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 29

Gipuma		99.03 79	99.16 61	98.64 214	99.94 2	98.51 111	99.32 26	99.75 42	99.58 38	98.60 263	99.62 40	98.22 103	99.51 392	97.70 186	99.73 177	97.89 425
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 29	99.31 41	99.53 39	99.91 3	98.98 72	99.63 7	99.58 85	99.44 52	99.78 39	99.76 15	96.39 244	99.92 64	99.44 54	99.92 68	99.68 70

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	99.87 133	99.36 57	99.92 68	99.64 83

PS-MVSNAJss		99.46 17	99.49 16	99.35 79	99.90 4	98.15 138	99.20 48	99.65 67	99.48 44	99.92 8	99.71 22	98.07 117	99.96 14	99.53 47	100.00 1	99.93 11

testf1		99.25 41	99.16 61	99.51 49	99.89 6	99.63 4	98.71 104	99.69 54	98.90 132	99.43 104	99.35 103	98.86 34	99.67 317	97.81 174	99.81 127	99.24 273

APD_test2		99.25 41	99.16 61	99.51 49	99.89 6	99.63 4	98.71 104	99.69 54	98.90 132	99.43 104	99.35 103	98.86 34	99.67 317	97.81 174	99.81 127	99.24 273

ANet_high		99.57 10	99.67 6	99.28 95	99.89 6	98.09 145	99.14 57	99.93 5	99.82 8	99.93 6	99.81 8	99.17 20	99.94 42	99.31 61	100.00 1	99.82 35

anonymousdsp		99.51 14	99.47 21	99.62 10	99.88 9	99.08 70	99.34 23	99.69 54	98.93 128	99.65 63	99.72 21	98.93 32	99.95 26	99.11 77	100.00 1	99.82 35

v7n		99.53 12	99.57 13	99.41 69	99.88 9	98.54 109	99.45 14	99.61 76	99.66 24	99.68 57	99.66 32	98.44 77	99.95 26	99.73 27	99.96 28	99.75 59

mvs_tets		99.63 6	99.67 6	99.49 55	99.88 9	98.61 101	99.34 23	99.71 47	99.27 73	99.90 14	99.74 18	99.68 4	99.97 7	99.55 42	99.99 5	99.88 20

test_fmvsmconf0.01_n		99.57 10	99.63 10	99.36 73	99.87 12	98.13 141	98.08 185	99.95 1	99.45 50	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	98.61 101	99.28 40	99.66 63	99.09 107	99.89 18	99.68 25	99.53 7	99.97 7	99.50 50	99.99 5	99.87 21

test_djsdf		99.52 13	99.51 15	99.53 39	99.86 14	98.74 91	99.39 20	99.56 100	99.11 97	99.70 51	99.73 20	99.00 27	99.97 7	99.26 65	99.98 12	99.89 16

MIMVSNet1		99.38 28	99.32 39	99.55 29	99.86 14	99.19 43	99.41 17	99.59 83	99.59 36	99.71 49	99.57 49	97.12 199	99.90 80	99.21 70	99.87 96	99.54 140

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 39	99.67 30	99.48 10	99.81 220	99.30 62	99.97 21	99.77 49
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 85	99.90 3	99.86 24	99.78 13	99.58 6	99.95 26	99.00 87	99.95 38	99.78 46

SixPastTwentyTwo		98.75 127	98.62 141	99.16 117	99.83 18	97.96 165	99.28 40	98.20 372	99.37 60	99.70 51	99.65 36	92.65 350	99.93 53	99.04 84	99.84 110	99.60 99

sc_t1		99.62 7	99.66 8	99.53 39	99.82 19	99.09 69	99.50 11	99.63 71	99.88 4	99.86 24	99.80 11	99.03 24	99.89 96	99.48 52	99.93 55	99.60 99

Baseline_NR-MVSNet		98.98 87	98.86 105	99.36 73	99.82 19	98.55 106	97.47 290	99.57 92	99.37 60	99.21 157	99.61 43	96.76 226	99.83 191	98.06 152	99.83 117	99.71 62

pm-mvs1		99.44 19	99.48 18	99.33 88	99.80 21	98.63 98	99.29 36	99.63 71	99.30 70	99.65 63	99.60 45	99.16 22	99.82 203	99.07 80	99.83 117	99.56 127

TransMVSNet (Re)		99.44 19	99.47 21	99.36 73	99.80 21	98.58 104	99.27 42	99.57 92	99.39 58	99.75 44	99.62 40	99.17 20	99.83 191	99.06 82	99.62 235	99.66 77

K. test v3		98.00 244	97.66 269	99.03 144	99.79 23	97.56 201	99.19 52	92.47 458	99.62 32	99.52 86	99.66 32	89.61 381	99.96 14	99.25 67	99.81 127	99.56 127

test_fmvsmconf0.1_n		99.49 15	99.54 14	99.34 82	99.78 24	98.11 142	97.77 241	99.90 11	99.33 65	99.97 3	99.66 32	99.71 3	99.96 14	99.79 19	99.99 5	99.96 8

APD_test1		98.83 111	98.66 134	99.34 82	99.78 24	99.47 9	98.42 147	99.45 148	98.28 184	98.98 192	99.19 146	97.76 147	99.58 366	96.57 281	99.55 262	98.97 327

test_vis3_rt		99.14 61	99.17 59	99.07 134	99.78 24	98.38 118	98.92 82	99.94 2	97.80 228	99.91 12	99.67 30	97.15 198	98.91 451	99.76 23	99.56 258	99.92 12

EGC-MVSNET		85.24 437	80.54 440	99.34 82	99.77 27	99.20 40	99.08 61	99.29 228	12.08 476	20.84 477	99.42 88	97.55 166	99.85 155	97.08 230	99.72 185	98.96 329

Anonymous20240521		98.69 139	98.87 101	98.16 290	99.77 27	95.11 331	99.08 61	99.44 156	99.34 64	99.33 127	99.55 57	94.10 325	99.94 42	99.25 67	99.96 28	99.42 203

FC-MVSNet-test		99.27 38	99.25 52	99.34 82	99.77 27	98.37 120	99.30 35	99.57 92	99.61 34	99.40 113	99.50 67	97.12 199	99.85 155	99.02 86	99.94 49	99.80 41

test_vis1_n		98.31 208	98.50 161	97.73 324	99.76 30	94.17 359	98.68 107	99.91 9	96.31 342	99.79 38	99.57 49	92.85 346	99.42 412	99.79 19	99.84 110	99.60 99

test_fmvs3		99.12 68	99.41 26	98.25 278	99.76 30	95.07 332	99.05 67	99.94 2	97.78 231	99.82 33	99.84 3	98.56 68	99.71 293	99.96 1	99.96 28	99.97 4

XXY-MVS		99.14 61	99.15 66	99.10 127	99.76 30	97.74 190	98.85 92	99.62 73	98.48 167	99.37 118	99.49 73	98.75 46	99.86 142	98.20 142	99.80 138	99.71 62

TDRefinement		99.42 24	99.38 29	99.55 29	99.76 30	99.33 21	99.68 6	99.71 47	99.38 59	99.53 82	99.61 43	98.64 56	99.80 228	98.24 137	99.84 110	99.52 152

fmvsm_s_conf0.1_n_a		99.17 52	99.30 44	98.80 181	99.75 34	96.59 265	97.97 215	99.86 16	98.22 187	99.88 21	99.71 22	98.59 62	99.84 173	99.73 27	99.98 12	99.98 3

tt0805		98.69 139	98.62 141	98.90 169	99.75 34	99.30 23	99.15 56	96.97 409	98.86 137	98.87 225	97.62 387	98.63 58	98.96 448	99.41 56	98.29 400	98.45 391

test_vis1_n_1920		98.40 191	98.92 94	96.81 386	99.74 36	90.76 437	98.15 173	99.91 9	98.33 175	99.89 18	99.55 57	95.07 296	99.88 114	99.76 23	99.93 55	99.79 43

FOURS1					99.73 37	99.67 3	99.43 15	99.54 109	99.43 54	99.26 145

PEN-MVS		99.41 25	99.34 36	99.62 10	99.73 37	99.14 58	99.29 36	99.54 109	99.62 32	99.56 73	99.42 88	98.16 111	99.96 14	98.78 101	99.93 55	99.77 49

lessismore_v0				98.97 156	99.73 37	97.53 203		86.71 473		99.37 118	99.52 66	89.93 377	99.92 64	98.99 88	99.72 185	99.44 195

SteuartSystems-ACMMP		98.79 120	98.54 154	99.54 32	99.73 37	99.16 49	98.23 163	99.31 212	97.92 219	98.90 214	98.90 232	98.00 123	99.88 114	96.15 313	99.72 185	99.58 114
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 229	98.15 221	98.22 284	99.73 37	95.15 328	97.36 304	99.68 59	94.45 399	98.99 191	99.27 122	96.87 215	99.94 42	97.13 227	99.91 77	99.57 121

Vis-MVSNet		99.34 30	99.36 33	99.27 98	99.73 37	98.26 127	99.17 53	99.78 36	99.11 97	99.27 141	99.48 74	98.82 37	99.95 26	98.94 91	99.93 55	99.59 106
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 80	99.54 43	99.95 38	99.61 97

SSC-MVS		98.71 131	98.74 116	98.62 220	99.72 43	96.08 289	98.74 97	98.64 352	99.74 13	99.67 59	99.24 135	94.57 311	99.95 26	99.11 77	99.24 324	99.82 35

test_f		98.67 148	98.87 101	98.05 299	99.72 43	95.59 304	98.51 131	99.81 31	96.30 344	99.78 39	99.82 5	96.14 255	98.63 458	99.82 12	99.93 55	99.95 9

ACMH	96.65 7	99.25 41	99.24 53	99.26 100	99.72 43	98.38 118	99.07 64	99.55 104	98.30 179	99.65 63	99.45 83	99.22 17	99.76 264	98.44 127	99.77 155	99.64 83
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 80	99.54 43	99.95 38	99.59 106

fmvsm_s_conf0.1_n		99.16 56	99.33 37	98.64 214	99.71 47	96.10 284	97.87 227	99.85 18	98.56 163	99.90 14	99.68 25	98.69 52	99.85 155	99.72 29	99.98 12	99.97 4

PS-CasMVS		99.40 26	99.33 37	99.62 10	99.71 47	99.10 66	99.29 36	99.53 113	99.53 41	99.46 99	99.41 92	98.23 100	99.95 26	98.89 95	99.95 38	99.81 39

DTE-MVSNet		99.43 23	99.35 34	99.66 7	99.71 47	99.30 23	99.31 30	99.51 119	99.64 27	99.56 73	99.46 79	98.23 100	99.97 7	98.78 101	99.93 55	99.72 61

WR-MVS_H		99.33 31	99.22 54	99.65 8	99.71 47	99.24 31	99.32 26	99.55 104	99.46 49	99.50 92	99.34 107	97.30 188	99.93 53	98.90 93	99.93 55	99.77 49

HPM-MVS_fast		99.01 81	98.82 109	99.57 22	99.71 47	99.35 17	99.00 72	99.50 122	97.33 276	98.94 209	98.86 242	98.75 46	99.82 203	97.53 198	99.71 194	99.56 127

ACMH+	96.62 9	99.08 75	99.00 86	99.33 88	99.71 47	98.83 86	98.60 117	99.58 85	99.11 97	99.53 82	99.18 150	98.81 38	99.67 317	96.71 268	99.77 155	99.50 158

PMVS	91.26 20	97.86 258	97.94 245	97.65 331	99.71 47	97.94 167	98.52 126	98.68 348	98.99 120	97.52 356	99.35 103	97.41 181	98.18 464	91.59 427	99.67 215	96.82 453
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
KinetiMVS		99.03 79	99.02 82	99.03 144	99.70 55	97.48 206	98.43 144	99.29 228	99.70 16	99.60 70	99.07 179	96.13 256	99.94 42	99.42 55	99.87 96	99.68 70

FIs		99.14 61	99.09 74	99.29 94	99.70 55	98.28 126	99.13 58	99.52 118	99.48 44	99.24 151	99.41 92	96.79 223	99.82 203	98.69 111	99.88 92	99.76 55

VPNet		98.87 102	98.83 108	99.01 148	99.70 55	97.62 199	98.43 144	99.35 193	99.47 47	99.28 139	99.05 187	96.72 229	99.82 203	98.09 149	99.36 303	99.59 106

fmvsm_s_conf0.1_n_2		99.20 50	99.38 29	98.65 212	99.69 58	96.08 289	97.49 286	99.90 11	99.53 41	99.88 21	99.64 37	98.51 71	99.90 80	99.83 10	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 205	98.68 130	97.27 362	99.69 58	92.29 411	98.03 196	99.85 18	97.62 241	99.96 4	99.62 40	93.98 326	99.74 277	99.52 49	99.86 103	99.79 43

MP-MVS-pluss		98.57 165	98.23 209	99.60 16	99.69 58	99.35 17	97.16 325	99.38 179	94.87 389	98.97 196	98.99 209	98.01 122	99.88 114	97.29 214	99.70 201	99.58 114
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 46	99.32 39	98.96 157	99.68 61	97.35 214	98.84 94	99.48 131	99.69 18	99.63 66	99.68 25	99.03 24	99.96 14	97.97 162	99.92 68	99.57 121

sd_testset		99.28 37	99.31 41	99.19 111	99.68 61	98.06 154	99.41 17	99.30 220	99.69 18	99.63 66	99.68 25	99.25 16	99.96 14	97.25 217	99.92 68	99.57 121

test_fmvs1_n		98.09 235	98.28 200	97.52 348	99.68 61	93.47 390	98.63 113	99.93 5	95.41 377	99.68 57	99.64 37	91.88 360	99.48 399	99.82 12	99.87 96	99.62 89

CHOSEN 1792x2688		97.49 287	97.14 302	98.54 242	99.68 61	96.09 287	96.50 361	99.62 73	91.58 437	98.84 228	98.97 216	92.36 352	99.88 114	96.76 261	99.95 38	99.67 75

tfpnnormal		98.90 98	98.90 96	98.91 166	99.67 65	97.82 182	99.00 72	99.44 156	99.45 50	99.51 91	99.24 135	98.20 106	99.86 142	95.92 322	99.69 204	99.04 314

