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 81	99.16 63	98.64 218	99.94 2	98.51 113	99.32 27	99.75 43	99.58 39	98.60 267	99.62 41	98.22 104	99.51 396	97.70 189	99.73 180	97.89 429
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 30	99.31 43	99.53 39	99.91 3	98.98 72	99.63 7	99.58 88	99.44 54	99.78 40	99.76 15	96.39 248	99.92 65	99.44 55	99.92 69	99.68 71

FE-MVSNET1		99.51 14	99.54 14	99.43 68	99.90 4	98.85 86	99.33 26	99.79 36	99.47 48	99.51 93	99.75 16	99.10 24	99.84 174	99.14 76	99.91 78	99.59 107

pmmvs6		99.67 3	99.70 3	99.60 16	99.90 4	99.27 28	99.53 9	99.76 40	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 18	99.49 17	99.35 81	99.90 4	98.15 140	99.20 49	99.65 69	99.48 45	99.92 8	99.71 23	98.07 119	99.96 14	99.53 48	100.00 1	99.93 11

testf1		99.25 42	99.16 63	99.51 49	99.89 7	99.63 4	98.71 105	99.69 55	98.90 134	99.43 107	99.35 105	98.86 35	99.67 320	97.81 176	99.81 129	99.24 277

APD_test2		99.25 42	99.16 63	99.51 49	99.89 7	99.63 4	98.71 105	99.69 55	98.90 134	99.43 107	99.35 105	98.86 35	99.67 320	97.81 176	99.81 129	99.24 277

ANet_high		99.57 10	99.67 6	99.28 97	99.89 7	98.09 147	99.14 58	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 22	99.62 10	99.88 10	99.08 70	99.34 23	99.69 55	98.93 130	99.65 64	99.72 22	98.93 33	99.95 26	99.11 79	100.00 1	99.82 36

v7n		99.53 12	99.57 13	99.41 71	99.88 10	98.54 111	99.45 14	99.61 78	99.66 24	99.68 58	99.66 33	98.44 78	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 10	98.61 103	99.34 23	99.71 48	99.27 75	99.90 14	99.74 19	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 75	99.87 13	98.13 143	98.08 187	99.95 1	99.45 52	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 13	98.61 103	99.28 41	99.66 65	99.09 109	99.89 18	99.68 26	99.53 7	99.97 7	99.50 51	99.99 5	99.87 22

test_djsdf		99.52 13	99.51 16	99.53 39	99.86 15	98.74 93	99.39 20	99.56 104	99.11 99	99.70 52	99.73 21	99.00 28	99.97 7	99.26 66	99.98 12	99.89 16

MIMVSNet1		99.38 29	99.32 41	99.55 29	99.86 15	99.19 43	99.41 17	99.59 86	99.59 37	99.71 50	99.57 50	97.12 203	99.90 81	99.21 71	99.87 98	99.54 143

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 27	99.85 17	99.11 65	99.90 1	99.78 37	99.63 29	99.78 40	99.67 31	99.48 10	99.81 223	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 18	99.34 20	99.69 5	99.58 88	99.90 3	99.86 24	99.78 13	99.58 6	99.95 26	99.00 89	99.95 38	99.78 47

SixPastTwentyTwo		98.75 130	98.62 145	99.16 119	99.83 19	97.96 167	99.28 41	98.20 376	99.37 62	99.70 52	99.65 37	92.65 354	99.93 54	99.04 86	99.84 112	99.60 100

sc_t1		99.62 7	99.66 8	99.53 39	99.82 20	99.09 69	99.50 11	99.63 73	99.88 4	99.86 24	99.80 11	99.03 25	99.89 97	99.48 53	99.93 56	99.60 100

Baseline_NR-MVSNet		98.98 89	98.86 107	99.36 75	99.82 20	98.55 108	97.47 294	99.57 95	99.37 62	99.21 160	99.61 44	96.76 230	99.83 193	98.06 154	99.83 119	99.71 63

pm-mvs1		99.44 20	99.48 19	99.33 90	99.80 22	98.63 100	99.29 37	99.63 73	99.30 72	99.65 64	99.60 46	99.16 22	99.82 206	99.07 82	99.83 119	99.56 130

TransMVSNet (Re)		99.44 20	99.47 22	99.36 75	99.80 22	98.58 106	99.27 43	99.57 95	99.39 60	99.75 45	99.62 41	99.17 20	99.83 193	99.06 84	99.62 239	99.66 78

K. test v3		98.00 248	97.66 273	99.03 146	99.79 24	97.56 203	99.19 53	92.47 462	99.62 33	99.52 88	99.66 33	89.61 385	99.96 14	99.25 68	99.81 129	99.56 130

test_fmvsmconf0.1_n		99.49 16	99.54 14	99.34 84	99.78 25	98.11 144	97.77 244	99.90 11	99.33 67	99.97 3	99.66 33	99.71 3	99.96 14	99.79 19	99.99 5	99.96 8

APD_test1		98.83 114	98.66 138	99.34 84	99.78 25	99.47 9	98.42 149	99.45 152	98.28 186	98.98 196	99.19 149	97.76 151	99.58 370	96.57 285	99.55 266	98.97 331

test_vis3_rt		99.14 63	99.17 61	99.07 136	99.78 25	98.38 120	98.92 83	99.94 2	97.80 232	99.91 12	99.67 31	97.15 202	98.91 455	99.76 23	99.56 262	99.92 12

EGC-MVSNET		85.24 441	80.54 444	99.34 84	99.77 28	99.20 40	99.08 62	99.29 232	12.08 480	20.84 481	99.42 90	97.55 170	99.85 156	97.08 233	99.72 188	98.96 333

Anonymous20240521		98.69 143	98.87 103	98.16 294	99.77 28	95.11 335	99.08 62	99.44 160	99.34 66	99.33 130	99.55 58	94.10 329	99.94 42	99.25 68	99.96 28	99.42 207

FC-MVSNet-test		99.27 39	99.25 54	99.34 84	99.77 28	98.37 122	99.30 36	99.57 95	99.61 35	99.40 116	99.50 69	97.12 203	99.85 156	99.02 88	99.94 50	99.80 42

test_vis1_n		98.31 212	98.50 165	97.73 328	99.76 31	94.17 363	98.68 108	99.91 9	96.31 346	99.79 39	99.57 50	92.85 350	99.42 416	99.79 19	99.84 112	99.60 100

test_fmvs3		99.12 70	99.41 27	98.25 282	99.76 31	95.07 336	99.05 68	99.94 2	97.78 235	99.82 34	99.84 3	98.56 69	99.71 296	99.96 1	99.96 28	99.97 4

XXY-MVS		99.14 63	99.15 68	99.10 129	99.76 31	97.74 192	98.85 93	99.62 75	98.48 169	99.37 121	99.49 75	98.75 47	99.86 143	98.20 144	99.80 140	99.71 63

TDRefinement		99.42 25	99.38 30	99.55 29	99.76 31	99.33 21	99.68 6	99.71 48	99.38 61	99.53 83	99.61 44	98.64 57	99.80 231	98.24 139	99.84 112	99.52 155

fmvsm_s_conf0.1_n_a		99.17 54	99.30 46	98.80 183	99.75 35	96.59 268	97.97 217	99.86 16	98.22 189	99.88 21	99.71 23	98.59 63	99.84 174	99.73 28	99.98 12	99.98 3

tt0805		98.69 143	98.62 145	98.90 171	99.75 35	99.30 23	99.15 57	96.97 413	98.86 139	98.87 229	97.62 391	98.63 59	98.96 452	99.41 57	98.29 404	98.45 395

test_vis1_n_1920		98.40 195	98.92 96	96.81 390	99.74 37	90.76 441	98.15 175	99.91 9	98.33 177	99.89 18	99.55 58	95.07 300	99.88 115	99.76 23	99.93 56	99.79 44

FOURS1					99.73 38	99.67 3	99.43 15	99.54 113	99.43 56	99.26 148

PEN-MVS		99.41 26	99.34 37	99.62 10	99.73 38	99.14 58	99.29 37	99.54 113	99.62 33	99.56 74	99.42 90	98.16 113	99.96 14	98.78 103	99.93 56	99.77 50

lessismore_v0				98.97 158	99.73 38	97.53 205		86.71 477		99.37 121	99.52 68	89.93 381	99.92 65	98.99 90	99.72 188	99.44 198

SteuartSystems-ACMMP		98.79 123	98.54 158	99.54 32	99.73 38	99.16 49	98.23 165	99.31 216	97.92 223	98.90 218	98.90 235	98.00 125	99.88 115	96.15 317	99.72 188	99.58 116
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 233	98.15 225	98.22 288	99.73 38	95.15 332	97.36 308	99.68 61	94.45 403	98.99 195	99.27 124	96.87 219	99.94 42	97.13 230	99.91 78	99.57 124

Vis-MVSNet		99.34 31	99.36 34	99.27 100	99.73 38	98.26 129	99.17 54	99.78 37	99.11 99	99.27 144	99.48 76	98.82 38	99.95 26	98.94 93	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 44	98.98 72	99.51 10	99.85 18	99.86 6	99.88 21	99.82 5	99.02 27	99.90 81	99.54 44	99.95 38	99.61 98

SSC-MVS		98.71 134	98.74 118	98.62 224	99.72 44	96.08 293	98.74 98	98.64 356	99.74 13	99.67 60	99.24 137	94.57 315	99.95 26	99.11 79	99.24 328	99.82 36

test_f		98.67 152	98.87 103	98.05 303	99.72 44	95.59 308	98.51 133	99.81 31	96.30 348	99.78 40	99.82 5	96.14 259	98.63 462	99.82 12	99.93 56	99.95 9

ACMH	96.65 7	99.25 42	99.24 55	99.26 102	99.72 44	98.38 120	99.07 65	99.55 108	98.30 181	99.65 64	99.45 85	99.22 17	99.76 267	98.44 129	99.77 157	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 48	98.94 79	99.54 8	99.83 25	99.87 5	99.89 18	99.82 5	98.75 47	99.90 81	99.54 44	99.95 38	99.59 107

fmvsm_s_conf0.1_n		99.16 58	99.33 39	98.64 218	99.71 48	96.10 288	97.87 230	99.85 18	98.56 165	99.90 14	99.68 26	98.69 53	99.85 156	99.72 30	99.98 12	99.97 4

PS-CasMVS		99.40 27	99.33 39	99.62 10	99.71 48	99.10 66	99.29 37	99.53 117	99.53 42	99.46 102	99.41 94	98.23 101	99.95 26	98.89 97	99.95 38	99.81 40

DTE-MVSNet		99.43 24	99.35 35	99.66 7	99.71 48	99.30 23	99.31 31	99.51 123	99.64 27	99.56 74	99.46 81	98.23 101	99.97 7	98.78 103	99.93 56	99.72 62

WR-MVS_H		99.33 32	99.22 56	99.65 8	99.71 48	99.24 31	99.32 27	99.55 108	99.46 51	99.50 95	99.34 109	97.30 192	99.93 54	98.90 95	99.93 56	99.77 50

HPM-MVS_fast		99.01 83	98.82 111	99.57 22	99.71 48	99.35 17	99.00 73	99.50 126	97.33 280	98.94 213	98.86 245	98.75 47	99.82 206	97.53 201	99.71 197	99.56 130

ACMH+	96.62 9	99.08 77	99.00 88	99.33 90	99.71 48	98.83 88	98.60 119	99.58 88	99.11 99	99.53 83	99.18 153	98.81 39	99.67 320	96.71 271	99.77 157	99.50 161

PMVS	91.26 20	97.86 262	97.94 249	97.65 335	99.71 48	97.94 169	98.52 128	98.68 352	98.99 122	97.52 360	99.35 105	97.41 185	98.18 468	91.59 431	99.67 218	96.82 457
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
KinetiMVS		99.03 81	99.02 84	99.03 146	99.70 56	97.48 208	98.43 146	99.29 232	99.70 16	99.60 71	99.07 182	96.13 260	99.94 42	99.42 56	99.87 98	99.68 71

FIs		99.14 63	99.09 76	99.29 96	99.70 56	98.28 128	99.13 59	99.52 122	99.48 45	99.24 154	99.41 94	96.79 227	99.82 206	98.69 113	99.88 94	99.76 56

VPNet		98.87 105	98.83 110	99.01 150	99.70 56	97.62 201	98.43 146	99.35 197	99.47 48	99.28 142	99.05 190	96.72 233	99.82 206	98.09 151	99.36 307	99.59 107

fmvsm_s_conf0.1_n_2		99.20 52	99.38 30	98.65 216	99.69 59	96.08 293	97.49 289	99.90 11	99.53 42	99.88 21	99.64 38	98.51 72	99.90 81	99.83 10	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 209	98.68 133	97.27 366	99.69 59	92.29 415	98.03 198	99.85 18	97.62 245	99.96 4	99.62 41	93.98 330	99.74 280	99.52 50	99.86 105	99.79 44

MP-MVS-pluss		98.57 169	98.23 213	99.60 16	99.69 59	99.35 17	97.16 329	99.38 183	94.87 393	98.97 200	98.99 212	98.01 124	99.88 115	97.29 217	99.70 204	99.58 116
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 47	99.32 41	98.96 159	99.68 62	97.35 216	98.84 95	99.48 135	99.69 18	99.63 67	99.68 26	99.03 25	99.96 14	97.97 164	99.92 69	99.57 124

sd_testset		99.28 38	99.31 43	99.19 113	99.68 62	98.06 156	99.41 17	99.30 224	99.69 18	99.63 67	99.68 26	99.25 16	99.96 14	97.25 220	99.92 69	99.57 124

test_fmvs1_n		98.09 239	98.28 204	97.52 352	99.68 62	93.47 394	98.63 115	99.93 5	95.41 381	99.68 58	99.64 38	91.88 364	99.48 403	99.82 12	99.87 98	99.62 90

CHOSEN 1792x2688		97.49 291	97.14 306	98.54 246	99.68 62	96.09 291	96.50 365	99.62 75	91.58 441	98.84 232	98.97 219	92.36 356	99.88 115	96.76 264	99.95 38	99.67 76

tfpnnormal		98.90 100	98.90 98	98.91 168	99.67 66	97.82 184	99.00 73	99.44 160	99.45 52	99.51 93	99.24 137	98.20 108	99.86 143	95.92 326	99.69 207	99.04 318

