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 83	99.16 63	98.64 221	99.94 2	98.51 112	99.32 26	99.75 42	99.58 39	98.60 271	99.62 40	98.22 107	99.51 403	97.70 192	99.73 183	97.89 436
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 29	99.31 42	99.53 39	99.91 3	98.98 72	99.63 7	99.58 92	99.44 53	99.78 40	99.76 15	96.39 252	99.92 65	99.44 55	99.92 69	99.68 71

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

PS-MVSNAJss		99.46 17	99.49 16	99.35 80	99.90 4	98.15 139	99.20 48	99.65 69	99.48 45	99.92 8	99.71 22	98.07 122	99.96 14	99.53 48	100.00 1	99.93 11

testf1		99.25 41	99.16 63	99.51 49	99.89 6	99.63 4	98.71 105	99.69 54	98.90 133	99.43 106	99.35 107	98.86 34	99.67 326	97.81 179	99.81 132	99.24 281

APD_test2		99.25 41	99.16 63	99.51 49	99.89 6	99.63 4	98.71 105	99.69 54	98.90 133	99.43 106	99.35 107	98.86 34	99.67 326	97.81 179	99.81 132	99.24 281

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

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

v7n		99.53 12	99.57 13	99.41 70	99.88 9	98.54 110	99.45 14	99.61 80	99.66 24	99.68 58	99.66 32	98.44 80	99.95 26	99.73 28	99.96 28	99.75 60

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

test_fmvsmconf0.01_n		99.57 10	99.63 10	99.36 74	99.87 12	98.13 142	98.08 190	99.95 1	99.45 51	99.98 2	99.75 16	99.80 1	99.97 7	99.82 12	99.99 5	99.99 2

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

test_djsdf		99.52 13	99.51 15	99.53 39	99.86 14	98.74 92	99.39 20	99.56 108	99.11 98	99.70 52	99.73 20	99.00 27	99.97 7	99.26 66	99.98 12	99.89 16

MIMVSNet1		99.38 28	99.32 40	99.55 29	99.86 14	99.19 43	99.41 17	99.59 89	99.59 37	99.71 50	99.57 49	97.12 207	99.90 81	99.21 71	99.87 98	99.54 142

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 27	99.85 16	99.11 65	99.90 1	99.78 36	99.63 29	99.78 40	99.67 30	99.48 10	99.81 222	99.30 63	99.97 21	99.77 50
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 17	99.34 20	99.69 5	99.58 92	99.90 3	99.86 24	99.78 13	99.58 6	99.95 26	99.00 88	99.95 38	99.78 47

SixPastTwentyTwo		98.75 133	98.62 148	99.16 118	99.83 18	97.96 166	99.28 40	98.20 383	99.37 61	99.70 52	99.65 36	92.65 358	99.93 54	99.04 85	99.84 112	99.60 100

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

Baseline_NR-MVSNet		98.98 91	98.86 110	99.36 74	99.82 19	98.55 107	97.47 298	99.57 99	99.37 61	99.21 162	99.61 43	96.76 234	99.83 192	98.06 156	99.83 121	99.71 63

pm-mvs1		99.44 19	99.48 18	99.33 89	99.80 21	98.63 99	99.29 36	99.63 73	99.30 71	99.65 64	99.60 45	99.16 22	99.82 205	99.07 81	99.83 121	99.56 129

TransMVSNet (Re)		99.44 19	99.47 21	99.36 74	99.80 21	98.58 105	99.27 42	99.57 99	99.39 59	99.75 45	99.62 40	99.17 20	99.83 192	99.06 83	99.62 242	99.66 78

K. test v3		98.00 252	97.66 277	99.03 145	99.79 23	97.56 202	99.19 52	92.47 469	99.62 33	99.52 88	99.66 32	89.61 390	99.96 14	99.25 68	99.81 132	99.56 129

test_fmvsmconf0.1_n		99.49 15	99.54 14	99.34 83	99.78 24	98.11 143	97.77 247	99.90 11	99.33 66	99.97 3	99.66 32	99.71 3	99.96 14	99.79 19	99.99 5	99.96 8

APD_test1		98.83 117	98.66 141	99.34 83	99.78 24	99.47 9	98.42 150	99.45 157	98.28 190	98.98 199	99.19 152	97.76 154	99.58 377	96.57 292	99.55 269	98.97 338

test_vis3_rt		99.14 63	99.17 61	99.07 135	99.78 24	98.38 119	98.92 82	99.94 2	97.80 236	99.91 12	99.67 30	97.15 206	98.91 462	99.76 23	99.56 265	99.92 12

EGC-MVSNET		85.24 448	80.54 451	99.34 83	99.77 27	99.20 40	99.08 61	99.29 237	12.08 487	20.84 488	99.42 90	97.55 173	99.85 156	97.08 238	99.72 191	98.96 340

Anonymous20240521		98.69 146	98.87 106	98.16 298	99.77 27	95.11 340	99.08 61	99.44 165	99.34 65	99.33 130	99.55 57	94.10 333	99.94 42	99.25 68	99.96 28	99.42 210

FC-MVSNet-test		99.27 38	99.25 53	99.34 83	99.77 27	98.37 121	99.30 35	99.57 99	99.61 35	99.40 115	99.50 69	97.12 207	99.85 156	99.02 87	99.94 50	99.80 42

test_vis1_n		98.31 216	98.50 168	97.73 335	99.76 30	94.17 370	98.68 108	99.91 9	96.31 352	99.79 39	99.57 49	92.85 354	99.42 423	99.79 19	99.84 112	99.60 100

test_fmvs3		99.12 70	99.41 26	98.25 286	99.76 30	95.07 341	99.05 67	99.94 2	97.78 239	99.82 34	99.84 3	98.56 70	99.71 299	99.96 1	99.96 28	99.97 4

XXY-MVS		99.14 63	99.15 68	99.10 128	99.76 30	97.74 191	98.85 92	99.62 77	98.48 173	99.37 120	99.49 75	98.75 46	99.86 143	98.20 146	99.80 143	99.71 63

TDRefinement		99.42 24	99.38 29	99.55 29	99.76 30	99.33 21	99.68 6	99.71 47	99.38 60	99.53 83	99.61 43	98.64 58	99.80 231	98.24 141	99.84 112	99.52 156

fmvsm_s_conf0.1_n_a		99.17 53	99.30 45	98.80 186	99.75 34	96.59 272	97.97 220	99.86 16	98.22 193	99.88 21	99.71 22	98.59 64	99.84 174	99.73 28	99.98 12	99.98 3

tt0805		98.69 146	98.62 148	98.90 171	99.75 34	99.30 23	99.15 56	96.97 420	98.86 139	98.87 232	97.62 396	98.63 60	98.96 459	99.41 57	98.29 409	98.45 402

test_vis1_n_1920		98.40 199	98.92 98	96.81 397	99.74 36	90.76 448	98.15 178	99.91 9	98.33 181	99.89 18	99.55 57	95.07 304	99.88 115	99.76 23	99.93 56	99.79 44

FOURS1					99.73 37	99.67 3	99.43 15	99.54 117	99.43 55	99.26 148

PEN-MVS		99.41 25	99.34 36	99.62 10	99.73 37	99.14 58	99.29 36	99.54 117	99.62 33	99.56 74	99.42 90	98.16 116	99.96 14	98.78 103	99.93 56	99.77 50

lessismore_v0				98.97 157	99.73 37	97.53 204		86.71 484		99.37 120	99.52 68	89.93 386	99.92 65	98.99 89	99.72 191	99.44 201

SteuartSystems-ACMMP		98.79 126	98.54 161	99.54 32	99.73 37	99.16 49	98.23 168	99.31 221	97.92 227	98.90 221	98.90 239	98.00 128	99.88 115	96.15 324	99.72 191	99.58 115
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 237	98.15 229	98.22 292	99.73 37	95.15 337	97.36 312	99.68 60	94.45 410	98.99 198	99.27 127	96.87 223	99.94 42	97.13 235	99.91 78	99.57 123

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

SSC-MVS		98.71 137	98.74 121	98.62 227	99.72 43	96.08 297	98.74 98	98.64 362	99.74 13	99.67 60	99.24 140	94.57 319	99.95 26	99.11 78	99.24 333	99.82 36

test_f		98.67 155	98.87 106	98.05 308	99.72 43	95.59 312	98.51 134	99.81 31	96.30 354	99.78 40	99.82 5	96.14 263	98.63 469	99.82 12	99.93 56	99.95 9

ACMH	96.65 7	99.25 41	99.24 54	99.26 101	99.72 43	98.38 119	99.07 64	99.55 112	98.30 185	99.65 64	99.45 85	99.22 17	99.76 267	98.44 129	99.77 160	99.64 84
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0320		99.61 8	99.65 9	99.48 57	99.71 47	98.94 79	99.54 8	99.83 25	99.87 5	99.89 18	99.82 5	98.75 46	99.90 81	99.54 44	99.95 38	99.59 107

fmvsm_s_conf0.1_n		99.16 57	99.33 38	98.64 221	99.71 47	96.10 292	97.87 233	99.85 18	98.56 169	99.90 14	99.68 25	98.69 54	99.85 156	99.72 30	99.98 12	99.97 4

PS-CasMVS		99.40 26	99.33 38	99.62 10	99.71 47	99.10 66	99.29 36	99.53 121	99.53 42	99.46 101	99.41 94	98.23 104	99.95 26	98.89 97	99.95 38	99.81 40

DTE-MVSNet		99.43 23	99.35 34	99.66 7	99.71 47	99.30 23	99.31 30	99.51 127	99.64 27	99.56 74	99.46 81	98.23 104	99.97 7	98.78 103	99.93 56	99.72 62

WR-MVS_H		99.33 31	99.22 55	99.65 8	99.71 47	99.24 31	99.32 26	99.55 112	99.46 50	99.50 94	99.34 111	97.30 195	99.93 54	98.90 95	99.93 56	99.77 50

HPM-MVS_fast		99.01 85	98.82 114	99.57 22	99.71 47	99.35 17	99.00 72	99.50 130	97.33 285	98.94 216	98.86 249	98.75 46	99.82 205	97.53 204	99.71 200	99.56 129

ACMH+	96.62 9	99.08 77	99.00 90	99.33 89	99.71 47	98.83 87	98.60 120	99.58 92	99.11 98	99.53 83	99.18 156	98.81 38	99.67 326	96.71 276	99.77 160	99.50 164

PMVS	91.26 20	97.86 266	97.94 253	97.65 342	99.71 47	97.94 168	98.52 129	98.68 358	98.99 121	97.52 365	99.35 107	97.41 188	98.18 475	91.59 438	99.67 221	96.82 464
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FE-MVSNET2		99.15 58	99.22 55	98.94 161	99.70 55	97.49 205	98.62 117	99.67 64	98.85 142	99.34 127	99.54 63	98.47 74	99.81 222	98.93 93	99.91 78	99.51 160

KinetiMVS		99.03 83	99.02 86	99.03 145	99.70 55	97.48 208	98.43 147	99.29 237	99.70 16	99.60 71	99.07 185	96.13 264	99.94 42	99.42 56	99.87 98	99.68 71

FIs		99.14 63	99.09 78	99.29 95	99.70 55	98.28 127	99.13 58	99.52 126	99.48 45	99.24 156	99.41 94	96.79 231	99.82 205	98.69 113	99.88 94	99.76 56

VPNet		98.87 107	98.83 113	99.01 149	99.70 55	97.62 200	98.43 147	99.35 202	99.47 48	99.28 142	99.05 193	96.72 237	99.82 205	98.09 153	99.36 312	99.59 107

fmvsm_s_conf0.1_n_2		99.20 51	99.38 29	98.65 219	99.69 59	96.08 297	97.49 293	99.90 11	99.53 42	99.88 21	99.64 37	98.51 73	99.90 81	99.83 10	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 213	98.68 136	97.27 373	99.69 59	92.29 422	98.03 201	99.85 18	97.62 249	99.96 4	99.62 40	93.98 334	99.74 281	99.52 50	99.86 105	99.79 44

MP-MVS-pluss		98.57 172	98.23 217	99.60 16	99.69 59	99.35 17	97.16 334	99.38 188	94.87 400	98.97 203	98.99 215	98.01 127	99.88 115	97.29 222	99.70 207	99.58 115
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 46	99.32 40	98.96 158	99.68 62	97.35 216	98.84 94	99.48 140	99.69 18	99.63 67	99.68 25	99.03 24	99.96 14	97.97 167	99.92 69	99.57 123

sd_testset		99.28 37	99.31 42	99.19 112	99.68 62	98.06 155	99.41 17	99.30 229	99.69 18	99.63 67	99.68 25	99.25 16	99.96 14	97.25 225	99.92 69	99.57 123

test_fmvs1_n		98.09 243	98.28 208	97.52 359	99.68 62	93.47 401	98.63 115	99.93 5	95.41 388	99.68 58	99.64 37	91.88 369	99.48 410	99.82 12	99.87 98	99.62 90

