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 85	99.16 63	98.64 223	99.94 2	98.51 112	99.32 26	99.75 42	99.58 39	98.60 273	99.62 40	98.22 109	99.51 407	97.70 194	99.73 185	97.89 440
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 94	99.44 53	99.78 40	99.76 15	96.39 254	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	98.07 124	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	99.35 109	98.86 34	99.67 330	97.81 181	99.81 134	99.24 283

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	99.35 109	98.86 34	99.67 330	97.81 181	99.81 134	99.24 283

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 82	99.66 24	99.68 58	99.66 32	98.44 82	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	98.08 192	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	99.56 110	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 91	99.59 37	99.71 50	99.57 49	97.12 209	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 94	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		98.75 135	98.62 150	99.16 118	99.83 18	97.96 166	99.28 40	98.20 387	99.37 61	99.70 52	99.65 36	92.65 360	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 93	98.86 112	99.36 74	99.82 19	98.55 107	97.47 300	99.57 101	99.37 61	99.21 164	99.61 43	96.76 236	99.83 192	98.06 158	99.83 123	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	99.83 123	99.56 129

TransMVSNet (Re)		99.44 19	99.47 21	99.36 74	99.80 21	98.58 105	99.27 42	99.57 101	99.39 59	99.75 45	99.62 40	99.17 20	99.83 192	99.06 83	99.62 244	99.66 78

K. test v3		98.00 254	97.66 279	99.03 145	99.79 23	97.56 202	99.19 52	92.47 473	99.62 33	99.52 88	99.66 32	89.61 392	99.96 14	99.25 68	99.81 134	99.56 129

test_fmvsmconf0.1_n		99.49 15	99.54 14	99.34 83	99.78 24	98.11 143	97.77 249	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		98.83 119	98.66 143	99.34 83	99.78 24	99.47 9	98.42 150	99.45 159	98.28 192	98.98 201	99.19 154	97.76 156	99.58 381	96.57 296	99.55 271	98.97 342

test_vis3_rt		99.14 63	99.17 61	99.07 135	99.78 24	98.38 119	98.92 82	99.94 2	97.80 238	99.91 12	99.67 30	97.15 208	98.91 466	99.76 23	99.56 267	99.92 12

EGC-MVSNET		85.24 452	80.54 455	99.34 83	99.77 27	99.20 40	99.08 61	99.29 239	12.08 491	20.84 492	99.42 90	97.55 175	99.85 156	97.08 242	99.72 193	98.96 344

Anonymous20240521		98.69 148	98.87 108	98.16 300	99.77 27	95.11 342	99.08 61	99.44 167	99.34 65	99.33 130	99.55 57	94.10 335	99.94 42	99.25 68	99.96 28	99.42 212

FC-MVSNet-test		99.27 38	99.25 53	99.34 83	99.77 27	98.37 121	99.30 35	99.57 101	99.61 35	99.40 115	99.50 69	97.12 209	99.85 156	99.02 87	99.94 50	99.80 42

test_vis1_n		98.31 218	98.50 170	97.73 338	99.76 30	94.17 373	98.68 108	99.91 9	96.31 354	99.79 39	99.57 49	92.85 356	99.42 427	99.79 19	99.84 112	99.60 100

test_fmvs3		99.12 70	99.41 26	98.25 288	99.76 30	95.07 343	99.05 67	99.94 2	97.78 241	99.82 34	99.84 3	98.56 72	99.71 301	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 79	98.48 175	99.37 120	99.49 75	98.75 46	99.86 143	98.20 148	99.80 145	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 60	99.80 231	98.24 143	99.84 112	99.52 158

fmvsm_s_conf0.1_n_a		99.17 53	99.30 45	98.80 188	99.75 34	96.59 274	97.97 222	99.86 16	98.22 195	99.88 21	99.71 22	98.59 66	99.84 174	99.73 28	99.98 12	99.98 3

tt0805		98.69 148	98.62 150	98.90 171	99.75 34	99.30 23	99.15 56	96.97 424	98.86 139	98.87 234	97.62 398	98.63 62	98.96 463	99.41 57	98.29 411	98.45 406

test_vis1_n_1920		98.40 201	98.92 100	96.81 401	99.74 36	90.76 452	98.15 180	99.91 9	98.33 183	99.89 18	99.55 57	95.07 306	99.88 115	99.76 23	99.93 56	99.79 44

FOURS1					99.73 37	99.67 3	99.43 15	99.54 119	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	99.54 119	99.62 33	99.56 74	99.42 90	98.16 118	99.96 14	98.78 103	99.93 56	99.77 50

lessismore_v0				98.97 157	99.73 37	97.53 204		86.71 488		99.37 120	99.52 68	89.93 388	99.92 65	98.99 89	99.72 193	99.44 203

SteuartSystems-ACMMP		98.79 128	98.54 163	99.54 32	99.73 37	99.16 49	98.23 170	99.31 223	97.92 229	98.90 223	98.90 241	98.00 130	99.88 115	96.15 328	99.72 193	99.58 115
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 239	98.15 231	98.22 294	99.73 37	95.15 339	97.36 314	99.68 60	94.45 414	98.99 200	99.27 129	96.87 225	99.94 42	97.13 239	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		98.71 139	98.74 123	98.62 229	99.72 43	96.08 299	98.74 98	98.64 364	99.74 13	99.67 60	99.24 142	94.57 321	99.95 26	99.11 78	99.24 335	99.82 36

test_f		98.67 157	98.87 108	98.05 310	99.72 43	95.59 314	98.51 134	99.81 31	96.30 356	99.78 40	99.82 5	96.14 265	98.63 473	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	99.55 114	98.30 187	99.65 64	99.45 85	99.22 17	99.76 267	98.44 129	99.77 162	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	98.64 223	99.71 47	96.10 294	97.87 235	99.85 18	98.56 171	99.90 14	99.68 25	98.69 56	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	99.53 123	99.53 42	99.46 101	99.41 94	98.23 106	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	99.51 129	99.64 27	99.56 74	99.46 81	98.23 106	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	99.55 114	99.46 50	99.50 94	99.34 113	97.30 197	99.93 54	98.90 95	99.93 56	99.77 50

HPM-MVS_fast		99.01 87	98.82 116	99.57 22	99.71 47	99.35 17	99.00 72	99.50 132	97.33 287	98.94 218	98.86 251	98.75 46	99.82 205	97.53 208	99.71 202	99.56 129

ACMH+	96.62 9	99.08 77	99.00 92	99.33 89	99.71 47	98.83 87	98.60 120	99.58 94	99.11 98	99.53 83	99.18 158	98.81 38	99.67 330	96.71 280	99.77 162	99.50 166

PMVS	91.26 20	97.86 268	97.94 255	97.65 346	99.71 47	97.94 168	98.52 129	98.68 360	98.99 121	97.52 367	99.35 109	97.41 190	98.18 479	91.59 442	99.67 223	96.82 468
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 76	99.81 222	98.93 93	99.91 78	99.51 162

KinetiMVS		99.03 85	99.02 88	99.03 145	99.70 55	97.48 208	98.43 147	99.29 239	99.70 16	99.60 71	99.07 187	96.13 266	99.94 42	99.42 56	99.87 98	99.68 71

FIs		99.14 63	99.09 80	99.29 95	99.70 55	98.28 127	99.13 58	99.52 128	99.48 45	99.24 158	99.41 94	96.79 233	99.82 205	98.69 113	99.88 94	99.76 56

VPNet		98.87 109	98.83 115	99.01 149	99.70 55	97.62 200	98.43 147	99.35 204	99.47 48	99.28 142	99.05 195	96.72 239	99.82 205	98.09 155	99.36 314	99.59 107

fmvsm_s_conf0.1_n_2		99.20 51	99.38 29	98.65 221	99.69 59	96.08 299	97.49 295	99.90 11	99.53 42	99.88 21	99.64 37	98.51 75	99.90 81	99.83 10	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 215	98.68 138	97.27 377	99.69 59	92.29 426	98.03 203	99.85 18	97.62 251	99.96 4	99.62 40	93.98 336	99.74 283	99.52 50	99.86 105	99.79 44

MP-MVS-pluss		98.57 174	98.23 219	99.60 16	99.69 59	99.35 17	97.16 336	99.38 190	94.87 404	98.97 205	98.99 217	98.01 129	99.88 115	97.29 226	99.70 209	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	99.48 142	99.69 18	99.63 67	99.68 25	99.03 24	99.96 14	97.97 169	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	99.30 231	99.69 18	99.63 67	99.68 25	99.25 16	99.96 14	97.25 229	99.92 69	99.57 123

test_fmvs1_n		98.09 245	98.28 210	97.52 363	99.68 62	93.47 405	98.63 115	99.93 5	95.41 392	99.68 58	99.64 37	91.88 371	99.48 414	99.82 12	99.87 98	99.62 90

CHOSEN 1792x2688		97.49 297	97.14 312	98.54 252	99.68 62	96.09 297	96.50 372	99.62 79	91.58 452	98.84 237	98.97 224	92.36 362	99.88 115	96.76 273	99.95 38	99.67 76

tfpnnormal		98.90 104	98.90 102	98.91 168	99.67 66	97.82 183	99.00 72	99.44 167	99.45 51	99.51 93	99.24 142	98.20 113	99.86 143	95.92 337	99.69 212	99.04 328

MTAPA		98.88 108	98.64 146	99.61 14	99.67 66	99.36 16	98.43 147	99.20 263	98.83 144	98.89 226	98.90 241	96.98 219	99.92 65	97.16 234	99.70 209	99.56 129

test_fmvsmvis_n_1920		99.26 40	99.49 16	98.54 252	99.66 68	96.97 253	98.00 210	99.85 18	99.24 76	99.92 8	99.50 69	99.39 12	99.95 26	99.89 3	99.98 12	98.71 383

mvs5depth		99.30 34	99.59 12	98.44 266	99.65 69	95.35 331	99.82 3	99.94 2	99.83 7	99.42 110	99.94 2	98.13 121	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	97.05 248	97.80 244	99.76 39	98.70 153	99.78 40	99.11 177	98.79 42	99.95 26	99.85 6	99.96 28	99.83 33

WB-MVS		98.52 188	98.55 161	98.43 267	99.65 69	95.59 314	98.52 129	98.77 349	99.65 26	99.52 88	99.00 215	94.34 327	99.93 54	98.65 115	98.83 383	99.76 56

CP-MVSNet		99.21 48	99.09 80	99.56 27	99.65 69	98.96 78	99.13 58	99.34 210	99.42 56	99.33 130	99.26 135	97.01 217	99.94 42	98.74 108	99.93 56	99.79 44

HPM-MVS		98.79 128	98.53 165	99.59 20	99.65 69	99.29 25	99.16 54	99.43 173	96.74 334	98.61 271	98.38 342	98.62 63	99.87 134	96.47 308	99.67 223	99.59 107
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 166	98.36 196	99.42 68	99.65 69	99.42 11	98.55 125	99.57 101	97.72 245	98.90 223	99.26 135	96.12 268	99.52 402	95.72 348	99.71 202	99.32 259

NormalMVS		98.26 225	97.97 252	99.15 121	99.64 75	97.83 178	98.28 164	99.43 173	99.24 76	98.80 245	98.85 254	89.76 390	99.94 42	98.04 160	99.67 223	99.68 71

lecture		99.25 41	99.12 71	99.62 10	99.64 75	99.40 12	98.89 87	99.51 129	99.19 88	99.37 120	99.25 140	98.36 87	99.88 115	98.23 145	99.67 223	99.59 107

fmvsm_l_conf0.5_n		99.21 48	99.28 47	99.02 148	99.64 75	97.28 227	97.82 240	99.76 39	98.73 146	99.82 34	99.09 185	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	97.68 263	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.		98.63 163	98.49 175	99.06 141	99.64 75	97.90 172	98.51 134	98.94 314	96.96 318	99.24 158	98.89 247	97.83 148	99.81 222	96.88 263	99.49 293	99.48 184
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 122	98.72 127	99.12 124	99.64 75	98.54 110	97.98 218	99.68 60	97.62 251	99.34 127	99.18 158	97.54 177	99.77 261	97.79 183	99.74 182	99.04 328

Elysia		99.15 58	99.14 69	99.18 113	99.63 81	97.92 169	98.50 136	99.43 173	99.67 21	99.70 52	99.13 173	96.66 242	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	99.43 173	99.67 21	99.70 52	99.13 173	96.66 242	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	99.54 119	99.31 69	99.62 70	99.53 65	97.36 194	99.86 143	99.24 70	99.71 202	99.39 225

EU-MVSNet		97.66 285	98.50 170	95.13 443	99.63 81	85.84 474	98.35 160	98.21 386	98.23 194	99.54 79	99.46 81	95.02 307	99.68 326	98.24 143	99.87 98	99.87 22

HyFIR lowres test		97.19 324	96.60 348	98.96 158	99.62 85	97.28 227	95.17 439	99.50 132	94.21 419	99.01 195	98.32 350	86.61 411	99.99 2	97.10 241	99.84 112	99.60 100

E5new		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	99.70 308	98.43 131	99.84 112	99.54 142

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	99.70 308	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	99.70 308	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	99.70 308	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 90	97.18 239	97.44 304	99.83 25	99.56 40	99.91 12	99.34 113	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 90	98.21 136	97.82 240	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 92	98.93 80	98.68 108	99.60 84	96.46 347	99.53 83	98.77 274		99.83 192	96.67 285	99.64 234	99.58 115

MED-MVS		98.90 104	98.72 127	99.45 64	99.58 92	98.93 80	98.68 108	99.60 84	98.14 213	99.53 83	98.77 274	97.87 145	99.83 192	96.67 285	99.64 234	99.58 115

TestfortrainingZip a		98.95 97	98.72 127	99.64 9	99.58 92	99.32 22	98.68 108	99.60 84	96.46 347	99.53 83	98.77 274	97.87 145	99.83 192	98.39 136	99.64 234	99.77 50