MTAPA		98.88 104	98.64 141	99.61 14	99.67 66	99.36 16	98.43 146	99.20 256	98.83 143	98.89 221	98.90 235	96.98 213	99.92 65	97.16 225	99.70 204	99.56 130

test_fmvsmvis_n_1920		99.26 41	99.49 17	98.54 246	99.66 68	96.97 248	98.00 205	99.85 18	99.24 77	99.92 8	99.50 69	99.39 12	99.95 26	99.89 3	99.98 12	98.71 372

mvs5depth		99.30 35	99.59 12	98.44 260	99.65 69	95.35 324	99.82 3	99.94 2	99.83 7	99.42 111	99.94 2	98.13 116	99.96 14	99.63 36	99.96 28	100.00 1

fmvsm_l_conf0.5_n_a		99.19 53	99.27 49	98.94 162	99.65 69	97.05 243	97.80 239	99.76 40	98.70 148	99.78 40	99.11 172	98.79 43	99.95 26	99.85 6	99.96 28	99.83 33

WB-MVS		98.52 183	98.55 156	98.43 261	99.65 69	95.59 308	98.52 128	98.77 341	99.65 26	99.52 88	99.00 210	94.34 321	99.93 54	98.65 115	98.83 376	99.76 56

CP-MVSNet		99.21 49	99.09 76	99.56 27	99.65 69	98.96 78	99.13 59	99.34 203	99.42 57	99.33 130	99.26 130	97.01 211	99.94 42	98.74 108	99.93 56	99.79 44

HPM-MVS		98.79 123	98.53 160	99.59 20	99.65 69	99.29 25	99.16 55	99.43 166	96.74 326	98.61 265	98.38 336	98.62 60	99.87 134	96.47 297	99.67 218	99.59 107
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 161	98.36 191	99.42 69	99.65 69	99.42 11	98.55 124	99.57 95	97.72 239	98.90 218	99.26 130	96.12 262	99.52 391	95.72 337	99.71 197	99.32 254

NormalMVS		98.26 219	97.97 246	99.15 122	99.64 75	97.83 179	98.28 159	99.43 166	99.24 77	98.80 240	98.85 248	89.76 383	99.94 42	98.04 156	99.67 218	99.68 71

lecture		99.25 42	99.12 71	99.62 10	99.64 75	99.40 12	98.89 88	99.51 123	99.19 89	99.37 121	99.25 135	98.36 83	99.88 115	98.23 141	99.67 218	99.59 107

fmvsm_l_conf0.5_n		99.21 49	99.28 48	99.02 149	99.64 75	97.28 223	97.82 235	99.76 40	98.73 145	99.82 34	99.09 180	98.81 39	99.95 26	99.86 4	99.96 28	99.83 33

test_fmvsmconf_n		99.44 20	99.48 19	99.31 95	99.64 75	98.10 146	97.68 258	99.84 22	99.29 73	99.92 8	99.57 50	99.60 5	99.96 14	99.74 27	99.98 12	99.89 16

TSAR-MVS + MP.		98.63 158	98.49 170	99.06 142	99.64 75	97.90 173	98.51 133	98.94 306	96.96 311	99.24 154	98.89 241	97.83 143	99.81 223	96.88 254	99.49 287	99.48 179
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 117	98.72 122	99.12 125	99.64 75	98.54 111	97.98 213	99.68 61	97.62 245	99.34 128	99.18 153	97.54 172	99.77 261	97.79 178	99.74 177	99.04 318

Elysia		99.15 59	99.14 69	99.18 114	99.63 81	97.92 170	98.50 135	99.43 166	99.67 21	99.70 52	99.13 168	96.66 236	99.98 4	99.54 44	99.96 28	99.64 84

StellarMVS		99.15 59	99.14 69	99.18 114	99.63 81	97.92 170	98.50 135	99.43 166	99.67 21	99.70 52	99.13 168	96.66 236	99.98 4	99.54 44	99.96 28	99.64 84

KD-MVS_self_test		99.25 42	99.18 60	99.44 66	99.63 81	99.06 71	98.69 107	99.54 113	99.31 70	99.62 70	99.53 65	97.36 189	99.86 143	99.24 70	99.71 197	99.39 220

EU-MVSNet		97.66 279	98.50 165	95.13 432	99.63 81	85.84 463	98.35 155	98.21 375	98.23 188	99.54 79	99.46 81	95.02 301	99.68 316	98.24 139	99.87 98	99.87 22

HyFIR lowres test		97.19 317	96.60 341	98.96 159	99.62 85	97.28 223	95.17 430	99.50 126	94.21 408	99.01 190	98.32 344	86.61 403	99.99 2	97.10 232	99.84 112	99.60 100

fmvsm_l_conf0.5_n_9		99.32 34	99.43 25	98.98 156	99.59 86	97.18 234	97.44 298	99.83 25	99.56 40	99.91 12	99.34 109	99.36 13	99.93 54	99.83 10	99.98 12	99.85 30

fmvsm_l_conf0.5_n_3		99.45 19	99.48 19	99.34 84	99.59 86	98.21 137	97.82 235	99.84 22	99.41 59	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 88	98.93 80	98.68 108	99.60 79	96.46 339	99.53 83	98.77 268		99.83 193	96.67 274	99.64 229	99.58 116

MED-MVS		98.90 100	98.72 122	99.45 64	99.58 88	98.93 80	98.68 108	99.60 79	98.14 207	99.53 83	98.77 268	97.87 140	99.83 193	96.67 274	99.64 229	99.58 116

TestfortrainingZip a		98.95 93	98.72 122	99.64 9	99.58 88	99.32 22	98.68 108	99.60 79	96.46 339	99.53 83	98.77 268	97.87 140	99.83 193	98.39 132	99.64 229	99.77 50

FE-MVSNET		98.59 166	98.50 165	98.87 172	99.58 88	97.30 221	98.08 187	99.74 44	96.94 313	98.97 200	99.10 175	96.94 215	99.74 280	97.33 215	99.86 105	99.55 137

mmtdpeth		99.30 35	99.42 26	98.92 167	99.58 88	96.89 255	99.48 13	99.92 7	99.92 2	98.26 303	99.80 11	98.33 89	99.91 74	99.56 41	99.95 38	99.97 4

ACMMP_NAP		98.75 130	98.48 171	99.57 22	99.58 88	99.29 25	97.82 235	99.25 245	96.94 313	98.78 242	99.12 171	98.02 123	99.84 174	97.13 230	99.67 218	99.59 107

nrg030		99.40 27	99.35 35	99.54 32	99.58 88	99.13 61	98.98 76	99.48 135	99.68 20	99.46 102	99.26 130	98.62 60	99.73 287	99.17 75	99.92 69	99.76 56

VDDNet		98.21 226	97.95 247	99.01 150	99.58 88	97.74 192	99.01 71	97.29 404	99.67 21	98.97 200	99.50 69	90.45 378	99.80 231	97.88 171	99.20 336	99.48 179

COLMAP_ROB	96.50 10	98.99 86	98.85 109	99.41 71	99.58 88	99.10 66	98.74 98	99.56 104	99.09 109	99.33 130	99.19 149	98.40 80	99.72 295	95.98 324	99.76 172	99.42 207
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 32	99.45 24	98.99 152	99.57 97	97.73 194	97.93 219	99.83 25	99.22 80	99.93 6	99.30 118	99.42 11	99.96 14	99.85 6	99.99 5	99.29 263

ZNCC-MVS		98.68 149	98.40 183	99.54 32	99.57 97	99.21 34	98.46 143	99.29 232	97.28 286	98.11 315	98.39 334	98.00 125	99.87 134	96.86 257	99.64 229	99.55 137

MSP-MVS		98.40 195	98.00 241	99.61 14	99.57 97	99.25 30	98.57 122	99.35 197	97.55 256	99.31 138	97.71 384	94.61 314	99.88 115	96.14 318	99.19 339	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		98.32 210	98.39 186	98.13 295	99.57 97	95.54 311	97.78 241	99.49 133	97.37 277	99.19 162	97.65 388	98.96 30	99.49 400	96.50 296	98.99 364	99.34 245

MP-MVS		98.46 189	98.09 230	99.54 32	99.57 97	99.22 33	98.50 135	99.19 260	97.61 248	97.58 354	98.66 296	97.40 186	99.88 115	94.72 363	99.60 246	99.54 143
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 134	98.46 175	99.47 61	99.57 97	98.97 74	98.23 165	99.48 135	96.60 331	99.10 172	99.06 183	98.71 51	99.83 193	95.58 344	99.78 151	99.62 90

LGP-MVS_train				99.47 61	99.57 97	98.97 74		99.48 135	96.60 331	99.10 172	99.06 183	98.71 51	99.83 193	95.58 344	99.78 151	99.62 90

IS-MVSNet		98.19 229	97.90 255	99.08 134	99.57 97	97.97 164	99.31 31	98.32 371	99.01 121	98.98 196	99.03 194	91.59 366	99.79 244	95.49 346	99.80 140	99.48 179

viewdifsd2359ckpt11		98.84 111	99.04 81	98.24 284	99.56 105	95.51 313	97.38 303	99.70 53	99.16 94	99.57 72	99.40 97	98.26 97	99.71 296	98.55 124	99.82 123	99.50 161

viewmsd2359difaftdt		98.84 111	99.04 81	98.24 284	99.56 105	95.51 313	97.38 303	99.70 53	99.16 94	99.57 72	99.40 97	98.26 97	99.71 296	98.55 124	99.82 123	99.50 161

dcpmvs_2		98.78 125	99.11 72	97.78 318	99.56 105	93.67 389	99.06 66	99.86 16	99.50 44	99.66 61	99.26 130	97.21 200	99.99 2	98.00 161	99.91 78	99.68 71

test_0402		98.76 129	98.71 127	98.93 164	99.56 105	98.14 142	98.45 145	99.34 203	99.28 74	98.95 206	98.91 232	98.34 88	99.79 244	95.63 341	99.91 78	98.86 350

EPP-MVSNet		98.30 213	98.04 237	99.07 136	99.56 105	97.83 179	99.29 37	98.07 382	99.03 119	98.59 269	99.13 168	92.16 360	99.90 81	96.87 255	99.68 212	99.49 168

ACMMP		98.75 130	98.50 165	99.52 45	99.56 105	99.16 49	98.87 89	99.37 187	97.16 301	98.82 236	99.01 206	97.71 154	99.87 134	96.29 309	99.69 207	99.54 143
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	98.78 190	99.55 111	96.59 268	97.79 240	99.82 30	98.21 191	99.81 37	99.53 65	98.46 76	99.84 174	99.70 33	99.97 21	99.90 15

fmvsm_s_conf0.5_n		99.09 73	99.26 52	98.61 227	99.55 111	96.09 291	97.74 251	99.81 31	98.55 166	99.85 27	99.55 58	98.60 62	99.84 174	99.69 35	99.98 12	99.89 16

FMVSNet1		99.17 54	99.17 61	99.17 116	99.55 111	98.24 131	99.20 49	99.44 160	99.21 82	99.43 107	99.55 58	97.82 146	99.86 143	98.42 131	99.89 92	99.41 210

Vis-MVSNet (Re-imp)		97.46 293	97.16 303	98.34 273	99.55 111	96.10 288	98.94 81	98.44 365	98.32 179	98.16 309	98.62 305	88.76 390	99.73 287	93.88 389	99.79 146	99.18 297

ACMM	96.08 12	98.91 98	98.73 120	99.48 57	99.55 111	99.14 58	98.07 191	99.37 187	97.62 245	99.04 186	98.96 222	98.84 37	99.79 244	97.43 210	99.65 227	99.49 168
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 139	98.97 92	97.89 311	99.54 116	94.05 366	98.55 124	99.92 7	96.78 324	99.72 48	99.78 13	96.60 240	99.67 320	99.91 2	99.90 86	99.94 10

mPP-MVS		98.64 156	98.34 194	99.54 32	99.54 116	99.17 45	98.63 115	99.24 250	97.47 264	98.09 317	98.68 291	97.62 163	99.89 97	96.22 312	99.62 239	99.57 124

XVG-ACMP-BASELINE		98.56 170	98.34 194	99.22 110	99.54 116	98.59 105	97.71 254	99.46 148	97.25 289	98.98 196	98.99 212	97.54 172	99.84 174	95.88 327	99.74 177	99.23 279

viewmacassd2359aftdt		98.86 108	98.87 103	98.83 177	99.53 119	97.32 220	97.70 256	99.64 71	98.22 189	99.25 152	99.27 124	98.40 80	99.61 356	97.98 163	99.87 98	99.55 137

region2R		98.69 143	98.40 183	99.54 32	99.53 119	99.17 45	98.52 128	99.31 216	97.46 269	98.44 288	98.51 319	97.83 143	99.88 115	96.46 298	99.58 255	99.58 116

PGM-MVS		98.66 153	98.37 190	99.55 29	99.53 119	99.18 44	98.23 165	99.49 133	97.01 310	98.69 253	98.88 242	98.00 125	99.89 97	95.87 330	99.59 250	99.58 116

Patchmatch-RL test		97.26 310	97.02 311	97.99 307	99.52 122	95.53 312	96.13 390	99.71 48	97.47 264	99.27 144	99.16 159	84.30 424	99.62 349	97.89 168	99.77 157	98.81 358

ACMMPR		98.70 139	98.42 181	99.54 32	99.52 122	99.14 58	98.52 128	99.31 216	97.47 264	98.56 275	98.54 314	97.75 152	99.88 115	96.57 285	99.59 250	99.58 116

fmvsm_s_conf0.5_n_9		99.17 54	99.38 30	98.53 248	99.51 124	95.82 303	97.62 269	99.78 37	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		98.16 235	98.07 235	98.41 263	99.51 124	95.86 300	98.00 205	95.14 445	98.97 125	99.43 107	99.24 137	93.25 338	99.84 174	99.21 71	99.87 98	99.54 143

fmvsm_s_conf0.5_n_8		99.13 67	99.26 52	98.74 203	99.51 124	96.44 280	97.65 264	99.65 69	99.66 24	99.78 40	99.48 76	97.92 133	99.93 54	99.72 30	99.95 38	99.87 22

GST-MVS		98.61 162	98.30 201	99.52 45	99.51 124	99.20 40	98.26 163	99.25 245	97.44 272	98.67 256	98.39 334	97.68 155	99.85 156	96.00 322	99.51 277	99.52 155

Anonymous20231206		98.21 226	98.21 214	98.20 289	99.51 124	95.43 322	98.13 177	99.32 211	96.16 352	98.93 214	98.82 258	96.00 267	99.83 193	97.32 216	99.73 180	99.36 238