MTAPA		98.88 101	98.64 137	99.61 14	99.67 65	99.36 16	98.43 144	99.20 252	98.83 141	98.89 217	98.90 232	96.98 209	99.92 64	97.16 222	99.70 201	99.56 127

test_fmvsmvis_n_1920		99.26 40	99.49 16	98.54 242	99.66 67	96.97 245	98.00 203	99.85 18	99.24 75	99.92 8	99.50 67	99.39 12	99.95 26	99.89 3	99.98 12	98.71 368

mvs5depth		99.30 34	99.59 12	98.44 256	99.65 68	95.35 320	99.82 3	99.94 2	99.83 7	99.42 108	99.94 2	98.13 114	99.96 14	99.63 35	99.96 28	100.00 1

fmvsm_l_conf0.5_n_a		99.19 51	99.27 47	98.94 160	99.65 68	97.05 240	97.80 236	99.76 39	98.70 146	99.78 39	99.11 169	98.79 42	99.95 26	99.85 6	99.96 28	99.83 32

WB-MVS		98.52 179	98.55 152	98.43 257	99.65 68	95.59 304	98.52 126	98.77 337	99.65 26	99.52 86	99.00 207	94.34 317	99.93 53	98.65 113	98.83 372	99.76 55

CP-MVSNet		99.21 48	99.09 74	99.56 27	99.65 68	98.96 78	99.13 58	99.34 199	99.42 55	99.33 127	99.26 128	97.01 207	99.94 42	98.74 106	99.93 55	99.79 43

HPM-MVS		98.79 120	98.53 156	99.59 20	99.65 68	99.29 25	99.16 54	99.43 162	96.74 322	98.61 261	98.38 332	98.62 59	99.87 133	96.47 293	99.67 215	99.59 106
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 157	98.36 187	99.42 67	99.65 68	99.42 11	98.55 122	99.57 92	97.72 235	98.90 214	99.26 128	96.12 258	99.52 387	95.72 333	99.71 194	99.32 250

NormalMVS		98.26 215	97.97 242	99.15 120	99.64 74	97.83 177	98.28 157	99.43 162	99.24 75	98.80 236	98.85 245	89.76 379	99.94 42	98.04 154	99.67 215	99.68 70

lecture		99.25 41	99.12 69	99.62 10	99.64 74	99.40 12	98.89 87	99.51 119	99.19 87	99.37 118	99.25 133	98.36 82	99.88 114	98.23 139	99.67 215	99.59 106

fmvsm_l_conf0.5_n		99.21 48	99.28 46	99.02 147	99.64 74	97.28 221	97.82 232	99.76 39	98.73 143	99.82 33	99.09 177	98.81 38	99.95 26	99.86 4	99.96 28	99.83 32

test_fmvsmconf_n		99.44 19	99.48 18	99.31 93	99.64 74	98.10 144	97.68 255	99.84 22	99.29 71	99.92 8	99.57 49	99.60 5	99.96 14	99.74 26	99.98 12	99.89 16

TSAR-MVS + MP.		98.63 154	98.49 166	99.06 140	99.64 74	97.90 171	98.51 131	98.94 302	96.96 307	99.24 151	98.89 238	97.83 139	99.81 220	96.88 251	99.49 283	99.48 176
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 114	98.72 120	99.12 123	99.64 74	98.54 109	97.98 211	99.68 59	97.62 241	99.34 125	99.18 150	97.54 168	99.77 258	97.79 176	99.74 174	99.04 314

Elysia		99.15 57	99.14 67	99.18 112	99.63 80	97.92 168	98.50 133	99.43 162	99.67 21	99.70 51	99.13 165	96.66 232	99.98 4	99.54 43	99.96 28	99.64 83

StellarMVS		99.15 57	99.14 67	99.18 112	99.63 80	97.92 168	98.50 133	99.43 162	99.67 21	99.70 51	99.13 165	96.66 232	99.98 4	99.54 43	99.96 28	99.64 83

KD-MVS_self_test		99.25 41	99.18 58	99.44 65	99.63 80	99.06 71	98.69 106	99.54 109	99.31 68	99.62 69	99.53 63	97.36 185	99.86 142	99.24 69	99.71 194	99.39 216

EU-MVSNet		97.66 275	98.50 161	95.13 428	99.63 80	85.84 459	98.35 153	98.21 371	98.23 186	99.54 78	99.46 79	95.02 297	99.68 313	98.24 137	99.87 96	99.87 21

HyFIR lowres test		97.19 313	96.60 337	98.96 157	99.62 84	97.28 221	95.17 426	99.50 122	94.21 404	99.01 187	98.32 340	86.61 399	99.99 2	97.10 229	99.84 110	99.60 99

fmvsm_l_conf0.5_n_9		99.32 33	99.43 24	98.98 154	99.59 85	97.18 232	97.44 294	99.83 25	99.56 39	99.91 12	99.34 107	99.36 13	99.93 53	99.83 10	99.98 12	99.85 29

fmvsm_l_conf0.5_n_3		99.45 18	99.48 18	99.34 82	99.59 85	98.21 135	97.82 232	99.84 22	99.41 57	99.92 8	99.41 92	99.51 8	99.95 26	99.84 9	99.97 21	99.87 21

MED-MVS test				99.45 64	99.58 87	98.93 80	98.68 107	99.60 77	96.46 335	99.53 82	98.77 265		99.83 191	96.67 271	99.64 226	99.58 114

TestfortrainingZip a		98.95 91	98.72 120	99.64 9	99.58 87	99.32 22	98.68 107	99.60 77	96.46 335	99.53 82	98.77 265	97.87 137	99.83 191	98.39 130	99.64 226	99.77 49

FE-MVSNET		98.59 162	98.50 161	98.87 170	99.58 87	97.30 219	98.08 185	99.74 43	96.94 309	98.97 196	99.10 172	96.94 211	99.74 277	97.33 212	99.86 103	99.55 134

mmtdpeth		99.30 34	99.42 25	98.92 165	99.58 87	96.89 252	99.48 13	99.92 7	99.92 2	98.26 299	99.80 11	98.33 88	99.91 73	99.56 40	99.95 38	99.97 4

ACMMP_NAP		98.75 127	98.48 167	99.57 22	99.58 87	99.29 25	97.82 232	99.25 241	96.94 309	98.78 238	99.12 168	98.02 121	99.84 173	97.13 227	99.67 215	99.59 106

nrg030		99.40 26	99.35 34	99.54 32	99.58 87	99.13 61	98.98 75	99.48 131	99.68 20	99.46 99	99.26 128	98.62 59	99.73 284	99.17 74	99.92 68	99.76 55

VDDNet		98.21 222	97.95 243	99.01 148	99.58 87	97.74 190	99.01 70	97.29 400	99.67 21	98.97 196	99.50 67	90.45 374	99.80 228	97.88 169	99.20 332	99.48 176

COLMAP_ROB	96.50 10	98.99 84	98.85 107	99.41 69	99.58 87	99.10 66	98.74 97	99.56 100	99.09 107	99.33 127	99.19 146	98.40 79	99.72 292	95.98 320	99.76 169	99.42 203
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	98.99 150	99.57 95	97.73 192	97.93 216	99.83 25	99.22 78	99.93 6	99.30 116	99.42 11	99.96 14	99.85 6	99.99 5	99.29 259

ZNCC-MVS		98.68 145	98.40 179	99.54 32	99.57 95	99.21 34	98.46 141	99.29 228	97.28 282	98.11 311	98.39 330	98.00 123	99.87 133	96.86 254	99.64 226	99.55 134

MSP-MVS		98.40 191	98.00 237	99.61 14	99.57 95	99.25 30	98.57 120	99.35 193	97.55 252	99.31 135	97.71 380	94.61 310	99.88 114	96.14 314	99.19 335	99.70 67
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		98.32 206	98.39 182	98.13 291	99.57 95	95.54 307	97.78 238	99.49 129	97.37 273	99.19 159	97.65 384	98.96 29	99.49 396	96.50 292	98.99 360	99.34 241

MP-MVS		98.46 185	98.09 226	99.54 32	99.57 95	99.22 33	98.50 133	99.19 256	97.61 244	97.58 350	98.66 292	97.40 182	99.88 114	94.72 359	99.60 242	99.54 140
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 131	98.46 171	99.47 61	99.57 95	98.97 74	98.23 163	99.48 131	96.60 327	99.10 169	99.06 180	98.71 50	99.83 191	95.58 340	99.78 149	99.62 89

LGP-MVS_train				99.47 61	99.57 95	98.97 74		99.48 131	96.60 327	99.10 169	99.06 180	98.71 50	99.83 191	95.58 340	99.78 149	99.62 89

IS-MVSNet		98.19 225	97.90 251	99.08 132	99.57 95	97.97 162	99.31 30	98.32 367	99.01 119	98.98 192	99.03 191	91.59 362	99.79 241	95.49 342	99.80 138	99.48 176

viewdifsd2359ckpt11		98.84 108	99.04 79	98.24 280	99.56 103	95.51 309	97.38 299	99.70 52	99.16 92	99.57 71	99.40 95	98.26 96	99.71 293	98.55 122	99.82 121	99.50 158

viewmsd2359difaftdt		98.84 108	99.04 79	98.24 280	99.56 103	95.51 309	97.38 299	99.70 52	99.16 92	99.57 71	99.40 95	98.26 96	99.71 293	98.55 122	99.82 121	99.50 158

dcpmvs_2		98.78 122	99.11 70	97.78 314	99.56 103	93.67 385	99.06 65	99.86 16	99.50 43	99.66 60	99.26 128	97.21 196	99.99 2	98.00 159	99.91 77	99.68 70

test_0402		98.76 126	98.71 124	98.93 162	99.56 103	98.14 140	98.45 143	99.34 199	99.28 72	98.95 202	98.91 229	98.34 87	99.79 241	95.63 337	99.91 77	98.86 346

EPP-MVSNet		98.30 209	98.04 233	99.07 134	99.56 103	97.83 177	99.29 36	98.07 378	99.03 117	98.59 265	99.13 165	92.16 356	99.90 80	96.87 252	99.68 209	99.49 165

ACMMP		98.75 127	98.50 161	99.52 45	99.56 103	99.16 49	98.87 88	99.37 183	97.16 297	98.82 232	99.01 203	97.71 150	99.87 133	96.29 305	99.69 204	99.54 140
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 70	99.20 57	98.78 187	99.55 109	96.59 265	97.79 237	99.82 30	98.21 189	99.81 36	99.53 63	98.46 75	99.84 173	99.70 32	99.97 21	99.90 15

fmvsm_s_conf0.5_n		99.09 71	99.26 50	98.61 223	99.55 109	96.09 287	97.74 248	99.81 31	98.55 164	99.85 27	99.55 57	98.60 61	99.84 173	99.69 34	99.98 12	99.89 16

FMVSNet1		99.17 52	99.17 59	99.17 114	99.55 109	98.24 129	99.20 48	99.44 156	99.21 80	99.43 104	99.55 57	97.82 142	99.86 142	98.42 129	99.89 90	99.41 206

Vis-MVSNet (Re-imp)		97.46 289	97.16 299	98.34 269	99.55 109	96.10 284	98.94 80	98.44 361	98.32 177	98.16 305	98.62 301	88.76 386	99.73 284	93.88 385	99.79 144	99.18 293

ACMM	96.08 12	98.91 96	98.73 118	99.48 57	99.55 109	99.14 58	98.07 189	99.37 183	97.62 241	99.04 183	98.96 219	98.84 36	99.79 241	97.43 207	99.65 224	99.49 165
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 136	98.97 90	97.89 307	99.54 114	94.05 362	98.55 122	99.92 7	96.78 320	99.72 47	99.78 13	96.60 236	99.67 317	99.91 2	99.90 84	99.94 10

mPP-MVS		98.64 152	98.34 190	99.54 32	99.54 114	99.17 45	98.63 113	99.24 246	97.47 260	98.09 313	98.68 287	97.62 159	99.89 96	96.22 308	99.62 235	99.57 121

XVG-ACMP-BASELINE		98.56 166	98.34 190	99.22 108	99.54 114	98.59 103	97.71 251	99.46 144	97.25 285	98.98 192	98.99 209	97.54 168	99.84 173	95.88 323	99.74 174	99.23 275

viewmacassd2359aftdt		98.86 105	98.87 101	98.83 175	99.53 117	97.32 218	97.70 253	99.64 69	98.22 187	99.25 149	99.27 122	98.40 79	99.61 352	97.98 161	99.87 96	99.55 134

region2R		98.69 139	98.40 179	99.54 32	99.53 117	99.17 45	98.52 126	99.31 212	97.46 265	98.44 284	98.51 315	97.83 139	99.88 114	96.46 294	99.58 251	99.58 114

PGM-MVS		98.66 149	98.37 186	99.55 29	99.53 117	99.18 44	98.23 163	99.49 129	97.01 306	98.69 249	98.88 239	98.00 123	99.89 96	95.87 326	99.59 246	99.58 114

Patchmatch-RL test		97.26 306	97.02 307	97.99 303	99.52 120	95.53 308	96.13 386	99.71 47	97.47 260	99.27 141	99.16 156	84.30 420	99.62 345	97.89 166	99.77 155	98.81 354

ACMMPR		98.70 136	98.42 177	99.54 32	99.52 120	99.14 58	98.52 126	99.31 212	97.47 260	98.56 271	98.54 310	97.75 148	99.88 114	96.57 281	99.59 246	99.58 114

fmvsm_s_conf0.5_n_9		99.17 52	99.38 29	98.53 244	99.51 122	95.82 299	97.62 266	99.78 36	99.72 15	99.90 14	99.48 74	98.66 54	99.89 96	99.85 6	99.93 55	99.89 16

AstraMVS		98.16 231	98.07 231	98.41 259	99.51 122	95.86 296	98.00 203	95.14 441	98.97 123	99.43 104	99.24 135	93.25 334	99.84 173	99.21 70	99.87 96	99.54 140

fmvsm_s_conf0.5_n_8		99.13 65	99.26 50	98.74 200	99.51 122	96.44 276	97.65 261	99.65 67	99.66 24	99.78 39	99.48 74	97.92 131	99.93 53	99.72 29	99.95 38	99.87 21

GST-MVS		98.61 158	98.30 197	99.52 45	99.51 122	99.20 40	98.26 161	99.25 241	97.44 268	98.67 252	98.39 330	97.68 151	99.85 155	96.00 318	99.51 273	99.52 152

Anonymous20231206		98.21 222	98.21 210	98.20 285	99.51 122	95.43 318	98.13 175	99.32 207	96.16 348	98.93 210	98.82 255	96.00 263	99.83 191	97.32 213	99.73 177	99.36 234