CHOSEN 1792x2688		97.49 295	97.14 310	98.54 250	99.68 62	96.09 295	96.50 370	99.62 77	91.58 448	98.84 235	98.97 222	92.36 360	99.88 115	96.76 269	99.95 38	99.67 76

tfpnnormal		98.90 102	98.90 100	98.91 168	99.67 66	97.82 183	99.00 72	99.44 165	99.45 51	99.51 93	99.24 140	98.20 111	99.86 143	95.92 333	99.69 210	99.04 324

MTAPA		98.88 106	98.64 144	99.61 14	99.67 66	99.36 16	98.43 147	99.20 261	98.83 144	98.89 224	98.90 239	96.98 217	99.92 65	97.16 230	99.70 207	99.56 129

test_fmvsmvis_n_1920		99.26 40	99.49 16	98.54 250	99.66 68	96.97 251	98.00 208	99.85 18	99.24 76	99.92 8	99.50 69	99.39 12	99.95 26	99.89 3	99.98 12	98.71 379

mvs5depth		99.30 34	99.59 12	98.44 264	99.65 69	95.35 329	99.82 3	99.94 2	99.83 7	99.42 110	99.94 2	98.13 119	99.96 14	99.63 36	99.96 28	100.00 1

fmvsm_l_conf0.5_n_a		99.19 52	99.27 48	98.94 161	99.65 69	97.05 246	97.80 242	99.76 39	98.70 151	99.78 40	99.11 175	98.79 42	99.95 26	99.85 6	99.96 28	99.83 33

WB-MVS		98.52 186	98.55 159	98.43 265	99.65 69	95.59 312	98.52 129	98.77 347	99.65 26	99.52 88	99.00 213	94.34 325	99.93 54	98.65 115	98.83 381	99.76 56

CP-MVSNet		99.21 48	99.09 78	99.56 27	99.65 69	98.96 78	99.13 58	99.34 208	99.42 56	99.33 130	99.26 133	97.01 215	99.94 42	98.74 108	99.93 56	99.79 44

HPM-MVS		98.79 126	98.53 163	99.59 20	99.65 69	99.29 25	99.16 54	99.43 171	96.74 332	98.61 269	98.38 340	98.62 61	99.87 134	96.47 304	99.67 221	99.59 107
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 164	98.36 194	99.42 68	99.65 69	99.42 11	98.55 125	99.57 99	97.72 243	98.90 221	99.26 133	96.12 266	99.52 398	95.72 344	99.71 200	99.32 257

NormalMVS		98.26 223	97.97 250	99.15 121	99.64 75	97.83 178	98.28 162	99.43 171	99.24 76	98.80 243	98.85 252	89.76 388	99.94 42	98.04 158	99.67 221	99.68 71

lecture		99.25 41	99.12 71	99.62 10	99.64 75	99.40 12	98.89 87	99.51 127	99.19 88	99.37 120	99.25 138	98.36 85	99.88 115	98.23 143	99.67 221	99.59 107

fmvsm_l_conf0.5_n		99.21 48	99.28 47	99.02 148	99.64 75	97.28 225	97.82 238	99.76 39	98.73 146	99.82 34	99.09 183	98.81 38	99.95 26	99.86 4	99.96 28	99.83 33

test_fmvsmconf_n		99.44 19	99.48 18	99.31 94	99.64 75	98.10 145	97.68 261	99.84 22	99.29 72	99.92 8	99.57 49	99.60 5	99.96 14	99.74 27	99.98 12	99.89 16

TSAR-MVS + MP.		98.63 161	98.49 173	99.06 141	99.64 75	97.90 172	98.51 134	98.94 312	96.96 316	99.24 156	98.89 245	97.83 146	99.81 222	96.88 259	99.49 291	99.48 182
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 120	98.72 125	99.12 124	99.64 75	98.54 110	97.98 216	99.68 60	97.62 249	99.34 127	99.18 156	97.54 175	99.77 261	97.79 181	99.74 180	99.04 324

Elysia		99.15 58	99.14 69	99.18 113	99.63 81	97.92 169	98.50 136	99.43 171	99.67 21	99.70 52	99.13 171	96.66 240	99.98 4	99.54 44	99.96 28	99.64 84

StellarMVS		99.15 58	99.14 69	99.18 113	99.63 81	97.92 169	98.50 136	99.43 171	99.67 21	99.70 52	99.13 171	96.66 240	99.98 4	99.54 44	99.96 28	99.64 84

KD-MVS_self_test		99.25 41	99.18 60	99.44 66	99.63 81	99.06 71	98.69 107	99.54 117	99.31 69	99.62 70	99.53 65	97.36 192	99.86 143	99.24 70	99.71 200	99.39 223

EU-MVSNet		97.66 283	98.50 168	95.13 439	99.63 81	85.84 470	98.35 158	98.21 382	98.23 192	99.54 79	99.46 81	95.02 305	99.68 322	98.24 141	99.87 98	99.87 22

HyFIR lowres test		97.19 322	96.60 346	98.96 158	99.62 85	97.28 225	95.17 436	99.50 130	94.21 415	99.01 193	98.32 348	86.61 408	99.99 2	97.10 237	99.84 112	99.60 100

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

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

fmvsm_l_conf0.5_n_9		99.32 33	99.43 24	98.98 155	99.59 88	97.18 237	97.44 302	99.83 25	99.56 40	99.91 12	99.34 111	99.36 13	99.93 54	99.83 10	99.98 12	99.85 30

fmvsm_l_conf0.5_n_3		99.45 18	99.48 18	99.34 83	99.59 88	98.21 136	97.82 238	99.84 22	99.41 58	99.92 8	99.41 94	99.51 8	99.95 26	99.84 9	99.97 21	99.87 22

MED-MVS test				99.45 64	99.58 90	98.93 80	98.68 108	99.60 82	96.46 345	99.53 83	98.77 272		99.83 192	96.67 281	99.64 232	99.58 115

MED-MVS		98.90 102	98.72 125	99.45 64	99.58 90	98.93 80	98.68 108	99.60 82	98.14 211	99.53 83	98.77 272	97.87 143	99.83 192	96.67 281	99.64 232	99.58 115

TestfortrainingZip a		98.95 95	98.72 125	99.64 9	99.58 90	99.32 22	98.68 108	99.60 82	96.46 345	99.53 83	98.77 272	97.87 143	99.83 192	98.39 134	99.64 232	99.77 50

FE-MVSNET		98.59 169	98.50 168	98.87 172	99.58 90	97.30 221	98.08 190	99.74 43	96.94 318	98.97 203	99.10 178	96.94 219	99.74 281	97.33 220	99.86 105	99.55 136

mmtdpeth		99.30 34	99.42 25	98.92 167	99.58 90	96.89 259	99.48 13	99.92 7	99.92 2	98.26 307	99.80 11	98.33 91	99.91 74	99.56 41	99.95 38	99.97 4

ACMMP_NAP		98.75 133	98.48 174	99.57 22	99.58 90	99.29 25	97.82 238	99.25 250	96.94 318	98.78 245	99.12 174	98.02 126	99.84 174	97.13 235	99.67 221	99.59 107

nrg030		99.40 26	99.35 34	99.54 32	99.58 90	99.13 61	98.98 75	99.48 140	99.68 20	99.46 101	99.26 133	98.62 61	99.73 288	99.17 75	99.92 69	99.76 56

VDDNet		98.21 230	97.95 251	99.01 149	99.58 90	97.74 191	99.01 70	97.29 411	99.67 21	98.97 203	99.50 69	90.45 383	99.80 231	97.88 174	99.20 341	99.48 182

COLMAP_ROB	96.50 10	98.99 88	98.85 112	99.41 70	99.58 90	99.10 66	98.74 98	99.56 108	99.09 108	99.33 130	99.19 152	98.40 82	99.72 298	95.98 331	99.76 175	99.42 210
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_fmvsm_n_1920		99.33 31	99.45 23	98.99 151	99.57 99	97.73 193	97.93 222	99.83 25	99.22 79	99.93 6	99.30 121	99.42 11	99.96 14	99.85 6	99.99 5	99.29 267

ZNCC-MVS		98.68 152	98.40 186	99.54 32	99.57 99	99.21 34	98.46 144	99.29 237	97.28 291	98.11 319	98.39 338	98.00 128	99.87 134	96.86 262	99.64 232	99.55 136

MSP-MVS		98.40 199	98.00 245	99.61 14	99.57 99	99.25 30	98.57 123	99.35 202	97.55 260	99.31 138	97.71 389	94.61 318	99.88 115	96.14 325	99.19 344	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		98.32 214	98.39 189	98.13 299	99.57 99	95.54 315	97.78 244	99.49 138	97.37 282	99.19 164	97.65 393	98.96 29	99.49 407	96.50 303	98.99 369	99.34 248

MP-MVS		98.46 192	98.09 234	99.54 32	99.57 99	99.22 33	98.50 136	99.19 265	97.61 252	97.58 359	98.66 300	97.40 189	99.88 115	94.72 370	99.60 249	99.54 142
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 137	98.46 178	99.47 61	99.57 99	98.97 74	98.23 168	99.48 140	96.60 337	99.10 175	99.06 186	98.71 50	99.83 192	95.58 351	99.78 154	99.62 90

LGP-MVS_train				99.47 61	99.57 99	98.97 74		99.48 140	96.60 337	99.10 175	99.06 186	98.71 50	99.83 192	95.58 351	99.78 154	99.62 90

IS-MVSNet		98.19 233	97.90 259	99.08 133	99.57 99	97.97 163	99.31 30	98.32 378	99.01 120	98.98 199	99.03 197	91.59 371	99.79 244	95.49 353	99.80 143	99.48 182

viewdifsd2359ckpt11		98.84 114	99.04 83	98.24 288	99.56 107	95.51 317	97.38 307	99.70 52	99.16 93	99.57 72	99.40 97	98.26 100	99.71 299	98.55 124	99.82 126	99.50 164

viewmsd2359difaftdt		98.84 114	99.04 83	98.24 288	99.56 107	95.51 317	97.38 307	99.70 52	99.16 93	99.57 72	99.40 97	98.26 100	99.71 299	98.55 124	99.82 126	99.50 164

dcpmvs_2		98.78 128	99.11 72	97.78 325	99.56 107	93.67 396	99.06 65	99.86 16	99.50 44	99.66 61	99.26 133	97.21 203	99.99 2	98.00 163	99.91 78	99.68 71

test_0402		98.76 132	98.71 130	98.93 164	99.56 107	98.14 141	98.45 146	99.34 208	99.28 73	98.95 209	98.91 236	98.34 90	99.79 244	95.63 348	99.91 78	98.86 357

EPP-MVSNet		98.30 217	98.04 241	99.07 135	99.56 107	97.83 178	99.29 36	98.07 389	99.03 118	98.59 273	99.13 171	92.16 364	99.90 81	96.87 260	99.68 215	99.49 171

ACMMP		98.75 133	98.50 168	99.52 45	99.56 107	99.16 49	98.87 88	99.37 192	97.16 306	98.82 239	99.01 209	97.71 157	99.87 134	96.29 316	99.69 210	99.54 142
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
fmvsm_s_conf0.5_n_a		99.10 72	99.20 59	98.78 193	99.55 113	96.59 272	97.79 243	99.82 30	98.21 195	99.81 37	99.53 65	98.46 78	99.84 174	99.70 33	99.97 21	99.90 15

fmvsm_s_conf0.5_n		99.09 73	99.26 51	98.61 231	99.55 113	96.09 295	97.74 254	99.81 31	98.55 170	99.85 27	99.55 57	98.60 63	99.84 174	99.69 35	99.98 12	99.89 16

FMVSNet1		99.17 53	99.17 61	99.17 115	99.55 113	98.24 130	99.20 48	99.44 165	99.21 81	99.43 106	99.55 57	97.82 149	99.86 143	98.42 133	99.89 92	99.41 213

Vis-MVSNet (Re-imp)		97.46 297	97.16 307	98.34 277	99.55 113	96.10 292	98.94 80	98.44 372	98.32 183	98.16 313	98.62 309	88.76 395	99.73 288	93.88 396	99.79 149	99.18 301