ACMP	95.32 15	98.41 193	98.09 230	99.36 75	99.51 124	98.79 91	97.68 258	99.38 183	95.76 368	98.81 238	98.82 258	98.36 83	99.82 206	94.75 360	99.77 157	99.48 179
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LuminaMVS		98.39 201	98.20 215	98.98 156	99.50 130	97.49 206	97.78 241	97.69 391	98.75 144	99.49 96	99.25 135	92.30 358	99.94 42	99.14 76	99.88 94	99.50 161

DVP-MVS		98.77 128	98.52 161	99.52 45	99.50 130	99.21 34	98.02 201	98.84 330	97.97 217	99.08 174	99.02 195	97.61 165	99.88 115	96.99 241	99.63 236	99.48 179
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	99.50 130	99.23 32	98.02 201	99.32 211					99.88 115	96.99 241	99.63 236	99.68 71

test0726					99.50 130	99.21 34	98.17 173	99.35 197	97.97 217	99.26 148	99.06 183	97.61 165

AllTest		98.44 191	98.20 215	99.16 119	99.50 130	98.55 108	98.25 164	99.58 88	96.80 322	98.88 225	99.06 183	97.65 158	99.57 372	94.45 370	99.61 244	99.37 231

TestCases				99.16 119	99.50 130	98.55 108		99.58 88	96.80 322	98.88 225	99.06 183	97.65 158	99.57 372	94.45 370	99.61 244	99.37 231

XVG-OURS		98.53 179	98.34 194	99.11 127	99.50 130	98.82 90	95.97 396	99.50 126	97.30 284	99.05 184	98.98 217	99.35 14	99.32 430	95.72 337	99.68 212	99.18 297

EG-PatchMatch MVS		98.99 86	99.01 86	98.94 162	99.50 130	97.47 209	98.04 196	99.59 86	98.15 206	99.40 116	99.36 104	98.58 68	99.76 267	98.78 103	99.68 212	99.59 107

fmvsm_s_conf0.5_n_2		99.14 63	99.31 43	98.63 222	99.49 138	96.08 293	97.38 303	99.81 31	99.48 45	99.84 30	99.57 50	98.46 76	99.89 97	99.82 12	99.97 21	99.91 13

SED-MVS		98.91 98	98.72 122	99.49 55	99.49 138	99.17 45	98.10 184	99.31 216	98.03 213	99.66 61	99.02 195	98.36 83	99.88 115	96.91 247	99.62 239	99.41 210

IU-MVS					99.49 138	99.15 53		98.87 321	92.97 426	99.41 113				96.76 264	99.62 239	99.66 78

test_241102_ONE					99.49 138	99.17 45		99.31 216	97.98 216	99.66 61	98.90 235	98.36 83	99.48 403

UA-Net		99.47 17	99.40 28	99.70 2	99.49 138	99.29 25	99.80 4	99.72 46	99.82 8	99.04 186	99.81 8	98.05 122	99.96 14	98.85 99	99.99 5	99.86 28

HFP-MVS		98.71 134	98.44 178	99.51 49	99.49 138	99.16 49	98.52 128	99.31 216	97.47 264	98.58 271	98.50 323	97.97 129	99.85 156	96.57 285	99.59 250	99.53 152

VPA-MVSNet		99.30 35	99.30 46	99.28 97	99.49 138	98.36 125	99.00 73	99.45 152	99.63 29	99.52 88	99.44 86	98.25 99	99.88 115	99.09 81	99.84 112	99.62 90

XVG-OURS-SEG-HR		98.49 186	98.28 204	99.14 123	99.49 138	98.83 88	96.54 361	99.48 135	97.32 282	99.11 169	98.61 307	99.33 15	99.30 433	96.23 311	98.38 400	99.28 266

fmvsm_s_conf0.5_n_11		99.21 49	99.34 37	98.80 183	99.48 146	96.56 273	97.97 217	99.69 55	99.63 29	99.84 30	99.54 64	98.21 106	99.94 42	99.76 23	99.95 38	99.88 20

114514_t		96.50 350	95.77 359	98.69 211	99.48 146	97.43 213	97.84 234	99.55 108	81.42 473	96.51 413	98.58 311	95.53 287	99.67 320	93.41 402	99.58 255	98.98 328

IterMVS-LS		98.55 174	98.70 130	98.09 296	99.48 146	94.73 346	97.22 323	99.39 181	98.97 125	99.38 119	99.31 117	96.00 267	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 59	99.27 49	98.78 190	99.47 149	96.56 273	97.75 250	99.71 48	99.60 36	99.74 47	99.44 86	97.96 130	99.95 26	99.86 4	99.94 50	99.82 36

fmvsm_s_conf0.5_n_5		99.07 79	99.10 74	98.99 152	99.47 149	97.22 228	97.40 300	99.83 25	97.61 248	99.85 27	99.30 118	98.80 41	99.95 26	99.71 32	99.90 86	99.78 47

v8		99.01 83	99.16 63	98.57 234	99.47 149	96.31 285	98.90 84	99.47 144	99.03 119	99.52 88	99.57 50	96.93 216	99.81 223	99.60 37	99.98 12	99.60 100

SSC-MVS3.2		98.53 179	98.79 114	97.74 325	99.46 152	93.62 392	96.45 367	99.34 203	99.33 67	98.93 214	98.70 287	97.90 134	99.90 81	99.12 78	99.92 69	99.69 70

fmvsm_s_conf0.5_n_3		99.22 48	99.37 33	98.78 190	99.46 152	96.58 271	97.65 264	99.72 46	99.47 48	99.86 24	99.50 69	98.94 31	99.89 97	99.75 26	99.97 21	99.86 28

XVS		98.72 133	98.45 176	99.53 39	99.46 152	99.21 34	98.65 113	99.34 203	98.62 155	97.54 358	98.63 303	97.50 178	99.83 193	96.79 260	99.53 272	99.56 130

X-MVStestdata		94.32 399	92.59 418	99.53 39	99.46 152	99.21 34	98.65 113	99.34 203	98.62 155	97.54 358	45.85 478	97.50 178	99.83 193	96.79 260	99.53 272	99.56 130

test20.03		98.78 125	98.77 117	98.78 190	99.46 152	97.20 231	97.78 241	99.24 250	99.04 118	99.41 113	98.90 235	97.65 158	99.76 267	97.70 189	99.79 146	99.39 220

guyue		98.01 247	97.93 251	98.26 280	99.45 157	95.48 317	98.08 187	96.24 428	98.89 136	99.34 128	99.14 166	91.32 370	99.82 206	99.07 82	99.83 119	99.48 179

CSCG		98.68 149	98.50 165	99.20 111	99.45 157	98.63 100	98.56 123	99.57 95	97.87 227	98.85 230	98.04 365	97.66 157	99.84 174	96.72 269	99.81 129	99.13 307

GeoE		99.05 80	98.99 90	99.25 105	99.44 159	98.35 126	98.73 102	99.56 104	98.42 172	98.91 217	98.81 261	98.94 31	99.91 74	98.35 134	99.73 180	99.49 168

v148		98.45 190	98.60 150	98.00 306	99.44 159	94.98 338	97.44 298	99.06 286	98.30 181	99.32 136	98.97 219	96.65 238	99.62 349	98.37 133	99.85 107	99.39 220

v10		98.97 90	99.11 72	98.55 241	99.44 159	96.21 287	98.90 84	99.55 108	98.73 145	99.48 97	99.60 46	96.63 239	99.83 193	99.70 33	99.99 5	99.61 98

V42		98.78 125	98.78 116	98.76 197	99.44 159	97.04 244	98.27 162	99.19 260	97.87 227	99.25 152	99.16 159	96.84 220	99.78 255	99.21 71	99.84 112	99.46 189

MDA-MVSNet-bldmvs		97.94 253	97.91 254	98.06 301	99.44 159	94.96 339	96.63 357	99.15 276	98.35 175	98.83 233	99.11 172	94.31 322	99.85 156	96.60 282	98.72 382	99.37 231

viewdifsd2359ckpt07		98.71 134	98.86 107	98.26 280	99.43 164	95.65 307	97.20 324	99.66 65	99.20 84	99.29 140	99.01 206	98.29 92	99.73 287	97.92 167	99.75 176	99.39 220

casdiffmvs_mvg		99.12 70	99.16 63	98.99 152	99.43 164	97.73 194	98.00 205	99.62 75	99.22 80	99.55 77	99.22 143	98.93 33	99.75 275	98.66 114	99.81 129	99.50 161
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		98.90 100	99.01 86	98.57 234	99.42 166	96.59 268	98.13 177	99.66 65	99.09 109	99.30 139	99.02 195	98.79 43	99.89 97	97.87 173	99.80 140	99.23 279

test1111		96.49 351	96.82 325	95.52 425	99.42 166	87.08 460	99.22 46	87.14 476	99.11 99	99.46 102	99.58 48	88.69 391	99.86 143	98.80 101	99.95 38	99.62 90

v2v482		98.56 170	98.62 145	98.37 270	99.42 166	95.81 304	97.58 277	99.16 271	97.90 225	99.28 142	99.01 206	95.98 272	99.79 244	99.33 60	99.90 86	99.51 158

OPM-MVS		98.56 170	98.32 199	99.25 105	99.41 169	98.73 96	97.13 331	99.18 264	97.10 304	98.75 248	98.92 230	98.18 109	99.65 340	96.68 273	99.56 262	99.37 231
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 241	98.08 233	98.04 304	99.41 169	94.59 352	94.59 448	99.40 179	97.50 261	98.82 236	98.83 255	96.83 222	99.84 174	97.50 204	99.81 129	99.71 63

E2		98.70 139	98.68 133	98.73 205	99.40 171	97.10 241	97.48 290	99.57 95	98.09 210	99.00 191	99.20 146	97.90 134	99.67 320	97.73 187	99.77 157	99.43 202

E3		98.69 143	98.68 133	98.73 205	99.40 171	97.10 241	97.48 290	99.57 95	98.09 210	99.00 191	99.20 146	97.90 134	99.67 320	97.73 187	99.77 157	99.43 202

test_one_0601					99.39 173	99.20 40		99.31 216	98.49 168	98.66 258	99.02 195	97.64 161

mvsany_test3		98.87 105	98.92 96	98.74 203	99.38 174	96.94 252	98.58 121	99.10 281	96.49 336	99.96 4	99.81 8	98.18 109	99.45 411	98.97 91	99.79 146	99.83 33

patch_mono-2		98.51 184	98.63 143	98.17 292	99.38 174	94.78 343	97.36 308	99.69 55	98.16 201	98.49 284	99.29 121	97.06 206	99.97 7	98.29 138	99.91 78	99.76 56

test2506		92.39 430	91.89 432	93.89 446	99.38 174	82.28 477	99.32 27	66.03 484	99.08 113	98.77 245	99.57 50	66.26 471	99.84 174	98.71 111	99.95 38	99.54 143

ECVR-MVS		96.42 353	96.61 339	95.85 417	99.38 174	88.18 455	99.22 46	86.00 478	99.08 113	99.36 124	99.57 50	88.47 396	99.82 206	98.52 126	99.95 38	99.54 143

casdiffmvs		98.95 93	99.00 88	98.81 181	99.38 174	97.33 218	97.82 235	99.57 95	99.17 93	99.35 126	99.17 157	98.35 87	99.69 307	98.46 128	99.73 180	99.41 210
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 92	99.02 84	98.76 197	99.38 174	97.26 225	98.49 138	99.50 126	98.86 139	99.19 162	99.06 183	98.23 101	99.69 307	98.71 111	99.76 172	99.33 251

TranMVSNet+NR-MVSNet		99.17 54	99.07 79	99.46 63	99.37 180	98.87 85	98.39 151	99.42 172	99.42 57	99.36 124	99.06 183	98.38 82	99.95 26	98.34 135	99.90 86	99.57 124

fmvsm_s_conf0.5_n_6		99.08 77	99.21 58	98.69 211	99.36 181	96.51 275	97.62 269	99.68 61	98.43 171	99.85 27	99.10 175	99.12 23	99.88 115	99.77 22	99.92 69	99.67 76

tttt0517		95.64 378	94.98 388	97.64 338	99.36 181	93.81 384	98.72 103	90.47 470	98.08 212	98.67 256	98.34 341	73.88 457	99.92 65	97.77 180	99.51 277	99.20 289

test_part2					99.36 181	99.10 66				99.05 184

v1144		98.60 164	98.66 138	98.41 263	99.36 181	95.90 298	97.58 277	99.34 203	97.51 260	99.27 144	99.15 163	96.34 253	99.80 231	99.47 54	99.93 56	99.51 158

CP-MVS		98.70 139	98.42 181	99.52 45	99.36 181	99.12 63	98.72 103	99.36 191	97.54 258	98.30 297	98.40 333	97.86 142	99.89 97	96.53 294	99.72 188	99.56 130

diffmvs_AUTHOR		98.50 185	98.59 152	98.23 287	99.35 186	95.48 317	96.61 358	99.60 79	98.37 173	98.90 218	99.00 210	97.37 188	99.76 267	98.22 142	99.85 107	99.46 189

Test_1112_low_res		96.99 332	96.55 343	98.31 276	99.35 186	95.47 320	95.84 408	99.53 117	91.51 443	96.80 400	98.48 326	91.36 369	99.83 193	96.58 283	99.53 272	99.62 90

DeepC-MVS	97.60 4	98.97 90	98.93 95	99.10 129	99.35 186	97.98 163	98.01 204	99.46 148	97.56 254	99.54 79	99.50 69	98.97 29	99.84 174	98.06 154	99.92 69	99.49 168
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 309	96.86 321	98.58 231	99.34 189	96.32 284	96.75 350	99.58 88	93.14 424	96.89 395	97.48 398	92.11 361	99.86 143	96.91 247	99.54 268	99.57 124

reproduce_model		99.15 59	98.97 92	99.67 4	99.33 190	99.44 10	98.15 175	99.47 144	99.12 98	99.52 88	99.32 116	98.31 90	99.90 81	97.78 179	99.73 180	99.66 78

MVSMamba_PlusPlus		98.83 114	98.98 91	98.36 271	99.32 191	96.58 271	98.90 84	99.41 176	99.75 11	98.72 251	99.50 69	96.17 258	99.94 42	99.27 65	99.78 151	98.57 388

fmvsm_s_conf0.5_n_4		99.01 83	99.22 56	98.38 267	99.31 192	95.48 317	97.56 279	99.73 45	98.87 137	99.75 45	99.27 124	98.80 41	99.86 143	99.80 17	99.90 86	99.81 40