ACMP	95.32 15	98.41 189	98.09 226	99.36 73	99.51 122	98.79 89	97.68 255	99.38 179	95.76 364	98.81 234	98.82 255	98.36 82	99.82 203	94.75 356	99.77 155	99.48 176
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LuminaMVS		98.39 197	98.20 211	98.98 154	99.50 128	97.49 204	97.78 238	97.69 387	98.75 142	99.49 93	99.25 133	92.30 354	99.94 42	99.14 75	99.88 92	99.50 158

DVP-MVS		98.77 125	98.52 157	99.52 45	99.50 128	99.21 34	98.02 199	98.84 326	97.97 213	99.08 171	99.02 192	97.61 161	99.88 114	96.99 238	99.63 232	99.48 176
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	99.50 128	99.23 32	98.02 199	99.32 207					99.88 114	96.99 238	99.63 232	99.68 70

test0726					99.50 128	99.21 34	98.17 171	99.35 193	97.97 213	99.26 145	99.06 180	97.61 161

AllTest		98.44 187	98.20 211	99.16 117	99.50 128	98.55 106	98.25 162	99.58 85	96.80 318	98.88 221	99.06 180	97.65 154	99.57 368	94.45 366	99.61 240	99.37 227

TestCases				99.16 117	99.50 128	98.55 106		99.58 85	96.80 318	98.88 221	99.06 180	97.65 154	99.57 368	94.45 366	99.61 240	99.37 227

XVG-OURS		98.53 175	98.34 190	99.11 125	99.50 128	98.82 88	95.97 392	99.50 122	97.30 280	99.05 181	98.98 214	99.35 14	99.32 426	95.72 333	99.68 209	99.18 293

EG-PatchMatch MVS		98.99 84	99.01 84	98.94 160	99.50 128	97.47 207	98.04 194	99.59 83	98.15 204	99.40 113	99.36 102	98.58 67	99.76 264	98.78 101	99.68 209	99.59 106

fmvsm_s_conf0.5_n_2		99.14 61	99.31 41	98.63 218	99.49 136	96.08 289	97.38 299	99.81 31	99.48 44	99.84 30	99.57 49	98.46 75	99.89 96	99.82 12	99.97 21	99.91 13

SED-MVS		98.91 96	98.72 120	99.49 55	99.49 136	99.17 45	98.10 182	99.31 212	98.03 209	99.66 60	99.02 192	98.36 82	99.88 114	96.91 244	99.62 235	99.41 206

IU-MVS					99.49 136	99.15 53		98.87 317	92.97 422	99.41 110				96.76 261	99.62 235	99.66 77

test_241102_ONE					99.49 136	99.17 45		99.31 212	97.98 212	99.66 60	98.90 232	98.36 82	99.48 399

UA-Net		99.47 16	99.40 27	99.70 2	99.49 136	99.29 25	99.80 4	99.72 45	99.82 8	99.04 183	99.81 8	98.05 120	99.96 14	98.85 97	99.99 5	99.86 27

HFP-MVS		98.71 131	98.44 174	99.51 49	99.49 136	99.16 49	98.52 126	99.31 212	97.47 260	98.58 267	98.50 319	97.97 127	99.85 155	96.57 281	99.59 246	99.53 149

VPA-MVSNet		99.30 34	99.30 44	99.28 95	99.49 136	98.36 123	99.00 72	99.45 148	99.63 29	99.52 86	99.44 84	98.25 98	99.88 114	99.09 79	99.84 110	99.62 89

XVG-OURS-SEG-HR		98.49 182	98.28 200	99.14 121	99.49 136	98.83 86	96.54 357	99.48 131	97.32 278	99.11 166	98.61 303	99.33 15	99.30 429	96.23 307	98.38 396	99.28 262

114514_t		96.50 346	95.77 355	98.69 207	99.48 144	97.43 211	97.84 231	99.55 104	81.42 469	96.51 409	98.58 307	95.53 283	99.67 317	93.41 398	99.58 251	98.98 324

IterMVS-LS		98.55 170	98.70 127	98.09 292	99.48 144	94.73 342	97.22 319	99.39 177	98.97 123	99.38 116	99.31 115	96.00 263	99.93 53	98.58 116	99.97 21	99.60 99
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 57	99.27 47	98.78 187	99.47 146	96.56 270	97.75 247	99.71 47	99.60 35	99.74 46	99.44 84	97.96 128	99.95 26	99.86 4	99.94 49	99.82 35

fmvsm_s_conf0.5_n_5		99.07 77	99.10 72	98.99 150	99.47 146	97.22 226	97.40 296	99.83 25	97.61 244	99.85 27	99.30 116	98.80 40	99.95 26	99.71 31	99.90 84	99.78 46

v8		99.01 81	99.16 61	98.57 230	99.47 146	96.31 281	98.90 83	99.47 140	99.03 117	99.52 86	99.57 49	96.93 212	99.81 220	99.60 36	99.98 12	99.60 99

SSC-MVS3.2		98.53 175	98.79 112	97.74 321	99.46 149	93.62 388	96.45 363	99.34 199	99.33 65	98.93 210	98.70 283	97.90 132	99.90 80	99.12 76	99.92 68	99.69 69

fmvsm_s_conf0.5_n_3		99.22 47	99.37 32	98.78 187	99.46 149	96.58 268	97.65 261	99.72 45	99.47 47	99.86 24	99.50 67	98.94 30	99.89 96	99.75 25	99.97 21	99.86 27

XVS		98.72 130	98.45 172	99.53 39	99.46 149	99.21 34	98.65 111	99.34 199	98.62 153	97.54 354	98.63 299	97.50 174	99.83 191	96.79 257	99.53 268	99.56 127

X-MVStestdata		94.32 395	92.59 414	99.53 39	99.46 149	99.21 34	98.65 111	99.34 199	98.62 153	97.54 354	45.85 474	97.50 174	99.83 191	96.79 257	99.53 268	99.56 127

test20.03		98.78 122	98.77 115	98.78 187	99.46 149	97.20 229	97.78 238	99.24 246	99.04 116	99.41 110	98.90 232	97.65 154	99.76 264	97.70 186	99.79 144	99.39 216

guyue		98.01 243	97.93 247	98.26 276	99.45 154	95.48 313	98.08 185	96.24 424	98.89 134	99.34 125	99.14 163	91.32 366	99.82 203	99.07 80	99.83 117	99.48 176

CSCG		98.68 145	98.50 161	99.20 109	99.45 154	98.63 98	98.56 121	99.57 92	97.87 223	98.85 226	98.04 361	97.66 153	99.84 173	96.72 266	99.81 127	99.13 303

GeoE		99.05 78	98.99 88	99.25 103	99.44 156	98.35 124	98.73 101	99.56 100	98.42 170	98.91 213	98.81 258	98.94 30	99.91 73	98.35 132	99.73 177	99.49 165

v148		98.45 186	98.60 146	98.00 302	99.44 156	94.98 334	97.44 294	99.06 282	98.30 179	99.32 133	98.97 216	96.65 234	99.62 345	98.37 131	99.85 105	99.39 216

v10		98.97 88	99.11 70	98.55 237	99.44 156	96.21 283	98.90 83	99.55 104	98.73 143	99.48 94	99.60 45	96.63 235	99.83 191	99.70 32	99.99 5	99.61 97

V42		98.78 122	98.78 114	98.76 194	99.44 156	97.04 241	98.27 160	99.19 256	97.87 223	99.25 149	99.16 156	96.84 216	99.78 252	99.21 70	99.84 110	99.46 186

MDA-MVSNet-bldmvs		97.94 249	97.91 250	98.06 297	99.44 156	94.96 335	96.63 353	99.15 272	98.35 173	98.83 229	99.11 169	94.31 318	99.85 155	96.60 278	98.72 378	99.37 227

viewdifsd2359ckpt07		98.71 131	98.86 105	98.26 276	99.43 161	95.65 303	97.20 320	99.66 63	99.20 82	99.29 137	99.01 203	98.29 91	99.73 284	97.92 165	99.75 173	99.39 216

casdiffmvs_mvg		99.12 68	99.16 61	98.99 150	99.43 161	97.73 192	98.00 203	99.62 73	99.22 78	99.55 76	99.22 141	98.93 32	99.75 272	98.66 112	99.81 127	99.50 158
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SSM_0404		98.90 98	99.01 84	98.57 230	99.42 163	96.59 265	98.13 175	99.66 63	99.09 107	99.30 136	99.02 192	98.79 42	99.89 96	97.87 171	99.80 138	99.23 275

test1111		96.49 347	96.82 321	95.52 421	99.42 163	87.08 456	99.22 45	87.14 472	99.11 97	99.46 99	99.58 47	88.69 387	99.86 142	98.80 99	99.95 38	99.62 89

v2v482		98.56 166	98.62 141	98.37 266	99.42 163	95.81 300	97.58 274	99.16 267	97.90 221	99.28 139	99.01 203	95.98 268	99.79 241	99.33 59	99.90 84	99.51 155

OPM-MVS		98.56 166	98.32 195	99.25 103	99.41 166	98.73 94	97.13 327	99.18 260	97.10 300	98.75 244	98.92 227	98.18 107	99.65 336	96.68 270	99.56 258	99.37 227
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 237	98.08 229	98.04 300	99.41 166	94.59 348	94.59 444	99.40 175	97.50 257	98.82 232	98.83 252	96.83 218	99.84 173	97.50 201	99.81 127	99.71 62

E3		98.69 139	98.68 130	98.73 202	99.40 168	97.10 239	97.48 287	99.57 92	98.09 207	99.00 188	99.20 144	97.90 132	99.67 317	97.73 185	99.77 155	99.43 199

test_one_0601					99.39 169	99.20 40		99.31 212	98.49 166	98.66 254	99.02 192	97.64 157

mvsany_test3		98.87 102	98.92 94	98.74 200	99.38 170	96.94 249	98.58 119	99.10 277	96.49 332	99.96 4	99.81 8	98.18 107	99.45 407	98.97 89	99.79 144	99.83 32

patch_mono-2		98.51 180	98.63 139	98.17 288	99.38 170	94.78 339	97.36 304	99.69 54	98.16 199	98.49 280	99.29 119	97.06 202	99.97 7	98.29 136	99.91 77	99.76 55

test2506		92.39 426	91.89 428	93.89 442	99.38 170	82.28 473	99.32 26	66.03 480	99.08 111	98.77 241	99.57 49	66.26 467	99.84 173	98.71 109	99.95 38	99.54 140

ECVR-MVS		96.42 349	96.61 335	95.85 413	99.38 170	88.18 451	99.22 45	86.00 474	99.08 111	99.36 121	99.57 49	88.47 392	99.82 203	98.52 124	99.95 38	99.54 140

casdiffmvs		98.95 91	99.00 86	98.81 179	99.38 170	97.33 216	97.82 232	99.57 92	99.17 91	99.35 123	99.17 154	98.35 86	99.69 304	98.46 126	99.73 177	99.41 206
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 90	99.02 82	98.76 194	99.38 170	97.26 223	98.49 136	99.50 122	98.86 137	99.19 159	99.06 180	98.23 100	99.69 304	98.71 109	99.76 169	99.33 247

TranMVSNet+NR-MVSNet		99.17 52	99.07 77	99.46 63	99.37 176	98.87 84	98.39 149	99.42 168	99.42 55	99.36 121	99.06 180	98.38 81	99.95 26	98.34 133	99.90 84	99.57 121

fmvsm_s_conf0.5_n_6		99.08 75	99.21 56	98.69 207	99.36 177	96.51 271	97.62 266	99.68 59	98.43 169	99.85 27	99.10 172	99.12 23	99.88 114	99.77 22	99.92 68	99.67 75

tttt0517		95.64 374	94.98 384	97.64 334	99.36 177	93.81 380	98.72 102	90.47 466	98.08 208	98.67 252	98.34 337	73.88 453	99.92 64	97.77 178	99.51 273	99.20 285

test_part2					99.36 177	99.10 66				99.05 181

v1144		98.60 160	98.66 134	98.41 259	99.36 177	95.90 294	97.58 274	99.34 199	97.51 256	99.27 141	99.15 160	96.34 249	99.80 228	99.47 53	99.93 55	99.51 155

CP-MVS		98.70 136	98.42 177	99.52 45	99.36 177	99.12 63	98.72 102	99.36 187	97.54 254	98.30 293	98.40 329	97.86 138	99.89 96	96.53 290	99.72 185	99.56 127

diffmvs_AUTHOR		98.50 181	98.59 148	98.23 283	99.35 182	95.48 313	96.61 354	99.60 77	98.37 171	98.90 214	99.00 207	97.37 184	99.76 264	98.22 140	99.85 105	99.46 186

Test_1112_low_res		96.99 328	96.55 339	98.31 272	99.35 182	95.47 316	95.84 404	99.53 113	91.51 439	96.80 396	98.48 322	91.36 365	99.83 191	96.58 279	99.53 268	99.62 89

DeepC-MVS	97.60 4	98.97 88	98.93 93	99.10 127	99.35 182	97.98 161	98.01 202	99.46 144	97.56 250	99.54 78	99.50 67	98.97 28	99.84 173	98.06 152	99.92 68	99.49 165
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 305	96.86 317	98.58 227	99.34 185	96.32 280	96.75 346	99.58 85	93.14 420	96.89 391	97.48 394	92.11 357	99.86 142	96.91 244	99.54 264	99.57 121

reproduce_model		99.15 57	98.97 90	99.67 4	99.33 186	99.44 10	98.15 173	99.47 140	99.12 96	99.52 86	99.32 114	98.31 89	99.90 80	97.78 177	99.73 177	99.66 77

MVSMamba_PlusPlus		98.83 111	98.98 89	98.36 267	99.32 187	96.58 268	98.90 83	99.41 172	99.75 11	98.72 247	99.50 67	96.17 254	99.94 42	99.27 64	99.78 149	98.57 384

fmvsm_s_conf0.5_n_4		99.01 81	99.22 54	98.38 263	99.31 188	95.48 313	97.56 276	99.73 44	98.87 135	99.75 44	99.27 122	98.80 40	99.86 142	99.80 17	99.90 84	99.81 39

SF-MVS		98.53 175	98.27 203	99.32 90	99.31 188	98.75 90	98.19 167	99.41 172	96.77 321	98.83 229	98.90 232	97.80 144	99.82 203	95.68 336	99.52 271	99.38 225