FE-MVSNET		98.59 171	98.50 170	98.87 172	99.58 92	97.30 221	98.08 192	99.74 43	96.94 320	98.97 205	99.10 180	96.94 221	99.74 283	97.33 224	99.86 105	99.55 136

mmtdpeth		99.30 34	99.42 25	98.92 167	99.58 92	96.89 261	99.48 13	99.92 7	99.92 2	98.26 309	99.80 11	98.33 93	99.91 74	99.56 41	99.95 38	99.97 4

ACMMP_NAP		98.75 135	98.48 176	99.57 22	99.58 92	99.29 25	97.82 240	99.25 252	96.94 320	98.78 247	99.12 176	98.02 128	99.84 174	97.13 239	99.67 223	99.59 107

nrg030		99.40 26	99.35 34	99.54 32	99.58 92	99.13 61	98.98 75	99.48 142	99.68 20	99.46 101	99.26 135	98.62 63	99.73 290	99.17 75	99.92 69	99.76 56

VDDNet		98.21 232	97.95 253	99.01 149	99.58 92	97.74 191	99.01 70	97.29 415	99.67 21	98.97 205	99.50 69	90.45 385	99.80 231	97.88 176	99.20 343	99.48 184

COLMAP_ROB	96.50 10	98.99 90	98.85 114	99.41 70	99.58 92	99.10 66	98.74 98	99.56 110	99.09 108	99.33 130	99.19 154	98.40 84	99.72 300	95.98 335	99.76 177	99.42 212
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	99.57 101	97.73 193	97.93 224	99.83 25	99.22 79	99.93 6	99.30 123	99.42 11	99.96 14	99.85 6	99.99 5	99.29 269

ZNCC-MVS		98.68 154	98.40 188	99.54 32	99.57 101	99.21 34	98.46 144	99.29 239	97.28 293	98.11 321	98.39 340	98.00 130	99.87 134	96.86 266	99.64 234	99.55 136

MSP-MVS		98.40 201	98.00 247	99.61 14	99.57 101	99.25 30	98.57 123	99.35 204	97.55 262	99.31 138	97.71 391	94.61 320	99.88 115	96.14 329	99.19 346	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		98.32 216	98.39 191	98.13 301	99.57 101	95.54 317	97.78 246	99.49 140	97.37 284	99.19 166	97.65 395	98.96 29	99.49 411	96.50 307	98.99 371	99.34 250

MP-MVS		98.46 194	98.09 236	99.54 32	99.57 101	99.22 33	98.50 136	99.19 267	97.61 254	97.58 361	98.66 302	97.40 191	99.88 115	94.72 374	99.60 251	99.54 142
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 139	98.46 180	99.47 61	99.57 101	98.97 74	98.23 170	99.48 142	96.60 339	99.10 177	99.06 188	98.71 50	99.83 192	95.58 355	99.78 156	99.62 90

LGP-MVS_train				99.47 61	99.57 101	98.97 74		99.48 142	96.60 339	99.10 177	99.06 188	98.71 50	99.83 192	95.58 355	99.78 156	99.62 90

IS-MVSNet		98.19 235	97.90 261	99.08 133	99.57 101	97.97 163	99.31 30	98.32 382	99.01 120	98.98 201	99.03 199	91.59 373	99.79 244	95.49 357	99.80 145	99.48 184

viewdifsd2359ckpt11		98.84 116	99.04 85	98.24 290	99.56 109	95.51 319	97.38 309	99.70 52	99.16 93	99.57 72	99.40 97	98.26 102	99.71 301	98.55 124	99.82 128	99.50 166

viewmsd2359difaftdt		98.84 116	99.04 85	98.24 290	99.56 109	95.51 319	97.38 309	99.70 52	99.16 93	99.57 72	99.40 97	98.26 102	99.71 301	98.55 124	99.82 128	99.50 166

dcpmvs_2		98.78 130	99.11 72	97.78 328	99.56 109	93.67 400	99.06 65	99.86 16	99.50 44	99.66 61	99.26 135	97.21 205	99.99 2	98.00 165	99.91 78	99.68 71

test_0402		98.76 134	98.71 132	98.93 164	99.56 109	98.14 141	98.45 146	99.34 210	99.28 73	98.95 211	98.91 238	98.34 92	99.79 244	95.63 352	99.91 78	98.86 361

EPP-MVSNet		98.30 219	98.04 243	99.07 135	99.56 109	97.83 178	99.29 36	98.07 393	99.03 118	98.59 275	99.13 173	92.16 366	99.90 81	96.87 264	99.68 217	99.49 173

ACMMP		98.75 135	98.50 170	99.52 45	99.56 109	99.16 49	98.87 88	99.37 194	97.16 308	98.82 241	99.01 211	97.71 159	99.87 134	96.29 320	99.69 212	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	98.78 195	99.55 115	96.59 274	97.79 245	99.82 30	98.21 197	99.81 37	99.53 65	98.46 80	99.84 174	99.70 33	99.97 21	99.90 15

fmvsm_s_conf0.5_n		99.09 73	99.26 51	98.61 233	99.55 115	96.09 297	97.74 256	99.81 31	98.55 172	99.85 27	99.55 57	98.60 65	99.84 174	99.69 35	99.98 12	99.89 16

FMVSNet1		99.17 53	99.17 61	99.17 115	99.55 115	98.24 130	99.20 48	99.44 167	99.21 81	99.43 106	99.55 57	97.82 151	99.86 143	98.42 135	99.89 92	99.41 215

Vis-MVSNet (Re-imp)		97.46 299	97.16 309	98.34 279	99.55 115	96.10 294	98.94 80	98.44 376	98.32 185	98.16 315	98.62 311	88.76 397	99.73 290	93.88 400	99.79 151	99.18 304

ACMM	96.08 12	98.91 102	98.73 125	99.48 57	99.55 115	99.14 58	98.07 196	99.37 194	97.62 251	99.04 191	98.96 227	98.84 36	99.79 244	97.43 218	99.65 232	99.49 173
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 144	98.97 96	97.89 320	99.54 120	94.05 377	98.55 125	99.92 7	96.78 332	99.72 48	99.78 13	96.60 246	99.67 330	99.91 2	99.90 86	99.94 10

mPP-MVS		98.64 161	98.34 199	99.54 32	99.54 120	99.17 45	98.63 115	99.24 257	97.47 270	98.09 323	98.68 297	97.62 168	99.89 97	96.22 323	99.62 244	99.57 123

XVG-ACMP-BASELINE		98.56 175	98.34 199	99.22 109	99.54 120	98.59 104	97.71 259	99.46 155	97.25 296	98.98 201	98.99 217	97.54 177	99.84 174	95.88 338	99.74 182	99.23 285

viewmacassd2359aftdt		98.86 113	98.87 108	98.83 181	99.53 123	97.32 220	97.70 261	99.64 71	98.22 195	99.25 156	99.27 129	98.40 84	99.61 367	97.98 168	99.87 98	99.55 136

region2R		98.69 148	98.40 188	99.54 32	99.53 123	99.17 45	98.52 129	99.31 223	97.46 275	98.44 294	98.51 325	97.83 148	99.88 115	96.46 309	99.58 260	99.58 115

PGM-MVS		98.66 158	98.37 195	99.55 29	99.53 123	99.18 44	98.23 170	99.49 140	97.01 317	98.69 258	98.88 248	98.00 130	99.89 97	95.87 341	99.59 255	99.58 115

E4		98.87 109	98.88 105	98.81 185	99.52 126	97.23 230	97.62 274	99.61 82	98.58 166	99.18 170	99.33 116	98.29 96	99.69 316	97.99 167	99.83 123	99.52 158

Patchmatch-RL test		97.26 317	97.02 318	97.99 314	99.52 126	95.53 318	96.13 397	99.71 47	97.47 270	99.27 144	99.16 164	84.30 434	99.62 360	97.89 173	99.77 162	98.81 369

ACMMPR		98.70 144	98.42 186	99.54 32	99.52 126	99.14 58	98.52 129	99.31 223	97.47 270	98.56 281	98.54 320	97.75 157	99.88 115	96.57 296	99.59 255	99.58 115

fmvsm_s_conf0.5_n_9		99.17 53	99.38 29	98.53 254	99.51 129	95.82 309	97.62 274	99.78 36	99.72 15	99.90 14	99.48 76	98.66 58	99.89 97	99.85 6	99.93 56	99.89 16

AstraMVS		98.16 241	98.07 241	98.41 269	99.51 129	95.86 306	98.00 210	95.14 456	98.97 124	99.43 106	99.24 142	93.25 344	99.84 174	99.21 71	99.87 98	99.54 142

fmvsm_s_conf0.5_n_8		99.13 67	99.26 51	98.74 208	99.51 129	96.44 286	97.65 269	99.65 69	99.66 24	99.78 40	99.48 76	97.92 138	99.93 54	99.72 30	99.95 38	99.87 22

GST-MVS		98.61 167	98.30 207	99.52 45	99.51 129	99.20 40	98.26 168	99.25 252	97.44 278	98.67 261	98.39 340	97.68 160	99.85 156	96.00 333	99.51 283	99.52 158

Anonymous20231206		98.21 232	98.21 220	98.20 295	99.51 129	95.43 328	98.13 182	99.32 218	96.16 362	98.93 219	98.82 264	96.00 273	99.83 192	97.32 225	99.73 185	99.36 243

ACMP	95.32 15	98.41 198	98.09 236	99.36 74	99.51 129	98.79 90	97.68 263	99.38 190	95.76 379	98.81 243	98.82 264	98.36 87	99.82 205	94.75 371	99.77 162	99.48 184
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LuminaMVS		98.39 207	98.20 221	98.98 155	99.50 135	97.49 205	97.78 246	97.69 402	98.75 145	99.49 95	99.25 140	92.30 364	99.94 42	99.14 76	99.88 94	99.50 166

DVP-MVS		98.77 133	98.52 166	99.52 45	99.50 135	99.21 34	98.02 206	98.84 338	97.97 223	99.08 179	99.02 200	97.61 170	99.88 115	96.99 250	99.63 241	99.48 184
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	99.50 135	99.23 32	98.02 206	99.32 218					99.88 115	96.99 250	99.63 241	99.68 71

test0726					99.50 135	99.21 34	98.17 178	99.35 204	97.97 223	99.26 148	99.06 188	97.61 170

AllTest		98.44 196	98.20 221	99.16 118	99.50 135	98.55 107	98.25 169	99.58 94	96.80 330	98.88 230	99.06 188	97.65 163	99.57 383	94.45 381	99.61 249	99.37 236

TestCases				99.16 118	99.50 135	98.55 107		99.58 94	96.80 330	98.88 230	99.06 188	97.65 163	99.57 383	94.45 381	99.61 249	99.37 236

XVG-OURS		98.53 184	98.34 199	99.11 126	99.50 135	98.82 89	95.97 403	99.50 132	97.30 291	99.05 189	98.98 222	99.35 14	99.32 441	95.72 348	99.68 217	99.18 304

EG-PatchMatch MVS		98.99 90	99.01 90	98.94 161	99.50 135	97.47 209	98.04 201	99.59 91	98.15 212	99.40 115	99.36 108	98.58 71	99.76 267	98.78 103	99.68 217	99.59 107

fmvsm_s_conf0.5_n_2		99.14 63	99.31 42	98.63 227	99.49 143	96.08 299	97.38 309	99.81 31	99.48 45	99.84 30	99.57 49	98.46 80	99.89 97	99.82 12	99.97 21	99.91 13

SED-MVS		98.91 102	98.72 127	99.49 55	99.49 143	99.17 45	98.10 189	99.31 223	98.03 219	99.66 61	99.02 200	98.36 87	99.88 115	96.91 256	99.62 244	99.41 215

IU-MVS					99.49 143	99.15 53		98.87 329	92.97 437	99.41 112				96.76 273	99.62 244	99.66 78

test_241102_ONE					99.49 143	99.17 45		99.31 223	97.98 222	99.66 61	98.90 241	98.36 87	99.48 414

UA-Net		99.47 16	99.40 27	99.70 2	99.49 143	99.29 25	99.80 4	99.72 45	99.82 8	99.04 191	99.81 8	98.05 127	99.96 14	98.85 99	99.99 5	99.86 28

HFP-MVS		98.71 139	98.44 183	99.51 49	99.49 143	99.16 49	98.52 129	99.31 223	97.47 270	98.58 277	98.50 329	97.97 134	99.85 156	96.57 296	99.59 255	99.53 155

VPA-MVSNet		99.30 34	99.30 45	99.28 96	99.49 143	98.36 124	99.00 72	99.45 159	99.63 29	99.52 88	99.44 86	98.25 104	99.88 115	99.09 80	99.84 112	99.62 90

XVG-OURS-SEG-HR		98.49 191	98.28 210	99.14 122	99.49 143	98.83 87	96.54 368	99.48 142	97.32 289	99.11 174	98.61 313	99.33 15	99.30 444	96.23 322	98.38 407	99.28 272

fmvsm_s_conf0.5_n_11		99.21 48	99.34 36	98.80 188	99.48 151	96.56 279	97.97 222	99.69 54	99.63 29	99.84 30	99.54 63	98.21 111	99.94 42	99.76 23	99.95 38	99.88 20

114514_t		96.50 357	95.77 366	98.69 216	99.48 151	97.43 213	97.84 239	99.55 114	81.42 484	96.51 423	98.58 317	95.53 293	99.67 330	93.41 413	99.58 260	98.98 338

IterMVS-LS		98.55 179	98.70 135	98.09 303	99.48 151	94.73 356	97.22 330	99.39 188	98.97 124	99.38 118	99.31 122	96.00 273	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	98.78 195	99.47 154	96.56 279	97.75 255	99.71 47	99.60 36	99.74 47	99.44 86	97.96 135	99.95 26	99.86 4	99.94 50	99.82 36

fmvsm_s_conf0.5_n_5		99.07 79	99.10 78	98.99 151	99.47 154	97.22 233	97.40 306	99.83 25	97.61 254	99.85 27	99.30 123	98.80 40	99.95 26	99.71 32	99.90 86	99.78 47

v8		99.01 87	99.16 63	98.57 240	99.47 154	96.31 291	98.90 83	99.47 151	99.03 118	99.52 88	99.57 49	96.93 222	99.81 222	99.60 37	99.98 12	99.60 100