SF-MVS		98.53 179	98.27 207	99.32 92	99.31 192	98.75 92	98.19 169	99.41 176	96.77 325	98.83 233	98.90 235	97.80 148	99.82 206	95.68 340	99.52 275	99.38 229

CPTT-MVS		97.84 268	97.36 292	99.27 100	99.31 192	98.46 116	98.29 158	99.27 239	94.90 392	97.83 338	98.37 337	94.90 303	99.84 174	93.85 391	99.54 268	99.51 158

UnsupCasMVSNet_eth		97.89 257	97.60 278	98.75 199	99.31 192	97.17 236	97.62 269	99.35 197	98.72 147	98.76 247	98.68 291	92.57 355	99.74 280	97.76 184	95.60 462	99.34 245

fmvsm_s_conf0.5_n_7		98.83 114	99.04 81	98.20 289	99.30 196	94.83 341	97.23 319	99.36 191	98.64 150	99.84 30	99.43 89	98.10 118	99.91 74	99.56 41	99.96 28	99.87 22

pmmvs-eth3d		98.47 188	98.34 194	98.86 174	99.30 196	97.76 190	97.16 329	99.28 236	95.54 374	99.42 111	99.19 149	97.27 195	99.63 346	97.89 168	99.97 21	99.20 289

mamv4		99.44 20	99.39 29	99.58 21	99.30 196	99.74 2	99.04 69	99.81 31	99.77 10	99.82 34	99.57 50	97.82 146	99.98 4	99.53 48	99.89 92	99.01 322

viewcassd2359sk11		98.55 174	98.51 162	98.67 214	99.29 199	96.99 247	97.39 301	99.54 113	97.73 237	98.81 238	99.08 181	97.55 170	99.66 333	97.52 203	99.67 218	99.36 238

SymmetryMVS		98.05 243	97.71 268	99.09 133	99.29 199	97.83 179	98.28 159	97.64 396	99.24 77	98.80 240	98.85 248	89.76 383	99.94 42	98.04 156	99.50 285	99.49 168

Anonymous20231211		99.27 39	99.27 49	99.26 102	99.29 199	98.18 138	99.49 12	99.51 123	99.70 16	99.80 38	99.68 26	96.84 220	99.83 193	99.21 71	99.91 78	99.77 50

viewmanbaseed2359cas		98.58 168	98.54 158	98.70 209	99.28 202	97.13 240	97.47 294	99.55 108	97.55 256	98.96 205	98.92 230	97.77 150	99.59 363	97.59 197	99.77 157	99.39 220

UnsupCasMVSNet_bld		97.30 307	96.92 317	98.45 258	99.28 202	96.78 262	96.20 384	99.27 239	95.42 378	98.28 301	98.30 345	93.16 341	99.71 296	94.99 354	97.37 438	98.87 349

EC-MVSNet		99.09 73	99.05 80	99.20 111	99.28 202	98.93 80	99.24 45	99.84 22	99.08 113	98.12 314	98.37 337	98.72 50	99.90 81	99.05 85	99.77 157	98.77 366

mamba_0408		98.80 121	98.88 101	98.55 241	99.27 205	96.50 276	98.00 205	99.60 79	98.93 130	99.22 157	98.84 253	98.59 63	99.89 97	97.74 185	99.72 188	99.27 267

SSM_04072		98.80 121	98.88 101	98.56 239	99.27 205	96.50 276	98.00 205	99.60 79	98.93 130	99.22 157	98.84 253	98.59 63	99.90 81	97.74 185	99.72 188	99.27 267

SSM_0407		98.86 108	98.96 94	98.55 241	99.27 205	96.50 276	98.04 196	99.66 65	99.09 109	99.22 157	99.02 195	98.79 43	99.87 134	97.87 173	99.72 188	99.27 267

reproduce-ours		99.09 73	98.90 98	99.67 4	99.27 205	99.49 6	98.00 205	99.42 172	99.05 116	99.48 97	99.27 124	98.29 92	99.89 97	97.61 194	99.71 197	99.62 90

our_new_method		99.09 73	98.90 98	99.67 4	99.27 205	99.49 6	98.00 205	99.42 172	99.05 116	99.48 97	99.27 124	98.29 92	99.89 97	97.61 194	99.71 197	99.62 90

DPE-MVS		98.59 166	98.26 208	99.57 22	99.27 205	99.15 53	97.01 334	99.39 181	97.67 241	99.44 106	98.99 212	97.53 174	99.89 97	95.40 348	99.68 212	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		97.85 267	98.18 220	96.87 386	99.27 205	91.16 435	95.53 418	99.25 245	99.10 106	99.41 113	99.35 105	93.10 343	99.96 14	98.65 115	99.94 50	99.49 168

v1192		98.60 164	98.66 138	98.41 263	99.27 205	95.88 299	97.52 284	99.36 191	97.41 273	99.33 130	99.20 146	96.37 251	99.82 206	99.57 39	99.92 69	99.55 137

N_pmnet		97.63 281	97.17 302	98.99 152	99.27 205	97.86 176	95.98 395	93.41 459	95.25 383	99.47 101	98.90 235	95.63 284	99.85 156	96.91 247	99.73 180	99.27 267

viewdifsd2359ckpt13		98.39 201	98.29 203	98.70 209	99.26 214	97.19 232	97.51 286	99.48 135	96.94 313	98.58 271	98.82 258	97.47 183	99.55 379	97.21 222	99.33 312	99.34 245

FPMVS		93.44 416	92.23 423	97.08 374	99.25 215	97.86 176	95.61 415	97.16 408	92.90 428	93.76 461	98.65 298	75.94 455	95.66 475	79.30 473	97.49 431	97.73 439

ME-MVS		98.61 162	98.33 198	99.44 66	99.24 216	98.93 80	97.45 296	99.06 286	98.14 207	99.06 176	98.77 268	96.97 214	99.82 206	96.67 274	99.64 229	99.58 116

new-patchmatchnet		98.35 204	98.74 118	97.18 369	99.24 216	92.23 417	96.42 371	99.48 135	98.30 181	99.69 56	99.53 65	97.44 184	99.82 206	98.84 100	99.77 157	99.49 168

MCST-MVS		98.00 248	97.63 276	99.10 129	99.24 216	98.17 139	96.89 343	98.73 349	95.66 369	97.92 329	97.70 386	97.17 201	99.66 333	96.18 316	99.23 331	99.47 187

UniMVSNet (Re)		98.87 105	98.71 127	99.35 81	99.24 216	98.73 96	97.73 253	99.38 183	98.93 130	99.12 168	98.73 277	96.77 228	99.86 143	98.63 117	99.80 140	99.46 189

jason		97.45 295	97.35 293	97.76 322	99.24 216	93.93 378	95.86 405	98.42 367	94.24 407	98.50 283	98.13 355	94.82 307	99.91 74	97.22 221	99.73 180	99.43 202
jason: jason.
IterMVS		97.73 273	98.11 229	96.57 396	99.24 216	90.28 444	95.52 420	99.21 254	98.86 139	99.33 130	99.33 112	93.11 342	99.94 42	98.49 127	99.94 50	99.48 179
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 174	98.62 145	98.32 274	99.22 222	95.58 310	97.51 286	99.45 152	97.16 301	99.45 105	99.24 137	96.12 262	99.85 156	99.60 37	99.88 94	99.55 137

ITE_SJBPF				98.87 172	99.22 222	98.48 115		99.35 197	97.50 261	98.28 301	98.60 309	97.64 161	99.35 426	93.86 390	99.27 323	98.79 364

h-mvs33		97.77 271	97.33 295	99.10 129	99.21 224	97.84 178	98.35 155	98.57 359	99.11 99	98.58 271	99.02 195	88.65 394	99.96 14	98.11 149	96.34 454	99.49 168

v144192		98.54 177	98.57 154	98.45 258	99.21 224	95.98 296	97.63 268	99.36 191	97.15 303	99.32 136	99.18 153	95.84 279	99.84 174	99.50 51	99.91 78	99.54 143

APDe-MVS		98.99 86	98.79 114	99.60 16	99.21 224	99.15 53	98.87 89	99.48 135	97.57 252	99.35 126	99.24 137	97.83 143	99.89 97	97.88 171	99.70 204	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 96	98.81 113	99.28 97	99.21 224	98.45 117	98.46 143	99.33 209	99.63 29	99.48 97	99.15 163	97.23 198	99.75 275	97.17 224	99.66 226	99.63 89

SR-MVS-dyc-post		98.81 119	98.55 156	99.57 22	99.20 228	99.38 13	98.48 141	99.30 224	98.64 150	98.95 206	98.96 222	97.49 181	99.86 143	96.56 289	99.39 303	99.45 194

RE-MVS-def			98.58 153		99.20 228	99.38 13	98.48 141	99.30 224	98.64 150	98.95 206	98.96 222	97.75 152		96.56 289	99.39 303	99.45 194

v1921920		98.54 177	98.60 150	98.38 267	99.20 228	95.76 306	97.56 279	99.36 191	97.23 295	99.38 119	99.17 157	96.02 265	99.84 174	99.57 39	99.90 86	99.54 143

thisisatest0530		95.27 385	94.45 396	97.74 325	99.19 231	94.37 356	97.86 231	90.20 471	97.17 300	98.22 304	97.65 388	73.53 458	99.90 81	96.90 252	99.35 309	98.95 334

Anonymous20240529		98.93 96	98.87 103	99.12 125	99.19 231	98.22 136	99.01 71	98.99 304	99.25 76	99.54 79	99.37 100	97.04 207	99.80 231	97.89 168	99.52 275	99.35 243

APD-MVS_3200maxsize		98.84 111	98.61 149	99.53 39	99.19 231	99.27 28	98.49 138	99.33 209	98.64 150	99.03 189	98.98 217	97.89 138	99.85 156	96.54 293	99.42 300	99.46 189

HQP_MVS		97.99 251	97.67 270	98.93 164	99.19 231	97.65 198	97.77 244	99.27 239	98.20 195	97.79 341	97.98 369	94.90 303	99.70 303	94.42 372	99.51 277	99.45 194

plane_prior7					99.19 231	97.87 175

ab-mvs		98.41 193	98.36 191	98.59 230	99.19 231	97.23 226	99.32 27	98.81 335	97.66 242	98.62 263	99.40 97	96.82 223	99.80 231	95.88 327	99.51 277	98.75 369

F-COLMAP		97.30 307	96.68 334	99.14 123	99.19 231	98.39 119	97.27 318	99.30 224	92.93 427	96.62 406	98.00 367	95.73 282	99.68 316	92.62 418	98.46 399	99.35 243

viewdifsd2359ckpt09		98.13 236	97.92 252	98.77 195	99.18 238	97.35 216	97.29 314	99.53 117	95.81 366	98.09 317	98.47 327	96.34 253	99.66 333	97.02 237	99.51 277	99.29 263

SR-MVS		98.71 134	98.43 179	99.57 22	99.18 238	99.35 17	98.36 154	99.29 232	98.29 184	98.88 225	98.85 248	97.53 174	99.87 134	96.14 318	99.31 316	99.48 179

UniMVSNet_NR-MVSNet		98.86 108	98.68 133	99.40 73	99.17 240	98.74 93	97.68 258	99.40 179	99.14 97	99.06 176	98.59 310	96.71 234	99.93 54	98.57 120	99.77 157	99.53 152

LF4IMVS		97.90 255	97.69 269	98.52 249	99.17 240	97.66 197	97.19 328	99.47 144	96.31 346	97.85 337	98.20 352	96.71 234	99.52 391	94.62 364	99.72 188	98.38 405

SMA-MVS		98.40 195	98.03 238	99.51 49	99.16 242	99.21 34	98.05 194	99.22 253	94.16 409	98.98 196	99.10 175	97.52 176	99.79 244	96.45 299	99.64 229	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		98.82 117	98.63 143	99.39 74	99.16 242	98.74 93	97.54 282	99.25 245	98.84 142	99.06 176	98.76 274	96.76 230	99.93 54	98.57 120	99.77 157	99.50 161

NR-MVSNet		98.95 93	98.82 111	99.36 75	99.16 242	98.72 98	99.22 46	99.20 256	99.10 106	99.72 48	98.76 274	96.38 250	99.86 143	98.00 161	99.82 123	99.50 161

MVS_111021_LR		98.30 213	98.12 228	98.83 177	99.16 242	98.03 158	96.09 392	99.30 224	97.58 251	98.10 316	98.24 348	98.25 99	99.34 427	96.69 272	99.65 227	99.12 308

DSMNet-mixed		97.42 298	97.60 278	96.87 386	99.15 246	91.46 424	98.54 126	99.12 278	92.87 429	97.58 354	99.63 40	96.21 257	99.90 81	95.74 336	99.54 268	99.27 267

D2MVS		97.84 268	97.84 259	97.83 314	99.14 247	94.74 345	96.94 338	98.88 319	95.84 365	98.89 221	98.96 222	94.40 319	99.69 307	97.55 198	99.95 38	99.05 314

pmmvs5		97.64 280	97.49 284	98.08 299	99.14 247	95.12 334	96.70 353	99.05 290	93.77 416	98.62 263	98.83 255	93.23 339	99.75 275	98.33 137	99.76 172	99.36 238

SPE-MVS-test		99.13 67	99.09 76	99.26 102	99.13 249	98.97 74	99.31 31	99.88 14	99.44 54	98.16 309	98.51 319	98.64 57	99.93 54	98.91 94	99.85 107	98.88 348

VDD-MVS		98.56 170	98.39 186	99.07 136	99.13 249	98.07 153	98.59 120	97.01 411	99.59 37	99.11 169	99.27 124	94.82 307	99.79 244	98.34 135	99.63 236	99.34 245

save fliter					99.11 251	97.97 164	96.53 363	99.02 298	98.24 187

APD-MVS		98.10 237	97.67 270	99.42 69	99.11 251	98.93 80	97.76 247	99.28 236	94.97 390	98.72 251	98.77 268	97.04 207	99.85 156	93.79 392	99.54 268	99.49 168
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 143	98.71 127	98.62 224	99.10 253	96.37 282	97.23 319	98.87 321	99.20 84	99.19 162	98.99 212	97.30 192	99.85 156	98.77 106	99.79 146	99.65 83

EI-MVSNet		98.40 195	98.51 162	98.04 304	99.10 253	94.73 346	97.20 324	98.87 321	98.97 125	99.06 176	99.02 195	96.00 267	99.80 231	98.58 118	99.82 123	99.60 100