CPTT-MVS		97.84 264	97.36 288	99.27 98	99.31 188	98.46 114	98.29 156	99.27 235	94.90 388	97.83 334	98.37 333	94.90 299	99.84 173	93.85 387	99.54 264	99.51 155

UnsupCasMVSNet_eth		97.89 253	97.60 274	98.75 196	99.31 188	97.17 234	97.62 266	99.35 193	98.72 145	98.76 243	98.68 287	92.57 351	99.74 277	97.76 182	95.60 458	99.34 241

fmvsm_s_conf0.5_n_7		98.83 111	99.04 79	98.20 285	99.30 192	94.83 337	97.23 315	99.36 187	98.64 148	99.84 30	99.43 87	98.10 116	99.91 73	99.56 40	99.96 28	99.87 21

pmmvs-eth3d		98.47 184	98.34 190	98.86 172	99.30 192	97.76 188	97.16 325	99.28 232	95.54 370	99.42 108	99.19 146	97.27 191	99.63 342	97.89 166	99.97 21	99.20 285

mamv4		99.44 19	99.39 28	99.58 21	99.30 192	99.74 2	99.04 68	99.81 31	99.77 10	99.82 33	99.57 49	97.82 142	99.98 4	99.53 47	99.89 90	99.01 318

viewcassd2359sk11		98.55 170	98.51 158	98.67 210	99.29 195	96.99 244	97.39 297	99.54 109	97.73 233	98.81 234	99.08 178	97.55 166	99.66 329	97.52 200	99.67 215	99.36 234

SymmetryMVS		98.05 239	97.71 264	99.09 131	99.29 195	97.83 177	98.28 157	97.64 392	99.24 75	98.80 236	98.85 245	89.76 379	99.94 42	98.04 154	99.50 281	99.49 165

Anonymous20231211		99.27 38	99.27 47	99.26 100	99.29 195	98.18 136	99.49 12	99.51 119	99.70 16	99.80 37	99.68 25	96.84 216	99.83 191	99.21 70	99.91 77	99.77 49

viewmanbaseed2359cas		98.58 164	98.54 154	98.70 205	99.28 198	97.13 238	97.47 290	99.55 104	97.55 252	98.96 201	98.92 227	97.77 146	99.59 359	97.59 194	99.77 155	99.39 216

UnsupCasMVSNet_bld		97.30 303	96.92 313	98.45 254	99.28 198	96.78 259	96.20 380	99.27 235	95.42 374	98.28 297	98.30 341	93.16 337	99.71 293	94.99 350	97.37 434	98.87 345

EC-MVSNet		99.09 71	99.05 78	99.20 109	99.28 198	98.93 80	99.24 44	99.84 22	99.08 111	98.12 310	98.37 333	98.72 49	99.90 80	99.05 83	99.77 155	98.77 362

mamba_0408		98.80 118	98.88 99	98.55 237	99.27 201	96.50 272	98.00 203	99.60 77	98.93 128	99.22 154	98.84 250	98.59 62	99.89 96	97.74 183	99.72 185	99.27 263

SSM_04072		98.80 118	98.88 99	98.56 235	99.27 201	96.50 272	98.00 203	99.60 77	98.93 128	99.22 154	98.84 250	98.59 62	99.90 80	97.74 183	99.72 185	99.27 263

SSM_0407		98.86 105	98.96 92	98.55 237	99.27 201	96.50 272	98.04 194	99.66 63	99.09 107	99.22 154	99.02 192	98.79 42	99.87 133	97.87 171	99.72 185	99.27 263

reproduce-ours		99.09 71	98.90 96	99.67 4	99.27 201	99.49 6	98.00 203	99.42 168	99.05 114	99.48 94	99.27 122	98.29 91	99.89 96	97.61 191	99.71 194	99.62 89

our_new_method		99.09 71	98.90 96	99.67 4	99.27 201	99.49 6	98.00 203	99.42 168	99.05 114	99.48 94	99.27 122	98.29 91	99.89 96	97.61 191	99.71 194	99.62 89

DPE-MVS		98.59 162	98.26 204	99.57 22	99.27 201	99.15 53	97.01 330	99.39 177	97.67 237	99.44 103	98.99 209	97.53 170	99.89 96	95.40 344	99.68 209	99.66 77
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 263	98.18 216	96.87 382	99.27 201	91.16 431	95.53 414	99.25 241	99.10 104	99.41 110	99.35 103	93.10 339	99.96 14	98.65 113	99.94 49	99.49 165

v1192		98.60 160	98.66 134	98.41 259	99.27 201	95.88 295	97.52 281	99.36 187	97.41 269	99.33 127	99.20 144	96.37 247	99.82 203	99.57 38	99.92 68	99.55 134

N_pmnet		97.63 277	97.17 298	98.99 150	99.27 201	97.86 174	95.98 391	93.41 455	95.25 379	99.47 98	98.90 232	95.63 280	99.85 155	96.91 244	99.73 177	99.27 263

viewdifsd2359ckpt13		98.39 197	98.29 199	98.70 205	99.26 210	97.19 230	97.51 283	99.48 131	96.94 309	98.58 267	98.82 255	97.47 179	99.55 375	97.21 219	99.33 308	99.34 241

FPMVS		93.44 412	92.23 419	97.08 370	99.25 211	97.86 174	95.61 411	97.16 404	92.90 424	93.76 457	98.65 294	75.94 451	95.66 471	79.30 469	97.49 427	97.73 435

ME-MVS		98.61 158	98.33 194	99.44 65	99.24 212	98.93 80	97.45 292	99.06 282	98.14 205	99.06 173	98.77 265	96.97 210	99.82 203	96.67 271	99.64 226	99.58 114

new-patchmatchnet		98.35 200	98.74 116	97.18 365	99.24 212	92.23 413	96.42 367	99.48 131	98.30 179	99.69 55	99.53 63	97.44 180	99.82 203	98.84 98	99.77 155	99.49 165

MCST-MVS		98.00 244	97.63 272	99.10 127	99.24 212	98.17 137	96.89 339	98.73 345	95.66 365	97.92 325	97.70 382	97.17 197	99.66 329	96.18 312	99.23 327	99.47 184

UniMVSNet (Re)		98.87 102	98.71 124	99.35 79	99.24 212	98.73 94	97.73 250	99.38 179	98.93 128	99.12 165	98.73 273	96.77 224	99.86 142	98.63 115	99.80 138	99.46 186

jason		97.45 291	97.35 289	97.76 318	99.24 212	93.93 374	95.86 401	98.42 363	94.24 403	98.50 279	98.13 351	94.82 303	99.91 73	97.22 218	99.73 177	99.43 199
jason: jason.
IterMVS		97.73 269	98.11 225	96.57 392	99.24 212	90.28 440	95.52 416	99.21 250	98.86 137	99.33 127	99.33 110	93.11 338	99.94 42	98.49 125	99.94 49	99.48 176
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 170	98.62 141	98.32 270	99.22 218	95.58 306	97.51 283	99.45 148	97.16 297	99.45 102	99.24 135	96.12 258	99.85 155	99.60 36	99.88 92	99.55 134

ITE_SJBPF				98.87 170	99.22 218	98.48 113		99.35 193	97.50 257	98.28 297	98.60 305	97.64 157	99.35 422	93.86 386	99.27 319	98.79 360

h-mvs33		97.77 267	97.33 291	99.10 127	99.21 220	97.84 176	98.35 153	98.57 355	99.11 97	98.58 267	99.02 192	88.65 390	99.96 14	98.11 147	96.34 450	99.49 165

v144192		98.54 173	98.57 150	98.45 254	99.21 220	95.98 292	97.63 265	99.36 187	97.15 299	99.32 133	99.18 150	95.84 275	99.84 173	99.50 50	99.91 77	99.54 140

APDe-MVS		98.99 84	98.79 112	99.60 16	99.21 220	99.15 53	98.87 88	99.48 131	97.57 248	99.35 123	99.24 135	97.83 139	99.89 96	97.88 169	99.70 201	99.75 59
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 94	98.81 111	99.28 95	99.21 220	98.45 115	98.46 141	99.33 205	99.63 29	99.48 94	99.15 160	97.23 194	99.75 272	97.17 221	99.66 223	99.63 88

SR-MVS-dyc-post		98.81 116	98.55 152	99.57 22	99.20 224	99.38 13	98.48 139	99.30 220	98.64 148	98.95 202	98.96 219	97.49 177	99.86 142	96.56 285	99.39 299	99.45 191

RE-MVS-def			98.58 149		99.20 224	99.38 13	98.48 139	99.30 220	98.64 148	98.95 202	98.96 219	97.75 148		96.56 285	99.39 299	99.45 191

v1921920		98.54 173	98.60 146	98.38 263	99.20 224	95.76 302	97.56 276	99.36 187	97.23 291	99.38 116	99.17 154	96.02 261	99.84 173	99.57 38	99.90 84	99.54 140

thisisatest0530		95.27 381	94.45 392	97.74 321	99.19 227	94.37 352	97.86 228	90.20 467	97.17 296	98.22 300	97.65 384	73.53 454	99.90 80	96.90 249	99.35 305	98.95 330

Anonymous20240529		98.93 94	98.87 101	99.12 123	99.19 227	98.22 134	99.01 70	98.99 300	99.25 74	99.54 78	99.37 98	97.04 203	99.80 228	97.89 166	99.52 271	99.35 239

APD-MVS_3200maxsize		98.84 108	98.61 145	99.53 39	99.19 227	99.27 28	98.49 136	99.33 205	98.64 148	99.03 186	98.98 214	97.89 135	99.85 155	96.54 289	99.42 296	99.46 186

HQP_MVS		97.99 247	97.67 266	98.93 162	99.19 227	97.65 196	97.77 241	99.27 235	98.20 193	97.79 337	97.98 365	94.90 299	99.70 300	94.42 368	99.51 273	99.45 191

plane_prior7					99.19 227	97.87 173

ab-mvs		98.41 189	98.36 187	98.59 226	99.19 227	97.23 224	99.32 26	98.81 331	97.66 238	98.62 259	99.40 95	96.82 219	99.80 228	95.88 323	99.51 273	98.75 365

F-COLMAP		97.30 303	96.68 330	99.14 121	99.19 227	98.39 117	97.27 314	99.30 220	92.93 423	96.62 402	98.00 363	95.73 278	99.68 313	92.62 414	98.46 395	99.35 239

viewdifsd2359ckpt09		98.13 232	97.92 248	98.77 192	99.18 234	97.35 214	97.29 310	99.53 113	95.81 362	98.09 313	98.47 323	96.34 249	99.66 329	97.02 234	99.51 273	99.29 259

SR-MVS		98.71 131	98.43 175	99.57 22	99.18 234	99.35 17	98.36 152	99.29 228	98.29 182	98.88 221	98.85 245	97.53 170	99.87 133	96.14 314	99.31 312	99.48 176

UniMVSNet_NR-MVSNet		98.86 105	98.68 130	99.40 71	99.17 236	98.74 91	97.68 255	99.40 175	99.14 95	99.06 173	98.59 306	96.71 230	99.93 53	98.57 118	99.77 155	99.53 149

LF4IMVS		97.90 251	97.69 265	98.52 245	99.17 236	97.66 195	97.19 324	99.47 140	96.31 342	97.85 333	98.20 348	96.71 230	99.52 387	94.62 360	99.72 185	98.38 401

SMA-MVS		98.40 191	98.03 234	99.51 49	99.16 238	99.21 34	98.05 192	99.22 249	94.16 405	98.98 192	99.10 172	97.52 172	99.79 241	96.45 295	99.64 226	99.53 149
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		98.82 114	98.63 139	99.39 72	99.16 238	98.74 91	97.54 279	99.25 241	98.84 140	99.06 173	98.76 270	96.76 226	99.93 53	98.57 118	99.77 155	99.50 158

NR-MVSNet		98.95 91	98.82 109	99.36 73	99.16 238	98.72 96	99.22 45	99.20 252	99.10 104	99.72 47	98.76 270	96.38 246	99.86 142	98.00 159	99.82 121	99.50 158

MVS_111021_LR		98.30 209	98.12 224	98.83 175	99.16 238	98.03 156	96.09 388	99.30 220	97.58 247	98.10 312	98.24 344	98.25 98	99.34 423	96.69 269	99.65 224	99.12 304

DSMNet-mixed		97.42 294	97.60 274	96.87 382	99.15 242	91.46 420	98.54 124	99.12 274	92.87 425	97.58 350	99.63 39	96.21 253	99.90 80	95.74 332	99.54 264	99.27 263

D2MVS		97.84 264	97.84 255	97.83 310	99.14 243	94.74 341	96.94 334	98.88 315	95.84 361	98.89 217	98.96 219	94.40 315	99.69 304	97.55 195	99.95 38	99.05 310

pmmvs5		97.64 276	97.49 280	98.08 295	99.14 243	95.12 330	96.70 349	99.05 286	93.77 412	98.62 259	98.83 252	93.23 335	99.75 272	98.33 135	99.76 169	99.36 234

SPE-MVS-test		99.13 65	99.09 74	99.26 100	99.13 245	98.97 74	99.31 30	99.88 14	99.44 52	98.16 305	98.51 315	98.64 56	99.93 53	98.91 92	99.85 105	98.88 344

VDD-MVS		98.56 166	98.39 182	99.07 134	99.13 245	98.07 151	98.59 118	97.01 407	99.59 36	99.11 166	99.27 122	94.82 303	99.79 241	98.34 133	99.63 232	99.34 241

save fliter					99.11 247	97.97 162	96.53 359	99.02 294	98.24 185

APD-MVS		98.10 233	97.67 266	99.42 67	99.11 247	98.93 80	97.76 244	99.28 232	94.97 386	98.72 247	98.77 265	97.04 203	99.85 155	93.79 388	99.54 264	99.49 165
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 139	98.71 124	98.62 220	99.10 249	96.37 278	97.23 315	98.87 317	99.20 82	99.19 159	98.99 209	97.30 188	99.85 155	98.77 104	99.79 144	99.65 82

EI-MVSNet		98.40 191	98.51 158	98.04 300	99.10 249	94.73 342	97.20 320	98.87 317	98.97 123	99.06 173	99.02 192	96.00 263	99.80 228	98.58 116	99.82 121	99.60 99

CVMVSNet		96.25 355	97.21 297	93.38 449	99.10 249	80.56 477	97.20 320	98.19 374	96.94 309	99.00 188	99.02 192	89.50 383	99.80 228	96.36 301	99.59 246	99.78 46