ACMM	96.08 12	98.91 100	98.73 123	99.48 57	99.55 113	99.14 58	98.07 194	99.37 192	97.62 249	99.04 189	98.96 225	98.84 36	99.79 244	97.43 214	99.65 230	99.49 171
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 142	98.97 94	97.89 317	99.54 118	94.05 373	98.55 125	99.92 7	96.78 330	99.72 48	99.78 13	96.60 244	99.67 326	99.91 2	99.90 86	99.94 10

mPP-MVS		98.64 159	98.34 197	99.54 32	99.54 118	99.17 45	98.63 115	99.24 255	97.47 268	98.09 321	98.68 295	97.62 166	99.89 97	96.22 319	99.62 242	99.57 123

XVG-ACMP-BASELINE		98.56 173	98.34 197	99.22 109	99.54 118	98.59 104	97.71 257	99.46 153	97.25 294	98.98 199	98.99 215	97.54 175	99.84 174	95.88 334	99.74 180	99.23 283

viewmacassd2359aftdt		98.86 111	98.87 106	98.83 179	99.53 121	97.32 220	97.70 259	99.64 71	98.22 193	99.25 154	99.27 127	98.40 82	99.61 363	97.98 166	99.87 98	99.55 136

region2R		98.69 146	98.40 186	99.54 32	99.53 121	99.17 45	98.52 129	99.31 221	97.46 273	98.44 292	98.51 323	97.83 146	99.88 115	96.46 305	99.58 258	99.58 115

PGM-MVS		98.66 156	98.37 193	99.55 29	99.53 121	99.18 44	98.23 168	99.49 138	97.01 315	98.69 256	98.88 246	98.00 128	99.89 97	95.87 337	99.59 253	99.58 115

E4		98.87 107	98.88 103	98.81 183	99.52 124	97.23 228	97.62 272	99.61 80	98.58 164	99.18 168	99.33 114	98.29 94	99.69 312	97.99 165	99.83 121	99.52 156

Patchmatch-RL test		97.26 315	97.02 316	97.99 312	99.52 124	95.53 316	96.13 395	99.71 47	97.47 268	99.27 144	99.16 162	84.30 430	99.62 356	97.89 171	99.77 160	98.81 365

ACMMPR		98.70 142	98.42 184	99.54 32	99.52 124	99.14 58	98.52 129	99.31 221	97.47 268	98.56 279	98.54 318	97.75 155	99.88 115	96.57 292	99.59 253	99.58 115

fmvsm_s_conf0.5_n_9		99.17 53	99.38 29	98.53 252	99.51 127	95.82 307	97.62 272	99.78 36	99.72 15	99.90 14	99.48 76	98.66 56	99.89 97	99.85 6	99.93 56	99.89 16

AstraMVS		98.16 239	98.07 239	98.41 267	99.51 127	95.86 304	98.00 208	95.14 452	98.97 124	99.43 106	99.24 140	93.25 342	99.84 174	99.21 71	99.87 98	99.54 142

fmvsm_s_conf0.5_n_8		99.13 67	99.26 51	98.74 206	99.51 127	96.44 284	97.65 267	99.65 69	99.66 24	99.78 40	99.48 76	97.92 136	99.93 54	99.72 30	99.95 38	99.87 22

GST-MVS		98.61 165	98.30 205	99.52 45	99.51 127	99.20 40	98.26 166	99.25 250	97.44 276	98.67 259	98.39 338	97.68 158	99.85 156	96.00 329	99.51 281	99.52 156

Anonymous20231206		98.21 230	98.21 218	98.20 293	99.51 127	95.43 326	98.13 180	99.32 216	96.16 359	98.93 217	98.82 262	96.00 271	99.83 192	97.32 221	99.73 183	99.36 241

ACMP	95.32 15	98.41 196	98.09 234	99.36 74	99.51 127	98.79 90	97.68 261	99.38 188	95.76 375	98.81 241	98.82 262	98.36 85	99.82 205	94.75 367	99.77 160	99.48 182
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LuminaMVS		98.39 205	98.20 219	98.98 155	99.50 133	97.49 205	97.78 244	97.69 398	98.75 145	99.49 95	99.25 138	92.30 362	99.94 42	99.14 76	99.88 94	99.50 164

DVP-MVS		98.77 131	98.52 164	99.52 45	99.50 133	99.21 34	98.02 204	98.84 336	97.97 221	99.08 177	99.02 198	97.61 168	99.88 115	96.99 246	99.63 239	99.48 182
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	99.50 133	99.23 32	98.02 204	99.32 216					99.88 115	96.99 246	99.63 239	99.68 71

test0726					99.50 133	99.21 34	98.17 176	99.35 202	97.97 221	99.26 148	99.06 186	97.61 168

AllTest		98.44 194	98.20 219	99.16 118	99.50 133	98.55 107	98.25 167	99.58 92	96.80 328	98.88 228	99.06 186	97.65 161	99.57 379	94.45 377	99.61 247	99.37 234

TestCases				99.16 118	99.50 133	98.55 107		99.58 92	96.80 328	98.88 228	99.06 186	97.65 161	99.57 379	94.45 377	99.61 247	99.37 234

XVG-OURS		98.53 182	98.34 197	99.11 126	99.50 133	98.82 89	95.97 401	99.50 130	97.30 289	99.05 187	98.98 220	99.35 14	99.32 437	95.72 344	99.68 215	99.18 301

EG-PatchMatch MVS		98.99 88	99.01 88	98.94 161	99.50 133	97.47 209	98.04 199	99.59 89	98.15 210	99.40 115	99.36 106	98.58 69	99.76 267	98.78 103	99.68 215	99.59 107

fmvsm_s_conf0.5_n_2		99.14 63	99.31 42	98.63 225	99.49 141	96.08 297	97.38 307	99.81 31	99.48 45	99.84 30	99.57 49	98.46 78	99.89 97	99.82 12	99.97 21	99.91 13

SED-MVS		98.91 100	98.72 125	99.49 55	99.49 141	99.17 45	98.10 187	99.31 221	98.03 217	99.66 61	99.02 198	98.36 85	99.88 115	96.91 252	99.62 242	99.41 213

IU-MVS					99.49 141	99.15 53		98.87 327	92.97 433	99.41 112				96.76 269	99.62 242	99.66 78

test_241102_ONE					99.49 141	99.17 45		99.31 221	97.98 220	99.66 61	98.90 239	98.36 85	99.48 410

UA-Net		99.47 16	99.40 27	99.70 2	99.49 141	99.29 25	99.80 4	99.72 45	99.82 8	99.04 189	99.81 8	98.05 125	99.96 14	98.85 99	99.99 5	99.86 28

HFP-MVS		98.71 137	98.44 181	99.51 49	99.49 141	99.16 49	98.52 129	99.31 221	97.47 268	98.58 275	98.50 327	97.97 132	99.85 156	96.57 292	99.59 253	99.53 153

VPA-MVSNet		99.30 34	99.30 45	99.28 96	99.49 141	98.36 124	99.00 72	99.45 157	99.63 29	99.52 88	99.44 86	98.25 102	99.88 115	99.09 80	99.84 112	99.62 90

XVG-OURS-SEG-HR		98.49 189	98.28 208	99.14 122	99.49 141	98.83 87	96.54 366	99.48 140	97.32 287	99.11 172	98.61 311	99.33 15	99.30 440	96.23 318	98.38 405	99.28 270

fmvsm_s_conf0.5_n_11		99.21 48	99.34 36	98.80 186	99.48 149	96.56 277	97.97 220	99.69 54	99.63 29	99.84 30	99.54 63	98.21 109	99.94 42	99.76 23	99.95 38	99.88 20

114514_t		96.50 355	95.77 364	98.69 214	99.48 149	97.43 213	97.84 237	99.55 112	81.42 480	96.51 419	98.58 315	95.53 291	99.67 326	93.41 409	99.58 258	98.98 334

IterMVS-LS		98.55 177	98.70 133	98.09 301	99.48 149	94.73 353	97.22 328	99.39 186	98.97 124	99.38 118	99.31 120	96.00 271	99.93 54	98.58 118	99.97 21	99.60 100
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
fmvsm_s_conf0.5_n_10		99.15 58	99.27 48	98.78 193	99.47 152	96.56 277	97.75 253	99.71 47	99.60 36	99.74 47	99.44 86	97.96 133	99.95 26	99.86 4	99.94 50	99.82 36

fmvsm_s_conf0.5_n_5		99.07 79	99.10 76	98.99 151	99.47 152	97.22 231	97.40 304	99.83 25	97.61 252	99.85 27	99.30 121	98.80 40	99.95 26	99.71 32	99.90 86	99.78 47

v8		99.01 85	99.16 63	98.57 238	99.47 152	96.31 289	98.90 83	99.47 149	99.03 118	99.52 88	99.57 49	96.93 220	99.81 222	99.60 37	99.98 12	99.60 100

SSC-MVS3.2		98.53 182	98.79 117	97.74 332	99.46 155	93.62 399	96.45 372	99.34 208	99.33 66	98.93 217	98.70 291	97.90 137	99.90 81	99.12 77	99.92 69	99.69 70

fmvsm_s_conf0.5_n_3		99.22 47	99.37 32	98.78 193	99.46 155	96.58 275	97.65 267	99.72 45	99.47 48	99.86 24	99.50 69	98.94 30	99.89 97	99.75 26	99.97 21	99.86 28

XVS		98.72 136	98.45 179	99.53 39	99.46 155	99.21 34	98.65 113	99.34 208	98.62 158	97.54 363	98.63 307	97.50 181	99.83 192	96.79 265	99.53 275	99.56 129

X-MVStestdata		94.32 405	92.59 424	99.53 39	99.46 155	99.21 34	98.65 113	99.34 208	98.62 158	97.54 363	45.85 485	97.50 181	99.83 192	96.79 265	99.53 275	99.56 129

test20.03		98.78 128	98.77 120	98.78 193	99.46 155	97.20 234	97.78 244	99.24 255	99.04 117	99.41 112	98.90 239	97.65 161	99.76 267	97.70 192	99.79 149	99.39 223

guyue		98.01 251	97.93 255	98.26 284	99.45 160	95.48 321	98.08 190	96.24 435	98.89 135	99.34 127	99.14 169	91.32 375	99.82 205	99.07 81	99.83 121	99.48 182

CSCG		98.68 152	98.50 168	99.20 110	99.45 160	98.63 99	98.56 124	99.57 99	97.87 231	98.85 233	98.04 369	97.66 160	99.84 174	96.72 274	99.81 132	99.13 313

GeoE		99.05 80	98.99 92	99.25 104	99.44 162	98.35 125	98.73 102	99.56 108	98.42 176	98.91 220	98.81 265	98.94 30	99.91 74	98.35 136	99.73 183	99.49 171

v148		98.45 193	98.60 153	98.00 311	99.44 162	94.98 343	97.44 302	99.06 291	98.30 185	99.32 136	98.97 222	96.65 242	99.62 356	98.37 135	99.85 107	99.39 223

v10		98.97 92	99.11 72	98.55 245	99.44 162	96.21 291	98.90 83	99.55 112	98.73 146	99.48 96	99.60 45	96.63 243	99.83 192	99.70 33	99.99 5	99.61 98

V42		98.78 128	98.78 119	98.76 200	99.44 162	97.04 247	98.27 165	99.19 265	97.87 231	99.25 154	99.16 162	96.84 224	99.78 255	99.21 71	99.84 112	99.46 192

MDA-MVSNet-bldmvs		97.94 257	97.91 258	98.06 306	99.44 162	94.96 344	96.63 362	99.15 281	98.35 179	98.83 236	99.11 175	94.31 326	99.85 156	96.60 289	98.72 387	99.37 234

viewdifsd2359ckpt07		98.71 137	98.86 110	98.26 284	99.43 167	95.65 311	97.20 329	99.66 65	99.20 83	99.29 140	99.01 209	98.29 94	99.73 288	97.92 170	99.75 179	99.39 223

casdiffmvs_mvg		99.12 70	99.16 63	98.99 151	99.43 167	97.73 193	98.00 208	99.62 77	99.22 79	99.55 77	99.22 146	98.93 32	99.75 275	98.66 114	99.81 132	99.50 164
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		98.90 102	99.01 88	98.57 238	99.42 169	96.59 272	98.13 180	99.66 65	99.09 108	99.30 139	99.02 198	98.79 42	99.89 97	97.87 176	99.80 143	99.23 283

test1111		96.49 356	96.82 330	95.52 432	99.42 169	87.08 467	99.22 45	87.14 483	99.11 98	99.46 101	99.58 47	88.69 396	99.86 143	98.80 101	99.95 38	99.62 90

v2v482		98.56 173	98.62 148	98.37 274	99.42 169	95.81 308	97.58 281	99.16 276	97.90 229	99.28 142	99.01 209	95.98 276	99.79 244	99.33 60	99.90 86	99.51 160