SSC-MVS3.2		98.53 184	98.79 119	97.74 335	99.46 157	93.62 403	96.45 374	99.34 210	99.33 66	98.93 219	98.70 293	97.90 139	99.90 81	99.12 77	99.92 69	99.69 70

fmvsm_s_conf0.5_n_3		99.22 47	99.37 32	98.78 195	99.46 157	96.58 277	97.65 269	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		98.72 138	98.45 181	99.53 39	99.46 157	99.21 34	98.65 113	99.34 210	98.62 160	97.54 365	98.63 309	97.50 183	99.83 192	96.79 269	99.53 277	99.56 129

X-MVStestdata		94.32 409	92.59 428	99.53 39	99.46 157	99.21 34	98.65 113	99.34 210	98.62 160	97.54 365	45.85 489	97.50 183	99.83 192	96.79 269	99.53 277	99.56 129

test20.03		98.78 130	98.77 122	98.78 195	99.46 157	97.20 236	97.78 246	99.24 257	99.04 117	99.41 112	98.90 241	97.65 163	99.76 267	97.70 194	99.79 151	99.39 225

guyue		98.01 253	97.93 257	98.26 286	99.45 162	95.48 323	98.08 192	96.24 439	98.89 135	99.34 127	99.14 171	91.32 377	99.82 205	99.07 81	99.83 123	99.48 184

CSCG		98.68 154	98.50 170	99.20 110	99.45 162	98.63 99	98.56 124	99.57 101	97.87 233	98.85 235	98.04 371	97.66 162	99.84 174	96.72 278	99.81 134	99.13 317

GeoE		99.05 80	98.99 94	99.25 104	99.44 164	98.35 125	98.73 102	99.56 110	98.42 178	98.91 222	98.81 267	98.94 30	99.91 74	98.35 138	99.73 185	99.49 173

v148		98.45 195	98.60 155	98.00 313	99.44 164	94.98 345	97.44 304	99.06 293	98.30 187	99.32 136	98.97 224	96.65 244	99.62 360	98.37 137	99.85 107	99.39 225

v10		98.97 94	99.11 72	98.55 247	99.44 164	96.21 293	98.90 83	99.55 114	98.73 146	99.48 96	99.60 45	96.63 245	99.83 192	99.70 33	99.99 5	99.61 98

V42		98.78 130	98.78 121	98.76 202	99.44 164	97.04 249	98.27 167	99.19 267	97.87 233	99.25 156	99.16 164	96.84 226	99.78 255	99.21 71	99.84 112	99.46 194

MDA-MVSNet-bldmvs		97.94 259	97.91 260	98.06 308	99.44 164	94.96 346	96.63 364	99.15 283	98.35 181	98.83 238	99.11 177	94.31 328	99.85 156	96.60 293	98.72 389	99.37 236

viewdifsd2359ckpt07		98.71 139	98.86 112	98.26 286	99.43 169	95.65 313	97.20 331	99.66 65	99.20 83	99.29 140	99.01 211	98.29 96	99.73 290	97.92 172	99.75 181	99.39 225

casdiffmvs_mvg		99.12 70	99.16 63	98.99 151	99.43 169	97.73 193	98.00 210	99.62 79	99.22 79	99.55 77	99.22 148	98.93 32	99.75 277	98.66 114	99.81 134	99.50 166
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		98.90 104	99.01 90	98.57 240	99.42 171	96.59 274	98.13 182	99.66 65	99.09 108	99.30 139	99.02 200	98.79 42	99.89 97	97.87 178	99.80 145	99.23 285

test1111		96.49 358	96.82 332	95.52 436	99.42 171	87.08 471	99.22 45	87.14 487	99.11 98	99.46 101	99.58 47	88.69 398	99.86 143	98.80 101	99.95 38	99.62 90

v2v482		98.56 175	98.62 150	98.37 276	99.42 171	95.81 310	97.58 283	99.16 278	97.90 231	99.28 142	99.01 211	95.98 278	99.79 244	99.33 60	99.90 86	99.51 162

OPM-MVS		98.56 175	98.32 205	99.25 104	99.41 174	98.73 95	97.13 338	99.18 271	97.10 311	98.75 253	98.92 235	98.18 114	99.65 350	96.68 284	99.56 267	99.37 236
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 247	98.08 239	98.04 311	99.41 174	94.59 362	94.59 457	99.40 186	97.50 267	98.82 241	98.83 261	96.83 228	99.84 174	97.50 211	99.81 134	99.71 63

E2		98.70 144	98.68 138	98.73 210	99.40 176	97.10 246	97.48 296	99.57 101	98.09 216	99.00 196	99.20 151	97.90 139	99.67 330	97.73 192	99.77 162	99.43 207

E3		98.69 148	98.68 138	98.73 210	99.40 176	97.10 246	97.48 296	99.57 101	98.09 216	99.00 196	99.20 151	97.90 139	99.67 330	97.73 192	99.77 162	99.43 207

test_one_0601					99.39 178	99.20 40		99.31 223	98.49 174	98.66 263	99.02 200	97.64 166

mvsany_test3		98.87 109	98.92 100	98.74 208	99.38 179	96.94 257	98.58 122	99.10 288	96.49 344	99.96 4	99.81 8	98.18 114	99.45 422	98.97 90	99.79 151	99.83 33

patch_mono-2		98.51 189	98.63 148	98.17 298	99.38 179	94.78 353	97.36 314	99.69 54	98.16 207	98.49 290	99.29 126	97.06 212	99.97 7	98.29 142	99.91 78	99.76 56

test2506		92.39 440	91.89 442	93.89 457	99.38 179	82.28 488	99.32 26	66.03 495	99.08 112	98.77 250	99.57 49	66.26 481	99.84 174	98.71 111	99.95 38	99.54 142

ECVR-MVS		96.42 360	96.61 346	95.85 428	99.38 179	88.18 466	99.22 45	86.00 489	99.08 112	99.36 123	99.57 49	88.47 403	99.82 205	98.52 126	99.95 38	99.54 142

casdiffmvs		98.95 97	99.00 92	98.81 185	99.38 179	97.33 218	97.82 240	99.57 101	99.17 92	99.35 125	99.17 162	98.35 91	99.69 316	98.46 128	99.73 185	99.41 215
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		98.96 96	99.02 88	98.76 202	99.38 179	97.26 229	98.49 139	99.50 132	98.86 139	99.19 166	99.06 188	98.23 106	99.69 316	98.71 111	99.76 177	99.33 256

TranMVSNet+NR-MVSNet		99.17 53	99.07 83	99.46 63	99.37 185	98.87 85	98.39 156	99.42 179	99.42 56	99.36 123	99.06 188	98.38 86	99.95 26	98.34 139	99.90 86	99.57 123

fmvsm_s_conf0.5_n_6		99.08 77	99.21 58	98.69 216	99.36 186	96.51 281	97.62 274	99.68 60	98.43 177	99.85 27	99.10 180	99.12 23	99.88 115	99.77 22	99.92 69	99.67 76

tttt0517		95.64 387	94.98 397	97.64 349	99.36 186	93.81 395	98.72 103	90.47 481	98.08 218	98.67 261	98.34 347	73.88 467	99.92 65	97.77 185	99.51 283	99.20 295

test_part2					99.36 186	99.10 66				99.05 189

v1144		98.60 169	98.66 143	98.41 269	99.36 186	95.90 304	97.58 283	99.34 210	97.51 266	99.27 144	99.15 168	96.34 259	99.80 231	99.47 54	99.93 56	99.51 162

CP-MVS		98.70 144	98.42 186	99.52 45	99.36 186	99.12 63	98.72 103	99.36 198	97.54 264	98.30 303	98.40 339	97.86 147	99.89 97	96.53 305	99.72 193	99.56 129

diffmvs_AUTHOR		98.50 190	98.59 157	98.23 293	99.35 191	95.48 323	96.61 365	99.60 84	98.37 179	98.90 223	99.00 215	97.37 193	99.76 267	98.22 146	99.85 107	99.46 194

Test_1112_low_res		96.99 339	96.55 350	98.31 282	99.35 191	95.47 326	95.84 415	99.53 123	91.51 454	96.80 408	98.48 332	91.36 376	99.83 192	96.58 294	99.53 277	99.62 90

DeepC-MVS	97.60 4	98.97 94	98.93 99	99.10 128	99.35 191	97.98 162	98.01 209	99.46 155	97.56 260	99.54 79	99.50 69	98.97 28	99.84 174	98.06 158	99.92 69	99.49 173
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 316	96.86 328	98.58 237	99.34 194	96.32 290	96.75 357	99.58 94	93.14 435	96.89 403	97.48 405	92.11 368	99.86 143	96.91 256	99.54 273	99.57 123

reproduce_model		99.15 58	98.97 96	99.67 4	99.33 195	99.44 10	98.15 180	99.47 151	99.12 97	99.52 88	99.32 121	98.31 94	99.90 81	97.78 184	99.73 185	99.66 78

MVSMamba_PlusPlus		98.83 119	98.98 95	98.36 277	99.32 196	96.58 277	98.90 83	99.41 183	99.75 11	98.72 256	99.50 69	96.17 264	99.94 42	99.27 65	99.78 156	98.57 399

fmvsm_s_conf0.5_n_4		99.01 87	99.22 55	98.38 273	99.31 197	95.48 323	97.56 285	99.73 44	98.87 137	99.75 45	99.27 129	98.80 40	99.86 143	99.80 17	99.90 86	99.81 40

SF-MVS		98.53 184	98.27 213	99.32 91	99.31 197	98.75 91	98.19 174	99.41 183	96.77 333	98.83 238	98.90 241	97.80 153	99.82 205	95.68 351	99.52 280	99.38 234

CPTT-MVS		97.84 274	97.36 298	99.27 99	99.31 197	98.46 115	98.29 163	99.27 246	94.90 403	97.83 345	98.37 343	94.90 309	99.84 174	93.85 402	99.54 273	99.51 162

UnsupCasMVSNet_eth		97.89 263	97.60 284	98.75 204	99.31 197	97.17 241	97.62 274	99.35 204	98.72 152	98.76 252	98.68 297	92.57 361	99.74 283	97.76 189	95.60 472	99.34 250

fmvsm_s_conf0.5_n_7		98.83 119	99.04 85	98.20 295	99.30 201	94.83 351	97.23 326	99.36 198	98.64 155	99.84 30	99.43 89	98.10 123	99.91 74	99.56 41	99.96 28	99.87 22

pmmvs-eth3d		98.47 193	98.34 199	98.86 174	99.30 201	97.76 189	97.16 336	99.28 243	95.54 385	99.42 110	99.19 154	97.27 200	99.63 357	97.89 173	99.97 21	99.20 295

mamv4		99.44 19	99.39 28	99.58 21	99.30 201	99.74 2	99.04 68	99.81 31	99.77 10	99.82 34	99.57 49	97.82 151	99.98 4	99.53 48	99.89 92	99.01 332

viewcassd2359sk11		98.55 179	98.51 167	98.67 219	99.29 204	96.99 252	97.39 307	99.54 119	97.73 243	98.81 243	99.08 186	97.55 175	99.66 343	97.52 210	99.67 223	99.36 243

SymmetryMVS		98.05 249	97.71 274	99.09 132	99.29 204	97.83 178	98.28 164	97.64 407	99.24 76	98.80 245	98.85 254	89.76 390	99.94 42	98.04 160	99.50 291	99.49 173

Anonymous20231211		99.27 38	99.27 48	99.26 101	99.29 204	98.18 137	99.49 12	99.51 129	99.70 16	99.80 38	99.68 25	96.84 226	99.83 192	99.21 71	99.91 78	99.77 50

viewmanbaseed2359cas		98.58 173	98.54 163	98.70 214	99.28 207	97.13 245	97.47 300	99.55 114	97.55 262	98.96 210	98.92 235	97.77 155	99.59 374	97.59 203	99.77 162	99.39 225

UnsupCasMVSNet_bld		97.30 314	96.92 324	98.45 264	99.28 207	96.78 268	96.20 391	99.27 246	95.42 389	98.28 307	98.30 351	93.16 347	99.71 301	94.99 365	97.37 445	98.87 360

EC-MVSNet		99.09 73	99.05 84	99.20 110	99.28 207	98.93 80	99.24 44	99.84 22	99.08 112	98.12 320	98.37 343	98.72 49	99.90 81	99.05 84	99.77 162	98.77 377

mamba_0408		98.80 126	98.88 105	98.55 247	99.27 210	96.50 282	98.00 210	99.60 84	98.93 129	99.22 161	98.84 259	98.59 66	99.89 97	97.74 190	99.72 193	99.27 273

SSM_04072		98.80 126	98.88 105	98.56 245	99.27 210	96.50 282	98.00 210	99.60 84	98.93 129	99.22 161	98.84 259	98.59 66	99.90 81	97.74 190	99.72 193	99.27 273

SSM_0407		98.86 113	98.96 98	98.55 247	99.27 210	96.50 282	98.04 201	99.66 65	99.09 108	99.22 161	99.02 200	98.79 42	99.87 134	97.87 178	99.72 193	99.27 273

reproduce-ours		99.09 73	98.90 102	99.67 4	99.27 210	99.49 6	98.00 210	99.42 179	99.05 115	99.48 96	99.27 129	98.29 96	99.89 97	97.61 200	99.71 202	99.62 90

our_new_method		99.09 73	98.90 102	99.67 4	99.27 210	99.49 6	98.00 210	99.42 179	99.05 115	99.48 96	99.27 129	98.29 96	99.89 97	97.61 200	99.71 202	99.62 90

DPE-MVS		98.59 171	98.26 214	99.57 22	99.27 210	99.15 53	97.01 341	99.39 188	97.67 247	99.44 105	98.99 217	97.53 179	99.89 97	95.40 359	99.68 217	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		97.85 273	98.18 226	96.87 397	99.27 210	91.16 446	95.53 425	99.25 252	99.10 105	99.41 112	99.35 109	93.10 349	99.96 14	98.65 115	99.94 50	99.49 173

v1192		98.60 169	98.66 143	98.41 269	99.27 210	95.88 305	97.52 290	99.36 198	97.41 279	99.33 130	99.20 151	96.37 257	99.82 205	99.57 39	99.92 69	99.55 136