EI-MVSNet-Vis-set		98.68 145	98.70 127	98.63 218	99.09 252	96.40 277	97.23 315	98.86 322	99.20 82	99.18 163	98.97 216	97.29 190	99.85 155	98.72 108	99.78 149	99.64 83

HPM-MVS++		98.10 233	97.64 271	99.48 57	99.09 252	99.13 61	97.52 281	98.75 342	97.46 265	96.90 390	97.83 375	96.01 262	99.84 173	95.82 330	99.35 305	99.46 186

DP-MVS Recon		97.33 301	96.92 313	98.57 230	99.09 252	97.99 158	96.79 342	99.35 193	93.18 419	97.71 341	98.07 359	95.00 298	99.31 427	93.97 381	99.13 343	98.42 398

MVS_111021_HR		98.25 218	98.08 229	98.75 196	99.09 252	97.46 208	95.97 392	99.27 235	97.60 246	97.99 323	98.25 343	98.15 113	99.38 418	96.87 252	99.57 255	99.42 203

BP-MVS1		97.40 296	96.97 309	98.71 204	99.07 256	96.81 255	98.34 155	97.18 402	98.58 159	98.17 302	98.61 303	84.01 422	99.94 42	98.97 89	99.78 149	99.37 227

9.14			97.78 257		99.07 256		97.53 280	99.32 207	95.53 371	98.54 275	98.70 283	97.58 163	99.76 264	94.32 373	99.46 286

PAPM_NR		96.82 335	96.32 346	98.30 273	99.07 256	96.69 263	97.48 287	98.76 339	95.81 362	96.61 403	96.47 420	94.12 324	99.17 440	90.82 441	97.78 421	99.06 309

TAMVS		98.24 219	98.05 232	98.80 181	99.07 256	97.18 232	97.88 224	98.81 331	96.66 326	99.17 164	99.21 142	94.81 305	99.77 258	96.96 242	99.88 92	99.44 195

CLD-MVS		97.49 287	97.16 299	98.48 251	99.07 256	97.03 242	94.71 437	99.21 250	94.46 397	98.06 316	97.16 406	97.57 164	99.48 399	94.46 365	99.78 149	98.95 330
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 65	99.10 72	99.24 105	99.06 261	99.15 53	99.36 22	99.88 14	99.36 63	98.21 301	98.46 324	98.68 53	99.93 53	99.03 85	99.85 105	98.64 377

thres100view900		94.19 398	93.67 403	95.75 416	99.06 261	91.35 424	98.03 196	94.24 450	98.33 175	97.40 366	94.98 450	79.84 438	99.62 345	83.05 462	98.08 412	96.29 457

thres600view7		94.45 393	93.83 400	96.29 400	99.06 261	91.53 419	97.99 210	94.24 450	98.34 174	97.44 364	95.01 448	79.84 438	99.67 317	84.33 460	98.23 401	97.66 438

plane_prior1					99.05 264

YYNet1		97.60 278	97.67 266	97.39 358	99.04 265	93.04 397	95.27 423	98.38 366	97.25 285	98.92 212	98.95 223	95.48 287	99.73 284	96.99 238	98.74 376	99.41 206

MDA-MVSNet_test_wron		97.60 278	97.66 269	97.41 357	99.04 265	93.09 393	95.27 423	98.42 363	97.26 284	98.88 221	98.95 223	95.43 288	99.73 284	97.02 234	98.72 378	99.41 206

MIMVSNet		96.62 342	96.25 350	97.71 325	99.04 265	94.66 345	99.16 54	96.92 413	97.23 291	97.87 330	99.10 172	86.11 405	99.65 336	91.65 425	99.21 331	98.82 349

icg_test_0407_2		98.20 224	98.38 184	97.65 331	99.03 268	94.03 365	95.78 406	99.45 148	98.16 199	99.06 173	98.71 276	98.27 94	99.68 313	97.50 201	99.45 288	99.22 280

IMVS_0407		98.39 197	98.64 137	97.66 329	99.03 268	94.03 365	98.10 182	99.45 148	98.16 199	99.06 173	98.71 276	98.27 94	99.71 293	97.50 201	99.45 288	99.22 280

IMVS_0404		98.07 237	98.20 211	97.69 326	99.03 268	94.03 365	96.67 350	99.45 148	98.16 199	98.03 320	98.71 276	96.80 222	99.82 203	97.50 201	99.45 288	99.22 280

IMVS_0403		98.34 201	98.56 151	97.66 329	99.03 268	94.03 365	97.98 211	99.45 148	98.16 199	98.89 217	98.71 276	97.90 132	99.74 277	97.50 201	99.45 288	99.22 280

PatchMatch-RL		97.24 309	96.78 324	98.61 223	99.03 268	97.83 177	96.36 370	99.06 282	93.49 417	97.36 370	97.78 376	95.75 277	99.49 396	93.44 397	98.77 375	98.52 386

viewmambaseed2359dif		98.19 225	98.26 204	97.99 303	99.02 273	95.03 333	96.59 356	99.53 113	96.21 345	99.00 188	98.99 209	97.62 159	99.61 352	97.62 190	99.72 185	99.33 247

GDP-MVS		97.50 284	97.11 303	98.67 210	99.02 273	96.85 253	98.16 172	99.71 47	98.32 177	98.52 278	98.54 310	83.39 426	99.95 26	98.79 100	99.56 258	99.19 290

ZD-MVS					99.01 275	98.84 85		99.07 281	94.10 407	98.05 318	98.12 353	96.36 248	99.86 142	92.70 413	99.19 335

CDPH-MVS		97.26 306	96.66 333	99.07 134	99.00 276	98.15 138	96.03 390	99.01 297	91.21 443	97.79 337	97.85 374	96.89 214	99.69 304	92.75 411	99.38 302	99.39 216

diffmvs		98.22 220	98.24 208	98.17 288	99.00 276	95.44 317	96.38 369	99.58 85	97.79 230	98.53 276	98.50 319	96.76 226	99.74 277	97.95 164	99.64 226	99.34 241
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		98.40 191	98.19 215	99.03 144	99.00 276	97.65 196	96.85 340	98.94 302	98.57 160	98.89 217	98.50 319	95.60 281	99.85 155	97.54 197	99.85 105	99.59 106

plane_prior6					98.99 279	97.70 194						94.90 299

xiu_mvs_v1_base_debu		97.86 258	98.17 217	96.92 379	98.98 280	93.91 375	96.45 363	99.17 264	97.85 225	98.41 287	97.14 408	98.47 72	99.92 64	98.02 156	99.05 349	96.92 450

xiu_mvs_v1_base		97.86 258	98.17 217	96.92 379	98.98 280	93.91 375	96.45 363	99.17 264	97.85 225	98.41 287	97.14 408	98.47 72	99.92 64	98.02 156	99.05 349	96.92 450

xiu_mvs_v1_base_debi		97.86 258	98.17 217	96.92 379	98.98 280	93.91 375	96.45 363	99.17 264	97.85 225	98.41 287	97.14 408	98.47 72	99.92 64	98.02 156	99.05 349	96.92 450

MVP-Stereo		98.08 236	97.92 248	98.57 230	98.96 283	96.79 256	97.90 222	99.18 260	96.41 338	98.46 282	98.95 223	95.93 272	99.60 355	96.51 291	98.98 363	99.31 254
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 191	98.68 130	97.54 346	98.96 283	97.99 158	97.88 224	99.36 187	98.20 193	99.63 66	99.04 189	98.76 45	95.33 473	96.56 285	99.74 174	99.31 254
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				98.91 166	98.94 285	97.76 188		98.76 339	87.58 460	96.75 398	98.10 355	94.80 306	99.78 252	92.73 412	99.00 358	99.20 285

USDC		97.41 295	97.40 284	97.44 355	98.94 285	93.67 385	95.17 426	99.53 113	94.03 409	98.97 196	99.10 172	95.29 290	99.34 423	95.84 329	99.73 177	99.30 257

tfpn200view9		94.03 402	93.44 405	95.78 415	98.93 287	91.44 422	97.60 271	94.29 448	97.94 217	97.10 376	94.31 457	79.67 440	99.62 345	83.05 462	98.08 412	96.29 457

testdata				98.09 292	98.93 287	95.40 319		98.80 333	90.08 451	97.45 363	98.37 333	95.26 291	99.70 300	93.58 393	98.95 366	99.17 297

thres400		94.14 400	93.44 405	96.24 403	98.93 287	91.44 422	97.60 271	94.29 448	97.94 217	97.10 376	94.31 457	79.67 440	99.62 345	83.05 462	98.08 412	97.66 438

TAPA-MVS	96.21 11	96.63 341	95.95 352	98.65 212	98.93 287	98.09 145	96.93 336	99.28 232	83.58 466	98.13 309	97.78 376	96.13 256	99.40 414	93.52 394	99.29 317	98.45 391
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 291	96.93 250	95.54 413	98.78 336	85.72 463	96.86 393	98.11 354	94.43 313			99.10 348	99.23 275

PVSNet_BlendedMVS		97.55 283	97.53 277	97.60 338	98.92 291	93.77 382	96.64 352	99.43 162	94.49 395	97.62 346	99.18 150	96.82 219	99.67 317	94.73 357	99.93 55	99.36 234

PVSNet_Blended		96.88 331	96.68 330	97.47 353	98.92 291	93.77 382	94.71 437	99.43 162	90.98 445	97.62 346	97.36 402	96.82 219	99.67 317	94.73 357	99.56 258	98.98 324

MSDG		97.71 271	97.52 278	98.28 275	98.91 294	96.82 254	94.42 447	99.37 183	97.65 239	98.37 292	98.29 342	97.40 182	99.33 425	94.09 379	99.22 328	98.68 375

Anonymous202405211		97.90 251	97.50 279	99.08 132	98.90 295	98.25 128	98.53 125	96.16 425	98.87 135	99.11 166	98.86 242	90.40 375	99.78 252	97.36 210	99.31 312	99.19 290

原ACMM1				98.35 268	98.90 295	96.25 282		98.83 330	92.48 429	96.07 420	98.10 355	95.39 289	99.71 293	92.61 415	98.99 360	99.08 306

GBi-Net		98.65 150	98.47 169	99.17 114	98.90 295	98.24 129	99.20 48	99.44 156	98.59 156	98.95 202	99.55 57	94.14 321	99.86 142	97.77 178	99.69 204	99.41 206

test1		98.65 150	98.47 169	99.17 114	98.90 295	98.24 129	99.20 48	99.44 156	98.59 156	98.95 202	99.55 57	94.14 321	99.86 142	97.77 178	99.69 204	99.41 206

FMVSNet2		98.49 182	98.40 179	98.75 196	98.90 295	97.14 237	98.61 116	99.13 273	98.59 156	99.19 159	99.28 120	94.14 321	99.82 203	97.97 162	99.80 138	99.29 259

OMC-MVS		97.88 255	97.49 280	99.04 143	98.89 300	98.63 98	96.94 334	99.25 241	95.02 384	98.53 276	98.51 315	97.27 191	99.47 402	93.50 396	99.51 273	99.01 318

VortexMVS		97.98 248	98.31 196	97.02 373	98.88 301	91.45 421	98.03 196	99.47 140	98.65 147	99.55 76	99.47 77	91.49 364	99.81 220	99.32 60	99.91 77	99.80 41

MVSFormer		98.26 215	98.43 175	97.77 315	98.88 301	93.89 378	99.39 20	99.56 100	99.11 97	98.16 305	98.13 351	93.81 329	99.97 7	99.26 65	99.57 255	99.43 199

lupinMVS		97.06 321	96.86 317	97.65 331	98.88 301	93.89 378	95.48 417	97.97 380	93.53 415	98.16 305	97.58 388	93.81 329	99.91 73	96.77 260	99.57 255	99.17 297

dmvs_re		95.98 363	95.39 373	97.74 321	98.86 304	97.45 209	98.37 151	95.69 437	97.95 215	96.56 404	95.95 429	90.70 372	97.68 467	88.32 450	96.13 454	98.11 413

DELS-MVS		98.27 213	98.20 211	98.48 251	98.86 304	96.70 262	95.60 412	99.20 252	97.73 233	98.45 283	98.71 276	97.50 174	99.82 203	98.21 141	99.59 246	98.93 335
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		97.89 253	97.98 239	97.60 338	98.86 304	94.35 353	96.21 379	99.44 156	97.45 267	99.06 173	98.88 239	97.99 126	99.28 433	94.38 372	99.58 251	99.18 293

LCM-MVSNet-Re		98.64 152	98.48 167	99.11 125	98.85 307	98.51 111	98.49 136	99.83 25	98.37 171	99.69 55	99.46 79	98.21 105	99.92 64	94.13 378	99.30 315	98.91 339

pmmvs4		97.58 281	97.28 292	98.51 246	98.84 308	96.93 250	95.40 421	98.52 358	93.60 414	98.61 261	98.65 294	95.10 295	99.60 355	96.97 241	99.79 144	98.99 323

NP-MVS					98.84 308	97.39 213					96.84 411

sss		97.21 311	96.93 311	98.06 297	98.83 310	95.22 326	96.75 346	98.48 360	94.49 395	97.27 372	97.90 371	92.77 347	99.80 228	96.57 281	99.32 310	99.16 300

PVSNet	93.40 17	95.67 372	95.70 358	95.57 420	98.83 310	88.57 447	92.50 464	97.72 385	92.69 427	96.49 412	96.44 421	93.72 332	99.43 410	93.61 391	99.28 318	98.71 368

MVE	83.40 22	92.50 425	91.92 427	94.25 436	98.83 310	91.64 418	92.71 463	83.52 476	95.92 359	86.46 474	95.46 442	95.20 292	95.40 472	80.51 467	98.64 387	95.73 465
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 406	93.91 398	93.39 448	98.82 313	81.72 475	97.76 244	95.28 439	98.60 155	96.54 405	96.66 415	65.85 470	99.62 345	96.65 274	98.99 360	98.82 349

ambc				98.24 280	98.82 313	95.97 293	98.62 115	99.00 299		99.27 141	99.21 142	96.99 208	99.50 393	96.55 288	99.50 281	99.26 269

旧先验1					98.82 313	97.45 209		98.76 339			98.34 337	95.50 286			99.01 357	99.23 275

test_vis1_rt		97.75 268	97.72 263	97.83 310	98.81 316	96.35 279	97.30 309	99.69 54	94.61 393	97.87 330	98.05 360	96.26 252	98.32 461	98.74 106	98.18 404	98.82 349

