

ab-mvs-re		8.12 455	10.83 458	0.00 470	0.00 493	0.00 495	0.00 482	0.00 494	0.00 488	0.00 489	97.48 402	0.00 492	0.00 489	0.00 488	0.00 487	0.00 485

uanet		0.00 456	0.00 459	0.00 470	0.00 493	0.00 495	0.00 482	0.00 494	0.00 488	0.00 489	0.00 488	0.00 492	0.00 489	0.00 488	0.00 487	0.00 485

TestfortrainingZip							98.68 107

WAC-MVS						90.90 443								91.37 440

PC_three_1452									93.27 427	99.40 115	98.54 317	98.22 106	97.00 478	95.17 356	99.45 295	99.49 170

test_241102_TWO								99.30 227	98.03 215	99.26 148	99.02 197	97.51 179	99.88 115	96.91 251	99.60 248	99.66 78

test_0728_THIRD									98.17 200	99.08 176	99.02 197	97.89 140	99.88 115	97.07 238	99.71 199	99.70 68

GSMVS																98.81 363

sam_mvs1												84.74 423				98.81 363

sam_mvs												84.29 429

MTGPA								99.20 259

test_post1							97.59 278				20.48 487	83.07 437	99.66 337	94.16 383

test_post											21.25 486	83.86 432	99.70 305

patchmatchnet-post											98.77 271	84.37 426	99.85 156

MTMP							97.93 220	91.91 472

test9_res														93.28 409	99.15 348	99.38 231

agg_prior2														92.50 425	99.16 346	99.37 233

test_prior4						97.97 163	95.86 408

test_prior2							95.74 415		96.48 341	96.11 426	97.63 394	95.92 280		94.16 383	99.20 340

旧先验2							95.76 414		88.56 467	97.52 364			99.66 337	94.48 373

新几何2							95.93 404

无先验							95.74 415	98.74 352	89.38 463				99.73 288	92.38 427		99.22 287

原ACMM2							95.53 421

testdata2													99.79 244	92.80 419

segment_acmp												97.02 213

testdata1							95.44 426		96.32 349

plane_prior5								99.27 242					99.70 305	94.42 377	99.51 280	99.45 196

plane_prior4											97.98 372

plane_prior3						97.78 188			97.41 275	97.79 345

plane_prior2							97.77 245		98.20 197

plane_prior						97.65 197	97.07 335		96.72 331						99.36 311

n2								0.00 494

nn								0.00 494

door-mid								99.57 97

test11								98.87 325

door								99.41 179

HQP5-MVS						96.79 262

BP-MVS														92.82 417

HQP4-MVS										95.56 437			99.54 390			99.32 256

HQP3-MVS								99.04 296							99.26 330

HQP2-MVS												93.84 334

MDTV_nov1_ep13_2view						74.92 488	97.69 258		90.06 461	97.75 348		85.78 415		93.52 403		98.69 381

ACMMP++_ref															99.77 159

ACMMP++															99.68 214

Test By Simon												96.52 246

High-resolution multi-view benchmark