N_pmnet		97.63 287	97.17 308	98.99 151	99.27 210	97.86 175	95.98 402	93.41 470	95.25 394	99.47 100	98.90 241	95.63 290	99.85 156	96.91 256	99.73 185	99.27 273

viewdifsd2359ckpt13		98.39 207	98.29 209	98.70 214	99.26 219	97.19 237	97.51 292	99.48 142	96.94 320	98.58 277	98.82 264	97.47 188	99.55 390	97.21 231	99.33 319	99.34 250

FPMVS		93.44 426	92.23 433	97.08 385	99.25 220	97.86 175	95.61 422	97.16 419	92.90 439	93.76 472	98.65 304	75.94 465	95.66 486	79.30 484	97.49 438	97.73 450

ME-MVS		98.61 167	98.33 204	99.44 66	99.24 221	98.93 80	97.45 302	99.06 293	98.14 213	99.06 181	98.77 274	96.97 220	99.82 205	96.67 285	99.64 234	99.58 115

new-patchmatchnet		98.35 210	98.74 123	97.18 380	99.24 221	92.23 428	96.42 378	99.48 142	98.30 187	99.69 56	99.53 65	97.44 189	99.82 205	98.84 100	99.77 162	99.49 173

MCST-MVS		98.00 254	97.63 282	99.10 128	99.24 221	98.17 138	96.89 350	98.73 357	95.66 380	97.92 336	97.70 393	97.17 207	99.66 343	96.18 327	99.23 338	99.47 192

UniMVSNet (Re)		98.87 109	98.71 132	99.35 80	99.24 221	98.73 95	97.73 258	99.38 190	98.93 129	99.12 173	98.73 283	96.77 234	99.86 143	98.63 117	99.80 145	99.46 194

jason		97.45 301	97.35 299	97.76 332	99.24 221	93.93 389	95.86 412	98.42 378	94.24 418	98.50 289	98.13 361	94.82 313	99.91 74	97.22 230	99.73 185	99.43 207
jason: jason.
IterMVS		97.73 279	98.11 235	96.57 407	99.24 221	90.28 455	95.52 427	99.21 261	98.86 139	99.33 130	99.33 116	93.11 348	99.94 42	98.49 127	99.94 50	99.48 184
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 179	98.62 150	98.32 280	99.22 227	95.58 316	97.51 292	99.45 159	97.16 308	99.45 104	99.24 142	96.12 268	99.85 156	99.60 37	99.88 94	99.55 136

ITE_SJBPF				98.87 172	99.22 227	98.48 114		99.35 204	97.50 267	98.28 307	98.60 315	97.64 166	99.35 437	93.86 401	99.27 330	98.79 375

h-mvs33		97.77 277	97.33 301	99.10 128	99.21 229	97.84 177	98.35 160	98.57 369	99.11 98	98.58 277	99.02 200	88.65 401	99.96 14	98.11 153	96.34 461	99.49 173

v144192		98.54 182	98.57 159	98.45 264	99.21 229	95.98 302	97.63 273	99.36 198	97.15 310	99.32 136	99.18 158	95.84 285	99.84 174	99.50 51	99.91 78	99.54 142

APDe-MVS		98.99 90	98.79 119	99.60 16	99.21 229	99.15 53	98.87 88	99.48 142	97.57 258	99.35 125	99.24 142	97.83 148	99.89 97	97.88 176	99.70 209	99.75 60
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 100	98.81 118	99.28 96	99.21 229	98.45 116	98.46 144	99.33 216	99.63 29	99.48 96	99.15 168	97.23 203	99.75 277	97.17 233	99.66 231	99.63 89

SR-MVS-dyc-post		98.81 124	98.55 161	99.57 22	99.20 233	99.38 13	98.48 142	99.30 231	98.64 155	98.95 211	98.96 227	97.49 186	99.86 143	96.56 300	99.39 310	99.45 199

RE-MVS-def			98.58 158		99.20 233	99.38 13	98.48 142	99.30 231	98.64 155	98.95 211	98.96 227	97.75 157		96.56 300	99.39 310	99.45 199

v1921920		98.54 182	98.60 155	98.38 273	99.20 233	95.76 312	97.56 285	99.36 198	97.23 302	99.38 118	99.17 162	96.02 271	99.84 174	99.57 39	99.90 86	99.54 142

E3new		98.41 198	98.34 199	98.62 229	99.19 236	96.90 260	97.32 317	99.50 132	97.40 281	98.63 266	98.92 235	97.21 205	99.65 350	97.34 222	99.52 280	99.31 263

thisisatest0530		95.27 395	94.45 406	97.74 335	99.19 236	94.37 366	97.86 236	90.20 482	97.17 307	98.22 310	97.65 395	73.53 468	99.90 81	96.90 261	99.35 316	98.95 345

Anonymous20240529		98.93 100	98.87 108	99.12 124	99.19 236	98.22 135	99.01 70	98.99 311	99.25 75	99.54 79	99.37 104	97.04 213	99.80 231	97.89 173	99.52 280	99.35 248

APD-MVS_3200maxsize		98.84 116	98.61 154	99.53 39	99.19 236	99.27 28	98.49 139	99.33 216	98.64 155	99.03 194	98.98 222	97.89 143	99.85 156	96.54 304	99.42 307	99.46 194

HQP_MVS		97.99 257	97.67 276	98.93 164	99.19 236	97.65 197	97.77 249	99.27 246	98.20 201	97.79 348	97.98 375	94.90 309	99.70 308	94.42 383	99.51 283	99.45 199

plane_prior7					99.19 236	97.87 174

ab-mvs		98.41 198	98.36 196	98.59 236	99.19 236	97.23 230	99.32 26	98.81 343	97.66 248	98.62 269	99.40 97	96.82 229	99.80 231	95.88 338	99.51 283	98.75 380

F-COLMAP		97.30 314	96.68 341	99.14 122	99.19 236	98.39 118	97.27 325	99.30 231	92.93 438	96.62 416	98.00 373	95.73 288	99.68 326	92.62 429	98.46 406	99.35 248

viewdifsd2359ckpt09		98.13 242	97.92 258	98.77 200	99.18 244	97.35 216	97.29 321	99.53 123	95.81 377	98.09 323	98.47 333	96.34 259	99.66 343	97.02 246	99.51 283	99.29 269

SR-MVS		98.71 139	98.43 184	99.57 22	99.18 244	99.35 17	98.36 159	99.29 239	98.29 190	98.88 230	98.85 254	97.53 179	99.87 134	96.14 329	99.31 323	99.48 184

UniMVSNet_NR-MVSNet		98.86 113	98.68 138	99.40 72	99.17 246	98.74 92	97.68 263	99.40 186	99.14 96	99.06 181	98.59 316	96.71 240	99.93 54	98.57 120	99.77 162	99.53 155

LF4IMVS		97.90 261	97.69 275	98.52 255	99.17 246	97.66 196	97.19 335	99.47 151	96.31 354	97.85 344	98.20 358	96.71 240	99.52 402	94.62 375	99.72 193	98.38 416

SMA-MVS		98.40 201	98.03 244	99.51 49	99.16 248	99.21 34	98.05 199	99.22 260	94.16 420	98.98 201	99.10 180	97.52 181	99.79 244	96.45 310	99.64 234	99.53 155
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		98.82 122	98.63 148	99.39 73	99.16 248	98.74 92	97.54 288	99.25 252	98.84 143	99.06 181	98.76 280	96.76 236	99.93 54	98.57 120	99.77 162	99.50 166

NR-MVSNet		98.95 97	98.82 116	99.36 74	99.16 248	98.72 97	99.22 45	99.20 263	99.10 105	99.72 48	98.76 280	96.38 256	99.86 143	98.00 165	99.82 128	99.50 166

MVS_111021_LR		98.30 219	98.12 234	98.83 181	99.16 248	98.03 157	96.09 399	99.30 231	97.58 257	98.10 322	98.24 354	98.25 104	99.34 438	96.69 283	99.65 232	99.12 318

DSMNet-mixed		97.42 304	97.60 284	96.87 397	99.15 252	91.46 435	98.54 127	99.12 285	92.87 440	97.58 361	99.63 39	96.21 263	99.90 81	95.74 347	99.54 273	99.27 273

D2MVS		97.84 274	97.84 265	97.83 324	99.14 253	94.74 355	96.94 345	98.88 327	95.84 375	98.89 226	98.96 227	94.40 325	99.69 316	97.55 205	99.95 38	99.05 324

pmmvs5		97.64 286	97.49 290	98.08 306	99.14 253	95.12 341	96.70 360	99.05 297	93.77 427	98.62 269	98.83 261	93.23 345	99.75 277	98.33 141	99.76 177	99.36 243

SPE-MVS-test		99.13 67	99.09 80	99.26 101	99.13 255	98.97 74	99.31 30	99.88 14	99.44 53	98.16 315	98.51 325	98.64 60	99.93 54	98.91 94	99.85 107	98.88 359

VDD-MVS		98.56 175	98.39 191	99.07 135	99.13 255	98.07 152	98.59 121	97.01 422	99.59 37	99.11 174	99.27 129	94.82 313	99.79 244	98.34 139	99.63 241	99.34 250

save fliter					99.11 257	97.97 163	96.53 370	99.02 305	98.24 193

APD-MVS		98.10 243	97.67 276	99.42 68	99.11 257	98.93 80	97.76 252	99.28 243	94.97 401	98.72 256	98.77 274	97.04 213	99.85 156	93.79 403	99.54 273	99.49 173
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 148	98.71 132	98.62 229	99.10 259	96.37 288	97.23 326	98.87 329	99.20 83	99.19 166	98.99 217	97.30 197	99.85 156	98.77 106	99.79 151	99.65 83

EI-MVSNet		98.40 201	98.51 167	98.04 311	99.10 259	94.73 356	97.20 331	98.87 329	98.97 124	99.06 181	99.02 200	96.00 273	99.80 231	98.58 118	99.82 128	99.60 100

CVMVSNet		96.25 366	97.21 307	93.38 464	99.10 259	80.56 492	97.20 331	98.19 389	96.94 320	99.00 196	99.02 200	89.50 394	99.80 231	96.36 316	99.59 255	99.78 47

EI-MVSNet-Vis-set		98.68 154	98.70 135	98.63 227	99.09 262	96.40 287	97.23 326	98.86 334	99.20 83	99.18 170	98.97 224	97.29 199	99.85 156	98.72 110	99.78 156	99.64 84

HPM-MVS++		98.10 243	97.64 281	99.48 57	99.09 262	99.13 61	97.52 290	98.75 354	97.46 275	96.90 402	97.83 385	96.01 272	99.84 174	95.82 345	99.35 316	99.46 194

DP-MVS Recon		97.33 312	96.92 324	98.57 240	99.09 262	97.99 159	96.79 353	99.35 204	93.18 434	97.71 352	98.07 369	95.00 308	99.31 442	93.97 396	99.13 354	98.42 413

MVS_111021_HR		98.25 228	98.08 239	98.75 204	99.09 262	97.46 210	95.97 403	99.27 246	97.60 256	97.99 333	98.25 353	98.15 120	99.38 433	96.87 264	99.57 264	99.42 212

BP-MVS1		97.40 306	96.97 320	98.71 213	99.07 266	96.81 264	98.34 162	97.18 417	98.58 166	98.17 312	98.61 313	84.01 436	99.94 42	98.97 90	99.78 156	99.37 236

9.14			97.78 267		99.07 266		97.53 289	99.32 218	95.53 386	98.54 285	98.70 293	97.58 172	99.76 267	94.32 388	99.46 296

PAPM_NR		96.82 346	96.32 357	98.30 283	99.07 266	96.69 272	97.48 296	98.76 351	95.81 377	96.61 417	96.47 431	94.12 334	99.17 455	90.82 456	97.78 432	99.06 323

TAMVS		98.24 229	98.05 242	98.80 188	99.07 266	97.18 239	97.88 232	98.81 343	96.66 338	99.17 172	99.21 149	94.81 315	99.77 261	96.96 254	99.88 94	99.44 203

CLD-MVS		97.49 297	97.16 309	98.48 261	99.07 266	97.03 250	94.71 450	99.21 261	94.46 412	98.06 326	97.16 417	97.57 173	99.48 414	94.46 380	99.78 156	98.95 345
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 78	99.24 106	99.06 271	99.15 53	99.36 22	99.88 14	99.36 64	98.21 311	98.46 334	98.68 57	99.93 54	99.03 86	99.85 107	98.64 392

thres100view900		94.19 412	93.67 417	95.75 431	99.06 271	91.35 439	98.03 203	94.24 465	98.33 183	97.40 377	94.98 461	79.84 452	99.62 360	83.05 477	98.08 423	96.29 472

thres600view7		94.45 407	93.83 414	96.29 415	99.06 271	91.53 434	97.99 217	94.24 465	98.34 182	97.44 375	95.01 459	79.84 452	99.67 330	84.33 475	98.23 412	97.66 453

plane_prior1					99.05 274

YYNet1		97.60 288	97.67 276	97.39 373	99.04 275	93.04 412	95.27 435	98.38 381	97.25 296	98.92 221	98.95 231	95.48 297	99.73 290	96.99 250	98.74 387	99.41 215

MDA-MVSNet_test_wron		97.60 288	97.66 279	97.41 372	99.04 275	93.09 408	95.27 435	98.42 378	97.26 295	98.88 230	98.95 231	95.43 298	99.73 290	97.02 246	98.72 389	99.41 215

MIMVSNet		96.62 353	96.25 361	97.71 339	99.04 275	94.66 359	99.16 54	96.92 428	97.23 302	97.87 341	99.10 180	86.11 417	99.65 350	91.65 440	99.21 342	98.82 364