WTY-MVS		96.67 339	96.27 349	97.87 308	98.81 316	94.61 347	96.77 344	97.92 382	94.94 387	97.12 375	97.74 379	91.11 368	99.82 203	93.89 384	98.15 408	99.18 293

3Dnovator+	97.89 3	98.69 139	98.51 158	99.24 105	98.81 316	98.40 116	99.02 69	99.19 256	98.99 120	98.07 315	99.28 120	97.11 201	99.84 173	96.84 255	99.32 310	99.47 184

QAPM		97.31 302	96.81 323	98.82 177	98.80 319	97.49 204	99.06 65	99.19 256	90.22 449	97.69 343	99.16 156	96.91 213	99.90 80	90.89 440	99.41 297	99.07 308

VNet		98.42 188	98.30 197	98.79 184	98.79 320	97.29 220	98.23 163	98.66 349	99.31 68	98.85 226	98.80 259	94.80 306	99.78 252	98.13 146	99.13 343	99.31 254

DPM-MVS		96.32 351	95.59 364	98.51 246	98.76 321	97.21 228	94.54 446	98.26 369	91.94 434	96.37 413	97.25 404	93.06 341	99.43 410	91.42 430	98.74 376	98.89 341

3Dnovator	98.27 2	98.81 116	98.73 118	99.05 141	98.76 321	97.81 185	99.25 43	99.30 220	98.57 160	98.55 273	99.33 110	97.95 129	99.90 80	97.16 222	99.67 215	99.44 195

PLC	94.65 16	96.51 344	95.73 357	98.85 173	98.75 323	97.91 170	96.42 367	99.06 282	90.94 446	95.59 426	97.38 400	94.41 314	99.59 359	90.93 438	98.04 417	99.05 310
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 333	96.75 326	97.08 370	98.74 324	93.33 391	96.71 348	98.26 369	96.72 323	98.44 284	97.37 401	95.20 292	99.47 402	91.89 420	97.43 431	98.44 394

hse-mvs2		97.46 289	97.07 304	98.64 214	98.73 325	97.33 216	97.45 292	97.64 392	99.11 97	98.58 267	97.98 365	88.65 390	99.79 241	98.11 147	97.39 433	98.81 354

CDS-MVSNet		97.69 272	97.35 289	98.69 207	98.73 325	97.02 243	96.92 338	98.75 342	95.89 360	98.59 265	98.67 289	92.08 358	99.74 277	96.72 266	99.81 127	99.32 250
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SD_0403		96.28 353	95.83 354	97.64 334	98.72 327	94.30 354	98.87 88	98.77 337	97.80 228	96.53 406	98.02 362	97.34 186	99.47 402	76.93 471	99.48 284	99.16 300

EIA-MVS		98.00 244	97.74 260	98.80 181	98.72 327	98.09 145	98.05 192	99.60 77	97.39 271	96.63 401	95.55 437	97.68 151	99.80 228	96.73 265	99.27 319	98.52 386

LFMVS		97.20 312	96.72 327	98.64 214	98.72 327	96.95 248	98.93 81	94.14 452	99.74 13	98.78 238	99.01 203	84.45 417	99.73 284	97.44 206	99.27 319	99.25 270

new_pmnet		96.99 328	96.76 325	97.67 327	98.72 327	94.89 336	95.95 396	98.20 372	92.62 428	98.55 273	98.54 310	94.88 302	99.52 387	93.96 382	99.44 295	98.59 383

Fast-Effi-MVS+		97.67 274	97.38 286	98.57 230	98.71 331	97.43 211	97.23 315	99.45 148	94.82 390	96.13 417	96.51 417	98.52 70	99.91 73	96.19 310	98.83 372	98.37 403

TEST9					98.71 331	98.08 149	95.96 394	99.03 291	91.40 440	95.85 423	97.53 390	96.52 239	99.76 264

train_agg		97.10 318	96.45 343	99.07 134	98.71 331	98.08 149	95.96 394	99.03 291	91.64 435	95.85 423	97.53 390	96.47 241	99.76 264	93.67 390	99.16 338	99.36 234

TSAR-MVS + GP.		98.18 227	97.98 239	98.77 192	98.71 331	97.88 172	96.32 373	98.66 349	96.33 340	99.23 153	98.51 315	97.48 178	99.40 414	97.16 222	99.46 286	99.02 317

FA-MVS(test-final)		96.99 328	96.82 321	97.50 350	98.70 335	94.78 339	99.34 23	96.99 408	95.07 383	98.48 281	99.33 110	88.41 393	99.65 336	96.13 316	98.92 369	98.07 416

AUN-MVS		96.24 357	95.45 369	98.60 225	98.70 335	97.22 226	97.38 299	97.65 390	95.95 358	95.53 433	97.96 369	82.11 434	99.79 241	96.31 303	97.44 430	98.80 359

our_test_3		97.39 297	97.73 262	96.34 398	98.70 335	89.78 443	94.61 443	98.97 301	96.50 331	99.04 183	98.85 245	95.98 268	99.84 173	97.26 216	99.67 215	99.41 206

ppachtmachnet_test		97.50 284	97.74 260	96.78 388	98.70 335	91.23 430	94.55 445	99.05 286	96.36 339	99.21 157	98.79 261	96.39 244	99.78 252	96.74 263	99.82 121	99.34 241

PCF-MVS	92.86 18	94.36 394	93.00 412	98.42 258	98.70 335	97.56 201	93.16 462	99.11 276	79.59 470	97.55 353	97.43 397	92.19 355	99.73 284	79.85 468	99.45 288	97.97 422
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 250	98.02 235	97.58 340	98.69 340	94.10 361	98.13 175	98.90 311	97.95 215	97.32 371	99.58 47	95.95 271	98.75 456	96.41 297	99.22 328	99.87 21

ETV-MVS		98.03 240	97.86 254	98.56 235	98.69 340	98.07 151	97.51 283	99.50 122	98.10 206	97.50 358	95.51 438	98.41 78	99.88 114	96.27 306	99.24 324	97.71 437

test_prior				98.95 159	98.69 340	97.95 166		99.03 291					99.59 359			99.30 257

mvsmamba		97.57 282	97.26 293	98.51 246	98.69 340	96.73 261	98.74 97	97.25 401	97.03 305	97.88 329	99.23 140	90.95 369	99.87 133	96.61 277	99.00 358	98.91 339

agg_prior					98.68 344	97.99 158		99.01 297		95.59 426			99.77 258

test_8					98.67 345	98.01 157	95.91 400	99.02 294	91.64 435	95.79 425	97.50 393	96.47 241	99.76 264

HQP-NCC					98.67 345		96.29 375		96.05 351	95.55 429

ACMP_Plane					98.67 345		96.29 375		96.05 351	95.55 429

CNVR-MVS		98.17 229	97.87 253	99.07 134	98.67 345	98.24 129	97.01 330	98.93 305	97.25 285	97.62 346	98.34 337	97.27 191	99.57 368	96.42 296	99.33 308	99.39 216

HQP-MVS		97.00 327	96.49 342	98.55 237	98.67 345	96.79 256	96.29 375	99.04 289	96.05 351	95.55 429	96.84 411	93.84 327	99.54 381	92.82 408	99.26 322	99.32 250

MM		98.22 220	97.99 238	98.91 166	98.66 350	96.97 245	97.89 223	94.44 446	99.54 40	98.95 202	99.14 163	93.50 333	99.92 64	99.80 17	99.96 28	99.85 29

test_fmvs1		97.72 270	97.94 245	97.07 372	98.66 350	92.39 408	97.68 255	99.81 31	95.20 382	99.54 78	99.44 84	91.56 363	99.41 413	99.78 21	99.77 155	99.40 215

balanced_conf03		98.63 154	98.72 120	98.38 263	98.66 350	96.68 264	98.90 83	99.42 168	98.99 120	98.97 196	99.19 146	95.81 276	99.85 155	98.77 104	99.77 155	98.60 380

thres200		93.72 408	93.14 410	95.46 424	98.66 350	91.29 426	96.61 354	94.63 445	97.39 271	96.83 394	93.71 460	79.88 437	99.56 371	82.40 465	98.13 409	95.54 466

wuyk23d		96.06 359	97.62 273	91.38 453	98.65 354	98.57 105	98.85 92	96.95 411	96.86 316	99.90 14	99.16 156	99.18 19	98.40 460	89.23 448	99.77 155	77.18 473

NCCC		97.86 258	97.47 283	99.05 141	98.61 355	98.07 151	96.98 332	98.90 311	97.63 240	97.04 380	97.93 370	95.99 267	99.66 329	95.31 345	98.82 374	99.43 199

DeepC-MVS_fast	96.85 6	98.30 209	98.15 221	98.75 196	98.61 355	97.23 224	97.76 244	99.09 279	97.31 279	98.75 244	98.66 292	97.56 165	99.64 339	96.10 317	99.55 262	99.39 216
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 410	92.09 421	97.75 319	98.60 357	94.40 351	97.32 307	95.26 440	97.56 250	96.79 397	95.50 439	53.57 478	99.77 258	95.26 346	98.97 364	99.08 306

thisisatest0515		94.12 401	93.16 409	96.97 377	98.60 357	92.90 398	93.77 458	90.61 465	94.10 407	96.91 387	95.87 432	74.99 452	99.80 228	94.52 363	99.12 346	98.20 409

GA-MVS		95.86 366	95.32 376	97.49 351	98.60 357	94.15 360	93.83 457	97.93 381	95.49 372	96.68 399	97.42 398	83.21 427	99.30 429	96.22 308	98.55 393	99.01 318

dmvs_testset		92.94 420	92.21 420	95.13 428	98.59 360	90.99 433	97.65 261	92.09 461	96.95 308	94.00 453	93.55 461	92.34 353	96.97 470	72.20 472	92.52 468	97.43 445

OPU-MVS				98.82 177	98.59 360	98.30 125	98.10 182				98.52 314	98.18 107	98.75 456	94.62 360	99.48 284	99.41 206

MSLP-MVS++		98.02 241	98.14 223	97.64 334	98.58 362	95.19 327	97.48 287	99.23 248	97.47 260	97.90 327	98.62 301	97.04 203	98.81 454	97.55 195	99.41 297	98.94 334

test12				98.93 162	98.58 362	97.83 177		98.66 349		96.53 406		95.51 285	99.69 304		99.13 343	99.27 263

CL-MVSNet_self_test		97.44 292	97.22 296	98.08 295	98.57 364	95.78 301	94.30 450	98.79 334	96.58 329	98.60 263	98.19 349	94.74 309	99.64 339	96.41 297	98.84 371	98.82 349

PS-MVSNAJ		97.08 320	97.39 285	96.16 409	98.56 365	92.46 406	95.24 425	98.85 325	97.25 285	97.49 359	95.99 428	98.07 117	99.90 80	96.37 299	98.67 386	96.12 462

CNLPA		97.17 315	96.71 328	98.55 237	98.56 365	98.05 155	96.33 372	98.93 305	96.91 313	97.06 379	97.39 399	94.38 316	99.45 407	91.66 424	99.18 337	98.14 412

xiu_mvs_v2_base		97.16 316	97.49 280	96.17 407	98.54 367	92.46 406	95.45 418	98.84 326	97.25 285	97.48 360	96.49 418	98.31 89	99.90 80	96.34 302	98.68 385	96.15 461

alignmvs		97.35 299	96.88 316	98.78 187	98.54 367	98.09 145	97.71 251	97.69 387	99.20 82	97.59 349	95.90 431	88.12 395	99.55 375	98.18 143	98.96 365	98.70 371

FE-MVS		95.66 373	94.95 386	97.77 315	98.53 369	95.28 323	99.40 19	96.09 428	93.11 421	97.96 324	99.26 128	79.10 444	99.77 258	92.40 417	98.71 380	98.27 407

Effi-MVS+		98.02 241	97.82 256	98.62 220	98.53 369	97.19 230	97.33 306	99.68 59	97.30 280	96.68 399	97.46 396	98.56 68	99.80 228	96.63 275	98.20 403	98.86 346

baseline1		95.96 364	95.44 370	97.52 348	98.51 371	93.99 372	98.39 149	96.09 428	98.21 189	98.40 291	97.76 378	86.88 397	99.63 342	95.42 343	89.27 471	98.95 330

MVS_Test		98.18 227	98.36 187	97.67 327	98.48 372	94.73 342	98.18 168	99.02 294	97.69 236	98.04 319	99.11 169	97.22 195	99.56 371	98.57 118	98.90 370	98.71 368

MGCFI-Net		98.34 201	98.28 200	98.51 246	98.47 373	97.59 200	98.96 77	99.48 131	99.18 90	97.40 366	95.50 439	98.66 54	99.50 393	98.18 143	98.71 380	98.44 394

BH-RMVSNet		96.83 333	96.58 338	97.58 340	98.47 373	94.05 362	96.67 350	97.36 396	96.70 325	97.87 330	97.98 365	95.14 294	99.44 409	90.47 443	98.58 392	99.25 270

sasdasda		98.34 201	98.26 204	98.58 227	98.46 375	97.82 182	98.96 77	99.46 144	99.19 87	97.46 361	95.46 442	98.59 62	99.46 405	98.08 150	98.71 380	98.46 388

canonicalmvs		98.34 201	98.26 204	98.58 227	98.46 375	97.82 182	98.96 77	99.46 144	99.19 87	97.46 361	95.46 442	98.59 62	99.46 405	98.08 150	98.71 380	98.46 388

MVS-HIRNet		94.32 395	95.62 361	90.42 454	98.46 375	75.36 478	96.29 375	89.13 469	95.25 379	95.38 435	99.75 16	92.88 344	99.19 439	94.07 380	99.39 299	96.72 455

PHI-MVS		98.29 212	97.95 243	99.34 82	98.44 378	99.16 49	98.12 179	99.38 179	96.01 355	98.06 316	98.43 327	97.80 144	99.67 317	95.69 335	99.58 251	99.20 285

DVP-MVS++		98.90 98	98.70 127	99.51 49	98.43 379	99.15 53	99.43 15	99.32 207	98.17 196	99.26 145	99.02 192	98.18 107	99.88 114	97.07 231	99.45 288	99.49 165

MSC_two_6792asdad				99.32 90	98.43 379	98.37 120		98.86 322					99.89 96	97.14 225	99.60 242	99.71 62