OPM-MVS		98.56 173	98.32 203	99.25 104	99.41 172	98.73 95	97.13 336	99.18 269	97.10 309	98.75 251	98.92 233	98.18 112	99.65 346	96.68 280	99.56 265	99.37 234
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 245	98.08 237	98.04 309	99.41 172	94.59 359	94.59 454	99.40 184	97.50 265	98.82 239	98.83 259	96.83 226	99.84 174	97.50 207	99.81 132	99.71 63

E2		98.70 142	98.68 136	98.73 208	99.40 174	97.10 244	97.48 294	99.57 99	98.09 214	99.00 194	99.20 149	97.90 137	99.67 326	97.73 190	99.77 160	99.43 205

E3		98.69 146	98.68 136	98.73 208	99.40 174	97.10 244	97.48 294	99.57 99	98.09 214	99.00 194	99.20 149	97.90 137	99.67 326	97.73 190	99.77 160	99.43 205

test_one_0601					99.39 176	99.20 40		99.31 221	98.49 172	98.66 261	99.02 198	97.64 164

mvsany_test3		98.87 107	98.92 98	98.74 206	99.38 177	96.94 255	98.58 122	99.10 286	96.49 342	99.96 4	99.81 8	98.18 112	99.45 418	98.97 90	99.79 149	99.83 33

patch_mono-2		98.51 187	98.63 146	98.17 296	99.38 177	94.78 350	97.36 312	99.69 54	98.16 205	98.49 288	99.29 124	97.06 210	99.97 7	98.29 140	99.91 78	99.76 56

test2506		92.39 436	91.89 438	93.89 453	99.38 177	82.28 484	99.32 26	66.03 491	99.08 112	98.77 248	99.57 49	66.26 477	99.84 174	98.71 111	99.95 38	99.54 142

ECVR-MVS		96.42 358	96.61 344	95.85 424	99.38 177	88.18 462	99.22 45	86.00 485	99.08 112	99.36 123	99.57 49	88.47 401	99.82 205	98.52 126	99.95 38	99.54 142

casdiffmvs		98.95 95	99.00 90	98.81 183	99.38 177	97.33 218	97.82 238	99.57 99	99.17 92	99.35 125	99.17 160	98.35 89	99.69 312	98.46 128	99.73 183	99.41 213
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 94	99.02 86	98.76 200	99.38 177	97.26 227	98.49 139	99.50 130	98.86 139	99.19 164	99.06 186	98.23 104	99.69 312	98.71 111	99.76 175	99.33 254

TranMVSNet+NR-MVSNet		99.17 53	99.07 81	99.46 63	99.37 183	98.87 85	98.39 154	99.42 177	99.42 56	99.36 123	99.06 186	98.38 84	99.95 26	98.34 137	99.90 86	99.57 123

fmvsm_s_conf0.5_n_6		99.08 77	99.21 58	98.69 214	99.36 184	96.51 279	97.62 272	99.68 60	98.43 175	99.85 27	99.10 178	99.12 23	99.88 115	99.77 22	99.92 69	99.67 76

tttt0517		95.64 384	94.98 394	97.64 345	99.36 184	93.81 391	98.72 103	90.47 477	98.08 216	98.67 259	98.34 345	73.88 463	99.92 65	97.77 183	99.51 281	99.20 293

test_part2					99.36 184	99.10 66				99.05 187

v1144		98.60 167	98.66 141	98.41 267	99.36 184	95.90 302	97.58 281	99.34 208	97.51 264	99.27 144	99.15 166	96.34 257	99.80 231	99.47 54	99.93 56	99.51 160

CP-MVS		98.70 142	98.42 184	99.52 45	99.36 184	99.12 63	98.72 103	99.36 196	97.54 262	98.30 301	98.40 337	97.86 145	99.89 97	96.53 301	99.72 191	99.56 129

diffmvs_AUTHOR		98.50 188	98.59 155	98.23 291	99.35 189	95.48 321	96.61 363	99.60 82	98.37 177	98.90 221	99.00 213	97.37 191	99.76 267	98.22 144	99.85 107	99.46 192

Test_1112_low_res		96.99 337	96.55 348	98.31 280	99.35 189	95.47 324	95.84 413	99.53 121	91.51 450	96.80 405	98.48 330	91.36 374	99.83 192	96.58 290	99.53 275	99.62 90

DeepC-MVS	97.60 4	98.97 92	98.93 97	99.10 128	99.35 189	97.98 162	98.01 207	99.46 153	97.56 258	99.54 79	99.50 69	98.97 28	99.84 174	98.06 156	99.92 69	99.49 171
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 314	96.86 326	98.58 235	99.34 192	96.32 288	96.75 355	99.58 92	93.14 431	96.89 400	97.48 403	92.11 366	99.86 143	96.91 252	99.54 271	99.57 123

reproduce_model		99.15 58	98.97 94	99.67 4	99.33 193	99.44 10	98.15 178	99.47 149	99.12 97	99.52 88	99.32 119	98.31 92	99.90 81	97.78 182	99.73 183	99.66 78

MVSMamba_PlusPlus		98.83 117	98.98 93	98.36 275	99.32 194	96.58 275	98.90 83	99.41 181	99.75 11	98.72 254	99.50 69	96.17 262	99.94 42	99.27 65	99.78 154	98.57 395

fmvsm_s_conf0.5_n_4		99.01 85	99.22 55	98.38 271	99.31 195	95.48 321	97.56 283	99.73 44	98.87 137	99.75 45	99.27 127	98.80 40	99.86 143	99.80 17	99.90 86	99.81 40

SF-MVS		98.53 182	98.27 211	99.32 91	99.31 195	98.75 91	98.19 172	99.41 181	96.77 331	98.83 236	98.90 239	97.80 151	99.82 205	95.68 347	99.52 278	99.38 232

CPTT-MVS		97.84 272	97.36 296	99.27 99	99.31 195	98.46 115	98.29 161	99.27 244	94.90 399	97.83 343	98.37 341	94.90 307	99.84 174	93.85 398	99.54 271	99.51 160

UnsupCasMVSNet_eth		97.89 261	97.60 282	98.75 202	99.31 195	97.17 239	97.62 272	99.35 202	98.72 150	98.76 250	98.68 295	92.57 359	99.74 281	97.76 187	95.60 468	99.34 248

fmvsm_s_conf0.5_n_7		98.83 117	99.04 83	98.20 293	99.30 199	94.83 348	97.23 324	99.36 196	98.64 153	99.84 30	99.43 89	98.10 121	99.91 74	99.56 41	99.96 28	99.87 22

pmmvs-eth3d		98.47 191	98.34 197	98.86 174	99.30 199	97.76 189	97.16 334	99.28 241	95.54 381	99.42 110	99.19 152	97.27 198	99.63 353	97.89 171	99.97 21	99.20 293

mamv4		99.44 19	99.39 28	99.58 21	99.30 199	99.74 2	99.04 68	99.81 31	99.77 10	99.82 34	99.57 49	97.82 149	99.98 4	99.53 48	99.89 92	99.01 328

viewcassd2359sk11		98.55 177	98.51 165	98.67 217	99.29 202	96.99 250	97.39 305	99.54 117	97.73 241	98.81 241	99.08 184	97.55 173	99.66 339	97.52 206	99.67 221	99.36 241

SymmetryMVS		98.05 247	97.71 272	99.09 132	99.29 202	97.83 178	98.28 162	97.64 403	99.24 76	98.80 243	98.85 252	89.76 388	99.94 42	98.04 158	99.50 289	99.49 171

Anonymous20231211		99.27 38	99.27 48	99.26 101	99.29 202	98.18 137	99.49 12	99.51 127	99.70 16	99.80 38	99.68 25	96.84 224	99.83 192	99.21 71	99.91 78	99.77 50

viewmanbaseed2359cas		98.58 171	98.54 161	98.70 212	99.28 205	97.13 243	97.47 298	99.55 112	97.55 260	98.96 208	98.92 233	97.77 153	99.59 370	97.59 200	99.77 160	99.39 223

UnsupCasMVSNet_bld		97.30 312	96.92 322	98.45 262	99.28 205	96.78 266	96.20 389	99.27 244	95.42 385	98.28 305	98.30 349	93.16 345	99.71 299	94.99 361	97.37 443	98.87 356

EC-MVSNet		99.09 73	99.05 82	99.20 110	99.28 205	98.93 80	99.24 44	99.84 22	99.08 112	98.12 318	98.37 341	98.72 49	99.90 81	99.05 84	99.77 160	98.77 373

mamba_0408		98.80 124	98.88 103	98.55 245	99.27 208	96.50 280	98.00 208	99.60 82	98.93 129	99.22 159	98.84 257	98.59 64	99.89 97	97.74 188	99.72 191	99.27 271

SSM_04072		98.80 124	98.88 103	98.56 243	99.27 208	96.50 280	98.00 208	99.60 82	98.93 129	99.22 159	98.84 257	98.59 64	99.90 81	97.74 188	99.72 191	99.27 271

SSM_0407		98.86 111	98.96 96	98.55 245	99.27 208	96.50 280	98.04 199	99.66 65	99.09 108	99.22 159	99.02 198	98.79 42	99.87 134	97.87 176	99.72 191	99.27 271

reproduce-ours		99.09 73	98.90 100	99.67 4	99.27 208	99.49 6	98.00 208	99.42 177	99.05 115	99.48 96	99.27 127	98.29 94	99.89 97	97.61 197	99.71 200	99.62 90

our_new_method		99.09 73	98.90 100	99.67 4	99.27 208	99.49 6	98.00 208	99.42 177	99.05 115	99.48 96	99.27 127	98.29 94	99.89 97	97.61 197	99.71 200	99.62 90

DPE-MVS		98.59 169	98.26 212	99.57 22	99.27 208	99.15 53	97.01 339	99.39 186	97.67 245	99.44 105	98.99 215	97.53 177	99.89 97	95.40 355	99.68 215	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		97.85 271	98.18 224	96.87 393	99.27 208	91.16 442	95.53 423	99.25 250	99.10 105	99.41 112	99.35 107	93.10 347	99.96 14	98.65 115	99.94 50	99.49 171

v1192		98.60 167	98.66 141	98.41 267	99.27 208	95.88 303	97.52 288	99.36 196	97.41 277	99.33 130	99.20 149	96.37 255	99.82 205	99.57 39	99.92 69	99.55 136

N_pmnet		97.63 285	97.17 306	98.99 151	99.27 208	97.86 175	95.98 400	93.41 466	95.25 390	99.47 100	98.90 239	95.63 288	99.85 156	96.91 252	99.73 183	99.27 271

viewdifsd2359ckpt13		98.39 205	98.29 207	98.70 212	99.26 217	97.19 235	97.51 290	99.48 140	96.94 318	98.58 275	98.82 262	97.47 186	99.55 386	97.21 227	99.33 317	99.34 248

FPMVS		93.44 422	92.23 429	97.08 381	99.25 218	97.86 175	95.61 420	97.16 415	92.90 435	93.76 468	98.65 302	75.94 461	95.66 482	79.30 480	97.49 436	97.73 446

ME-MVS		98.61 165	98.33 202	99.44 66	99.24 219	98.93 80	97.45 300	99.06 291	98.14 211	99.06 179	98.77 272	96.97 218	99.82 205	96.67 281	99.64 232	99.58 115

new-patchmatchnet		98.35 208	98.74 121	97.18 376	99.24 219	92.23 424	96.42 376	99.48 140	98.30 185	99.69 56	99.53 65	97.44 187	99.82 205	98.84 100	99.77 160	99.49 171

MCST-MVS		98.00 252	97.63 280	99.10 128	99.24 219	98.17 138	96.89 348	98.73 355	95.66 376	97.92 334	97.70 391	97.17 205	99.66 339	96.18 323	99.23 336	99.47 190

UniMVSNet (Re)		98.87 107	98.71 130	99.35 80	99.24 219	98.73 95	97.73 256	99.38 188	98.93 129	99.12 171	98.73 281	96.77 232	99.86 143	98.63 117	99.80 143	99.46 192

jason		97.45 299	97.35 297	97.76 329	99.24 219	93.93 385	95.86 410	98.42 374	94.24 414	98.50 287	98.13 359	94.82 311	99.91 74	97.22 226	99.73 183	99.43 205
jason: jason.
IterMVS		97.73 277	98.11 233	96.57 403	99.24 219	90.28 451	95.52 425	99.21 259	98.86 139	99.33 130	99.33 114	93.11 346	99.94 42	98.49 127	99.94 50	99.48 182
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 177	98.62 148	98.32 278	99.22 225	95.58 314	97.51 290	99.45 157	97.16 306	99.45 104	99.24 140	96.12 266	99.85 156	99.60 37	99.88 94	99.55 136