FE-MVSNET3		97.37 308	97.13 313	98.11 302	99.03 278	95.40 329	94.47 460	98.99 311	96.87 326	97.97 334	97.81 386	92.12 367	99.75 277	97.49 216	99.43 306	99.16 313

icg_test_0407_2		98.20 234	98.38 193	97.65 346	99.03 278	94.03 380	95.78 417	99.45 159	98.16 207	99.06 181	98.71 286	98.27 100	99.68 326	97.50 211	99.45 298	99.22 290

IMVS_0407		98.39 207	98.64 146	97.66 344	99.03 278	94.03 380	98.10 189	99.45 159	98.16 207	99.06 181	98.71 286	98.27 100	99.71 301	97.50 211	99.45 298	99.22 290

IMVS_0404		98.07 247	98.20 221	97.69 340	99.03 278	94.03 380	96.67 361	99.45 159	98.16 207	98.03 330	98.71 286	96.80 232	99.82 205	97.50 211	99.45 298	99.22 290

IMVS_0403		98.34 211	98.56 160	97.66 344	99.03 278	94.03 380	97.98 218	99.45 159	98.16 207	98.89 226	98.71 286	97.90 139	99.74 283	97.50 211	99.45 298	99.22 290

PatchMatch-RL		97.24 320	96.78 335	98.61 233	99.03 278	97.83 178	96.36 381	99.06 293	93.49 432	97.36 381	97.78 387	95.75 287	99.49 411	93.44 412	98.77 386	98.52 401

viewmambaseed2359dif		98.19 235	98.26 214	97.99 314	99.02 284	95.03 344	96.59 367	99.53 123	96.21 358	99.00 196	98.99 217	97.62 168	99.61 367	97.62 199	99.72 193	99.33 256

GDP-MVS		97.50 294	97.11 314	98.67 219	99.02 284	96.85 262	98.16 179	99.71 47	98.32 185	98.52 288	98.54 320	83.39 440	99.95 26	98.79 102	99.56 267	99.19 300

ZD-MVS					99.01 286	98.84 86		99.07 292	94.10 422	98.05 328	98.12 363	96.36 258	99.86 143	92.70 428	99.19 346

CDPH-MVS		97.26 317	96.66 344	99.07 135	99.00 287	98.15 139	96.03 401	99.01 308	91.21 458	97.79 348	97.85 384	96.89 224	99.69 316	92.75 426	99.38 313	99.39 225

diffmvs		98.22 230	98.24 218	98.17 298	99.00 287	95.44 327	96.38 380	99.58 94	97.79 240	98.53 286	98.50 329	96.76 236	99.74 283	97.95 171	99.64 234	99.34 250
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		98.40 201	98.19 225	99.03 145	99.00 287	97.65 197	96.85 351	98.94 314	98.57 168	98.89 226	98.50 329	95.60 291	99.85 156	97.54 207	99.85 107	99.59 107

plane_prior6					98.99 290	97.70 195						94.90 309

xiu_mvs_v1_base_debu		97.86 268	98.17 227	96.92 394	98.98 291	93.91 390	96.45 374	99.17 275	97.85 235	98.41 297	97.14 419	98.47 76	99.92 65	98.02 162	99.05 360	96.92 465

xiu_mvs_v1_base		97.86 268	98.17 227	96.92 394	98.98 291	93.91 390	96.45 374	99.17 275	97.85 235	98.41 297	97.14 419	98.47 76	99.92 65	98.02 162	99.05 360	96.92 465

xiu_mvs_v1_base_debi		97.86 268	98.17 227	96.92 394	98.98 291	93.91 390	96.45 374	99.17 275	97.85 235	98.41 297	97.14 419	98.47 76	99.92 65	98.02 162	99.05 360	96.92 465

MVP-Stereo		98.08 246	97.92 258	98.57 240	98.96 294	96.79 265	97.90 230	99.18 271	96.41 350	98.46 292	98.95 231	95.93 282	99.60 370	96.51 306	98.98 374	99.31 263
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 201	98.68 138	97.54 361	98.96 294	97.99 159	97.88 232	99.36 198	98.20 201	99.63 67	99.04 197	98.76 45	95.33 488	96.56 300	99.74 182	99.31 263
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	98.94 296	97.76 189		98.76 351	87.58 475	96.75 410	98.10 365	94.80 316	99.78 255	92.73 427	99.00 369	99.20 295

USDC		97.41 305	97.40 294	97.44 370	98.94 296	93.67 400	95.17 439	99.53 123	94.03 424	98.97 205	99.10 180	95.29 300	99.34 438	95.84 344	99.73 185	99.30 267

tfpn200view9		94.03 416	93.44 419	95.78 430	98.93 298	91.44 437	97.60 280	94.29 463	97.94 227	97.10 387	94.31 468	79.67 454	99.62 360	83.05 477	98.08 423	96.29 472

testdata				98.09 303	98.93 298	95.40 329		98.80 345	90.08 466	97.45 374	98.37 343	95.26 301	99.70 308	93.58 408	98.95 377	99.17 308

thres400		94.14 414	93.44 419	96.24 418	98.93 298	91.44 437	97.60 280	94.29 463	97.94 227	97.10 387	94.31 468	79.67 454	99.62 360	83.05 477	98.08 423	97.66 453

TAPA-MVS	96.21 11	96.63 352	95.95 363	98.65 221	98.93 298	98.09 146	96.93 347	99.28 243	83.58 481	98.13 319	97.78 387	96.13 266	99.40 429	93.52 409	99.29 328	98.45 406
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 302	96.93 258	95.54 424	98.78 348	85.72 478	96.86 405	98.11 364	94.43 323			99.10 359	99.23 285

PVSNet_BlendedMVS		97.55 293	97.53 287	97.60 353	98.92 302	93.77 397	96.64 363	99.43 173	94.49 410	97.62 357	99.18 158	96.82 229	99.67 330	94.73 372	99.93 56	99.36 243

PVSNet_Blended		96.88 342	96.68 341	97.47 368	98.92 302	93.77 397	94.71 450	99.43 173	90.98 460	97.62 357	97.36 413	96.82 229	99.67 330	94.73 372	99.56 267	98.98 338

MSDG		97.71 281	97.52 288	98.28 285	98.91 305	96.82 263	94.42 461	99.37 194	97.65 249	98.37 302	98.29 352	97.40 191	99.33 440	94.09 394	99.22 339	98.68 390

Anonymous202405211		97.90 261	97.50 289	99.08 133	98.90 306	98.25 129	98.53 128	96.16 440	98.87 137	99.11 174	98.86 251	90.40 386	99.78 255	97.36 221	99.31 323	99.19 300

原ACMM1				98.35 278	98.90 306	96.25 292		98.83 342	92.48 444	96.07 434	98.10 365	95.39 299	99.71 301	92.61 430	98.99 371	99.08 320

GBi-Net		98.65 159	98.47 178	99.17 115	98.90 306	98.24 130	99.20 48	99.44 167	98.59 163	98.95 211	99.55 57	94.14 331	99.86 143	97.77 185	99.69 212	99.41 215

test1		98.65 159	98.47 178	99.17 115	98.90 306	98.24 130	99.20 48	99.44 167	98.59 163	98.95 211	99.55 57	94.14 331	99.86 143	97.77 185	99.69 212	99.41 215

FMVSNet2		98.49 191	98.40 188	98.75 204	98.90 306	97.14 244	98.61 119	99.13 284	98.59 163	99.19 166	99.28 127	94.14 331	99.82 205	97.97 169	99.80 145	99.29 269

OMC-MVS		97.88 265	97.49 290	99.04 144	98.89 311	98.63 99	96.94 345	99.25 252	95.02 399	98.53 286	98.51 325	97.27 200	99.47 417	93.50 411	99.51 283	99.01 332

VortexMVS		97.98 258	98.31 206	97.02 388	98.88 312	91.45 436	98.03 203	99.47 151	98.65 154	99.55 77	99.47 79	91.49 375	99.81 222	99.32 61	99.91 78	99.80 42

MVSFormer		98.26 225	98.43 184	97.77 329	98.88 312	93.89 393	99.39 20	99.56 110	99.11 98	98.16 315	98.13 361	93.81 339	99.97 7	99.26 66	99.57 264	99.43 207

lupinMVS		97.06 332	96.86 328	97.65 346	98.88 312	93.89 393	95.48 428	97.97 395	93.53 430	98.16 315	97.58 399	93.81 339	99.91 74	96.77 272	99.57 264	99.17 308

dmvs_re		95.98 376	95.39 385	97.74 335	98.86 315	97.45 211	98.37 158	95.69 452	97.95 225	96.56 418	95.95 440	90.70 383	97.68 482	88.32 465	96.13 465	98.11 428

DELS-MVS		98.27 223	98.20 221	98.48 261	98.86 315	96.70 271	95.60 423	99.20 263	97.73 243	98.45 293	98.71 286	97.50 183	99.82 205	98.21 147	99.59 255	98.93 350
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		97.89 263	97.98 249	97.60 353	98.86 315	94.35 367	96.21 390	99.44 167	97.45 277	99.06 181	98.88 248	97.99 133	99.28 448	94.38 387	99.58 260	99.18 304

LCM-MVSNet-Re		98.64 161	98.48 176	99.11 126	98.85 318	98.51 112	98.49 139	99.83 25	98.37 179	99.69 56	99.46 81	98.21 111	99.92 65	94.13 393	99.30 326	98.91 354

pmmvs4		97.58 291	97.28 302	98.51 256	98.84 319	96.93 258	95.40 432	98.52 373	93.60 429	98.61 271	98.65 304	95.10 305	99.60 370	96.97 253	99.79 151	98.99 337

NP-MVS					98.84 319	97.39 215					96.84 422

sss		97.21 322	96.93 322	98.06 308	98.83 321	95.22 337	96.75 357	98.48 375	94.49 410	97.27 383	97.90 381	92.77 357	99.80 231	96.57 296	99.32 321	99.16 313

PVSNet	93.40 17	95.67 385	95.70 369	95.57 435	98.83 321	88.57 462	92.50 479	97.72 400	92.69 442	96.49 426	96.44 432	93.72 342	99.43 425	93.61 406	99.28 329	98.71 383

MVE	83.40 22	92.50 439	91.92 441	94.25 451	98.83 321	91.64 433	92.71 478	83.52 491	95.92 373	86.46 489	95.46 453	95.20 302	95.40 487	80.51 482	98.64 398	95.73 480
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 420	93.91 412	93.39 463	98.82 324	81.72 490	97.76 252	95.28 454	98.60 162	96.54 419	96.66 426	65.85 484	99.62 360	96.65 289	98.99 371	98.82 364

ambc				98.24 290	98.82 324	95.97 303	98.62 117	99.00 310		99.27 144	99.21 149	96.99 218	99.50 408	96.55 303	99.50 291	99.26 279

旧先验1					98.82 324	97.45 211		98.76 351			98.34 347	95.50 296			99.01 368	99.23 285

test_vis1_rt		97.75 278	97.72 273	97.83 324	98.81 327	96.35 289	97.30 320	99.69 54	94.61 408	97.87 341	98.05 370	96.26 262	98.32 476	98.74 108	98.18 415	98.82 364

WTY-MVS		96.67 350	96.27 360	97.87 322	98.81 327	94.61 361	96.77 355	97.92 397	94.94 402	97.12 386	97.74 390	91.11 379	99.82 205	93.89 399	98.15 419	99.18 304

3Dnovator+	97.89 3	98.69 148	98.51 167	99.24 106	98.81 327	98.40 117	99.02 69	99.19 267	98.99 121	98.07 325	99.28 127	97.11 211	99.84 174	96.84 267	99.32 321	99.47 192

QAPM		97.31 313	96.81 334	98.82 183	98.80 330	97.49 205	99.06 65	99.19 267	90.22 464	97.69 354	99.16 164	96.91 223	99.90 81	90.89 455	99.41 308	99.07 322

VNet		98.42 197	98.30 207	98.79 192	98.79 331	97.29 226	98.23 170	98.66 361	99.31 69	98.85 235	98.80 268	94.80 316	99.78 255	98.13 152	99.13 354	99.31 263

DPM-MVS		96.32 362	95.59 376	98.51 256	98.76 332	97.21 235	94.54 459	98.26 384	91.94 449	96.37 427	97.25 415	93.06 351	99.43 425	91.42 445	98.74 387	98.89 356

3Dnovator	98.27 2	98.81 124	98.73 125	99.05 142	98.76 332	97.81 186	99.25 43	99.30 231	98.57 168	98.55 283	99.33 116	97.95 136	99.90 81	97.16 234	99.67 223	99.44 203

PLC	94.65 16	96.51 355	95.73 368	98.85 175	98.75 334	97.91 171	96.42 378	99.06 293	90.94 461	95.59 441	97.38 411	94.41 324	99.59 374	90.93 453	98.04 428	99.05 324
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 344	96.75 337	97.08 385	98.74 335	93.33 406	96.71 359	98.26 384	96.72 335	98.44 294	97.37 412	95.20 302	99.47 417	91.89 435	97.43 442	98.44 409

hse-mvs2		97.46 299	97.07 315	98.64 223	98.73 336	97.33 218	97.45 302	97.64 407	99.11 98	98.58 277	97.98 375	88.65 401	99.79 244	98.11 153	97.39 444	98.81 369

CDS-MVSNet		97.69 282	97.35 299	98.69 216	98.73 336	97.02 251	96.92 349	98.75 354	95.89 374	98.59 275	98.67 299	92.08 369	99.74 283	96.72 278	99.81 134	99.32 259
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SD_0403		96.28 364	95.83 365	97.64 349	98.72 338	94.30 368	98.87 88	98.77 349	97.80 238	96.53 420	98.02 372	97.34 195	99.47 417	76.93 486	99.48 294	99.16 313

EIA-MVS		98.00 254	97.74 270	98.80 188	98.72 338	98.09 146	98.05 199	99.60 84	97.39 282	96.63 415	95.55 448	97.68 160	99.80 231	96.73 277	99.27 330	98.52 401