No_MVS				99.32 90	98.43 379	98.37 120		98.86 322					99.89 96	97.14 225	99.60 242	99.71 62

Fast-Effi-MVS+-dtu		98.27 213	98.09 226	98.81 179	98.43 379	98.11 142	97.61 270	99.50 122	98.64 148	97.39 368	97.52 392	98.12 115	99.95 26	96.90 249	98.71 380	98.38 401

OpenMVS_ROB	95.38 14	95.84 368	95.18 381	97.81 312	98.41 383	97.15 236	97.37 303	98.62 353	83.86 465	98.65 255	98.37 333	94.29 319	99.68 313	88.41 449	98.62 390	96.60 456

DeepPCF-MVS	96.93 5	98.32 206	98.01 236	99.23 107	98.39 384	98.97 74	95.03 430	99.18 260	96.88 314	99.33 127	98.78 263	98.16 111	99.28 433	96.74 263	99.62 235	99.44 195

Patchmatch-test		96.55 343	96.34 345	97.17 367	98.35 385	93.06 394	98.40 148	97.79 383	97.33 276	98.41 287	98.67 289	83.68 425	99.69 304	95.16 348	99.31 312	98.77 362

AdaColmap		97.14 317	96.71 328	98.46 253	98.34 386	97.80 186	96.95 333	98.93 305	95.58 369	96.92 385	97.66 383	95.87 274	99.53 383	90.97 437	99.14 341	98.04 417

OpenMVS	96.65 7	97.09 319	96.68 330	98.32 270	98.32 387	97.16 235	98.86 91	99.37 183	89.48 453	96.29 415	99.15 160	96.56 237	99.90 80	92.90 405	99.20 332	97.89 425

MG-MVS		96.77 336	96.61 335	97.26 363	98.31 388	93.06 394	95.93 397	98.12 377	96.45 337	97.92 325	98.73 273	93.77 331	99.39 416	91.19 435	99.04 352	99.33 247

test_yl		96.69 337	96.29 347	97.90 305	98.28 389	95.24 324	97.29 310	97.36 396	98.21 189	98.17 302	97.86 372	86.27 401	99.55 375	94.87 354	98.32 397	98.89 341

DCV-MVSNet		96.69 337	96.29 347	97.90 305	98.28 389	95.24 324	97.29 310	97.36 396	98.21 189	98.17 302	97.86 372	86.27 401	99.55 375	94.87 354	98.32 397	98.89 341

CHOSEN 280x420		95.51 378	95.47 367	95.65 419	98.25 391	88.27 450	93.25 461	98.88 315	93.53 415	94.65 444	97.15 407	86.17 403	99.93 53	97.41 208	99.93 55	98.73 367

SCA		96.41 350	96.66 333	95.67 417	98.24 392	88.35 449	95.85 403	96.88 414	96.11 349	97.67 344	98.67 289	93.10 339	99.85 155	94.16 374	99.22 328	98.81 354

DeepMVS_CX				93.44 447	98.24 392	94.21 357		94.34 447	64.28 473	91.34 467	94.87 454	89.45 384	92.77 474	77.54 470	93.14 467	93.35 469

MS-PatchMatch		97.68 273	97.75 259	97.45 354	98.23 394	93.78 381	97.29 310	98.84 326	96.10 350	98.64 256	98.65 294	96.04 260	99.36 419	96.84 255	99.14 341	99.20 285

BH-w/o		95.13 384	94.89 388	95.86 412	98.20 395	91.31 425	95.65 410	97.37 395	93.64 413	96.52 408	95.70 435	93.04 342	99.02 445	88.10 451	95.82 457	97.24 448

mvs_anonymous		97.83 266	98.16 220	96.87 382	98.18 396	91.89 415	97.31 308	98.90 311	97.37 273	98.83 229	99.46 79	96.28 251	99.79 241	98.90 93	98.16 407	98.95 330

miper_lstm_enhance		97.18 314	97.16 299	97.25 364	98.16 397	92.85 399	95.15 428	99.31 212	97.25 285	98.74 246	98.78 263	90.07 376	99.78 252	97.19 220	99.80 138	99.11 305

RRT-MVS		97.88 255	97.98 239	97.61 337	98.15 398	93.77 382	98.97 76	99.64 69	99.16 92	98.69 249	99.42 88	91.60 361	99.89 96	97.63 189	98.52 394	99.16 300

ET-MVSNet_ETH3D		94.30 397	93.21 408	97.58 340	98.14 399	94.47 350	94.78 436	93.24 457	94.72 391	89.56 469	95.87 432	78.57 447	99.81 220	96.91 244	97.11 442	98.46 388

ADS-MVSNet2		95.43 379	94.98 384	96.76 389	98.14 399	91.74 416	97.92 219	97.76 384	90.23 447	96.51 409	98.91 229	85.61 408	99.85 155	92.88 406	96.90 443	98.69 372

ADS-MVSNet		95.24 382	94.93 387	96.18 406	98.14 399	90.10 442	97.92 219	97.32 399	90.23 447	96.51 409	98.91 229	85.61 408	99.74 277	92.88 406	96.90 443	98.69 372

c3_l		97.36 298	97.37 287	97.31 359	98.09 402	93.25 392	95.01 431	99.16 267	97.05 302	98.77 241	98.72 275	92.88 344	99.64 339	96.93 243	99.76 169	99.05 310

FMVSNet3		97.50 284	97.24 295	98.29 274	98.08 403	95.83 298	97.86 228	98.91 310	97.89 222	98.95 202	98.95 223	87.06 396	99.81 220	97.77 178	99.69 204	99.23 275

PAPM		91.88 434	90.34 437	96.51 393	98.06 404	92.56 404	92.44 465	97.17 403	86.35 461	90.38 468	96.01 427	86.61 399	99.21 438	70.65 474	95.43 459	97.75 434

Effi-MVS+-dtu		98.26 215	97.90 251	99.35 79	98.02 405	99.49 6	98.02 199	99.16 267	98.29 182	97.64 345	97.99 364	96.44 243	99.95 26	96.66 273	98.93 368	98.60 380

eth_miper_zixun_eth		97.23 310	97.25 294	97.17 367	98.00 406	92.77 401	94.71 437	99.18 260	97.27 283	98.56 271	98.74 272	91.89 359	99.69 304	97.06 233	99.81 127	99.05 310

HY-MVS	95.94 13	95.90 365	95.35 375	97.55 345	97.95 407	94.79 338	98.81 96	96.94 412	92.28 432	95.17 437	98.57 308	89.90 378	99.75 272	91.20 434	97.33 438	98.10 414

UGNet		98.53 175	98.45 172	98.79 184	97.94 408	96.96 247	99.08 61	98.54 356	99.10 104	96.82 395	99.47 77	96.55 238	99.84 173	98.56 121	99.94 49	99.55 134
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		96.47 348	95.70 358	98.79 184	97.92 409	99.12 63	98.28 157	98.60 354	92.16 433	95.54 432	96.17 425	94.77 308	99.52 387	89.62 446	98.23 401	97.72 436
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		96.86 332	96.55 339	97.79 313	97.91 410	94.21 357	97.56 276	98.87 317	97.49 259	99.06 173	99.05 187	80.72 435	99.80 228	98.44 127	99.82 121	99.37 227

API-MVS		97.04 323	96.91 315	97.42 356	97.88 411	98.23 133	98.18 168	98.50 359	97.57 248	97.39 368	96.75 413	96.77 224	99.15 442	90.16 444	99.02 356	94.88 467

myMVS_eth3d28		92.92 421	92.31 417	94.77 431	97.84 412	87.59 454	96.19 381	96.11 427	97.08 301	94.27 447	93.49 463	66.07 469	98.78 455	91.78 422	97.93 420	97.92 424

miper_ehance_all_eth		97.06 321	97.03 306	97.16 369	97.83 413	93.06 394	94.66 440	99.09 279	95.99 356	98.69 249	98.45 325	92.73 349	99.61 352	96.79 257	99.03 353	98.82 349

cl____		97.02 324	96.83 320	97.58 340	97.82 414	94.04 364	94.66 440	99.16 267	97.04 303	98.63 257	98.71 276	88.68 389	99.69 304	97.00 236	99.81 127	99.00 322

DIV-MVS_self_test		97.02 324	96.84 319	97.58 340	97.82 414	94.03 365	94.66 440	99.16 267	97.04 303	98.63 257	98.71 276	88.69 387	99.69 304	97.00 236	99.81 127	99.01 318

CANet		97.87 257	97.76 258	98.19 287	97.75 416	95.51 309	96.76 345	99.05 286	97.74 232	96.93 384	98.21 347	95.59 282	99.89 96	97.86 173	99.93 55	99.19 290

UBG		93.25 415	92.32 416	96.04 411	97.72 417	90.16 441	95.92 399	95.91 432	96.03 354	93.95 455	93.04 466	69.60 459	99.52 387	90.72 442	97.98 418	98.45 391

mvsany_test1		97.60 278	97.54 276	97.77 315	97.72 417	95.35 320	95.36 422	97.13 405	94.13 406	99.71 49	99.33 110	97.93 130	99.30 429	97.60 193	98.94 367	98.67 376

PVSNet_0	89.98 21	91.15 435	90.30 438	93.70 444	97.72 417	84.34 468	90.24 468	97.42 394	90.20 450	93.79 456	93.09 465	90.90 371	98.89 453	86.57 457	72.76 474	97.87 427

CR-MVSNet		96.28 353	95.95 352	97.28 361	97.71 420	94.22 355	98.11 180	98.92 308	92.31 431	96.91 387	99.37 98	85.44 411	99.81 220	97.39 209	97.36 436	97.81 430

RPMNet		97.02 324	96.93 311	97.30 360	97.71 420	94.22 355	98.11 180	99.30 220	99.37 60	96.91 387	99.34 107	86.72 398	99.87 133	97.53 198	97.36 436	97.81 430

ETVMVS		92.60 424	91.08 433	97.18 365	97.70 422	93.65 387	96.54 357	95.70 435	96.51 330	94.68 443	92.39 469	61.80 475	99.50 393	86.97 454	97.41 432	98.40 399

pmmvs3		95.03 386	94.40 393	96.93 378	97.70 422	92.53 405	95.08 429	97.71 386	88.57 457	97.71 341	98.08 358	79.39 442	99.82 203	96.19 310	99.11 347	98.43 396

baseline2		93.73 407	92.83 413	96.42 396	97.70 422	91.28 427	96.84 341	89.77 468	93.96 411	92.44 463	95.93 430	79.14 443	99.77 258	92.94 404	96.76 447	98.21 408

WBMVS		95.18 383	94.78 389	96.37 397	97.68 425	89.74 444	95.80 405	98.73 345	97.54 254	98.30 293	98.44 326	70.06 457	99.82 203	96.62 276	99.87 96	99.54 140

tpm		94.67 391	94.34 395	95.66 418	97.68 425	88.42 448	97.88 224	94.90 442	94.46 397	96.03 422	98.56 309	78.66 445	99.79 241	95.88 323	95.01 461	98.78 361

CANet_DTU		97.26 306	97.06 305	97.84 309	97.57 427	94.65 346	96.19 381	98.79 334	97.23 291	95.14 438	98.24 344	93.22 336	99.84 173	97.34 211	99.84 110	99.04 314

testing11		93.08 418	92.02 423	96.26 402	97.56 428	90.83 436	96.32 373	95.70 435	96.47 334	92.66 462	93.73 459	64.36 473	99.59 359	93.77 389	97.57 425	98.37 403

tpm2		93.09 417	92.58 415	94.62 433	97.56 428	86.53 457	97.66 259	95.79 434	86.15 462	94.07 452	98.23 346	75.95 450	99.53 383	90.91 439	96.86 446	97.81 430

testing91		93.32 413	92.27 418	96.47 395	97.54 430	91.25 428	96.17 385	96.76 416	97.18 295	93.65 458	93.50 462	65.11 472	99.63 342	93.04 403	97.45 429	98.53 385

TR-MVS		95.55 376	95.12 382	96.86 385	97.54 430	93.94 373	96.49 362	96.53 421	94.36 402	97.03 382	96.61 416	94.26 320	99.16 441	86.91 456	96.31 451	97.47 444

testing99		93.04 419	91.98 426	96.23 404	97.53 432	90.70 438	96.35 371	95.94 431	96.87 315	93.41 459	93.43 464	63.84 474	99.59 359	93.24 401	97.19 439	98.40 399

1314		95.74 370	95.60 362	96.17 407	97.53 432	92.75 402	98.07 189	98.31 368	91.22 442	94.25 448	96.68 414	95.53 283	99.03 444	91.64 426	97.18 440	96.74 454

CostFormer		93.97 403	93.78 401	94.51 434	97.53 432	85.83 460	97.98 211	95.96 430	89.29 455	94.99 440	98.63 299	78.63 446	99.62 345	94.54 362	96.50 448	98.09 415

FMVSNet5		96.01 361	95.20 380	98.41 259	97.53 432	96.10 284	98.74 97	99.50 122	97.22 294	98.03 320	99.04 189	69.80 458	99.88 114	97.27 215	99.71 194	99.25 270

PMMVS		96.51 344	95.98 351	98.09 292	97.53 432	95.84 297	94.92 433	98.84 326	91.58 437	96.05 421	95.58 436	95.68 279	99.66 329	95.59 339	98.09 411	98.76 364

reproduce_monomvs		95.00 388	95.25 377	94.22 437	97.51 437	83.34 469	97.86 228	98.44 361	98.51 165	99.29 137	99.30 116	67.68 463	99.56 371	98.89 95	99.81 127	99.77 49

PAPR		95.29 380	94.47 391	97.75 319	97.50 438	95.14 329	94.89 434	98.71 347	91.39 441	95.35 436	95.48 441	94.57 311	99.14 443	84.95 459	97.37 434	98.97 327

testing222		91.96 432	90.37 436	96.72 390	97.47 439	92.59 403	96.11 387	94.76 443	96.83 317	92.90 461	92.87 467	57.92 476	99.55 375	86.93 455	97.52 426	98.00 421

PatchT		96.65 340	96.35 344	97.54 346	97.40 440	95.32 322	97.98 211	96.64 418	99.33 65	96.89 391	99.42 88	84.32 419	99.81 220	97.69 188	97.49 427	97.48 443

tpm cat1		93.29 414	93.13 411	93.75 443	97.39 441	84.74 463	97.39 297	97.65 390	83.39 467	94.16 449	98.41 328	82.86 430	99.39 416	91.56 428	95.35 460	97.14 449