ITE_SJBPF				98.87 172	99.22 225	98.48 114		99.35 202	97.50 265	98.28 305	98.60 313	97.64 164	99.35 433	93.86 397	99.27 328	98.79 371

h-mvs33		97.77 275	97.33 299	99.10 128	99.21 227	97.84 177	98.35 158	98.57 366	99.11 98	98.58 275	99.02 198	88.65 399	99.96 14	98.11 151	96.34 459	99.49 171

v144192		98.54 180	98.57 157	98.45 262	99.21 227	95.98 300	97.63 271	99.36 196	97.15 308	99.32 136	99.18 156	95.84 283	99.84 174	99.50 51	99.91 78	99.54 142

APDe-MVS		98.99 88	98.79 117	99.60 16	99.21 227	99.15 53	98.87 88	99.48 140	97.57 256	99.35 125	99.24 140	97.83 146	99.89 97	97.88 174	99.70 207	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 98	98.81 116	99.28 96	99.21 227	98.45 116	98.46 144	99.33 214	99.63 29	99.48 96	99.15 166	97.23 201	99.75 275	97.17 229	99.66 229	99.63 89

SR-MVS-dyc-post		98.81 122	98.55 159	99.57 22	99.20 231	99.38 13	98.48 142	99.30 229	98.64 153	98.95 209	98.96 225	97.49 184	99.86 143	96.56 296	99.39 308	99.45 197

RE-MVS-def			98.58 156		99.20 231	99.38 13	98.48 142	99.30 229	98.64 153	98.95 209	98.96 225	97.75 155		96.56 296	99.39 308	99.45 197

v1921920		98.54 180	98.60 153	98.38 271	99.20 231	95.76 310	97.56 283	99.36 196	97.23 300	99.38 118	99.17 160	96.02 269	99.84 174	99.57 39	99.90 86	99.54 142

E3new		98.41 196	98.34 197	98.62 227	99.19 234	96.90 258	97.32 315	99.50 130	97.40 279	98.63 264	98.92 233	97.21 203	99.65 346	97.34 218	99.52 278	99.31 261

thisisatest0530		95.27 391	94.45 402	97.74 332	99.19 234	94.37 363	97.86 234	90.20 478	97.17 305	98.22 308	97.65 393	73.53 464	99.90 81	96.90 257	99.35 314	98.95 341

Anonymous20240529		98.93 98	98.87 106	99.12 124	99.19 234	98.22 135	99.01 70	98.99 309	99.25 75	99.54 79	99.37 102	97.04 211	99.80 231	97.89 171	99.52 278	99.35 246

APD-MVS_3200maxsize		98.84 114	98.61 152	99.53 39	99.19 234	99.27 28	98.49 139	99.33 214	98.64 153	99.03 192	98.98 220	97.89 141	99.85 156	96.54 300	99.42 305	99.46 192

HQP_MVS		97.99 255	97.67 274	98.93 164	99.19 234	97.65 197	97.77 247	99.27 244	98.20 199	97.79 346	97.98 373	94.90 307	99.70 306	94.42 379	99.51 281	99.45 197

plane_prior7					99.19 234	97.87 174

ab-mvs		98.41 196	98.36 194	98.59 234	99.19 234	97.23 228	99.32 26	98.81 341	97.66 246	98.62 267	99.40 97	96.82 227	99.80 231	95.88 334	99.51 281	98.75 376

F-COLMAP		97.30 312	96.68 339	99.14 122	99.19 234	98.39 118	97.27 323	99.30 229	92.93 434	96.62 412	98.00 371	95.73 286	99.68 322	92.62 425	98.46 404	99.35 246

viewdifsd2359ckpt09		98.13 240	97.92 256	98.77 198	99.18 242	97.35 216	97.29 319	99.53 121	95.81 373	98.09 321	98.47 331	96.34 257	99.66 339	97.02 242	99.51 281	99.29 267

SR-MVS		98.71 137	98.43 182	99.57 22	99.18 242	99.35 17	98.36 157	99.29 237	98.29 188	98.88 228	98.85 252	97.53 177	99.87 134	96.14 325	99.31 321	99.48 182

UniMVSNet_NR-MVSNet		98.86 111	98.68 136	99.40 72	99.17 244	98.74 92	97.68 261	99.40 184	99.14 96	99.06 179	98.59 314	96.71 238	99.93 54	98.57 120	99.77 160	99.53 153

LF4IMVS		97.90 259	97.69 273	98.52 253	99.17 244	97.66 196	97.19 333	99.47 149	96.31 352	97.85 342	98.20 356	96.71 238	99.52 398	94.62 371	99.72 191	98.38 412

SMA-MVS		98.40 199	98.03 242	99.51 49	99.16 246	99.21 34	98.05 197	99.22 258	94.16 416	98.98 199	99.10 178	97.52 179	99.79 244	96.45 306	99.64 232	99.53 153
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		98.82 120	98.63 146	99.39 73	99.16 246	98.74 92	97.54 286	99.25 250	98.84 143	99.06 179	98.76 278	96.76 234	99.93 54	98.57 120	99.77 160	99.50 164

NR-MVSNet		98.95 95	98.82 114	99.36 74	99.16 246	98.72 97	99.22 45	99.20 261	99.10 105	99.72 48	98.76 278	96.38 254	99.86 143	98.00 163	99.82 126	99.50 164

MVS_111021_LR		98.30 217	98.12 232	98.83 179	99.16 246	98.03 157	96.09 397	99.30 229	97.58 255	98.10 320	98.24 352	98.25 102	99.34 434	96.69 279	99.65 230	99.12 314

DSMNet-mixed		97.42 302	97.60 282	96.87 393	99.15 250	91.46 431	98.54 127	99.12 283	92.87 436	97.58 359	99.63 39	96.21 261	99.90 81	95.74 343	99.54 271	99.27 271

D2MVS		97.84 272	97.84 263	97.83 321	99.14 251	94.74 352	96.94 343	98.88 325	95.84 372	98.89 224	98.96 225	94.40 323	99.69 312	97.55 201	99.95 38	99.05 320

pmmvs5		97.64 284	97.49 288	98.08 304	99.14 251	95.12 339	96.70 358	99.05 295	93.77 423	98.62 267	98.83 259	93.23 343	99.75 275	98.33 139	99.76 175	99.36 241

SPE-MVS-test		99.13 67	99.09 78	99.26 101	99.13 253	98.97 74	99.31 30	99.88 14	99.44 53	98.16 313	98.51 323	98.64 58	99.93 54	98.91 94	99.85 107	98.88 355

VDD-MVS		98.56 173	98.39 189	99.07 135	99.13 253	98.07 152	98.59 121	97.01 418	99.59 37	99.11 172	99.27 127	94.82 311	99.79 244	98.34 137	99.63 239	99.34 248

save fliter					99.11 255	97.97 163	96.53 368	99.02 303	98.24 191

APD-MVS		98.10 241	97.67 274	99.42 68	99.11 255	98.93 80	97.76 250	99.28 241	94.97 397	98.72 254	98.77 272	97.04 211	99.85 156	93.79 399	99.54 271	99.49 171
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 146	98.71 130	98.62 227	99.10 257	96.37 286	97.23 324	98.87 327	99.20 83	99.19 164	98.99 215	97.30 195	99.85 156	98.77 106	99.79 149	99.65 83

EI-MVSNet		98.40 199	98.51 165	98.04 309	99.10 257	94.73 353	97.20 329	98.87 327	98.97 124	99.06 179	99.02 198	96.00 271	99.80 231	98.58 118	99.82 126	99.60 100

CVMVSNet		96.25 364	97.21 305	93.38 460	99.10 257	80.56 488	97.20 329	98.19 385	96.94 318	99.00 194	99.02 198	89.50 392	99.80 231	96.36 312	99.59 253	99.78 47

EI-MVSNet-Vis-set		98.68 152	98.70 133	98.63 225	99.09 260	96.40 285	97.23 324	98.86 332	99.20 83	99.18 168	98.97 222	97.29 197	99.85 156	98.72 110	99.78 154	99.64 84

HPM-MVS++		98.10 241	97.64 279	99.48 57	99.09 260	99.13 61	97.52 288	98.75 352	97.46 273	96.90 399	97.83 383	96.01 270	99.84 174	95.82 341	99.35 314	99.46 192

DP-MVS Recon		97.33 310	96.92 322	98.57 238	99.09 260	97.99 159	96.79 351	99.35 202	93.18 430	97.71 350	98.07 367	95.00 306	99.31 438	93.97 392	99.13 352	98.42 409

MVS_111021_HR		98.25 226	98.08 237	98.75 202	99.09 260	97.46 210	95.97 401	99.27 244	97.60 254	97.99 331	98.25 351	98.15 118	99.38 429	96.87 260	99.57 262	99.42 210

BP-MVS1		97.40 304	96.97 318	98.71 211	99.07 264	96.81 262	98.34 160	97.18 413	98.58 164	98.17 310	98.61 311	84.01 432	99.94 42	98.97 90	99.78 154	99.37 234

9.14			97.78 265		99.07 264		97.53 287	99.32 216	95.53 382	98.54 283	98.70 291	97.58 170	99.76 267	94.32 384	99.46 294

PAPM_NR		96.82 344	96.32 355	98.30 281	99.07 264	96.69 270	97.48 294	98.76 349	95.81 373	96.61 413	96.47 429	94.12 332	99.17 451	90.82 452	97.78 430	99.06 319

TAMVS		98.24 227	98.05 240	98.80 186	99.07 264	97.18 237	97.88 230	98.81 341	96.66 336	99.17 170	99.21 147	94.81 313	99.77 261	96.96 250	99.88 94	99.44 201

CLD-MVS		97.49 295	97.16 307	98.48 259	99.07 264	97.03 248	94.71 447	99.21 259	94.46 408	98.06 324	97.16 415	97.57 171	99.48 410	94.46 376	99.78 154	98.95 341
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 76	99.24 106	99.06 269	99.15 53	99.36 22	99.88 14	99.36 64	98.21 309	98.46 332	98.68 55	99.93 54	99.03 86	99.85 107	98.64 388

thres100view900		94.19 408	93.67 413	95.75 427	99.06 269	91.35 435	98.03 201	94.24 461	98.33 181	97.40 375	94.98 459	79.84 448	99.62 356	83.05 473	98.08 421	96.29 468

thres600view7		94.45 403	93.83 410	96.29 411	99.06 269	91.53 430	97.99 215	94.24 461	98.34 180	97.44 373	95.01 457	79.84 448	99.67 326	84.33 471	98.23 410	97.66 449

plane_prior1					99.05 272

YYNet1		97.60 286	97.67 274	97.39 369	99.04 273	93.04 408	95.27 432	98.38 377	97.25 294	98.92 219	98.95 229	95.48 295	99.73 288	96.99 246	98.74 385	99.41 213

MDA-MVSNet_test_wron		97.60 286	97.66 277	97.41 368	99.04 273	93.09 404	95.27 432	98.42 374	97.26 293	98.88 228	98.95 229	95.43 296	99.73 288	97.02 242	98.72 387	99.41 213

MIMVSNet		96.62 351	96.25 359	97.71 336	99.04 273	94.66 356	99.16 54	96.92 424	97.23 300	97.87 339	99.10 178	86.11 414	99.65 346	91.65 436	99.21 340	98.82 360

FE-MVSNET3		97.37 306	97.13 311	98.11 300	99.03 276	95.40 327	94.47 457	98.99 309	96.87 324	97.97 332	97.81 384	92.12 365	99.75 275	97.49 212	99.43 304	99.16 309

icg_test_0407_2		98.20 232	98.38 191	97.65 342	99.03 276	94.03 376	95.78 415	99.45 157	98.16 205	99.06 179	98.71 284	98.27 98	99.68 322	97.50 207	99.45 296	99.22 288

IMVS_0407		98.39 205	98.64 144	97.66 340	99.03 276	94.03 376	98.10 187	99.45 157	98.16 205	99.06 179	98.71 284	98.27 98	99.71 299	97.50 207	99.45 296	99.22 288

IMVS_0404		98.07 245	98.20 219	97.69 337	99.03 276	94.03 376	96.67 359	99.45 157	98.16 205	98.03 328	98.71 284	96.80 230	99.82 205	97.50 207	99.45 296	99.22 288

IMVS_0403		98.34 209	98.56 158	97.66 340	99.03 276	94.03 376	97.98 216	99.45 157	98.16 205	98.89 224	98.71 284	97.90 137	99.74 281	97.50 207	99.45 296	99.22 288