LFMVS		97.20 323	96.72 338	98.64 223	98.72 338	96.95 256	98.93 81	94.14 467	99.74 13	98.78 247	99.01 211	84.45 431	99.73 290	97.44 217	99.27 330	99.25 280

new_pmnet		96.99 339	96.76 336	97.67 342	98.72 338	94.89 349	95.95 407	98.20 387	92.62 443	98.55 283	98.54 320	94.88 312	99.52 402	93.96 397	99.44 305	98.59 398

Fast-Effi-MVS+		97.67 284	97.38 296	98.57 240	98.71 342	97.43 213	97.23 326	99.45 159	94.82 405	96.13 431	96.51 428	98.52 74	99.91 74	96.19 325	98.83 383	98.37 418

TEST9					98.71 342	98.08 150	95.96 405	99.03 302	91.40 455	95.85 438	97.53 401	96.52 249	99.76 267

train_agg		97.10 329	96.45 354	99.07 135	98.71 342	98.08 150	95.96 405	99.03 302	91.64 450	95.85 438	97.53 401	96.47 251	99.76 267	93.67 405	99.16 349	99.36 243

TSAR-MVS + GP.		98.18 237	97.98 249	98.77 200	98.71 342	97.88 173	96.32 384	98.66 361	96.33 352	99.23 160	98.51 325	97.48 187	99.40 429	97.16 234	99.46 296	99.02 331

FA-MVS(test-final)		96.99 339	96.82 332	97.50 365	98.70 346	94.78 353	99.34 23	96.99 423	95.07 398	98.48 291	99.33 116	88.41 404	99.65 350	96.13 331	98.92 380	98.07 431

AUN-MVS		96.24 368	95.45 381	98.60 235	98.70 346	97.22 233	97.38 309	97.65 405	95.95 372	95.53 448	97.96 379	82.11 448	99.79 244	96.31 318	97.44 441	98.80 374

our_test_3		97.39 307	97.73 272	96.34 413	98.70 346	89.78 458	94.61 456	98.97 313	96.50 343	99.04 191	98.85 254	95.98 278	99.84 174	97.26 228	99.67 223	99.41 215

ppachtmachnet_test		97.50 294	97.74 270	96.78 403	98.70 346	91.23 445	94.55 458	99.05 297	96.36 351	99.21 164	98.79 270	96.39 254	99.78 255	96.74 275	99.82 128	99.34 250

PCF-MVS	92.86 18	94.36 408	93.00 426	98.42 268	98.70 346	97.56 202	93.16 477	99.11 287	79.59 485	97.55 364	97.43 408	92.19 365	99.73 290	79.85 483	99.45 298	97.97 437
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 260	98.02 245	97.58 355	98.69 351	94.10 376	98.13 182	98.90 323	97.95 225	97.32 382	99.58 47	95.95 281	98.75 471	96.41 312	99.22 339	99.87 22

ETV-MVS		98.03 250	97.86 264	98.56 245	98.69 351	98.07 152	97.51 292	99.50 132	98.10 215	97.50 369	95.51 449	98.41 83	99.88 115	96.27 321	99.24 335	97.71 452

test_prior				98.95 160	98.69 351	97.95 167		99.03 302					99.59 374			99.30 267

mvsmamba		97.57 292	97.26 303	98.51 256	98.69 351	96.73 270	98.74 98	97.25 416	97.03 316	97.88 340	99.23 147	90.95 380	99.87 134	96.61 292	99.00 369	98.91 354

agg_prior					98.68 355	97.99 159		99.01 308		95.59 441			99.77 261

test_8					98.67 356	98.01 158	95.91 411	99.02 305	91.64 450	95.79 440	97.50 404	96.47 251	99.76 267

HQP-NCC					98.67 356		96.29 386		96.05 365	95.55 444

ACMP_Plane					98.67 356		96.29 386		96.05 365	95.55 444

CNVR-MVS		98.17 239	97.87 263	99.07 135	98.67 356	98.24 130	97.01 341	98.93 317	97.25 296	97.62 357	98.34 347	97.27 200	99.57 383	96.42 311	99.33 319	99.39 225

HQP-MVS		97.00 338	96.49 353	98.55 247	98.67 356	96.79 265	96.29 386	99.04 300	96.05 365	95.55 444	96.84 422	93.84 337	99.54 396	92.82 423	99.26 333	99.32 259

MM		98.22 230	97.99 248	98.91 168	98.66 361	96.97 253	97.89 231	94.44 461	99.54 41	98.95 211	99.14 171	93.50 343	99.92 65	99.80 17	99.96 28	99.85 30

test_fmvs1		97.72 280	97.94 255	97.07 387	98.66 361	92.39 423	97.68 263	99.81 31	95.20 397	99.54 79	99.44 86	91.56 374	99.41 428	99.78 21	99.77 162	99.40 224

balanced_conf03		98.63 163	98.72 127	98.38 273	98.66 361	96.68 273	98.90 83	99.42 179	98.99 121	98.97 205	99.19 154	95.81 286	99.85 156	98.77 106	99.77 162	98.60 395

thres200		93.72 422	93.14 424	95.46 439	98.66 361	91.29 441	96.61 365	94.63 460	97.39 282	96.83 406	93.71 471	79.88 451	99.56 386	82.40 480	98.13 420	95.54 481

wuyk23d		96.06 371	97.62 283	91.38 468	98.65 365	98.57 106	98.85 92	96.95 426	96.86 328	99.90 14	99.16 164	99.18 19	98.40 475	89.23 463	99.77 162	77.18 488

NCCC		97.86 268	97.47 293	99.05 142	98.61 366	98.07 152	96.98 343	98.90 323	97.63 250	97.04 392	97.93 380	95.99 277	99.66 343	95.31 360	98.82 385	99.43 207

DeepC-MVS_fast	96.85 6	98.30 219	98.15 231	98.75 204	98.61 366	97.23 230	97.76 252	99.09 290	97.31 290	98.75 253	98.66 302	97.56 174	99.64 354	96.10 332	99.55 271	99.39 225
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 424	92.09 435	97.75 333	98.60 368	94.40 365	97.32 317	95.26 455	97.56 260	96.79 409	95.50 450	53.57 493	99.77 261	95.26 361	98.97 375	99.08 320

thisisatest0515		94.12 415	93.16 423	96.97 392	98.60 368	92.90 413	93.77 473	90.61 480	94.10 422	96.91 399	95.87 443	74.99 466	99.80 231	94.52 378	99.12 357	98.20 424

GA-MVS		95.86 379	95.32 389	97.49 366	98.60 368	94.15 374	93.83 472	97.93 396	95.49 387	96.68 413	97.42 409	83.21 441	99.30 444	96.22 323	98.55 404	99.01 332

dmvs_testset		92.94 434	92.21 434	95.13 443	98.59 371	90.99 448	97.65 269	92.09 476	96.95 319	94.00 468	93.55 472	92.34 363	96.97 485	72.20 487	92.52 482	97.43 460

OPU-MVS				98.82 183	98.59 371	98.30 126	98.10 189				98.52 324	98.18 114	98.75 471	94.62 375	99.48 294	99.41 215

MSLP-MVS++		98.02 251	98.14 233	97.64 349	98.58 373	95.19 338	97.48 296	99.23 259	97.47 270	97.90 338	98.62 311	97.04 213	98.81 469	97.55 205	99.41 308	98.94 349

test12				98.93 164	98.58 373	97.83 178		98.66 361		96.53 420		95.51 295	99.69 316		99.13 354	99.27 273

CL-MVSNet_self_test		97.44 302	97.22 306	98.08 306	98.57 375	95.78 311	94.30 464	98.79 346	96.58 341	98.60 273	98.19 359	94.74 319	99.64 354	96.41 312	98.84 382	98.82 364

PS-MVSNAJ		97.08 331	97.39 295	96.16 424	98.56 376	92.46 421	95.24 437	98.85 337	97.25 296	97.49 370	95.99 439	98.07 124	99.90 81	96.37 314	98.67 397	96.12 477

CNLPA		97.17 326	96.71 339	98.55 247	98.56 376	98.05 156	96.33 383	98.93 317	96.91 324	97.06 390	97.39 410	94.38 326	99.45 422	91.66 439	99.18 348	98.14 427

xiu_mvs_v2_base		97.16 327	97.49 290	96.17 422	98.54 378	92.46 421	95.45 429	98.84 338	97.25 296	97.48 371	96.49 429	98.31 94	99.90 81	96.34 317	98.68 396	96.15 476

alignmvs		97.35 310	96.88 327	98.78 195	98.54 378	98.09 146	97.71 259	97.69 402	99.20 83	97.59 360	95.90 442	88.12 406	99.55 390	98.18 149	98.96 376	98.70 386

FE-MVS		95.66 386	94.95 399	97.77 329	98.53 380	95.28 334	99.40 19	96.09 443	93.11 436	97.96 335	99.26 135	79.10 458	99.77 261	92.40 432	98.71 391	98.27 422

Effi-MVS+		98.02 251	97.82 266	98.62 229	98.53 380	97.19 237	97.33 316	99.68 60	97.30 291	96.68 413	97.46 407	98.56 72	99.80 231	96.63 290	98.20 414	98.86 361

baseline1		95.96 377	95.44 382	97.52 363	98.51 382	93.99 387	98.39 156	96.09 443	98.21 197	98.40 301	97.76 389	86.88 409	99.63 357	95.42 358	89.27 485	98.95 345

MVS_Test		98.18 237	98.36 196	97.67 342	98.48 383	94.73 356	98.18 175	99.02 305	97.69 246	98.04 329	99.11 177	97.22 204	99.56 386	98.57 120	98.90 381	98.71 383

MGCFI-Net		98.34 211	98.28 210	98.51 256	98.47 384	97.59 201	98.96 77	99.48 142	99.18 91	97.40 377	95.50 450	98.66 58	99.50 408	98.18 149	98.71 391	98.44 409

BH-RMVSNet		96.83 344	96.58 349	97.58 355	98.47 384	94.05 377	96.67 361	97.36 411	96.70 337	97.87 341	97.98 375	95.14 304	99.44 424	90.47 458	98.58 403	99.25 280

sasdasda		98.34 211	98.26 214	98.58 237	98.46 386	97.82 183	98.96 77	99.46 155	99.19 88	97.46 372	95.46 453	98.59 66	99.46 420	98.08 156	98.71 391	98.46 403

canonicalmvs		98.34 211	98.26 214	98.58 237	98.46 386	97.82 183	98.96 77	99.46 155	99.19 88	97.46 372	95.46 453	98.59 66	99.46 420	98.08 156	98.71 391	98.46 403

MVS-HIRNet		94.32 409	95.62 372	90.42 469	98.46 386	75.36 493	96.29 386	89.13 484	95.25 394	95.38 450	99.75 16	92.88 354	99.19 454	94.07 395	99.39 310	96.72 470

PHI-MVS		98.29 222	97.95 253	99.34 83	98.44 389	99.16 49	98.12 186	99.38 190	96.01 369	98.06 326	98.43 337	97.80 153	99.67 330	95.69 350	99.58 260	99.20 295

DVP-MVS++		98.90 104	98.70 135	99.51 49	98.43 390	99.15 53	99.43 15	99.32 218	98.17 204	99.26 148	99.02 200	98.18 114	99.88 115	97.07 243	99.45 298	99.49 173

MSC_two_6792asdad				99.32 91	98.43 390	98.37 121		98.86 334					99.89 97	97.14 237	99.60 251	99.71 63

No_MVS				99.32 91	98.43 390	98.37 121		98.86 334					99.89 97	97.14 237	99.60 251	99.71 63

Fast-Effi-MVS+-dtu		98.27 223	98.09 236	98.81 185	98.43 390	98.11 143	97.61 279	99.50 132	98.64 155	97.39 379	97.52 403	98.12 122	99.95 26	96.90 261	98.71 391	98.38 416

OpenMVS_ROB	95.38 14	95.84 381	95.18 394	97.81 326	98.41 394	97.15 243	97.37 313	98.62 365	83.86 480	98.65 264	98.37 343	94.29 329	99.68 326	88.41 464	98.62 401	96.60 471

DeepPCF-MVS	96.93 5	98.32 216	98.01 246	99.23 108	98.39 395	98.97 74	95.03 443	99.18 271	96.88 325	99.33 130	98.78 272	98.16 118	99.28 448	96.74 275	99.62 244	99.44 203

Patchmatch-test		96.55 354	96.34 356	97.17 382	98.35 396	93.06 409	98.40 155	97.79 398	97.33 287	98.41 297	98.67 299	83.68 439	99.69 316	95.16 363	99.31 323	98.77 377

AdaColmap		97.14 328	96.71 339	98.46 263	98.34 397	97.80 187	96.95 344	98.93 317	95.58 384	96.92 397	97.66 394	95.87 284	99.53 398	90.97 452	99.14 352	98.04 432

OpenMVS	96.65 7	97.09 330	96.68 341	98.32 280	98.32 398	97.16 242	98.86 91	99.37 194	89.48 468	96.29 429	99.15 168	96.56 247	99.90 81	92.90 420	99.20 343	97.89 440

MG-MVS		96.77 347	96.61 346	97.26 378	98.31 399	93.06 409	95.93 408	98.12 392	96.45 349	97.92 336	98.73 283	93.77 341	99.39 431	91.19 450	99.04 363	99.33 256

test_yl		96.69 348	96.29 358	97.90 318	98.28 400	95.24 335	97.29 321	97.36 411	98.21 197	98.17 312	97.86 382	86.27 413	99.55 390	94.87 369	98.32 408	98.89 356

DCV-MVSNet		96.69 348	96.29 358	97.90 318	98.28 400	95.24 335	97.29 321	97.36 411	98.21 197	98.17 312	97.86 382	86.27 413	99.55 390	94.87 369	98.32 408	98.89 356

CHOSEN 280x420		95.51 391	95.47 379	95.65 434	98.25 402	88.27 465	93.25 476	98.88 327	93.53 430	94.65 459	97.15 418	86.17 415	99.93 54	97.41 219	99.93 56	98.73 382