CVMVSNet		96.25 359	97.21 301	93.38 453	99.10 253	80.56 481	97.20 324	98.19 378	96.94 313	99.00 191	99.02 195	89.50 387	99.80 231	96.36 305	99.59 250	99.78 47

EI-MVSNet-Vis-set		98.68 149	98.70 130	98.63 222	99.09 256	96.40 281	97.23 319	98.86 326	99.20 84	99.18 166	98.97 219	97.29 194	99.85 156	98.72 110	99.78 151	99.64 84

HPM-MVS++		98.10 237	97.64 275	99.48 57	99.09 256	99.13 61	97.52 284	98.75 346	97.46 269	96.90 394	97.83 379	96.01 266	99.84 174	95.82 334	99.35 309	99.46 189

DP-MVS Recon		97.33 305	96.92 317	98.57 234	99.09 256	97.99 160	96.79 346	99.35 197	93.18 423	97.71 345	98.07 363	95.00 302	99.31 431	93.97 385	99.13 347	98.42 402

MVS_111021_HR		98.25 222	98.08 233	98.75 199	99.09 256	97.46 210	95.97 396	99.27 239	97.60 250	97.99 327	98.25 347	98.15 115	99.38 422	96.87 255	99.57 259	99.42 207

BP-MVS1		97.40 300	96.97 313	98.71 208	99.07 260	96.81 258	98.34 157	97.18 406	98.58 161	98.17 306	98.61 307	84.01 426	99.94 42	98.97 91	99.78 151	99.37 231

9.14			97.78 261		99.07 260		97.53 283	99.32 211	95.53 375	98.54 279	98.70 287	97.58 167	99.76 267	94.32 377	99.46 290

PAPM_NR		96.82 339	96.32 350	98.30 277	99.07 260	96.69 266	97.48 290	98.76 343	95.81 366	96.61 407	96.47 424	94.12 328	99.17 444	90.82 445	97.78 425	99.06 313

TAMVS		98.24 223	98.05 236	98.80 183	99.07 260	97.18 234	97.88 227	98.81 335	96.66 330	99.17 167	99.21 144	94.81 309	99.77 261	96.96 245	99.88 94	99.44 198

CLD-MVS		97.49 291	97.16 303	98.48 255	99.07 260	97.03 245	94.71 441	99.21 254	94.46 401	98.06 320	97.16 410	97.57 168	99.48 403	94.46 369	99.78 151	98.95 334
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 74	99.24 107	99.06 265	99.15 53	99.36 22	99.88 14	99.36 65	98.21 305	98.46 328	98.68 54	99.93 54	99.03 87	99.85 107	98.64 381

thres100view900		94.19 402	93.67 407	95.75 420	99.06 265	91.35 428	98.03 198	94.24 454	98.33 177	97.40 370	94.98 454	79.84 442	99.62 349	83.05 466	98.08 416	96.29 461

thres600view7		94.45 397	93.83 404	96.29 404	99.06 265	91.53 423	97.99 212	94.24 454	98.34 176	97.44 368	95.01 452	79.84 442	99.67 320	84.33 464	98.23 405	97.66 442

plane_prior1					99.05 268

YYNet1		97.60 282	97.67 270	97.39 362	99.04 269	93.04 401	95.27 427	98.38 370	97.25 289	98.92 216	98.95 226	95.48 291	99.73 287	96.99 241	98.74 380	99.41 210

MDA-MVSNet_test_wron		97.60 282	97.66 273	97.41 361	99.04 269	93.09 397	95.27 427	98.42 367	97.26 288	98.88 225	98.95 226	95.43 292	99.73 287	97.02 237	98.72 382	99.41 210

MIMVSNet		96.62 346	96.25 354	97.71 329	99.04 269	94.66 349	99.16 55	96.92 417	97.23 295	97.87 334	99.10 175	86.11 409	99.65 340	91.65 429	99.21 335	98.82 353

icg_test_0407_2		98.20 228	98.38 188	97.65 335	99.03 272	94.03 369	95.78 410	99.45 152	98.16 201	99.06 176	98.71 280	98.27 95	99.68 316	97.50 204	99.45 292	99.22 284

IMVS_0407		98.39 201	98.64 141	97.66 333	99.03 272	94.03 369	98.10 184	99.45 152	98.16 201	99.06 176	98.71 280	98.27 95	99.71 296	97.50 204	99.45 292	99.22 284

IMVS_0404		98.07 241	98.20 215	97.69 330	99.03 272	94.03 369	96.67 354	99.45 152	98.16 201	98.03 324	98.71 280	96.80 226	99.82 206	97.50 204	99.45 292	99.22 284

IMVS_0403		98.34 205	98.56 155	97.66 333	99.03 272	94.03 369	97.98 213	99.45 152	98.16 201	98.89 221	98.71 280	97.90 134	99.74 280	97.50 204	99.45 292	99.22 284

PatchMatch-RL		97.24 313	96.78 328	98.61 227	99.03 272	97.83 179	96.36 374	99.06 286	93.49 421	97.36 374	97.78 380	95.75 281	99.49 400	93.44 401	98.77 379	98.52 390

viewmambaseed2359dif		98.19 229	98.26 208	97.99 307	99.02 277	95.03 337	96.59 360	99.53 117	96.21 349	99.00 191	98.99 212	97.62 163	99.61 356	97.62 193	99.72 188	99.33 251

GDP-MVS		97.50 288	97.11 307	98.67 214	99.02 277	96.85 256	98.16 174	99.71 48	98.32 179	98.52 282	98.54 314	83.39 430	99.95 26	98.79 102	99.56 262	99.19 294

ZD-MVS					99.01 279	98.84 87		99.07 285	94.10 411	98.05 322	98.12 357	96.36 252	99.86 143	92.70 417	99.19 339

CDPH-MVS		97.26 310	96.66 337	99.07 136	99.00 280	98.15 140	96.03 394	99.01 301	91.21 447	97.79 341	97.85 378	96.89 218	99.69 307	92.75 415	99.38 306	99.39 220

diffmvs		98.22 224	98.24 212	98.17 292	99.00 280	95.44 321	96.38 373	99.58 88	97.79 234	98.53 280	98.50 323	96.76 230	99.74 280	97.95 166	99.64 229	99.34 245
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		98.40 195	98.19 219	99.03 146	99.00 280	97.65 198	96.85 344	98.94 306	98.57 162	98.89 221	98.50 323	95.60 285	99.85 156	97.54 200	99.85 107	99.59 107

plane_prior6					98.99 283	97.70 196						94.90 303

xiu_mvs_v1_base_debu		97.86 262	98.17 221	96.92 383	98.98 284	93.91 379	96.45 367	99.17 268	97.85 229	98.41 291	97.14 412	98.47 73	99.92 65	98.02 158	99.05 353	96.92 454

xiu_mvs_v1_base		97.86 262	98.17 221	96.92 383	98.98 284	93.91 379	96.45 367	99.17 268	97.85 229	98.41 291	97.14 412	98.47 73	99.92 65	98.02 158	99.05 353	96.92 454

xiu_mvs_v1_base_debi		97.86 262	98.17 221	96.92 383	98.98 284	93.91 379	96.45 367	99.17 268	97.85 229	98.41 291	97.14 412	98.47 73	99.92 65	98.02 158	99.05 353	96.92 454

MVP-Stereo		98.08 240	97.92 252	98.57 234	98.96 287	96.79 259	97.90 225	99.18 264	96.41 342	98.46 286	98.95 226	95.93 276	99.60 359	96.51 295	98.98 367	99.31 258
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 195	98.68 133	97.54 350	98.96 287	97.99 160	97.88 227	99.36 191	98.20 195	99.63 67	99.04 192	98.76 46	95.33 477	96.56 289	99.74 177	99.31 258
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	98.94 289	97.76 190		98.76 343	87.58 464	96.75 402	98.10 359	94.80 310	99.78 255	92.73 416	99.00 362	99.20 289

USDC		97.41 299	97.40 288	97.44 359	98.94 289	93.67 389	95.17 430	99.53 117	94.03 413	98.97 200	99.10 175	95.29 294	99.34 427	95.84 333	99.73 180	99.30 261

tfpn200view9		94.03 406	93.44 409	95.78 419	98.93 291	91.44 426	97.60 274	94.29 452	97.94 221	97.10 380	94.31 461	79.67 444	99.62 349	83.05 466	98.08 416	96.29 461

testdata				98.09 296	98.93 291	95.40 323		98.80 337	90.08 455	97.45 367	98.37 337	95.26 295	99.70 303	93.58 397	98.95 370	99.17 301

thres400		94.14 404	93.44 409	96.24 407	98.93 291	91.44 426	97.60 274	94.29 452	97.94 221	97.10 380	94.31 461	79.67 444	99.62 349	83.05 466	98.08 416	97.66 442

TAPA-MVS	96.21 11	96.63 345	95.95 356	98.65 216	98.93 291	98.09 147	96.93 340	99.28 236	83.58 470	98.13 313	97.78 380	96.13 260	99.40 418	93.52 398	99.29 321	98.45 395
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 295	96.93 253	95.54 417	98.78 340	85.72 467	96.86 397	98.11 358	94.43 317			99.10 352	99.23 279

PVSNet_BlendedMVS		97.55 287	97.53 281	97.60 342	98.92 295	93.77 386	96.64 356	99.43 166	94.49 399	97.62 350	99.18 153	96.82 223	99.67 320	94.73 361	99.93 56	99.36 238

PVSNet_Blended		96.88 335	96.68 334	97.47 357	98.92 295	93.77 386	94.71 441	99.43 166	90.98 449	97.62 350	97.36 406	96.82 223	99.67 320	94.73 361	99.56 262	98.98 328

MSDG		97.71 275	97.52 282	98.28 279	98.91 298	96.82 257	94.42 451	99.37 187	97.65 243	98.37 296	98.29 346	97.40 186	99.33 429	94.09 383	99.22 332	98.68 379

Anonymous202405211		97.90 255	97.50 283	99.08 134	98.90 299	98.25 130	98.53 127	96.16 429	98.87 137	99.11 169	98.86 245	90.40 379	99.78 255	97.36 213	99.31 316	99.19 294

原ACMM1				98.35 272	98.90 299	96.25 286		98.83 334	92.48 433	96.07 424	98.10 359	95.39 293	99.71 296	92.61 419	98.99 364	99.08 310

GBi-Net		98.65 154	98.47 173	99.17 116	98.90 299	98.24 131	99.20 49	99.44 160	98.59 158	98.95 206	99.55 58	94.14 325	99.86 143	97.77 180	99.69 207	99.41 210

test1		98.65 154	98.47 173	99.17 116	98.90 299	98.24 131	99.20 49	99.44 160	98.59 158	98.95 206	99.55 58	94.14 325	99.86 143	97.77 180	99.69 207	99.41 210

FMVSNet2		98.49 186	98.40 183	98.75 199	98.90 299	97.14 239	98.61 118	99.13 277	98.59 158	99.19 162	99.28 122	94.14 325	99.82 206	97.97 164	99.80 140	99.29 263

OMC-MVS		97.88 259	97.49 284	99.04 145	98.89 304	98.63 100	96.94 338	99.25 245	95.02 388	98.53 280	98.51 319	97.27 195	99.47 406	93.50 400	99.51 277	99.01 322

VortexMVS		97.98 252	98.31 200	97.02 377	98.88 305	91.45 425	98.03 198	99.47 144	98.65 149	99.55 77	99.47 79	91.49 368	99.81 223	99.32 61	99.91 78	99.80 42

MVSFormer		98.26 219	98.43 179	97.77 319	98.88 305	93.89 382	99.39 20	99.56 104	99.11 99	98.16 309	98.13 355	93.81 333	99.97 7	99.26 66	99.57 259	99.43 202

lupinMVS		97.06 325	96.86 321	97.65 335	98.88 305	93.89 382	95.48 421	97.97 384	93.53 419	98.16 309	97.58 392	93.81 333	99.91 74	96.77 263	99.57 259	99.17 301

dmvs_re		95.98 367	95.39 377	97.74 325	98.86 308	97.45 211	98.37 153	95.69 441	97.95 219	96.56 408	95.95 433	90.70 376	97.68 471	88.32 454	96.13 458	98.11 417

DELS-MVS		98.27 217	98.20 215	98.48 255	98.86 308	96.70 265	95.60 416	99.20 256	97.73 237	98.45 287	98.71 280	97.50 178	99.82 206	98.21 143	99.59 250	98.93 339
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		97.89 257	97.98 243	97.60 342	98.86 308	94.35 357	96.21 383	99.44 160	97.45 271	99.06 176	98.88 242	97.99 128	99.28 437	94.38 376	99.58 255	99.18 297

LCM-MVSNet-Re		98.64 156	98.48 171	99.11 127	98.85 311	98.51 113	98.49 138	99.83 25	98.37 173	99.69 56	99.46 81	98.21 106	99.92 65	94.13 382	99.30 319	98.91 343

pmmvs4		97.58 285	97.28 296	98.51 250	98.84 312	96.93 253	95.40 425	98.52 362	93.60 418	98.61 265	98.65 298	95.10 299	99.60 359	96.97 244	99.79 146	98.99 327

NP-MVS					98.84 312	97.39 215					96.84 415

sss		97.21 315	96.93 315	98.06 301	98.83 314	95.22 330	96.75 350	98.48 364	94.49 399	97.27 376	97.90 375	92.77 351	99.80 231	96.57 285	99.32 314	99.16 304

PVSNet	93.40 17	95.67 376	95.70 362	95.57 424	98.83 314	88.57 451	92.50 468	97.72 389	92.69 431	96.49 416	96.44 425	93.72 336	99.43 414	93.61 395	99.28 322	98.71 372

MVE	83.40 22	92.50 429	91.92 431	94.25 440	98.83 314	91.64 422	92.71 467	83.52 480	95.92 363	86.46 478	95.46 446	95.20 296	95.40 476	80.51 471	98.64 391	95.73 469
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 410	93.91 402	93.39 452	98.82 317	81.72 479	97.76 247	95.28 443	98.60 157	96.54 409	96.66 419	65.85 474	99.62 349	96.65 278	98.99 364	98.82 353

ambc				98.24 284	98.82 317	95.97 297	98.62 117	99.00 303		99.27 144	99.21 144	96.99 212	99.50 397	96.55 292	99.50 285	99.26 273