PatchMatch-RL		97.24 318	96.78 333	98.61 231	99.03 276	97.83 178	96.36 379	99.06 291	93.49 428	97.36 379	97.78 385	95.75 285	99.49 407	93.44 408	98.77 384	98.52 397

viewmambaseed2359dif		98.19 233	98.26 212	97.99 312	99.02 282	95.03 342	96.59 365	99.53 121	96.21 356	99.00 194	98.99 215	97.62 166	99.61 363	97.62 196	99.72 191	99.33 254

GDP-MVS		97.50 292	97.11 312	98.67 217	99.02 282	96.85 260	98.16 177	99.71 47	98.32 183	98.52 286	98.54 318	83.39 436	99.95 26	98.79 102	99.56 265	99.19 298

ZD-MVS					99.01 284	98.84 86		99.07 290	94.10 418	98.05 326	98.12 361	96.36 256	99.86 143	92.70 424	99.19 344

CDPH-MVS		97.26 315	96.66 342	99.07 135	99.00 285	98.15 139	96.03 399	99.01 306	91.21 454	97.79 346	97.85 382	96.89 222	99.69 312	92.75 422	99.38 311	99.39 223

diffmvs		98.22 228	98.24 216	98.17 296	99.00 285	95.44 325	96.38 378	99.58 92	97.79 238	98.53 284	98.50 327	96.76 234	99.74 281	97.95 169	99.64 232	99.34 248
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		98.40 199	98.19 223	99.03 145	99.00 285	97.65 197	96.85 349	98.94 312	98.57 166	98.89 224	98.50 327	95.60 289	99.85 156	97.54 203	99.85 107	99.59 107

plane_prior6					98.99 288	97.70 195						94.90 307

xiu_mvs_v1_base_debu		97.86 266	98.17 225	96.92 390	98.98 289	93.91 386	96.45 372	99.17 273	97.85 233	98.41 295	97.14 417	98.47 74	99.92 65	98.02 160	99.05 358	96.92 461

xiu_mvs_v1_base		97.86 266	98.17 225	96.92 390	98.98 289	93.91 386	96.45 372	99.17 273	97.85 233	98.41 295	97.14 417	98.47 74	99.92 65	98.02 160	99.05 358	96.92 461

xiu_mvs_v1_base_debi		97.86 266	98.17 225	96.92 390	98.98 289	93.91 386	96.45 372	99.17 273	97.85 233	98.41 295	97.14 417	98.47 74	99.92 65	98.02 160	99.05 358	96.92 461

MVP-Stereo		98.08 244	97.92 256	98.57 238	98.96 292	96.79 263	97.90 228	99.18 269	96.41 348	98.46 290	98.95 229	95.93 280	99.60 366	96.51 302	98.98 372	99.31 261
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 199	98.68 136	97.54 357	98.96 292	97.99 159	97.88 230	99.36 196	98.20 199	99.63 67	99.04 195	98.76 45	95.33 484	96.56 296	99.74 180	99.31 261
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	98.94 294	97.76 189		98.76 349	87.58 471	96.75 407	98.10 363	94.80 314	99.78 255	92.73 423	99.00 367	99.20 293

USDC		97.41 303	97.40 292	97.44 366	98.94 294	93.67 396	95.17 436	99.53 121	94.03 420	98.97 203	99.10 178	95.29 298	99.34 434	95.84 340	99.73 183	99.30 265

tfpn200view9		94.03 412	93.44 415	95.78 426	98.93 296	91.44 433	97.60 278	94.29 459	97.94 225	97.10 385	94.31 466	79.67 450	99.62 356	83.05 473	98.08 421	96.29 468

testdata				98.09 301	98.93 296	95.40 327		98.80 343	90.08 462	97.45 372	98.37 341	95.26 299	99.70 306	93.58 404	98.95 375	99.17 305

thres400		94.14 410	93.44 415	96.24 414	98.93 296	91.44 433	97.60 278	94.29 459	97.94 225	97.10 385	94.31 466	79.67 450	99.62 356	83.05 473	98.08 421	97.66 449

TAPA-MVS	96.21 11	96.63 350	95.95 361	98.65 219	98.93 296	98.09 146	96.93 345	99.28 241	83.58 477	98.13 317	97.78 385	96.13 264	99.40 425	93.52 405	99.29 326	98.45 402
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 300	96.93 256	95.54 422	98.78 346	85.72 474	96.86 402	98.11 362	94.43 321			99.10 357	99.23 283

PVSNet_BlendedMVS		97.55 291	97.53 285	97.60 349	98.92 300	93.77 393	96.64 361	99.43 171	94.49 406	97.62 355	99.18 156	96.82 227	99.67 326	94.73 368	99.93 56	99.36 241

PVSNet_Blended		96.88 340	96.68 339	97.47 364	98.92 300	93.77 393	94.71 447	99.43 171	90.98 456	97.62 355	97.36 411	96.82 227	99.67 326	94.73 368	99.56 265	98.98 334

MSDG		97.71 279	97.52 286	98.28 283	98.91 303	96.82 261	94.42 458	99.37 192	97.65 247	98.37 300	98.29 350	97.40 189	99.33 436	94.09 390	99.22 337	98.68 386

Anonymous202405211		97.90 259	97.50 287	99.08 133	98.90 304	98.25 129	98.53 128	96.16 436	98.87 137	99.11 172	98.86 249	90.40 384	99.78 255	97.36 217	99.31 321	99.19 298

原ACMM1				98.35 276	98.90 304	96.25 290		98.83 340	92.48 440	96.07 430	98.10 363	95.39 297	99.71 299	92.61 426	98.99 369	99.08 316

GBi-Net		98.65 157	98.47 176	99.17 115	98.90 304	98.24 130	99.20 48	99.44 165	98.59 161	98.95 209	99.55 57	94.14 329	99.86 143	97.77 183	99.69 210	99.41 213

test1		98.65 157	98.47 176	99.17 115	98.90 304	98.24 130	99.20 48	99.44 165	98.59 161	98.95 209	99.55 57	94.14 329	99.86 143	97.77 183	99.69 210	99.41 213

FMVSNet2		98.49 189	98.40 186	98.75 202	98.90 304	97.14 242	98.61 119	99.13 282	98.59 161	99.19 164	99.28 125	94.14 329	99.82 205	97.97 167	99.80 143	99.29 267

OMC-MVS		97.88 263	97.49 288	99.04 144	98.89 309	98.63 99	96.94 343	99.25 250	95.02 395	98.53 284	98.51 323	97.27 198	99.47 413	93.50 407	99.51 281	99.01 328

VortexMVS		97.98 256	98.31 204	97.02 384	98.88 310	91.45 432	98.03 201	99.47 149	98.65 152	99.55 77	99.47 79	91.49 373	99.81 222	99.32 61	99.91 78	99.80 42

MVSFormer		98.26 223	98.43 182	97.77 326	98.88 310	93.89 389	99.39 20	99.56 108	99.11 98	98.16 313	98.13 359	93.81 337	99.97 7	99.26 66	99.57 262	99.43 205

lupinMVS		97.06 330	96.86 326	97.65 342	98.88 310	93.89 389	95.48 426	97.97 391	93.53 426	98.16 313	97.58 397	93.81 337	99.91 74	96.77 268	99.57 262	99.17 305

dmvs_re		95.98 373	95.39 383	97.74 332	98.86 313	97.45 211	98.37 156	95.69 448	97.95 223	96.56 414	95.95 438	90.70 381	97.68 478	88.32 461	96.13 463	98.11 424

DELS-MVS		98.27 221	98.20 219	98.48 259	98.86 313	96.70 269	95.60 421	99.20 261	97.73 241	98.45 291	98.71 284	97.50 181	99.82 205	98.21 145	99.59 253	98.93 346
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		97.89 261	97.98 247	97.60 349	98.86 313	94.35 364	96.21 388	99.44 165	97.45 275	99.06 179	98.88 246	97.99 131	99.28 444	94.38 383	99.58 258	99.18 301

LCM-MVSNet-Re		98.64 159	98.48 174	99.11 126	98.85 316	98.51 112	98.49 139	99.83 25	98.37 177	99.69 56	99.46 81	98.21 109	99.92 65	94.13 389	99.30 324	98.91 350

pmmvs4		97.58 289	97.28 300	98.51 254	98.84 317	96.93 256	95.40 430	98.52 369	93.60 425	98.61 269	98.65 302	95.10 303	99.60 366	96.97 249	99.79 149	98.99 333

NP-MVS					98.84 317	97.39 215					96.84 420

sss		97.21 320	96.93 320	98.06 306	98.83 319	95.22 335	96.75 355	98.48 371	94.49 406	97.27 381	97.90 379	92.77 355	99.80 231	96.57 292	99.32 319	99.16 309

PVSNet	93.40 17	95.67 382	95.70 367	95.57 431	98.83 319	88.57 458	92.50 475	97.72 396	92.69 438	96.49 422	96.44 430	93.72 340	99.43 421	93.61 402	99.28 327	98.71 379

MVE	83.40 22	92.50 435	91.92 437	94.25 447	98.83 319	91.64 429	92.71 474	83.52 487	95.92 370	86.46 485	95.46 451	95.20 300	95.40 483	80.51 478	98.64 396	95.73 476
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 416	93.91 408	93.39 459	98.82 322	81.72 486	97.76 250	95.28 450	98.60 160	96.54 415	96.66 424	65.85 480	99.62 356	96.65 285	98.99 369	98.82 360

ambc				98.24 288	98.82 322	95.97 301	98.62 117	99.00 308		99.27 144	99.21 147	96.99 216	99.50 404	96.55 299	99.50 289	99.26 277

旧先验1					98.82 322	97.45 211		98.76 349			98.34 345	95.50 294			99.01 366	99.23 283

test_vis1_rt		97.75 276	97.72 271	97.83 321	98.81 325	96.35 287	97.30 318	99.69 54	94.61 404	97.87 339	98.05 368	96.26 260	98.32 472	98.74 108	98.18 413	98.82 360

WTY-MVS		96.67 348	96.27 358	97.87 319	98.81 325	94.61 358	96.77 353	97.92 393	94.94 398	97.12 384	97.74 388	91.11 377	99.82 205	93.89 395	98.15 417	99.18 301

3Dnovator+	97.89 3	98.69 146	98.51 165	99.24 106	98.81 325	98.40 117	99.02 69	99.19 265	98.99 121	98.07 323	99.28 125	97.11 209	99.84 174	96.84 263	99.32 319	99.47 190

QAPM		97.31 311	96.81 332	98.82 181	98.80 328	97.49 205	99.06 65	99.19 265	90.22 460	97.69 352	99.16 162	96.91 221	99.90 81	90.89 451	99.41 306	99.07 318

VNet		98.42 195	98.30 205	98.79 190	98.79 329	97.29 224	98.23 168	98.66 359	99.31 69	98.85 233	98.80 266	94.80 314	99.78 255	98.13 150	99.13 352	99.31 261

DPM-MVS		96.32 360	95.59 374	98.51 254	98.76 330	97.21 233	94.54 456	98.26 380	91.94 445	96.37 423	97.25 413	93.06 349	99.43 421	91.42 441	98.74 385	98.89 352

3Dnovator	98.27 2	98.81 122	98.73 123	99.05 142	98.76 330	97.81 186	99.25 43	99.30 229	98.57 166	98.55 281	99.33 114	97.95 134	99.90 81	97.16 230	99.67 221	99.44 201

PLC	94.65 16	96.51 353	95.73 366	98.85 175	98.75 332	97.91 171	96.42 376	99.06 291	90.94 457	95.59 437	97.38 409	94.41 322	99.59 370	90.93 449	98.04 426	99.05 320
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 342	96.75 335	97.08 381	98.74 333	93.33 402	96.71 357	98.26 380	96.72 333	98.44 292	97.37 410	95.20 300	99.47 413	91.89 431	97.43 440	98.44 405

hse-mvs2		97.46 297	97.07 313	98.64 221	98.73 334	97.33 218	97.45 300	97.64 403	99.11 98	98.58 275	97.98 373	88.65 399	99.79 244	98.11 151	97.39 442	98.81 365

CDS-MVSNet		97.69 280	97.35 297	98.69 214	98.73 334	97.02 249	96.92 347	98.75 352	95.89 371	98.59 273	98.67 297	92.08 367	99.74 281	96.72 274	99.81 132	99.32 257
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SD_0403		96.28 362	95.83 363	97.64 345	98.72 336	94.30 365	98.87 88	98.77 347	97.80 236	96.53 416	98.02 370	97.34 193	99.47 413	76.93 482	99.48 292	99.16 309

EIA-MVS		98.00 252	97.74 268	98.80 186	98.72 336	98.09 146	98.05 197	99.60 82	97.39 280	96.63 411	95.55 446	97.68 158	99.80 231	96.73 273	99.27 328	98.52 397