SCA		96.41 361	96.66 344	95.67 432	98.24 403	88.35 464	95.85 414	96.88 429	96.11 363	97.67 355	98.67 299	93.10 349	99.85 156	94.16 389	99.22 339	98.81 369

DeepMVS_CX				93.44 462	98.24 403	94.21 371		94.34 462	64.28 488	91.34 482	94.87 465	89.45 395	92.77 489	77.54 485	93.14 481	93.35 484

MS-PatchMatch		97.68 283	97.75 269	97.45 369	98.23 405	93.78 396	97.29 321	98.84 338	96.10 364	98.64 265	98.65 304	96.04 270	99.36 434	96.84 267	99.14 352	99.20 295

BH-w/o		95.13 398	94.89 401	95.86 427	98.20 406	91.31 440	95.65 421	97.37 410	93.64 428	96.52 422	95.70 446	93.04 352	99.02 460	88.10 466	95.82 471	97.24 463

mvs_anonymous		97.83 276	98.16 230	96.87 397	98.18 407	91.89 430	97.31 319	98.90 323	97.37 284	98.83 238	99.46 81	96.28 261	99.79 244	98.90 95	98.16 418	98.95 345

miper_lstm_enhance		97.18 325	97.16 309	97.25 379	98.16 408	92.85 414	95.15 441	99.31 223	97.25 296	98.74 255	98.78 272	90.07 387	99.78 255	97.19 232	99.80 145	99.11 319

RRT-MVS		97.88 265	97.98 249	97.61 352	98.15 409	93.77 397	98.97 76	99.64 71	99.16 93	98.69 258	99.42 90	91.60 372	99.89 97	97.63 198	98.52 405	99.16 313

ET-MVSNet_ETH3D		94.30 411	93.21 422	97.58 355	98.14 410	94.47 364	94.78 449	93.24 472	94.72 406	89.56 484	95.87 443	78.57 461	99.81 222	96.91 256	97.11 453	98.46 403

ADS-MVSNet2		95.43 393	94.98 397	96.76 404	98.14 410	91.74 431	97.92 227	97.76 399	90.23 462	96.51 423	98.91 238	85.61 422	99.85 156	92.88 421	96.90 454	98.69 387

ADS-MVSNet		95.24 396	94.93 400	96.18 421	98.14 410	90.10 457	97.92 227	97.32 414	90.23 462	96.51 423	98.91 238	85.61 422	99.74 283	92.88 421	96.90 454	98.69 387

c3_l		97.36 309	97.37 297	97.31 374	98.09 413	93.25 407	95.01 444	99.16 278	97.05 313	98.77 250	98.72 285	92.88 354	99.64 354	96.93 255	99.76 177	99.05 324

FMVSNet3		97.50 294	97.24 305	98.29 284	98.08 414	95.83 308	97.86 236	98.91 322	97.89 232	98.95 211	98.95 231	87.06 408	99.81 222	97.77 185	99.69 212	99.23 285

PAPM		91.88 449	90.34 451	96.51 408	98.06 415	92.56 419	92.44 480	97.17 418	86.35 476	90.38 483	96.01 438	86.61 411	99.21 453	70.65 489	95.43 473	97.75 449

Effi-MVS+-dtu		98.26 225	97.90 261	99.35 80	98.02 416	99.49 6	98.02 206	99.16 278	98.29 190	97.64 356	97.99 374	96.44 253	99.95 26	96.66 288	98.93 379	98.60 395

eth_miper_zixun_eth		97.23 321	97.25 304	97.17 382	98.00 417	92.77 416	94.71 450	99.18 271	97.27 294	98.56 281	98.74 282	91.89 370	99.69 316	97.06 245	99.81 134	99.05 324

HY-MVS	95.94 13	95.90 378	95.35 387	97.55 360	97.95 418	94.79 352	98.81 97	96.94 427	92.28 447	95.17 452	98.57 318	89.90 389	99.75 277	91.20 449	97.33 449	98.10 429

UGNet		98.53 184	98.45 181	98.79 192	97.94 419	96.96 255	99.08 61	98.54 371	99.10 105	96.82 407	99.47 79	96.55 248	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		96.47 359	95.70 369	98.79 192	97.92 420	99.12 63	98.28 164	98.60 366	92.16 448	95.54 447	96.17 436	94.77 318	99.52 402	89.62 461	98.23 412	97.72 451
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		96.86 343	96.55 350	97.79 327	97.91 421	94.21 371	97.56 285	98.87 329	97.49 269	99.06 181	99.05 195	80.72 449	99.80 231	98.44 129	99.82 128	99.37 236

API-MVS		97.04 334	96.91 326	97.42 371	97.88 422	98.23 134	98.18 175	98.50 374	97.57 258	97.39 379	96.75 424	96.77 234	99.15 457	90.16 459	99.02 367	94.88 482

myMVS_eth3d28		92.92 435	92.31 431	94.77 446	97.84 423	87.59 469	96.19 392	96.11 442	97.08 312	94.27 462	93.49 474	66.07 483	98.78 470	91.78 437	97.93 431	97.92 439

miper_ehance_all_eth		97.06 332	97.03 317	97.16 384	97.83 424	93.06 409	94.66 453	99.09 290	95.99 370	98.69 258	98.45 335	92.73 359	99.61 367	96.79 269	99.03 364	98.82 364

cl____		97.02 335	96.83 331	97.58 355	97.82 425	94.04 379	94.66 453	99.16 278	97.04 314	98.63 266	98.71 286	88.68 400	99.69 316	97.00 248	99.81 134	99.00 336

DIV-MVS_self_test		97.02 335	96.84 330	97.58 355	97.82 425	94.03 380	94.66 453	99.16 278	97.04 314	98.63 266	98.71 286	88.69 398	99.69 316	97.00 248	99.81 134	99.01 332

CANet		97.87 267	97.76 268	98.19 297	97.75 427	95.51 319	96.76 356	99.05 297	97.74 242	96.93 396	98.21 357	95.59 292	99.89 97	97.86 180	99.93 56	99.19 300

UBG		93.25 429	92.32 430	96.04 426	97.72 428	90.16 456	95.92 410	95.91 447	96.03 368	93.95 470	93.04 477	69.60 473	99.52 402	90.72 457	97.98 429	98.45 406

mvsany_test1		97.60 288	97.54 286	97.77 329	97.72 428	95.35 331	95.36 433	97.13 420	94.13 421	99.71 50	99.33 116	97.93 137	99.30 444	97.60 202	98.94 378	98.67 391

PVSNet_0	89.98 21	91.15 450	90.30 452	93.70 459	97.72 428	84.34 483	90.24 483	97.42 409	90.20 465	93.79 471	93.09 476	90.90 382	98.89 468	86.57 472	72.76 489	97.87 442

CR-MVSNet		96.28 364	95.95 363	97.28 376	97.71 431	94.22 369	98.11 187	98.92 320	92.31 446	96.91 399	99.37 104	85.44 425	99.81 222	97.39 220	97.36 447	97.81 445

RPMNet		97.02 335	96.93 322	97.30 375	97.71 431	94.22 369	98.11 187	99.30 231	99.37 61	96.91 399	99.34 113	86.72 410	99.87 134	97.53 208	97.36 447	97.81 445

ETVMVS		92.60 438	91.08 447	97.18 380	97.70 433	93.65 402	96.54 368	95.70 450	96.51 342	94.68 458	92.39 481	61.80 490	99.50 408	86.97 469	97.41 443	98.40 414

pmmvs3		95.03 400	94.40 407	96.93 393	97.70 433	92.53 420	95.08 442	97.71 401	88.57 472	97.71 352	98.08 368	79.39 456	99.82 205	96.19 325	99.11 358	98.43 411

baseline2		93.73 421	92.83 427	96.42 411	97.70 433	91.28 442	96.84 352	89.77 483	93.96 426	92.44 478	95.93 441	79.14 457	99.77 261	92.94 419	96.76 458	98.21 423

WBMVS		95.18 397	94.78 402	96.37 412	97.68 436	89.74 459	95.80 416	98.73 357	97.54 264	98.30 303	98.44 336	70.06 471	99.82 205	96.62 291	99.87 98	99.54 142

tpm		94.67 405	94.34 409	95.66 433	97.68 436	88.42 463	97.88 232	94.90 457	94.46 412	96.03 437	98.56 319	78.66 459	99.79 244	95.88 338	95.01 475	98.78 376

CANet_DTU		97.26 317	97.06 316	97.84 323	97.57 438	94.65 360	96.19 392	98.79 346	97.23 302	95.14 453	98.24 354	93.22 346	99.84 174	97.34 222	99.84 112	99.04 328

testing11		93.08 432	92.02 437	96.26 417	97.56 439	90.83 451	96.32 384	95.70 450	96.47 346	92.66 477	93.73 470	64.36 487	99.59 374	93.77 404	97.57 436	98.37 418

tpm2		93.09 431	92.58 429	94.62 448	97.56 439	86.53 472	97.66 267	95.79 449	86.15 477	94.07 467	98.23 356	75.95 464	99.53 398	90.91 454	96.86 457	97.81 445

testing91		93.32 427	92.27 432	96.47 410	97.54 441	91.25 443	96.17 396	96.76 431	97.18 306	93.65 473	93.50 473	65.11 486	99.63 357	93.04 418	97.45 440	98.53 400

TR-MVS		95.55 389	95.12 395	96.86 400	97.54 441	93.94 388	96.49 373	96.53 436	94.36 417	97.03 394	96.61 427	94.26 330	99.16 456	86.91 471	96.31 462	97.47 459

testing99		93.04 433	91.98 440	96.23 419	97.53 443	90.70 453	96.35 382	95.94 446	96.87 326	93.41 474	93.43 475	63.84 488	99.59 374	93.24 416	97.19 450	98.40 414

1314		95.74 383	95.60 374	96.17 422	97.53 443	92.75 417	98.07 196	98.31 383	91.22 457	94.25 463	96.68 425	95.53 293	99.03 459	91.64 441	97.18 451	96.74 469

CostFormer		93.97 417	93.78 415	94.51 449	97.53 443	85.83 475	97.98 218	95.96 445	89.29 470	94.99 455	98.63 309	78.63 460	99.62 360	94.54 377	96.50 459	98.09 430

FMVSNet5		96.01 373	95.20 393	98.41 269	97.53 443	96.10 294	98.74 98	99.50 132	97.22 305	98.03 330	99.04 197	69.80 472	99.88 115	97.27 227	99.71 202	99.25 280

PMMVS		96.51 355	95.98 362	98.09 303	97.53 443	95.84 307	94.92 446	98.84 338	91.58 452	96.05 436	95.58 447	95.68 289	99.66 343	95.59 354	98.09 422	98.76 379

reproduce_monomvs		95.00 402	95.25 390	94.22 452	97.51 448	83.34 484	97.86 236	98.44 376	98.51 173	99.29 140	99.30 123	67.68 477	99.56 386	98.89 97	99.81 134	99.77 50

PAPR		95.29 394	94.47 405	97.75 333	97.50 449	95.14 340	94.89 447	98.71 359	91.39 456	95.35 451	95.48 452	94.57 321	99.14 458	84.95 474	97.37 445	98.97 342

testing222		91.96 447	90.37 450	96.72 405	97.47 450	92.59 418	96.11 398	94.76 458	96.83 329	92.90 476	92.87 478	57.92 491	99.55 390	86.93 470	97.52 437	98.00 436

PatchT		96.65 351	96.35 355	97.54 361	97.40 451	95.32 333	97.98 218	96.64 433	99.33 66	96.89 403	99.42 90	84.32 433	99.81 222	97.69 196	97.49 438	97.48 458

tpm cat1		93.29 428	93.13 425	93.75 458	97.39 452	84.74 478	97.39 307	97.65 405	83.39 482	94.16 464	98.41 338	82.86 444	99.39 431	91.56 443	95.35 474	97.14 464

PatchmatchNet		95.58 388	95.67 371	95.30 442	97.34 453	87.32 470	97.65 269	96.65 432	95.30 393	97.07 389	98.69 295	84.77 428	99.75 277	94.97 367	98.64 398	98.83 363
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 310	96.97 320	98.50 260	97.31 454	96.47 285	98.18 175	98.92 320	98.95 128	98.78 247	99.37 104	85.44 425	99.85 156	95.96 336	99.83 123	99.17 308

LS3D		98.63 163	98.38 193	99.36 74	97.25 455	99.38 13	99.12 60	99.32 218	99.21 81	98.44 294	98.88 248	97.31 196	99.80 231	96.58 294	99.34 318	98.92 351

IB-MVS	91.63 19	92.24 444	90.90 448	96.27 416	97.22 456	91.24 444	94.36 463	93.33 471	92.37 445	92.24 480	94.58 467	66.20 482	99.89 97	93.16 417	94.63 477	97.66 453
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		92.38 441	91.76 444	94.21 453	97.16 457	84.65 479	95.42 431	88.45 485	95.96 371	96.17 430	95.84 445	66.36 480	99.71 301	91.87 436	98.64 398	98.28 421

tpmrst		95.07 399	95.46 380	93.91 456	97.11 458	84.36 482	97.62 274	96.96 425	94.98 400	96.35 428	98.80 268	85.46 424	99.59 374	95.60 353	96.23 463	97.79 448

Syy-MVS		96.04 372	95.56 378	97.49 366	97.10 459	94.48 363	96.18 394	96.58 434	95.65 381	94.77 456	92.29 482	91.27 378	99.36 434	98.17 151	98.05 426	98.63 393

myMVS_eth3d		91.92 448	90.45 449	96.30 414	97.10 459	90.90 449	96.18 394	96.58 434	95.65 381	94.77 456	92.29 482	53.88 492	99.36 434	89.59 462	98.05 426	98.63 393

blended_shiyan6		95.99 375	95.33 388	97.95 316	97.06 461	94.89 349	95.34 434	98.58 367	96.17 359	97.06 390	92.41 480	87.64 407	99.76 267	97.64 197	96.09 466	99.19 300

MDTV_nov1_ep13			95.22 392		97.06 461	83.20 485	97.74 256	96.16 440	94.37 416	96.99 395	98.83 261	83.95 437	99.53 398	93.90 398	97.95 430