旧先验1					98.82 317	97.45 211		98.76 343			98.34 341	95.50 290			99.01 361	99.23 279

test_vis1_rt		97.75 272	97.72 267	97.83 314	98.81 320	96.35 283	97.30 313	99.69 55	94.61 397	97.87 334	98.05 364	96.26 256	98.32 465	98.74 108	98.18 408	98.82 353

WTY-MVS		96.67 343	96.27 353	97.87 312	98.81 320	94.61 351	96.77 348	97.92 386	94.94 391	97.12 379	97.74 383	91.11 372	99.82 206	93.89 388	98.15 412	99.18 297

3Dnovator+	97.89 3	98.69 143	98.51 162	99.24 107	98.81 320	98.40 118	99.02 70	99.19 260	98.99 122	98.07 319	99.28 122	97.11 205	99.84 174	96.84 258	99.32 314	99.47 187

QAPM		97.31 306	96.81 327	98.82 179	98.80 323	97.49 206	99.06 66	99.19 260	90.22 453	97.69 347	99.16 159	96.91 217	99.90 81	90.89 444	99.41 301	99.07 312

VNet		98.42 192	98.30 201	98.79 187	98.79 324	97.29 222	98.23 165	98.66 353	99.31 70	98.85 230	98.80 262	94.80 310	99.78 255	98.13 148	99.13 347	99.31 258

DPM-MVS		96.32 355	95.59 368	98.51 250	98.76 325	97.21 230	94.54 450	98.26 373	91.94 438	96.37 417	97.25 408	93.06 345	99.43 414	91.42 434	98.74 380	98.89 345

3Dnovator	98.27 2	98.81 119	98.73 120	99.05 143	98.76 325	97.81 187	99.25 44	99.30 224	98.57 162	98.55 277	99.33 112	97.95 131	99.90 81	97.16 225	99.67 218	99.44 198

PLC	94.65 16	96.51 348	95.73 361	98.85 175	98.75 327	97.91 172	96.42 371	99.06 286	90.94 450	95.59 430	97.38 404	94.41 318	99.59 363	90.93 442	98.04 421	99.05 314
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 337	96.75 330	97.08 374	98.74 328	93.33 395	96.71 352	98.26 373	96.72 327	98.44 288	97.37 405	95.20 296	99.47 406	91.89 424	97.43 435	98.44 398

hse-mvs2		97.46 293	97.07 308	98.64 218	98.73 329	97.33 218	97.45 296	97.64 396	99.11 99	98.58 271	97.98 369	88.65 394	99.79 244	98.11 149	97.39 437	98.81 358

CDS-MVSNet		97.69 276	97.35 293	98.69 211	98.73 329	97.02 246	96.92 342	98.75 346	95.89 364	98.59 269	98.67 293	92.08 362	99.74 280	96.72 269	99.81 129	99.32 254
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SD_0403		96.28 357	95.83 358	97.64 338	98.72 331	94.30 358	98.87 89	98.77 341	97.80 232	96.53 410	98.02 366	97.34 190	99.47 406	76.93 475	99.48 288	99.16 304

EIA-MVS		98.00 248	97.74 264	98.80 183	98.72 331	98.09 147	98.05 194	99.60 79	97.39 275	96.63 405	95.55 441	97.68 155	99.80 231	96.73 268	99.27 323	98.52 390

LFMVS		97.20 316	96.72 331	98.64 218	98.72 331	96.95 251	98.93 82	94.14 456	99.74 13	98.78 242	99.01 206	84.45 421	99.73 287	97.44 209	99.27 323	99.25 274

new_pmnet		96.99 332	96.76 329	97.67 331	98.72 331	94.89 340	95.95 400	98.20 376	92.62 432	98.55 277	98.54 314	94.88 306	99.52 391	93.96 386	99.44 299	98.59 387

Fast-Effi-MVS+		97.67 278	97.38 290	98.57 234	98.71 335	97.43 213	97.23 319	99.45 152	94.82 394	96.13 421	96.51 421	98.52 71	99.91 74	96.19 314	98.83 376	98.37 407

TEST9					98.71 335	98.08 151	95.96 398	99.03 295	91.40 444	95.85 427	97.53 394	96.52 243	99.76 267

train_agg		97.10 322	96.45 347	99.07 136	98.71 335	98.08 151	95.96 398	99.03 295	91.64 439	95.85 427	97.53 394	96.47 245	99.76 267	93.67 394	99.16 342	99.36 238

TSAR-MVS + GP.		98.18 231	97.98 243	98.77 195	98.71 335	97.88 174	96.32 377	98.66 353	96.33 344	99.23 156	98.51 319	97.48 182	99.40 418	97.16 225	99.46 290	99.02 321

FA-MVS(test-final)		96.99 332	96.82 325	97.50 354	98.70 339	94.78 343	99.34 23	96.99 412	95.07 387	98.48 285	99.33 112	88.41 397	99.65 340	96.13 320	98.92 373	98.07 420

AUN-MVS		96.24 361	95.45 373	98.60 229	98.70 339	97.22 228	97.38 303	97.65 394	95.95 362	95.53 437	97.96 373	82.11 438	99.79 244	96.31 307	97.44 434	98.80 363

our_test_3		97.39 301	97.73 266	96.34 402	98.70 339	89.78 447	94.61 447	98.97 305	96.50 335	99.04 186	98.85 248	95.98 272	99.84 174	97.26 219	99.67 218	99.41 210

ppachtmachnet_test		97.50 288	97.74 264	96.78 392	98.70 339	91.23 434	94.55 449	99.05 290	96.36 343	99.21 160	98.79 264	96.39 248	99.78 255	96.74 266	99.82 123	99.34 245

PCF-MVS	92.86 18	94.36 398	93.00 416	98.42 262	98.70 339	97.56 203	93.16 466	99.11 280	79.59 474	97.55 357	97.43 401	92.19 359	99.73 287	79.85 472	99.45 292	97.97 426
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 254	98.02 239	97.58 344	98.69 344	94.10 365	98.13 177	98.90 315	97.95 219	97.32 375	99.58 48	95.95 275	98.75 460	96.41 301	99.22 332	99.87 22

ETV-MVS		98.03 244	97.86 258	98.56 239	98.69 344	98.07 153	97.51 286	99.50 126	98.10 209	97.50 362	95.51 442	98.41 79	99.88 115	96.27 310	99.24 328	97.71 441

test_prior				98.95 161	98.69 344	97.95 168		99.03 295					99.59 363			99.30 261

mvsmamba		97.57 286	97.26 297	98.51 250	98.69 344	96.73 264	98.74 98	97.25 405	97.03 309	97.88 333	99.23 142	90.95 373	99.87 134	96.61 281	99.00 362	98.91 343

agg_prior					98.68 348	97.99 160		99.01 301		95.59 430			99.77 261

test_8					98.67 349	98.01 159	95.91 404	99.02 298	91.64 439	95.79 429	97.50 397	96.47 245	99.76 267

HQP-NCC					98.67 349		96.29 379		96.05 355	95.55 433

ACMP_Plane					98.67 349		96.29 379		96.05 355	95.55 433

CNVR-MVS		98.17 233	97.87 257	99.07 136	98.67 349	98.24 131	97.01 334	98.93 309	97.25 289	97.62 350	98.34 341	97.27 195	99.57 372	96.42 300	99.33 312	99.39 220

HQP-MVS		97.00 331	96.49 346	98.55 241	98.67 349	96.79 259	96.29 379	99.04 293	96.05 355	95.55 433	96.84 415	93.84 331	99.54 385	92.82 412	99.26 326	99.32 254

MM		98.22 224	97.99 242	98.91 168	98.66 354	96.97 248	97.89 226	94.44 450	99.54 41	98.95 206	99.14 166	93.50 337	99.92 65	99.80 17	99.96 28	99.85 30

test_fmvs1		97.72 274	97.94 249	97.07 376	98.66 354	92.39 412	97.68 258	99.81 31	95.20 386	99.54 79	99.44 86	91.56 367	99.41 417	99.78 21	99.77 157	99.40 219

balanced_conf03		98.63 158	98.72 122	98.38 267	98.66 354	96.68 267	98.90 84	99.42 172	98.99 122	98.97 200	99.19 149	95.81 280	99.85 156	98.77 106	99.77 157	98.60 384

thres200		93.72 412	93.14 414	95.46 428	98.66 354	91.29 430	96.61 358	94.63 449	97.39 275	96.83 398	93.71 464	79.88 441	99.56 375	82.40 469	98.13 413	95.54 470

wuyk23d		96.06 363	97.62 277	91.38 457	98.65 358	98.57 107	98.85 93	96.95 415	96.86 320	99.90 14	99.16 159	99.18 19	98.40 464	89.23 452	99.77 157	77.18 477

NCCC		97.86 262	97.47 287	99.05 143	98.61 359	98.07 153	96.98 336	98.90 315	97.63 244	97.04 384	97.93 374	95.99 271	99.66 333	95.31 349	98.82 378	99.43 202

DeepC-MVS_fast	96.85 6	98.30 213	98.15 225	98.75 199	98.61 359	97.23 226	97.76 247	99.09 283	97.31 283	98.75 248	98.66 296	97.56 169	99.64 343	96.10 321	99.55 266	99.39 220
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 414	92.09 425	97.75 323	98.60 361	94.40 355	97.32 311	95.26 444	97.56 254	96.79 401	95.50 443	53.57 482	99.77 261	95.26 350	98.97 368	99.08 310

thisisatest0515		94.12 405	93.16 413	96.97 381	98.60 361	92.90 402	93.77 462	90.61 469	94.10 411	96.91 391	95.87 436	74.99 456	99.80 231	94.52 367	99.12 350	98.20 413

GA-MVS		95.86 370	95.32 380	97.49 355	98.60 361	94.15 364	93.83 461	97.93 385	95.49 376	96.68 403	97.42 402	83.21 431	99.30 433	96.22 312	98.55 397	99.01 322

dmvs_testset		92.94 424	92.21 424	95.13 432	98.59 364	90.99 437	97.65 264	92.09 465	96.95 312	94.00 457	93.55 465	92.34 357	96.97 474	72.20 476	92.52 472	97.43 449

OPU-MVS				98.82 179	98.59 364	98.30 127	98.10 184				98.52 318	98.18 109	98.75 460	94.62 364	99.48 288	99.41 210

MSLP-MVS++		98.02 245	98.14 227	97.64 338	98.58 366	95.19 331	97.48 290	99.23 252	97.47 264	97.90 331	98.62 305	97.04 207	98.81 458	97.55 198	99.41 301	98.94 338

test12				98.93 164	98.58 366	97.83 179		98.66 353		96.53 410		95.51 289	99.69 307		99.13 347	99.27 267

CL-MVSNet_self_test		97.44 296	97.22 300	98.08 299	98.57 368	95.78 305	94.30 454	98.79 338	96.58 333	98.60 267	98.19 353	94.74 313	99.64 343	96.41 301	98.84 375	98.82 353

PS-MVSNAJ		97.08 324	97.39 289	96.16 413	98.56 369	92.46 410	95.24 429	98.85 329	97.25 289	97.49 363	95.99 432	98.07 119	99.90 81	96.37 303	98.67 390	96.12 466

CNLPA		97.17 319	96.71 332	98.55 241	98.56 369	98.05 157	96.33 376	98.93 309	96.91 317	97.06 383	97.39 403	94.38 320	99.45 411	91.66 428	99.18 341	98.14 416

xiu_mvs_v2_base		97.16 320	97.49 284	96.17 411	98.54 371	92.46 410	95.45 422	98.84 330	97.25 289	97.48 364	96.49 422	98.31 90	99.90 81	96.34 306	98.68 389	96.15 465

alignmvs		97.35 303	96.88 320	98.78 190	98.54 371	98.09 147	97.71 254	97.69 391	99.20 84	97.59 353	95.90 435	88.12 399	99.55 379	98.18 145	98.96 369	98.70 375

FE-MVS		95.66 377	94.95 390	97.77 319	98.53 373	95.28 327	99.40 19	96.09 432	93.11 425	97.96 328	99.26 130	79.10 448	99.77 261	92.40 421	98.71 384	98.27 411

Effi-MVS+		98.02 245	97.82 260	98.62 224	98.53 373	97.19 232	97.33 310	99.68 61	97.30 284	96.68 403	97.46 400	98.56 69	99.80 231	96.63 279	98.20 407	98.86 350

baseline1		95.96 368	95.44 374	97.52 352	98.51 375	93.99 376	98.39 151	96.09 432	98.21 191	98.40 295	97.76 382	86.88 401	99.63 346	95.42 347	89.27 475	98.95 334

MVS_Test		98.18 231	98.36 191	97.67 331	98.48 376	94.73 346	98.18 170	99.02 298	97.69 240	98.04 323	99.11 172	97.22 199	99.56 375	98.57 120	98.90 374	98.71 372

MGCFI-Net		98.34 205	98.28 204	98.51 250	98.47 377	97.59 202	98.96 78	99.48 135	99.18 92	97.40 370	95.50 443	98.66 55	99.50 397	98.18 145	98.71 384	98.44 398

BH-RMVSNet		96.83 337	96.58 342	97.58 344	98.47 377	94.05 366	96.67 354	97.36 400	96.70 329	97.87 334	97.98 369	95.14 298	99.44 413	90.47 447	98.58 396	99.25 274

sasdasda		98.34 205	98.26 208	98.58 231	98.46 379	97.82 184	98.96 78	99.46 148	99.19 89	97.46 365	95.46 446	98.59 63	99.46 409	98.08 152	98.71 384	98.46 392

canonicalmvs		98.34 205	98.26 208	98.58 231	98.46 379	97.82 184	98.96 78	99.46 148	99.19 89	97.46 365	95.46 446	98.59 63	99.46 409	98.08 152	98.71 384	98.46 392

MVS-HIRNet		94.32 399	95.62 365	90.42 458	98.46 379	75.36 482	96.29 379	89.13 473	95.25 383	95.38 439	99.75 16	92.88 348	99.19 443	94.07 384	99.39 303	96.72 459

PHI-MVS		98.29 216	97.95 247	99.34 84	98.44 382	99.16 49	98.12 181	99.38 183	96.01 359	98.06 320	98.43 331	97.80 148	99.67 320	95.69 339	99.58 255	99.20 289

DVP-MVS++		98.90 100	98.70 130	99.51 49	98.43 383	99.15 53	99.43 15	99.32 211	98.17 198	99.26 148	99.02 195	98.18 109	99.88 115	97.07 234	99.45 292	99.49 168