PatchmatchNet		95.58 375	95.67 360	95.30 427	97.34 442	87.32 455	97.65 261	96.65 417	95.30 378	97.07 378	98.69 285	84.77 414	99.75 272	94.97 352	98.64 387	98.83 348
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 299	96.97 309	98.50 250	97.31 443	96.47 275	98.18 168	98.92 308	98.95 127	98.78 238	99.37 98	85.44 411	99.85 155	95.96 321	99.83 117	99.17 297

LS3D		98.63 154	98.38 184	99.36 73	97.25 444	99.38 13	99.12 60	99.32 207	99.21 80	98.44 284	98.88 239	97.31 187	99.80 228	96.58 279	99.34 307	98.92 336

IB-MVS	91.63 19	92.24 430	90.90 434	96.27 401	97.22 445	91.24 429	94.36 449	93.33 456	92.37 430	92.24 465	94.58 456	66.20 468	99.89 96	93.16 402	94.63 463	97.66 438
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		92.38 427	91.76 430	94.21 438	97.16 446	84.65 464	95.42 420	88.45 470	95.96 357	96.17 416	95.84 434	66.36 466	99.71 293	91.87 421	98.64 387	98.28 406

tpmrst		95.07 385	95.46 368	93.91 441	97.11 447	84.36 467	97.62 266	96.96 410	94.98 385	96.35 414	98.80 259	85.46 410	99.59 359	95.60 338	96.23 452	97.79 433

Syy-MVS		96.04 360	95.56 366	97.49 351	97.10 448	94.48 349	96.18 383	96.58 419	95.65 366	94.77 441	92.29 470	91.27 367	99.36 419	98.17 145	98.05 415	98.63 378

myMVS_eth3d		91.92 433	90.45 435	96.30 399	97.10 448	90.90 434	96.18 383	96.58 419	95.65 366	94.77 441	92.29 470	53.88 477	99.36 419	89.59 447	98.05 415	98.63 378

MDTV_nov1_ep13			95.22 379		97.06 450	83.20 470	97.74 248	96.16 425	94.37 401	96.99 383	98.83 252	83.95 423	99.53 383	93.90 383	97.95 419

MVS		93.19 416	92.09 421	96.50 394	96.91 451	94.03 365	98.07 189	98.06 379	68.01 472	94.56 446	96.48 419	95.96 270	99.30 429	83.84 461	96.89 445	96.17 459

E-PMN		94.17 399	94.37 394	93.58 445	96.86 452	85.71 461	90.11 470	97.07 406	98.17 196	97.82 336	97.19 405	84.62 416	98.94 449	89.77 445	97.68 424	96.09 463

JIA-IIPM		95.52 377	95.03 383	97.00 374	96.85 453	94.03 365	96.93 336	95.82 433	99.20 82	94.63 445	99.71 22	83.09 428	99.60 355	94.42 368	94.64 462	97.36 447

EMVS		93.83 405	94.02 397	93.23 450	96.83 454	84.96 462	89.77 471	96.32 423	97.92 219	97.43 365	96.36 424	86.17 403	98.93 450	87.68 452	97.73 423	95.81 464

cl22		95.79 369	95.39 373	96.98 376	96.77 455	92.79 400	94.40 448	98.53 357	94.59 394	97.89 328	98.17 350	82.82 431	99.24 435	96.37 299	99.03 353	98.92 336

WB-MVSnew		95.73 371	95.57 365	96.23 404	96.70 456	90.70 438	96.07 389	93.86 453	95.60 368	97.04 380	95.45 445	96.00 263	99.55 375	91.04 436	98.31 399	98.43 396

dp		93.47 411	93.59 404	93.13 451	96.64 457	81.62 476	97.66 259	96.42 422	92.80 426	96.11 418	98.64 297	78.55 448	99.59 359	93.31 399	92.18 470	98.16 411

MonoMVSNet		96.25 355	96.53 341	95.39 425	96.57 458	91.01 432	98.82 95	97.68 389	98.57 160	98.03 320	99.37 98	90.92 370	97.78 466	94.99 350	93.88 466	97.38 446

test-LLR		93.90 404	93.85 399	94.04 439	96.53 459	84.62 465	94.05 454	92.39 459	96.17 346	94.12 450	95.07 446	82.30 432	99.67 317	95.87 326	98.18 404	97.82 428

test-mter		92.33 429	91.76 430	94.04 439	96.53 459	84.62 465	94.05 454	92.39 459	94.00 410	94.12 450	95.07 446	65.63 471	99.67 317	95.87 326	98.18 404	97.82 428

TESTMET0.1,1		92.19 431	91.77 429	93.46 446	96.48 461	82.80 472	94.05 454	91.52 464	94.45 399	94.00 453	94.88 452	66.65 465	99.56 371	95.78 331	98.11 410	98.02 418

MGCNet		97.44 292	97.01 308	98.72 203	96.42 462	96.74 260	97.20 320	91.97 462	98.46 168	98.30 293	98.79 261	92.74 348	99.91 73	99.30 62	99.94 49	99.52 152

miper_enhance_ethall		96.01 361	95.74 356	96.81 386	96.41 463	92.27 412	93.69 459	98.89 314	91.14 444	98.30 293	97.35 403	90.58 373	99.58 366	96.31 303	99.03 353	98.60 380

tpmvs		95.02 387	95.25 377	94.33 435	96.39 464	85.87 458	98.08 185	96.83 415	95.46 373	95.51 434	98.69 285	85.91 406	99.53 383	94.16 374	96.23 452	97.58 441

CMPMVS	75.91 23	96.29 352	95.44 370	98.84 174	96.25 465	98.69 97	97.02 329	99.12 274	88.90 456	97.83 334	98.86 242	89.51 382	98.90 452	91.92 419	99.51 273	98.92 336
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 392	93.69 402	96.99 375	96.05 466	93.61 389	94.97 432	93.49 454	96.17 346	97.57 352	94.88 452	82.30 432	99.01 447	93.60 392	94.17 465	98.37 403

EPMVS		93.72 408	93.27 407	95.09 430	96.04 467	87.76 452	98.13 175	85.01 475	94.69 392	96.92 385	98.64 297	78.47 449	99.31 427	95.04 349	96.46 449	98.20 409

cascas		94.79 390	94.33 396	96.15 410	96.02 468	92.36 410	92.34 466	99.26 240	85.34 464	95.08 439	94.96 451	92.96 343	98.53 459	94.41 371	98.59 391	97.56 442

MVStest1		95.86 366	95.60 362	96.63 391	95.87 469	91.70 417	97.93 216	98.94 302	98.03 209	99.56 73	99.66 32	71.83 455	98.26 462	99.35 58	99.24 324	99.91 13

gg-mvs-nofinetune		92.37 428	91.20 432	95.85 413	95.80 470	92.38 409	99.31 30	81.84 477	99.75 11	91.83 466	99.74 18	68.29 460	99.02 445	87.15 453	97.12 441	96.16 460

gm-plane-assit					94.83 471	81.97 474			88.07 459		94.99 449		99.60 355	91.76 423

GG-mvs-BLEND				94.76 432	94.54 472	92.13 414	99.31 30	80.47 478		88.73 472	91.01 472	67.59 464	98.16 465	82.30 466	94.53 464	93.98 468

UWE-MVS-28		90.22 436	89.28 439	93.02 452	94.50 473	82.87 471	96.52 360	87.51 471	95.21 381	92.36 464	96.04 426	71.57 456	98.25 463	72.04 473	97.77 422	97.94 423

EPNet_dtu		94.93 389	94.78 389	95.38 426	93.58 474	87.68 453	96.78 343	95.69 437	97.35 275	89.14 471	98.09 357	88.15 394	99.49 396	94.95 353	99.30 315	98.98 324
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 440	75.95 443	77.12 457	92.39 475	67.91 481	90.16 469	59.44 482	82.04 468	89.42 470	94.67 455	49.68 479	81.74 475	48.06 475	77.66 473	81.72 471

KD-MVS_2432*1600		92.87 422	91.99 424	95.51 422	91.37 476	89.27 445	94.07 452	98.14 375	95.42 374	97.25 373	96.44 421	67.86 461	99.24 435	91.28 432	96.08 455	98.02 418

miper_refine_blended		92.87 422	91.99 424	95.51 422	91.37 476	89.27 445	94.07 452	98.14 375	95.42 374	97.25 373	96.44 421	67.86 461	99.24 435	91.28 432	96.08 455	98.02 418

EPNet		96.14 358	95.44 370	98.25 278	90.76 478	95.50 312	97.92 219	94.65 444	98.97 123	92.98 460	98.85 245	89.12 385	99.87 133	95.99 319	99.68 209	99.39 216
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 441	68.95 444	70.34 458	87.68 479	65.00 482	91.11 467	59.90 481	69.02 471	74.46 476	88.89 473	48.58 480	68.03 477	28.61 476	72.33 475	77.99 472

test_method		79.78 438	79.50 441	80.62 455	80.21 480	45.76 483	70.82 472	98.41 365	31.08 475	80.89 475	97.71 380	84.85 413	97.37 468	91.51 429	80.03 472	98.75 365

tmp_tt		78.77 439	78.73 442	78.90 456	58.45 481	74.76 480	94.20 451	78.26 479	39.16 474	86.71 473	92.82 468	80.50 436	75.19 476	86.16 458	92.29 469	86.74 470

testmvs		17.12 443	20.53 446	6.87 460	12.05 482	4.20 485	93.62 460	6.73 483	4.62 478	10.41 478	24.33 475	8.28 482	3.56 479	9.69 478	15.07 476	12.86 475

test123		17.04 444	20.11 447	7.82 459	10.25 483	4.91 484	94.80 435	4.47 484	4.93 477	10.00 479	24.28 476	9.69 481	3.64 478	10.14 477	12.43 477	14.92 474

mmdepth		0.00 447	0.00 450	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	0.00 479	0.00 483	0.00 480	0.00 479	0.00 478	0.00 476

monomultidepth		0.00 447	0.00 450	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	0.00 479	0.00 483	0.00 480	0.00 479	0.00 478	0.00 476

test_blank		0.00 447	0.00 450	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	0.00 479	0.00 483	0.00 480	0.00 479	0.00 478	0.00 476

eth-test2					0.00 484

eth-test					0.00 484

uanet_test		0.00 447	0.00 450	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	0.00 479	0.00 483	0.00 480	0.00 479	0.00 478	0.00 476

DCPMVS		0.00 447	0.00 450	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	0.00 479	0.00 483	0.00 480	0.00 479	0.00 478	0.00 476

cdsmvs_eth3d_5k		24.66 442	32.88 445	0.00 461	0.00 484	0.00 486	0.00 473	99.10 277	0.00 479	0.00 480	97.58 388	99.21 18	0.00 480	0.00 479	0.00 478	0.00 476

pcd_1.5k_mvsjas		8.17 445	10.90 448	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	0.00 479	98.07 117	0.00 480	0.00 479	0.00 478	0.00 476

sosnet-low-res		0.00 447	0.00 450	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	0.00 479	0.00 483	0.00 480	0.00 479	0.00 478	0.00 476

sosnet		0.00 447	0.00 450	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	0.00 479	0.00 483	0.00 480	0.00 479	0.00 478	0.00 476

uncertanet		0.00 447	0.00 450	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	0.00 479	0.00 483	0.00 480	0.00 479	0.00 478	0.00 476

Regformer		0.00 447	0.00 450	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	0.00 479	0.00 483	0.00 480	0.00 479	0.00 478	0.00 476

ab-mvs-re		8.12 446	10.83 449	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	97.48 394	0.00 483	0.00 480	0.00 479	0.00 478	0.00 476

uanet		0.00 447	0.00 450	0.00 461	0.00 484	0.00 486	0.00 473	0.00 485	0.00 479	0.00 480	0.00 479	0.00 483	0.00 480	0.00 479	0.00 478	0.00 476

TestfortrainingZip							98.68 107

WAC-MVS						90.90 434								91.37 431

PC_three_1452									93.27 418	99.40 113	98.54 310	98.22 103	97.00 469	95.17 347	99.45 288	99.49 165

test_241102_TWO								99.30 220	98.03 209	99.26 145	99.02 192	97.51 173	99.88 114	96.91 244	99.60 242	99.66 77

test_0728_THIRD									98.17 196	99.08 171	99.02 192	97.89 135	99.88 114	97.07 231	99.71 194	99.70 67

GSMVS																98.81 354

sam_mvs1												84.74 415				98.81 354

sam_mvs												84.29 421

MTGPA								99.20 252

test_post1							97.59 273				20.48 478	83.07 429	99.66 329	94.16 374

test_post											21.25 477	83.86 424	99.70 300

patchmatchnet-post											98.77 265	84.37 418	99.85 155

MTMP							97.93 216	91.91 463

test9_res														93.28 400	99.15 340	99.38 225

agg_prior2														92.50 416	99.16 338	99.37 227

test_prior4						97.97 162	95.86 401

test_prior2							95.74 408		96.48 333	96.11 418	97.63 386	95.92 273		94.16 374	99.20 332

旧先验2							95.76 407		88.56 458	97.52 356			99.66 329	94.48 364

新几何2							95.93 397

无先验							95.74 408	98.74 344	89.38 454				99.73 284	92.38 418		99.22 280

原ACMM2							95.53 414

testdata2													99.79 241	92.80 410

segment_acmp												97.02 206

testdata1							95.44 419		96.32 341

plane_prior5								99.27 235					99.70 300	94.42 368	99.51 273	99.45 191

plane_prior4											97.98 365

plane_prior3						97.78 187			97.41 269	97.79 337

plane_prior2							97.77 241		98.20 193

plane_prior						97.65 196	97.07 328		96.72 323						99.36 303

n2								0.00 485

nn								0.00 485

door-mid								99.57 92

test11								98.87 317

door								99.41 172

HQP5-MVS						96.79 256

BP-MVS														92.82 408

HQP4-MVS										95.56 428			99.54 381			99.32 250

HQP3-MVS								99.04 289							99.26 322

HQP2-MVS												93.84 327

MDTV_nov1_ep13_2view						74.92 479	97.69 254		90.06 452	97.75 340		85.78 407		93.52 394		98.69 372

ACMMP++_ref															99.77 155

ACMMP++															99.68 209

Test By Simon												96.52 239

High-resolution multi-view benchmark