MVS		93.19 430	92.09 435	96.50 409	96.91 463	94.03 380	98.07 196	98.06 394	68.01 487	94.56 461	96.48 430	95.96 280	99.30 444	83.84 476	96.89 456	96.17 474

E-PMN		94.17 413	94.37 408	93.58 460	96.86 464	85.71 476	90.11 485	97.07 421	98.17 204	97.82 347	97.19 416	84.62 430	98.94 464	89.77 460	97.68 435	96.09 478

JIA-IIPM		95.52 390	95.03 396	97.00 389	96.85 465	94.03 380	96.93 347	95.82 448	99.20 83	94.63 460	99.71 22	83.09 442	99.60 370	94.42 383	94.64 476	97.36 462

EMVS		93.83 419	94.02 411	93.23 465	96.83 466	84.96 477	89.77 486	96.32 438	97.92 229	97.43 376	96.36 435	86.17 415	98.93 465	87.68 467	97.73 434	95.81 479

blend_shiyan4		92.09 446	90.16 453	97.88 321	96.78 467	94.93 347	95.24 437	98.58 367	96.22 357	96.07 434	91.42 484	63.46 489	99.73 290	96.70 281	76.98 488	98.98 338

cl22		95.79 382	95.39 385	96.98 391	96.77 468	92.79 415	94.40 462	98.53 372	94.59 409	97.89 339	98.17 360	82.82 445	99.24 450	96.37 314	99.03 364	98.92 351

WB-MVSnew		95.73 384	95.57 377	96.23 419	96.70 469	90.70 453	96.07 400	93.86 468	95.60 383	97.04 392	95.45 456	96.00 273	99.55 390	91.04 451	98.31 410	98.43 411

dp		93.47 425	93.59 418	93.13 466	96.64 470	81.62 491	97.66 267	96.42 437	92.80 441	96.11 432	98.64 307	78.55 462	99.59 374	93.31 414	92.18 484	98.16 426

MonoMVSNet		96.25 366	96.53 352	95.39 440	96.57 471	91.01 447	98.82 96	97.68 404	98.57 168	98.03 330	99.37 104	90.92 381	97.78 481	94.99 365	93.88 480	97.38 461

FE-blended-shiyan7		95.48 392	94.74 404	97.68 341	96.53 472	94.12 375	94.17 466	98.57 369	95.84 375	96.71 411	91.16 485	86.05 418	99.76 267	97.57 204	96.09 466	99.17 308

usedtu_blend_shiyan5		96.20 369	95.62 372	97.94 317	96.53 472	94.93 347	98.83 95	99.59 91	98.89 135	96.71 411	91.16 485	86.05 418	99.73 290	96.70 281	96.09 466	99.17 308

test-LLR		93.90 418	93.85 413	94.04 454	96.53 472	84.62 480	94.05 469	92.39 474	96.17 359	94.12 465	95.07 457	82.30 446	99.67 330	95.87 341	98.18 415	97.82 443

test-mter		92.33 443	91.76 444	94.04 454	96.53 472	84.62 480	94.05 469	92.39 474	94.00 425	94.12 465	95.07 457	65.63 485	99.67 330	95.87 341	98.18 415	97.82 443

TESTMET0.1,1		92.19 445	91.77 443	93.46 461	96.48 476	82.80 487	94.05 469	91.52 479	94.45 414	94.00 468	94.88 463	66.65 479	99.56 386	95.78 346	98.11 421	98.02 433

MGCNet		97.44 302	97.01 319	98.72 212	96.42 477	96.74 269	97.20 331	91.97 477	98.46 176	98.30 303	98.79 270	92.74 358	99.91 74	99.30 63	99.94 50	99.52 158

miper_enhance_ethall		96.01 373	95.74 367	96.81 401	96.41 478	92.27 427	93.69 474	98.89 326	91.14 459	98.30 303	97.35 414	90.58 384	99.58 381	96.31 318	99.03 364	98.60 395

tpmvs		95.02 401	95.25 390	94.33 450	96.39 479	85.87 473	98.08 192	96.83 430	95.46 388	95.51 449	98.69 295	85.91 420	99.53 398	94.16 389	96.23 463	97.58 456

CMPMVS	75.91 23	96.29 363	95.44 382	98.84 180	96.25 480	98.69 98	97.02 340	99.12 285	88.90 471	97.83 345	98.86 251	89.51 393	98.90 467	91.92 434	99.51 283	98.92 351
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 406	93.69 416	96.99 390	96.05 481	93.61 404	94.97 445	93.49 469	96.17 359	97.57 363	94.88 463	82.30 446	99.01 462	93.60 407	94.17 479	98.37 418

EPMVS		93.72 422	93.27 421	95.09 445	96.04 482	87.76 467	98.13 182	85.01 490	94.69 407	96.92 397	98.64 307	78.47 463	99.31 442	95.04 364	96.46 460	98.20 424

cascas		94.79 404	94.33 410	96.15 425	96.02 483	92.36 425	92.34 481	99.26 251	85.34 479	95.08 454	94.96 462	92.96 353	98.53 474	94.41 386	98.59 402	97.56 457

MVStest1		95.86 379	95.60 374	96.63 406	95.87 484	91.70 432	97.93 224	98.94 314	98.03 219	99.56 74	99.66 32	71.83 469	98.26 477	99.35 59	99.24 335	99.91 13

gg-mvs-nofinetune		92.37 442	91.20 446	95.85 428	95.80 485	92.38 424	99.31 30	81.84 492	99.75 11	91.83 481	99.74 18	68.29 474	99.02 460	87.15 468	97.12 452	96.16 475

gm-plane-assit					94.83 486	81.97 489			88.07 474		94.99 460		99.60 370	91.76 438

GG-mvs-BLEND				94.76 447	94.54 487	92.13 429	99.31 30	80.47 493		88.73 487	91.01 487	67.59 478	98.16 480	82.30 481	94.53 478	93.98 483

UWE-MVS-28		90.22 451	89.28 454	93.02 467	94.50 488	82.87 486	96.52 371	87.51 486	95.21 396	92.36 479	96.04 437	71.57 470	98.25 478	72.04 488	97.77 433	97.94 438

EPNet_dtu		94.93 403	94.78 402	95.38 441	93.58 489	87.68 468	96.78 354	95.69 452	97.35 286	89.14 486	98.09 367	88.15 405	99.49 411	94.95 368	99.30 326	98.98 338
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 455	75.95 458	77.12 472	92.39 490	67.91 496	90.16 484	59.44 497	82.04 483	89.42 485	94.67 466	49.68 494	81.74 490	48.06 490	77.66 487	81.72 486

KD-MVS_2432*1600		92.87 436	91.99 438	95.51 437	91.37 491	89.27 460	94.07 467	98.14 390	95.42 389	97.25 384	96.44 432	67.86 475	99.24 450	91.28 447	96.08 469	98.02 433

miper_refine_blended		92.87 436	91.99 438	95.51 437	91.37 491	89.27 460	94.07 467	98.14 390	95.42 389	97.25 384	96.44 432	67.86 475	99.24 450	91.28 447	96.08 469	98.02 433

EPNet		96.14 370	95.44 382	98.25 288	90.76 493	95.50 322	97.92 227	94.65 459	98.97 124	92.98 475	98.85 254	89.12 396	99.87 134	95.99 334	99.68 217	99.39 225
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 456	68.95 459	70.34 473	87.68 494	65.00 497	91.11 482	59.90 496	69.02 486	74.46 491	88.89 488	48.58 495	68.03 492	28.61 491	72.33 490	77.99 487

test_method		79.78 453	79.50 456	80.62 470	80.21 495	45.76 498	70.82 487	98.41 380	31.08 490	80.89 490	97.71 391	84.85 427	97.37 483	91.51 444	80.03 486	98.75 380

tmp_tt		78.77 454	78.73 457	78.90 471	58.45 496	74.76 495	94.20 465	78.26 494	39.16 489	86.71 488	92.82 479	80.50 450	75.19 491	86.16 473	92.29 483	86.74 485

testmvs		17.12 458	20.53 461	6.87 475	12.05 497	4.20 500	93.62 475	6.73 498	4.62 493	10.41 493	24.33 490	8.28 497	3.56 494	9.69 493	15.07 491	12.86 490

test123		17.04 459	20.11 462	7.82 474	10.25 498	4.91 499	94.80 448	4.47 499	4.93 492	10.00 494	24.28 491	9.69 496	3.64 493	10.14 492	12.43 492	14.92 489

mmdepth		0.00 462	0.00 465	0.00 476	0.00 499	0.00 501	0.00 488	0.00 500	0.00 494	0.00 495	0.00 494	0.00 498	0.00 495	0.00 494	0.00 493	0.00 491

monomultidepth		0.00 462	0.00 465	0.00 476	0.00 499	0.00 501	0.00 488	0.00 500	0.00 494	0.00 495	0.00 494	0.00 498	0.00 495	0.00 494	0.00 493	0.00 491

test_blank		0.00 462	0.00 465	0.00 476	0.00 499	0.00 501	0.00 488	0.00 500	0.00 494	0.00 495	0.00 494	0.00 498	0.00 495	0.00 494	0.00 493	0.00 491

eth-test2					0.00 499

eth-test					0.00 499

uanet_test		0.00 462	0.00 465	0.00 476	0.00 499	0.00 501	0.00 488	0.00 500	0.00 494	0.00 495	0.00 494	0.00 498	0.00 495	0.00 494	0.00 493	0.00 491

DCPMVS		0.00 462	0.00 465	0.00 476	0.00 499	0.00 501	0.00 488	0.00 500	0.00 494	0.00 495	0.00 494	0.00 498	0.00 495	0.00 494	0.00 493	0.00 491

cdsmvs_eth3d_5k		24.66 457	32.88 460	0.00 476	0.00 499	0.00 501	0.00 488	99.10 288	0.00 494	0.00 495	97.58 399	99.21 18	0.00 495	0.00 494	0.00 493	0.00 491

pcd_1.5k_mvsjas		8.17 460	10.90 463	0.00 476	0.00 499	0.00 501	0.00 488	0.00 500	0.00 494	0.00 495	0.00 494	98.07 124	0.00 495	0.00 494	0.00 493	0.00 491

sosnet-low-res		0.00 462	0.00 465	0.00 476	0.00 499	0.00 501	0.00 488	0.00 500	0.00 494	0.00 495	0.00 494	0.00 498	0.00 495	0.00 494	0.00 493	0.00 491

sosnet		0.00 462	0.00 465	0.00 476	0.00 499	0.00 501	0.00 488	0.00 500	0.00 494	0.00 495	0.00 494	0.00 498	0.00 495	0.00 494	0.00 493	0.00 491

uncertanet		0.00 462	0.00 465	0.00 476	0.00 499	0.00 501	0.00 488	0.00 500	0.00 494	0.00 495	0.00 494	0.00 498	0.00 495	0.00 494	0.00 493	0.00 491

Regformer		0.00 462	0.00 465	0.00 476	0.00 499	0.00 501	0.00 488	0.00 500	0.00 494	0.00 495	0.00 494	0.00 498	0.00 495	0.00 494	0.00 493	0.00 491

ab-mvs-re		8.12 461	10.83 464	0.00 476	0.00 499	0.00 501	0.00 488	0.00 500	0.00 494	0.00 495	97.48 405	0.00 498	0.00 495	0.00 494	0.00 493	0.00 491

uanet		0.00 462	0.00 465	0.00 476	0.00 499	0.00 501	0.00 488	0.00 500	0.00 494	0.00 495	0.00 494	0.00 498	0.00 495	0.00 494	0.00 493	0.00 491

TestfortrainingZip							98.68 108

WAC-MVS						90.90 449								91.37 446

PC_three_1452									93.27 433	99.40 115	98.54 320	98.22 109	97.00 484	95.17 362	99.45 298	99.49 173

test_241102_TWO								99.30 231	98.03 219	99.26 148	99.02 200	97.51 182	99.88 115	96.91 256	99.60 251	99.66 78

test_0728_THIRD									98.17 204	99.08 179	99.02 200	97.89 143	99.88 115	97.07 243	99.71 202	99.70 68

GSMVS																98.81 369

sam_mvs1												84.74 429				98.81 369

sam_mvs												84.29 435

MTGPA								99.20 263

test_post1							97.59 282				20.48 493	83.07 443	99.66 343	94.16 389

test_post											21.25 492	83.86 438	99.70 308

patchmatchnet-post											98.77 274	84.37 432	99.85 156

MTMP							97.93 224	91.91 478

test9_res														93.28 415	99.15 351	99.38 234

agg_prior2														92.50 431	99.16 349	99.37 236

test_prior4						97.97 163	95.86 412

test_prior2							95.74 419		96.48 345	96.11 432	97.63 397	95.92 283		94.16 389	99.20 343

旧先验2							95.76 418		88.56 473	97.52 367			99.66 343	94.48 379

新几何2							95.93 408

无先验							95.74 419	98.74 356	89.38 469				99.73 290	92.38 433		99.22 290

原ACMM2							95.53 425

testdata2													99.79 244	92.80 425

segment_acmp												97.02 216

testdata1							95.44 430		96.32 353

plane_prior5								99.27 246					99.70 308	94.42 383	99.51 283	99.45 199

plane_prior4											97.98 375

plane_prior3						97.78 188			97.41 279	97.79 348

plane_prior2							97.77 249		98.20 201

plane_prior						97.65 197	97.07 339		96.72 335						99.36 314

n2								0.00 500

nn								0.00 500

door-mid								99.57 101

test11								98.87 329

door								99.41 183

HQP5-MVS						96.79 265

BP-MVS														92.82 423

HQP4-MVS										95.56 443			99.54 396			99.32 259

HQP3-MVS								99.04 300							99.26 333

HQP2-MVS												93.84 337

MDTV_nov1_ep13_2view						74.92 494	97.69 262		90.06 467	97.75 351		85.78 421		93.52 409		98.69 387

ACMMP++_ref															99.77 162

ACMMP++															99.68 217

Test By Simon												96.52 249

High-resolution multi-view benchmark