MSC_two_6792asdad				99.32 92	98.43 383	98.37 122		98.86 326					99.89 97	97.14 228	99.60 246	99.71 63

No_MVS				99.32 92	98.43 383	98.37 122		98.86 326					99.89 97	97.14 228	99.60 246	99.71 63

Fast-Effi-MVS+-dtu		98.27 217	98.09 230	98.81 181	98.43 383	98.11 144	97.61 273	99.50 126	98.64 150	97.39 372	97.52 396	98.12 117	99.95 26	96.90 252	98.71 384	98.38 405

OpenMVS_ROB	95.38 14	95.84 372	95.18 385	97.81 316	98.41 387	97.15 238	97.37 307	98.62 357	83.86 469	98.65 259	98.37 337	94.29 323	99.68 316	88.41 453	98.62 394	96.60 460

DeepPCF-MVS	96.93 5	98.32 210	98.01 240	99.23 109	98.39 388	98.97 74	95.03 434	99.18 264	96.88 318	99.33 130	98.78 266	98.16 113	99.28 437	96.74 266	99.62 239	99.44 198

Patchmatch-test		96.55 347	96.34 349	97.17 371	98.35 389	93.06 398	98.40 150	97.79 387	97.33 280	98.41 291	98.67 293	83.68 429	99.69 307	95.16 352	99.31 316	98.77 366

AdaColmap		97.14 321	96.71 332	98.46 257	98.34 390	97.80 188	96.95 337	98.93 309	95.58 373	96.92 389	97.66 387	95.87 278	99.53 387	90.97 441	99.14 345	98.04 421

OpenMVS	96.65 7	97.09 323	96.68 334	98.32 274	98.32 391	97.16 237	98.86 92	99.37 187	89.48 457	96.29 419	99.15 163	96.56 241	99.90 81	92.90 409	99.20 336	97.89 429

MG-MVS		96.77 340	96.61 339	97.26 367	98.31 392	93.06 398	95.93 401	98.12 381	96.45 341	97.92 329	98.73 277	93.77 335	99.39 420	91.19 439	99.04 356	99.33 251

test_yl		96.69 341	96.29 351	97.90 309	98.28 393	95.24 328	97.29 314	97.36 400	98.21 191	98.17 306	97.86 376	86.27 405	99.55 379	94.87 358	98.32 401	98.89 345

DCV-MVSNet		96.69 341	96.29 351	97.90 309	98.28 393	95.24 328	97.29 314	97.36 400	98.21 191	98.17 306	97.86 376	86.27 405	99.55 379	94.87 358	98.32 401	98.89 345

CHOSEN 280x420		95.51 382	95.47 371	95.65 423	98.25 395	88.27 454	93.25 465	98.88 319	93.53 419	94.65 448	97.15 411	86.17 407	99.93 54	97.41 211	99.93 56	98.73 371

SCA		96.41 354	96.66 337	95.67 421	98.24 396	88.35 453	95.85 407	96.88 418	96.11 353	97.67 348	98.67 293	93.10 343	99.85 156	94.16 378	99.22 332	98.81 358

DeepMVS_CX				93.44 451	98.24 396	94.21 361		94.34 451	64.28 477	91.34 471	94.87 458	89.45 388	92.77 478	77.54 474	93.14 471	93.35 473

MS-PatchMatch		97.68 277	97.75 263	97.45 358	98.23 398	93.78 385	97.29 314	98.84 330	96.10 354	98.64 260	98.65 298	96.04 264	99.36 423	96.84 258	99.14 345	99.20 289

BH-w/o		95.13 388	94.89 392	95.86 416	98.20 399	91.31 429	95.65 414	97.37 399	93.64 417	96.52 412	95.70 439	93.04 346	99.02 449	88.10 455	95.82 461	97.24 452

mvs_anonymous		97.83 270	98.16 224	96.87 386	98.18 400	91.89 419	97.31 312	98.90 315	97.37 277	98.83 233	99.46 81	96.28 255	99.79 244	98.90 95	98.16 411	98.95 334

miper_lstm_enhance		97.18 318	97.16 303	97.25 368	98.16 401	92.85 403	95.15 432	99.31 216	97.25 289	98.74 250	98.78 266	90.07 380	99.78 255	97.19 223	99.80 140	99.11 309

RRT-MVS		97.88 259	97.98 243	97.61 341	98.15 402	93.77 386	98.97 77	99.64 71	99.16 94	98.69 253	99.42 90	91.60 365	99.89 97	97.63 192	98.52 398	99.16 304

ET-MVSNet_ETH3D		94.30 401	93.21 412	97.58 344	98.14 403	94.47 354	94.78 440	93.24 461	94.72 395	89.56 473	95.87 436	78.57 451	99.81 223	96.91 247	97.11 446	98.46 392

ADS-MVSNet2		95.43 383	94.98 388	96.76 393	98.14 403	91.74 420	97.92 222	97.76 388	90.23 451	96.51 413	98.91 232	85.61 412	99.85 156	92.88 410	96.90 447	98.69 376

ADS-MVSNet		95.24 386	94.93 391	96.18 410	98.14 403	90.10 446	97.92 222	97.32 403	90.23 451	96.51 413	98.91 232	85.61 412	99.74 280	92.88 410	96.90 447	98.69 376

c3_l		97.36 302	97.37 291	97.31 363	98.09 406	93.25 396	95.01 435	99.16 271	97.05 306	98.77 245	98.72 279	92.88 348	99.64 343	96.93 246	99.76 172	99.05 314

FMVSNet3		97.50 288	97.24 299	98.29 278	98.08 407	95.83 302	97.86 231	98.91 314	97.89 226	98.95 206	98.95 226	87.06 400	99.81 223	97.77 180	99.69 207	99.23 279

PAPM		91.88 438	90.34 441	96.51 397	98.06 408	92.56 408	92.44 469	97.17 407	86.35 465	90.38 472	96.01 431	86.61 403	99.21 442	70.65 478	95.43 463	97.75 438

Effi-MVS+-dtu		98.26 219	97.90 255	99.35 81	98.02 409	99.49 6	98.02 201	99.16 271	98.29 184	97.64 349	97.99 368	96.44 247	99.95 26	96.66 277	98.93 372	98.60 384

eth_miper_zixun_eth		97.23 314	97.25 298	97.17 371	98.00 410	92.77 405	94.71 441	99.18 264	97.27 287	98.56 275	98.74 276	91.89 363	99.69 307	97.06 236	99.81 129	99.05 314

HY-MVS	95.94 13	95.90 369	95.35 379	97.55 349	97.95 411	94.79 342	98.81 97	96.94 416	92.28 436	95.17 441	98.57 312	89.90 382	99.75 275	91.20 438	97.33 442	98.10 418

UGNet		98.53 179	98.45 176	98.79 187	97.94 412	96.96 250	99.08 62	98.54 360	99.10 106	96.82 399	99.47 79	96.55 242	99.84 174	98.56 123	99.94 50	99.55 137
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		96.47 352	95.70 362	98.79 187	97.92 413	99.12 63	98.28 159	98.60 358	92.16 437	95.54 436	96.17 429	94.77 312	99.52 391	89.62 450	98.23 405	97.72 440
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		96.86 336	96.55 343	97.79 317	97.91 414	94.21 361	97.56 279	98.87 321	97.49 263	99.06 176	99.05 190	80.72 439	99.80 231	98.44 129	99.82 123	99.37 231

API-MVS		97.04 327	96.91 319	97.42 360	97.88 415	98.23 135	98.18 170	98.50 363	97.57 252	97.39 372	96.75 417	96.77 228	99.15 446	90.16 448	99.02 360	94.88 471

myMVS_eth3d28		92.92 425	92.31 421	94.77 435	97.84 416	87.59 458	96.19 385	96.11 431	97.08 305	94.27 451	93.49 467	66.07 473	98.78 459	91.78 426	97.93 424	97.92 428

miper_ehance_all_eth		97.06 325	97.03 310	97.16 373	97.83 417	93.06 398	94.66 444	99.09 283	95.99 360	98.69 253	98.45 329	92.73 353	99.61 356	96.79 260	99.03 357	98.82 353

cl____		97.02 328	96.83 324	97.58 344	97.82 418	94.04 368	94.66 444	99.16 271	97.04 307	98.63 261	98.71 280	88.68 393	99.69 307	97.00 239	99.81 129	99.00 326

DIV-MVS_self_test		97.02 328	96.84 323	97.58 344	97.82 418	94.03 369	94.66 444	99.16 271	97.04 307	98.63 261	98.71 280	88.69 391	99.69 307	97.00 239	99.81 129	99.01 322

CANet		97.87 261	97.76 262	98.19 291	97.75 420	95.51 313	96.76 349	99.05 290	97.74 236	96.93 388	98.21 351	95.59 286	99.89 97	97.86 175	99.93 56	99.19 294

UBG		93.25 419	92.32 420	96.04 415	97.72 421	90.16 445	95.92 403	95.91 436	96.03 358	93.95 459	93.04 470	69.60 463	99.52 391	90.72 446	97.98 422	98.45 395

mvsany_test1		97.60 282	97.54 280	97.77 319	97.72 421	95.35 324	95.36 426	97.13 409	94.13 410	99.71 50	99.33 112	97.93 132	99.30 433	97.60 196	98.94 371	98.67 380

PVSNet_0	89.98 21	91.15 439	90.30 442	93.70 448	97.72 421	84.34 472	90.24 472	97.42 398	90.20 454	93.79 460	93.09 469	90.90 375	98.89 457	86.57 461	72.76 478	97.87 431

CR-MVSNet		96.28 357	95.95 356	97.28 365	97.71 424	94.22 359	98.11 182	98.92 312	92.31 435	96.91 391	99.37 100	85.44 415	99.81 223	97.39 212	97.36 440	97.81 434

RPMNet		97.02 328	96.93 315	97.30 364	97.71 424	94.22 359	98.11 182	99.30 224	99.37 62	96.91 391	99.34 109	86.72 402	99.87 134	97.53 201	97.36 440	97.81 434

ETVMVS		92.60 428	91.08 437	97.18 369	97.70 426	93.65 391	96.54 361	95.70 439	96.51 334	94.68 447	92.39 473	61.80 479	99.50 397	86.97 458	97.41 436	98.40 403

pmmvs3		95.03 390	94.40 397	96.93 382	97.70 426	92.53 409	95.08 433	97.71 390	88.57 461	97.71 345	98.08 362	79.39 446	99.82 206	96.19 314	99.11 351	98.43 400

baseline2		93.73 411	92.83 417	96.42 400	97.70 426	91.28 431	96.84 345	89.77 472	93.96 415	92.44 467	95.93 434	79.14 447	99.77 261	92.94 408	96.76 451	98.21 412

WBMVS		95.18 387	94.78 393	96.37 401	97.68 429	89.74 448	95.80 409	98.73 349	97.54 258	98.30 297	98.44 330	70.06 461	99.82 206	96.62 280	99.87 98	99.54 143

tpm		94.67 395	94.34 399	95.66 422	97.68 429	88.42 452	97.88 227	94.90 446	94.46 401	96.03 426	98.56 313	78.66 449	99.79 244	95.88 327	95.01 465	98.78 365

CANet_DTU		97.26 310	97.06 309	97.84 313	97.57 431	94.65 350	96.19 385	98.79 338	97.23 295	95.14 442	98.24 348	93.22 340	99.84 174	97.34 214	99.84 112	99.04 318

testing11		93.08 422	92.02 427	96.26 406	97.56 432	90.83 440	96.32 377	95.70 439	96.47 338	92.66 466	93.73 463	64.36 477	99.59 363	93.77 393	97.57 429	98.37 407

tpm2		93.09 421	92.58 419	94.62 437	97.56 432	86.53 461	97.66 262	95.79 438	86.15 466	94.07 456	98.23 350	75.95 454	99.53 387	90.91 443	96.86 450	97.81 434

testing91		93.32 417	92.27 422	96.47 399	97.54 434	91.25 432	96.17 389	96.76 420	97.18 299	93.65 462	93.50 466	65.11 476	99.63 346	93.04 407	97.45 433	98.53 389

TR-MVS		95.55 380	95.12 386	96.86 389	97.54 434	93.94 377	96.49 366	96.53 425	94.36 406	97.03 386	96.61 420	94.26 324	99.16 445	86.91 460	96.31 455	97.47 448

testing99		93.04 423	91.98 430	96.23 408	97.53 436	90.70 442	96.35 375	95.94 435	96.87 319	93.41 463	93.43 468	63.84 478	99.59 363	93.24 405	97.19 443	98.40 403

1314		95.74 374	95.60 366	96.17 411	97.53 436	92.75 406	98.07 191	98.31 372	91.22 446	94.25 452	96.68 418	95.53 287	99.03 448	91.64 430	97.18 444	96.74 458

CostFormer		93.97 407	93.78 405	94.51 438	97.53 436	85.83 464	97.98 213	95.96 434	89.29 459	94.99 444	98.63 303	78.63 450	99.62 349	94.54 366	96.50 452	98.09 419

FMVSNet5		96.01 365	95.20 384	98.41 263	97.53 436	96.10 288	98.74 98	99.50 126	97.22 298	98.03 324	99.04 192	69.80 462	99.88 115	97.27 218	99.71 197	99.25 274

PMMVS		96.51 348	95.98 355	98.09 296	97.53 436	95.84 301	94.92 437	98.84 330	91.58 441	96.05 425	95.58 440	95.68 283	99.66 333	95.59 343	98.09 415	98.76 368

reproduce_monomvs		95.00 392	95.25 381	94.22 441	97.51 441	83.34 473	97.86 231	98.44 365	98.51 167	99.29 140	99.30 118	67.68 467	99.56 375	98.89 97	99.81 129	99.77 50

PAPR		95.29 384	94.47 395	97.75 323	97.50 442	95.14 333	94.89 438	98.71 351	91.39 445	95.35 440	95.48 445	94.57 315	99.14 447	84.95 463	97.37 438	98.97 331

testing222		91.96 436	90.37 440	96.72 394	97.47 443	92.59 407	96.11 391	94.76 447	96.83 321	92.90 465	92.87 471	57.92 480	99.55 379	86.93 459	97.52 430	98.00 425

PatchT		96.65 344	96.35 348	97.54 350	97.40 444	95.32 326	97.98 213	96.64 422	99.33 67	96.89 395	99.42 90	84.32 423	99.81 223	97.69 191	97.49 431	97.48 447

tpm cat1		93.29 418	93.13 415	93.75 447	97.39 445	84.74 467	97.39 301	97.65 394	83.39 471	94.16 453	98.41 332	82.86 434	99.39 420	91.56 432	95.35 464	97.14 453