LFMVS		97.20 321	96.72 336	98.64 221	98.72 336	96.95 254	98.93 81	94.14 463	99.74 13	98.78 245	99.01 209	84.45 427	99.73 288	97.44 213	99.27 328	99.25 278

new_pmnet		96.99 337	96.76 334	97.67 338	98.72 336	94.89 347	95.95 405	98.20 383	92.62 439	98.55 281	98.54 318	94.88 310	99.52 398	93.96 393	99.44 303	98.59 394

Fast-Effi-MVS+		97.67 282	97.38 294	98.57 238	98.71 340	97.43 213	97.23 324	99.45 157	94.82 401	96.13 427	96.51 426	98.52 72	99.91 74	96.19 321	98.83 381	98.37 414

TEST9					98.71 340	98.08 150	95.96 403	99.03 300	91.40 451	95.85 434	97.53 399	96.52 247	99.76 267

train_agg		97.10 327	96.45 352	99.07 135	98.71 340	98.08 150	95.96 403	99.03 300	91.64 446	95.85 434	97.53 399	96.47 249	99.76 267	93.67 401	99.16 347	99.36 241

TSAR-MVS + GP.		98.18 235	97.98 247	98.77 198	98.71 340	97.88 173	96.32 382	98.66 359	96.33 350	99.23 158	98.51 323	97.48 185	99.40 425	97.16 230	99.46 294	99.02 327

FA-MVS(test-final)		96.99 337	96.82 330	97.50 361	98.70 344	94.78 350	99.34 23	96.99 419	95.07 394	98.48 289	99.33 114	88.41 402	99.65 346	96.13 327	98.92 378	98.07 427

AUN-MVS		96.24 366	95.45 379	98.60 233	98.70 344	97.22 231	97.38 307	97.65 401	95.95 369	95.53 444	97.96 377	82.11 444	99.79 244	96.31 314	97.44 439	98.80 370

our_test_3		97.39 305	97.73 270	96.34 409	98.70 344	89.78 454	94.61 453	98.97 311	96.50 341	99.04 189	98.85 252	95.98 276	99.84 174	97.26 224	99.67 221	99.41 213

ppachtmachnet_test		97.50 292	97.74 268	96.78 399	98.70 344	91.23 441	94.55 455	99.05 295	96.36 349	99.21 162	98.79 268	96.39 252	99.78 255	96.74 271	99.82 126	99.34 248

PCF-MVS	92.86 18	94.36 404	93.00 422	98.42 266	98.70 344	97.56 202	93.16 473	99.11 285	79.59 481	97.55 362	97.43 406	92.19 363	99.73 288	79.85 479	99.45 296	97.97 433
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 258	98.02 243	97.58 351	98.69 349	94.10 372	98.13 180	98.90 321	97.95 223	97.32 380	99.58 47	95.95 279	98.75 467	96.41 308	99.22 337	99.87 22

ETV-MVS		98.03 248	97.86 262	98.56 243	98.69 349	98.07 152	97.51 290	99.50 130	98.10 213	97.50 367	95.51 447	98.41 81	99.88 115	96.27 317	99.24 333	97.71 448

test_prior				98.95 160	98.69 349	97.95 167		99.03 300					99.59 370			99.30 265

mvsmamba		97.57 290	97.26 301	98.51 254	98.69 349	96.73 268	98.74 98	97.25 412	97.03 314	97.88 338	99.23 145	90.95 378	99.87 134	96.61 288	99.00 367	98.91 350

agg_prior					98.68 353	97.99 159		99.01 306		95.59 437			99.77 261

test_8					98.67 354	98.01 158	95.91 409	99.02 303	91.64 446	95.79 436	97.50 402	96.47 249	99.76 267

HQP-NCC					98.67 354		96.29 384		96.05 362	95.55 440

ACMP_Plane					98.67 354		96.29 384		96.05 362	95.55 440

CNVR-MVS		98.17 237	97.87 261	99.07 135	98.67 354	98.24 130	97.01 339	98.93 315	97.25 294	97.62 355	98.34 345	97.27 198	99.57 379	96.42 307	99.33 317	99.39 223

HQP-MVS		97.00 336	96.49 351	98.55 245	98.67 354	96.79 263	96.29 384	99.04 298	96.05 362	95.55 440	96.84 420	93.84 335	99.54 392	92.82 419	99.26 331	99.32 257

MM		98.22 228	97.99 246	98.91 168	98.66 359	96.97 251	97.89 229	94.44 457	99.54 41	98.95 209	99.14 169	93.50 341	99.92 65	99.80 17	99.96 28	99.85 30

test_fmvs1		97.72 278	97.94 253	97.07 383	98.66 359	92.39 419	97.68 261	99.81 31	95.20 393	99.54 79	99.44 86	91.56 372	99.41 424	99.78 21	99.77 160	99.40 222

balanced_conf03		98.63 161	98.72 125	98.38 271	98.66 359	96.68 271	98.90 83	99.42 177	98.99 121	98.97 203	99.19 152	95.81 284	99.85 156	98.77 106	99.77 160	98.60 391

thres200		93.72 418	93.14 420	95.46 435	98.66 359	91.29 437	96.61 363	94.63 456	97.39 280	96.83 403	93.71 469	79.88 447	99.56 382	82.40 476	98.13 418	95.54 477

wuyk23d		96.06 369	97.62 281	91.38 464	98.65 363	98.57 106	98.85 92	96.95 422	96.86 326	99.90 14	99.16 162	99.18 19	98.40 471	89.23 459	99.77 160	77.18 484

NCCC		97.86 266	97.47 291	99.05 142	98.61 364	98.07 152	96.98 341	98.90 321	97.63 248	97.04 389	97.93 378	95.99 275	99.66 339	95.31 356	98.82 383	99.43 205

DeepC-MVS_fast	96.85 6	98.30 217	98.15 229	98.75 202	98.61 364	97.23 228	97.76 250	99.09 288	97.31 288	98.75 251	98.66 300	97.56 172	99.64 350	96.10 328	99.55 269	99.39 223
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 420	92.09 431	97.75 330	98.60 366	94.40 362	97.32 315	95.26 451	97.56 258	96.79 406	95.50 448	53.57 489	99.77 261	95.26 357	98.97 373	99.08 316

thisisatest0515		94.12 411	93.16 419	96.97 388	98.60 366	92.90 409	93.77 469	90.61 476	94.10 418	96.91 396	95.87 441	74.99 462	99.80 231	94.52 374	99.12 355	98.20 420

GA-MVS		95.86 376	95.32 386	97.49 362	98.60 366	94.15 371	93.83 468	97.93 392	95.49 383	96.68 409	97.42 407	83.21 437	99.30 440	96.22 319	98.55 402	99.01 328

dmvs_testset		92.94 430	92.21 430	95.13 439	98.59 369	90.99 444	97.65 267	92.09 472	96.95 317	94.00 464	93.55 470	92.34 361	96.97 481	72.20 483	92.52 478	97.43 456

OPU-MVS				98.82 181	98.59 369	98.30 126	98.10 187				98.52 322	98.18 112	98.75 467	94.62 371	99.48 292	99.41 213

MSLP-MVS++		98.02 249	98.14 231	97.64 345	98.58 371	95.19 336	97.48 294	99.23 257	97.47 268	97.90 336	98.62 309	97.04 211	98.81 465	97.55 201	99.41 306	98.94 345

test12				98.93 164	98.58 371	97.83 178		98.66 359		96.53 416		95.51 293	99.69 312		99.13 352	99.27 271

CL-MVSNet_self_test		97.44 300	97.22 304	98.08 304	98.57 373	95.78 309	94.30 461	98.79 344	96.58 339	98.60 271	98.19 357	94.74 317	99.64 350	96.41 308	98.84 380	98.82 360

PS-MVSNAJ		97.08 329	97.39 293	96.16 420	98.56 374	92.46 417	95.24 434	98.85 335	97.25 294	97.49 368	95.99 437	98.07 122	99.90 81	96.37 310	98.67 395	96.12 473

CNLPA		97.17 324	96.71 337	98.55 245	98.56 374	98.05 156	96.33 381	98.93 315	96.91 322	97.06 388	97.39 408	94.38 324	99.45 418	91.66 435	99.18 346	98.14 423

xiu_mvs_v2_base		97.16 325	97.49 288	96.17 418	98.54 376	92.46 417	95.45 427	98.84 336	97.25 294	97.48 369	96.49 427	98.31 92	99.90 81	96.34 313	98.68 394	96.15 472

alignmvs		97.35 308	96.88 325	98.78 193	98.54 376	98.09 146	97.71 257	97.69 398	99.20 83	97.59 358	95.90 440	88.12 404	99.55 386	98.18 147	98.96 374	98.70 382

FE-MVS		95.66 383	94.95 396	97.77 326	98.53 378	95.28 332	99.40 19	96.09 439	93.11 432	97.96 333	99.26 133	79.10 454	99.77 261	92.40 428	98.71 389	98.27 418

Effi-MVS+		98.02 249	97.82 264	98.62 227	98.53 378	97.19 235	97.33 314	99.68 60	97.30 289	96.68 409	97.46 405	98.56 70	99.80 231	96.63 286	98.20 412	98.86 357

baseline1		95.96 374	95.44 380	97.52 359	98.51 380	93.99 383	98.39 154	96.09 439	98.21 195	98.40 299	97.76 387	86.88 406	99.63 353	95.42 354	89.27 481	98.95 341

MVS_Test		98.18 235	98.36 194	97.67 338	98.48 381	94.73 353	98.18 173	99.02 303	97.69 244	98.04 327	99.11 175	97.22 202	99.56 382	98.57 120	98.90 379	98.71 379

MGCFI-Net		98.34 209	98.28 208	98.51 254	98.47 382	97.59 201	98.96 77	99.48 140	99.18 91	97.40 375	95.50 448	98.66 56	99.50 404	98.18 147	98.71 389	98.44 405

BH-RMVSNet		96.83 342	96.58 347	97.58 351	98.47 382	94.05 373	96.67 359	97.36 407	96.70 335	97.87 339	97.98 373	95.14 302	99.44 420	90.47 454	98.58 401	99.25 278

sasdasda		98.34 209	98.26 212	98.58 235	98.46 384	97.82 183	98.96 77	99.46 153	99.19 88	97.46 370	95.46 451	98.59 64	99.46 416	98.08 154	98.71 389	98.46 399

canonicalmvs		98.34 209	98.26 212	98.58 235	98.46 384	97.82 183	98.96 77	99.46 153	99.19 88	97.46 370	95.46 451	98.59 64	99.46 416	98.08 154	98.71 389	98.46 399

MVS-HIRNet		94.32 405	95.62 370	90.42 465	98.46 384	75.36 489	96.29 384	89.13 480	95.25 390	95.38 446	99.75 16	92.88 352	99.19 450	94.07 391	99.39 308	96.72 466

PHI-MVS		98.29 220	97.95 251	99.34 83	98.44 387	99.16 49	98.12 184	99.38 188	96.01 366	98.06 324	98.43 335	97.80 151	99.67 326	95.69 346	99.58 258	99.20 293

DVP-MVS++		98.90 102	98.70 133	99.51 49	98.43 388	99.15 53	99.43 15	99.32 216	98.17 202	99.26 148	99.02 198	98.18 112	99.88 115	97.07 239	99.45 296	99.49 171

MSC_two_6792asdad				99.32 91	98.43 388	98.37 121		98.86 332					99.89 97	97.14 233	99.60 249	99.71 63

No_MVS				99.32 91	98.43 388	98.37 121		98.86 332					99.89 97	97.14 233	99.60 249	99.71 63

Fast-Effi-MVS+-dtu		98.27 221	98.09 234	98.81 183	98.43 388	98.11 143	97.61 277	99.50 130	98.64 153	97.39 377	97.52 401	98.12 120	99.95 26	96.90 257	98.71 389	98.38 412

OpenMVS_ROB	95.38 14	95.84 378	95.18 391	97.81 323	98.41 392	97.15 241	97.37 311	98.62 363	83.86 476	98.65 262	98.37 341	94.29 327	99.68 322	88.41 460	98.62 399	96.60 467

DeepPCF-MVS	96.93 5	98.32 214	98.01 244	99.23 108	98.39 393	98.97 74	95.03 440	99.18 269	96.88 323	99.33 130	98.78 270	98.16 116	99.28 444	96.74 271	99.62 242	99.44 201

Patchmatch-test		96.55 352	96.34 354	97.17 378	98.35 394	93.06 405	98.40 153	97.79 394	97.33 285	98.41 295	98.67 297	83.68 435	99.69 312	95.16 359	99.31 321	98.77 373