PatchmatchNet		95.58 379	95.67 364	95.30 431	97.34 446	87.32 459	97.65 264	96.65 421	95.30 382	97.07 382	98.69 289	84.77 418	99.75 275	94.97 356	98.64 391	98.83 352
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 303	96.97 313	98.50 254	97.31 447	96.47 279	98.18 170	98.92 312	98.95 129	98.78 242	99.37 100	85.44 415	99.85 156	95.96 325	99.83 119	99.17 301

LS3D		98.63 158	98.38 188	99.36 75	97.25 448	99.38 13	99.12 61	99.32 211	99.21 82	98.44 288	98.88 242	97.31 191	99.80 231	96.58 283	99.34 311	98.92 340

IB-MVS	91.63 19	92.24 434	90.90 438	96.27 405	97.22 449	91.24 433	94.36 453	93.33 460	92.37 434	92.24 469	94.58 460	66.20 472	99.89 97	93.16 406	94.63 467	97.66 442
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		92.38 431	91.76 434	94.21 442	97.16 450	84.65 468	95.42 424	88.45 474	95.96 361	96.17 420	95.84 438	66.36 470	99.71 296	91.87 425	98.64 391	98.28 410

tpmrst		95.07 389	95.46 372	93.91 445	97.11 451	84.36 471	97.62 269	96.96 414	94.98 389	96.35 418	98.80 262	85.46 414	99.59 363	95.60 342	96.23 456	97.79 437

Syy-MVS		96.04 364	95.56 370	97.49 355	97.10 452	94.48 353	96.18 387	96.58 423	95.65 370	94.77 445	92.29 474	91.27 371	99.36 423	98.17 147	98.05 419	98.63 382

myMVS_eth3d		91.92 437	90.45 439	96.30 403	97.10 452	90.90 438	96.18 387	96.58 423	95.65 370	94.77 445	92.29 474	53.88 481	99.36 423	89.59 451	98.05 419	98.63 382

MDTV_nov1_ep13			95.22 383		97.06 454	83.20 474	97.74 251	96.16 429	94.37 405	96.99 387	98.83 255	83.95 427	99.53 387	93.90 387	97.95 423

MVS		93.19 420	92.09 425	96.50 398	96.91 455	94.03 369	98.07 191	98.06 383	68.01 476	94.56 450	96.48 423	95.96 274	99.30 433	83.84 465	96.89 449	96.17 463

E-PMN		94.17 403	94.37 398	93.58 449	96.86 456	85.71 465	90.11 474	97.07 410	98.17 198	97.82 340	97.19 409	84.62 420	98.94 453	89.77 449	97.68 428	96.09 467

JIA-IIPM		95.52 381	95.03 387	97.00 378	96.85 457	94.03 369	96.93 340	95.82 437	99.20 84	94.63 449	99.71 23	83.09 432	99.60 359	94.42 372	94.64 466	97.36 451

EMVS		93.83 409	94.02 401	93.23 454	96.83 458	84.96 466	89.77 475	96.32 427	97.92 223	97.43 369	96.36 428	86.17 407	98.93 454	87.68 456	97.73 427	95.81 468

cl22		95.79 373	95.39 377	96.98 380	96.77 459	92.79 404	94.40 452	98.53 361	94.59 398	97.89 332	98.17 354	82.82 435	99.24 439	96.37 303	99.03 357	98.92 340

WB-MVSnew		95.73 375	95.57 369	96.23 408	96.70 460	90.70 442	96.07 393	93.86 457	95.60 372	97.04 384	95.45 449	96.00 267	99.55 379	91.04 440	98.31 403	98.43 400

dp		93.47 415	93.59 408	93.13 455	96.64 461	81.62 480	97.66 262	96.42 426	92.80 430	96.11 422	98.64 301	78.55 452	99.59 363	93.31 403	92.18 474	98.16 415

MonoMVSNet		96.25 359	96.53 345	95.39 429	96.57 462	91.01 436	98.82 96	97.68 393	98.57 162	98.03 324	99.37 100	90.92 374	97.78 470	94.99 354	93.88 470	97.38 450

test-LLR		93.90 408	93.85 403	94.04 443	96.53 463	84.62 469	94.05 458	92.39 463	96.17 350	94.12 454	95.07 450	82.30 436	99.67 320	95.87 330	98.18 408	97.82 432

test-mter		92.33 433	91.76 434	94.04 443	96.53 463	84.62 469	94.05 458	92.39 463	94.00 414	94.12 454	95.07 450	65.63 475	99.67 320	95.87 330	98.18 408	97.82 432

TESTMET0.1,1		92.19 435	91.77 433	93.46 450	96.48 465	82.80 476	94.05 458	91.52 468	94.45 403	94.00 457	94.88 456	66.65 469	99.56 375	95.78 335	98.11 414	98.02 422

MGCNet		97.44 296	97.01 312	98.72 207	96.42 466	96.74 263	97.20 324	91.97 466	98.46 170	98.30 297	98.79 264	92.74 352	99.91 74	99.30 63	99.94 50	99.52 155

miper_enhance_ethall		96.01 365	95.74 360	96.81 390	96.41 467	92.27 416	93.69 463	98.89 318	91.14 448	98.30 297	97.35 407	90.58 377	99.58 370	96.31 307	99.03 357	98.60 384

tpmvs		95.02 391	95.25 381	94.33 439	96.39 468	85.87 462	98.08 187	96.83 419	95.46 377	95.51 438	98.69 289	85.91 410	99.53 387	94.16 378	96.23 456	97.58 445

CMPMVS	75.91 23	96.29 356	95.44 374	98.84 176	96.25 469	98.69 99	97.02 333	99.12 278	88.90 460	97.83 338	98.86 245	89.51 386	98.90 456	91.92 423	99.51 277	98.92 340
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 396	93.69 406	96.99 379	96.05 470	93.61 393	94.97 436	93.49 458	96.17 350	97.57 356	94.88 456	82.30 436	99.01 451	93.60 396	94.17 469	98.37 407

EPMVS		93.72 412	93.27 411	95.09 434	96.04 471	87.76 456	98.13 177	85.01 479	94.69 396	96.92 389	98.64 301	78.47 453	99.31 431	95.04 353	96.46 453	98.20 413

cascas		94.79 394	94.33 400	96.15 414	96.02 472	92.36 414	92.34 470	99.26 244	85.34 468	95.08 443	94.96 455	92.96 347	98.53 463	94.41 375	98.59 395	97.56 446

MVStest1		95.86 370	95.60 366	96.63 395	95.87 473	91.70 421	97.93 219	98.94 306	98.03 213	99.56 74	99.66 33	71.83 459	98.26 466	99.35 59	99.24 328	99.91 13

gg-mvs-nofinetune		92.37 432	91.20 436	95.85 417	95.80 474	92.38 413	99.31 31	81.84 481	99.75 11	91.83 470	99.74 19	68.29 464	99.02 449	87.15 457	97.12 445	96.16 464

gm-plane-assit					94.83 475	81.97 478			88.07 463		94.99 453		99.60 359	91.76 427

GG-mvs-BLEND				94.76 436	94.54 476	92.13 418	99.31 31	80.47 482		88.73 476	91.01 476	67.59 468	98.16 469	82.30 470	94.53 468	93.98 472

UWE-MVS-28		90.22 440	89.28 443	93.02 456	94.50 477	82.87 475	96.52 364	87.51 475	95.21 385	92.36 468	96.04 430	71.57 460	98.25 467	72.04 477	97.77 426	97.94 427

EPNet_dtu		94.93 393	94.78 393	95.38 430	93.58 478	87.68 457	96.78 347	95.69 441	97.35 279	89.14 475	98.09 361	88.15 398	99.49 400	94.95 357	99.30 319	98.98 328
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 444	75.95 447	77.12 461	92.39 479	67.91 485	90.16 473	59.44 486	82.04 472	89.42 474	94.67 459	49.68 483	81.74 479	48.06 479	77.66 477	81.72 475

KD-MVS_2432*1600		92.87 426	91.99 428	95.51 426	91.37 480	89.27 449	94.07 456	98.14 379	95.42 378	97.25 377	96.44 425	67.86 465	99.24 439	91.28 436	96.08 459	98.02 422

miper_refine_blended		92.87 426	91.99 428	95.51 426	91.37 480	89.27 449	94.07 456	98.14 379	95.42 378	97.25 377	96.44 425	67.86 465	99.24 439	91.28 436	96.08 459	98.02 422

EPNet		96.14 362	95.44 374	98.25 282	90.76 482	95.50 316	97.92 222	94.65 448	98.97 125	92.98 464	98.85 248	89.12 389	99.87 134	95.99 323	99.68 212	99.39 220
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 445	68.95 448	70.34 462	87.68 483	65.00 486	91.11 471	59.90 485	69.02 475	74.46 480	88.89 477	48.58 484	68.03 481	28.61 480	72.33 479	77.99 476

test_method		79.78 442	79.50 445	80.62 459	80.21 484	45.76 487	70.82 476	98.41 369	31.08 479	80.89 479	97.71 384	84.85 417	97.37 472	91.51 433	80.03 476	98.75 369

tmp_tt		78.77 443	78.73 446	78.90 460	58.45 485	74.76 484	94.20 455	78.26 483	39.16 478	86.71 477	92.82 472	80.50 440	75.19 480	86.16 462	92.29 473	86.74 474

testmvs		17.12 447	20.53 450	6.87 464	12.05 486	4.20 489	93.62 464	6.73 487	4.62 482	10.41 482	24.33 479	8.28 486	3.56 483	9.69 482	15.07 480	12.86 479

test123		17.04 448	20.11 451	7.82 463	10.25 487	4.91 488	94.80 439	4.47 488	4.93 481	10.00 483	24.28 480	9.69 485	3.64 482	10.14 481	12.43 481	14.92 478

mmdepth		0.00 451	0.00 454	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	0.00 483	0.00 487	0.00 484	0.00 483	0.00 482	0.00 480

monomultidepth		0.00 451	0.00 454	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	0.00 483	0.00 487	0.00 484	0.00 483	0.00 482	0.00 480

test_blank		0.00 451	0.00 454	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	0.00 483	0.00 487	0.00 484	0.00 483	0.00 482	0.00 480

eth-test2					0.00 488

eth-test					0.00 488

uanet_test		0.00 451	0.00 454	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	0.00 483	0.00 487	0.00 484	0.00 483	0.00 482	0.00 480

DCPMVS		0.00 451	0.00 454	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	0.00 483	0.00 487	0.00 484	0.00 483	0.00 482	0.00 480

cdsmvs_eth3d_5k		24.66 446	32.88 449	0.00 465	0.00 488	0.00 490	0.00 477	99.10 281	0.00 483	0.00 484	97.58 392	99.21 18	0.00 484	0.00 483	0.00 482	0.00 480

pcd_1.5k_mvsjas		8.17 449	10.90 452	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	0.00 483	98.07 119	0.00 484	0.00 483	0.00 482	0.00 480

sosnet-low-res		0.00 451	0.00 454	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	0.00 483	0.00 487	0.00 484	0.00 483	0.00 482	0.00 480

sosnet		0.00 451	0.00 454	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	0.00 483	0.00 487	0.00 484	0.00 483	0.00 482	0.00 480

uncertanet		0.00 451	0.00 454	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	0.00 483	0.00 487	0.00 484	0.00 483	0.00 482	0.00 480

Regformer		0.00 451	0.00 454	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	0.00 483	0.00 487	0.00 484	0.00 483	0.00 482	0.00 480

ab-mvs-re		8.12 450	10.83 453	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	97.48 398	0.00 487	0.00 484	0.00 483	0.00 482	0.00 480

uanet		0.00 451	0.00 454	0.00 465	0.00 488	0.00 490	0.00 477	0.00 489	0.00 483	0.00 484	0.00 483	0.00 487	0.00 484	0.00 483	0.00 482	0.00 480

TestfortrainingZip							98.68 108

WAC-MVS						90.90 438								91.37 435

PC_three_1452									93.27 422	99.40 116	98.54 314	98.22 104	97.00 473	95.17 351	99.45 292	99.49 168

test_241102_TWO								99.30 224	98.03 213	99.26 148	99.02 195	97.51 177	99.88 115	96.91 247	99.60 246	99.66 78

test_0728_THIRD									98.17 198	99.08 174	99.02 195	97.89 138	99.88 115	97.07 234	99.71 197	99.70 68

GSMVS																98.81 358

sam_mvs1												84.74 419				98.81 358

sam_mvs												84.29 425

MTGPA								99.20 256

test_post1							97.59 276				20.48 482	83.07 433	99.66 333	94.16 378

test_post											21.25 481	83.86 428	99.70 303

patchmatchnet-post											98.77 268	84.37 422	99.85 156

MTMP							97.93 219	91.91 467

test9_res														93.28 404	99.15 344	99.38 229

agg_prior2														92.50 420	99.16 342	99.37 231

test_prior4						97.97 164	95.86 405

test_prior2							95.74 412		96.48 337	96.11 422	97.63 390	95.92 277		94.16 378	99.20 336

旧先验2							95.76 411		88.56 462	97.52 360			99.66 333	94.48 368

新几何2							95.93 401

无先验							95.74 412	98.74 348	89.38 458				99.73 287	92.38 422		99.22 284

原ACMM2							95.53 418

testdata2													99.79 244	92.80 414

segment_acmp												97.02 210

testdata1							95.44 423		96.32 345

plane_prior5								99.27 239					99.70 303	94.42 372	99.51 277	99.45 194

plane_prior4											97.98 369

plane_prior3						97.78 189			97.41 273	97.79 341

plane_prior2							97.77 244		98.20 195

plane_prior						97.65 198	97.07 332		96.72 327						99.36 307

n2								0.00 489

nn								0.00 489

door-mid								99.57 95

test11								98.87 321

door								99.41 176

HQP5-MVS						96.79 259

BP-MVS														92.82 412

HQP4-MVS										95.56 432			99.54 385			99.32 254

HQP3-MVS								99.04 293							99.26 326

HQP2-MVS												93.84 331

MDTV_nov1_ep13_2view						74.92 483	97.69 257		90.06 456	97.75 344		85.78 411		93.52 398		98.69 376

ACMMP++_ref															99.77 157

ACMMP++															99.68 212

Test By Simon												96.52 243

High-resolution multi-view benchmark