AdaColmap		97.14 326	96.71 337	98.46 261	98.34 395	97.80 187	96.95 342	98.93 315	95.58 380	96.92 394	97.66 392	95.87 282	99.53 394	90.97 448	99.14 350	98.04 428

OpenMVS	96.65 7	97.09 328	96.68 339	98.32 278	98.32 396	97.16 240	98.86 91	99.37 192	89.48 464	96.29 425	99.15 166	96.56 245	99.90 81	92.90 416	99.20 341	97.89 436

MG-MVS		96.77 345	96.61 344	97.26 374	98.31 397	93.06 405	95.93 406	98.12 388	96.45 347	97.92 334	98.73 281	93.77 339	99.39 427	91.19 446	99.04 361	99.33 254

test_yl		96.69 346	96.29 356	97.90 315	98.28 398	95.24 333	97.29 319	97.36 407	98.21 195	98.17 310	97.86 380	86.27 410	99.55 386	94.87 365	98.32 406	98.89 352

DCV-MVSNet		96.69 346	96.29 356	97.90 315	98.28 398	95.24 333	97.29 319	97.36 407	98.21 195	98.17 310	97.86 380	86.27 410	99.55 386	94.87 365	98.32 406	98.89 352

CHOSEN 280x420		95.51 388	95.47 377	95.65 430	98.25 400	88.27 461	93.25 472	98.88 325	93.53 426	94.65 455	97.15 416	86.17 412	99.93 54	97.41 215	99.93 56	98.73 378

SCA		96.41 359	96.66 342	95.67 428	98.24 401	88.35 460	95.85 412	96.88 425	96.11 360	97.67 353	98.67 297	93.10 347	99.85 156	94.16 385	99.22 337	98.81 365

DeepMVS_CX				93.44 458	98.24 401	94.21 368		94.34 458	64.28 484	91.34 478	94.87 463	89.45 393	92.77 485	77.54 481	93.14 477	93.35 480

MS-PatchMatch		97.68 281	97.75 267	97.45 365	98.23 403	93.78 392	97.29 319	98.84 336	96.10 361	98.64 263	98.65 302	96.04 268	99.36 430	96.84 263	99.14 350	99.20 293

BH-w/o		95.13 394	94.89 398	95.86 423	98.20 404	91.31 436	95.65 419	97.37 406	93.64 424	96.52 418	95.70 444	93.04 350	99.02 456	88.10 462	95.82 467	97.24 459

mvs_anonymous		97.83 274	98.16 228	96.87 393	98.18 405	91.89 426	97.31 317	98.90 321	97.37 282	98.83 236	99.46 81	96.28 259	99.79 244	98.90 95	98.16 416	98.95 341

miper_lstm_enhance		97.18 323	97.16 307	97.25 375	98.16 406	92.85 410	95.15 438	99.31 221	97.25 294	98.74 253	98.78 270	90.07 385	99.78 255	97.19 228	99.80 143	99.11 315

RRT-MVS		97.88 263	97.98 247	97.61 348	98.15 407	93.77 393	98.97 76	99.64 71	99.16 93	98.69 256	99.42 90	91.60 370	99.89 97	97.63 195	98.52 403	99.16 309

ET-MVSNet_ETH3D		94.30 407	93.21 418	97.58 351	98.14 408	94.47 361	94.78 446	93.24 468	94.72 402	89.56 480	95.87 441	78.57 457	99.81 222	96.91 252	97.11 451	98.46 399

ADS-MVSNet2		95.43 389	94.98 394	96.76 400	98.14 408	91.74 427	97.92 225	97.76 395	90.23 458	96.51 419	98.91 236	85.61 418	99.85 156	92.88 417	96.90 452	98.69 383

ADS-MVSNet		95.24 392	94.93 397	96.18 417	98.14 408	90.10 453	97.92 225	97.32 410	90.23 458	96.51 419	98.91 236	85.61 418	99.74 281	92.88 417	96.90 452	98.69 383

c3_l		97.36 307	97.37 295	97.31 370	98.09 411	93.25 403	95.01 441	99.16 276	97.05 311	98.77 248	98.72 283	92.88 352	99.64 350	96.93 251	99.76 175	99.05 320

FMVSNet3		97.50 292	97.24 303	98.29 282	98.08 412	95.83 306	97.86 234	98.91 320	97.89 230	98.95 209	98.95 229	87.06 405	99.81 222	97.77 183	99.69 210	99.23 283

PAPM		91.88 445	90.34 447	96.51 404	98.06 413	92.56 415	92.44 476	97.17 414	86.35 472	90.38 479	96.01 436	86.61 408	99.21 449	70.65 485	95.43 469	97.75 445

Effi-MVS+-dtu		98.26 223	97.90 259	99.35 80	98.02 414	99.49 6	98.02 204	99.16 276	98.29 188	97.64 354	97.99 372	96.44 251	99.95 26	96.66 284	98.93 377	98.60 391

eth_miper_zixun_eth		97.23 319	97.25 302	97.17 378	98.00 415	92.77 412	94.71 447	99.18 269	97.27 292	98.56 279	98.74 280	91.89 368	99.69 312	97.06 241	99.81 132	99.05 320

HY-MVS	95.94 13	95.90 375	95.35 385	97.55 356	97.95 416	94.79 349	98.81 97	96.94 423	92.28 443	95.17 448	98.57 316	89.90 387	99.75 275	91.20 445	97.33 447	98.10 425

UGNet		98.53 182	98.45 179	98.79 190	97.94 417	96.96 253	99.08 61	98.54 367	99.10 105	96.82 404	99.47 79	96.55 246	99.84 174	98.56 123	99.94 50	99.55 136
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
MAR-MVS		96.47 357	95.70 367	98.79 190	97.92 418	99.12 63	98.28 162	98.60 364	92.16 444	95.54 443	96.17 434	94.77 316	99.52 398	89.62 457	98.23 410	97.72 447
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		96.86 341	96.55 348	97.79 324	97.91 419	94.21 368	97.56 283	98.87 327	97.49 267	99.06 179	99.05 193	80.72 445	99.80 231	98.44 129	99.82 126	99.37 234

API-MVS		97.04 332	96.91 324	97.42 367	97.88 420	98.23 134	98.18 173	98.50 370	97.57 256	97.39 377	96.75 422	96.77 232	99.15 453	90.16 455	99.02 365	94.88 478

myMVS_eth3d28		92.92 431	92.31 427	94.77 442	97.84 421	87.59 465	96.19 390	96.11 438	97.08 310	94.27 458	93.49 472	66.07 479	98.78 466	91.78 433	97.93 429	97.92 435

miper_ehance_all_eth		97.06 330	97.03 315	97.16 380	97.83 422	93.06 405	94.66 450	99.09 288	95.99 367	98.69 256	98.45 333	92.73 357	99.61 363	96.79 265	99.03 362	98.82 360

cl____		97.02 333	96.83 329	97.58 351	97.82 423	94.04 375	94.66 450	99.16 276	97.04 312	98.63 264	98.71 284	88.68 398	99.69 312	97.00 244	99.81 132	99.00 332

DIV-MVS_self_test		97.02 333	96.84 328	97.58 351	97.82 423	94.03 376	94.66 450	99.16 276	97.04 312	98.63 264	98.71 284	88.69 396	99.69 312	97.00 244	99.81 132	99.01 328

CANet		97.87 265	97.76 266	98.19 295	97.75 425	95.51 317	96.76 354	99.05 295	97.74 240	96.93 393	98.21 355	95.59 290	99.89 97	97.86 178	99.93 56	99.19 298

UBG		93.25 425	92.32 426	96.04 422	97.72 426	90.16 452	95.92 408	95.91 443	96.03 365	93.95 466	93.04 475	69.60 469	99.52 398	90.72 453	97.98 427	98.45 402

mvsany_test1		97.60 286	97.54 284	97.77 326	97.72 426	95.35 329	95.36 431	97.13 416	94.13 417	99.71 50	99.33 114	97.93 135	99.30 440	97.60 199	98.94 376	98.67 387

PVSNet_0	89.98 21	91.15 446	90.30 448	93.70 455	97.72 426	84.34 479	90.24 479	97.42 405	90.20 461	93.79 467	93.09 474	90.90 380	98.89 464	86.57 468	72.76 485	97.87 438

CR-MVSNet		96.28 362	95.95 361	97.28 372	97.71 429	94.22 366	98.11 185	98.92 318	92.31 442	96.91 396	99.37 102	85.44 421	99.81 222	97.39 216	97.36 445	97.81 441

RPMNet		97.02 333	96.93 320	97.30 371	97.71 429	94.22 366	98.11 185	99.30 229	99.37 61	96.91 396	99.34 111	86.72 407	99.87 134	97.53 204	97.36 445	97.81 441

ETVMVS		92.60 434	91.08 443	97.18 376	97.70 431	93.65 398	96.54 366	95.70 446	96.51 340	94.68 454	92.39 478	61.80 486	99.50 404	86.97 465	97.41 441	98.40 410

pmmvs3		95.03 396	94.40 403	96.93 389	97.70 431	92.53 416	95.08 439	97.71 397	88.57 468	97.71 350	98.08 366	79.39 452	99.82 205	96.19 321	99.11 356	98.43 407

baseline2		93.73 417	92.83 423	96.42 407	97.70 431	91.28 438	96.84 350	89.77 479	93.96 422	92.44 474	95.93 439	79.14 453	99.77 261	92.94 415	96.76 456	98.21 419

WBMVS		95.18 393	94.78 399	96.37 408	97.68 434	89.74 455	95.80 414	98.73 355	97.54 262	98.30 301	98.44 334	70.06 467	99.82 205	96.62 287	99.87 98	99.54 142

tpm		94.67 401	94.34 405	95.66 429	97.68 434	88.42 459	97.88 230	94.90 453	94.46 408	96.03 433	98.56 317	78.66 455	99.79 244	95.88 334	95.01 471	98.78 372

CANet_DTU		97.26 315	97.06 314	97.84 320	97.57 436	94.65 357	96.19 390	98.79 344	97.23 300	95.14 449	98.24 352	93.22 344	99.84 174	97.34 218	99.84 112	99.04 324

testing11		93.08 428	92.02 433	96.26 413	97.56 437	90.83 447	96.32 382	95.70 446	96.47 344	92.66 473	93.73 468	64.36 483	99.59 370	93.77 400	97.57 434	98.37 414

tpm2		93.09 427	92.58 425	94.62 444	97.56 437	86.53 468	97.66 265	95.79 445	86.15 473	94.07 463	98.23 354	75.95 460	99.53 394	90.91 450	96.86 455	97.81 441

testing91		93.32 423	92.27 428	96.47 406	97.54 439	91.25 439	96.17 394	96.76 427	97.18 304	93.65 469	93.50 471	65.11 482	99.63 353	93.04 414	97.45 438	98.53 396

TR-MVS		95.55 386	95.12 392	96.86 396	97.54 439	93.94 384	96.49 371	96.53 432	94.36 413	97.03 391	96.61 425	94.26 328	99.16 452	86.91 467	96.31 460	97.47 455

testing99		93.04 429	91.98 436	96.23 415	97.53 441	90.70 449	96.35 380	95.94 442	96.87 324	93.41 470	93.43 473	63.84 484	99.59 370	93.24 412	97.19 448	98.40 410

1314		95.74 380	95.60 372	96.17 418	97.53 441	92.75 413	98.07 194	98.31 379	91.22 453	94.25 459	96.68 423	95.53 291	99.03 455	91.64 437	97.18 449	96.74 465

CostFormer		93.97 413	93.78 411	94.51 445	97.53 441	85.83 471	97.98 216	95.96 441	89.29 466	94.99 451	98.63 307	78.63 456	99.62 356	94.54 373	96.50 457	98.09 426

FMVSNet5		96.01 371	95.20 390	98.41 267	97.53 441	96.10 292	98.74 98	99.50 130	97.22 303	98.03 328	99.04 195	69.80 468	99.88 115	97.27 223	99.71 200	99.25 278

PMMVS		96.51 353	95.98 360	98.09 301	97.53 441	95.84 305	94.92 443	98.84 336	91.58 448	96.05 432	95.58 445	95.68 287	99.66 339	95.59 350	98.09 420	98.76 375

reproduce_monomvs		95.00 398	95.25 387	94.22 448	97.51 446	83.34 480	97.86 234	98.44 372	98.51 171	99.29 140	99.30 121	67.68 473	99.56 382	98.89 97	99.81 132	99.77 50

PAPR		95.29 390	94.47 401	97.75 330	97.50 447	95.14 338	94.89 444	98.71 357	91.39 452	95.35 447	95.48 450	94.57 319	99.14 454	84.95 470	97.37 443	98.97 338

testing222		91.96 443	90.37 446	96.72 401	97.47 448	92.59 414	96.11 396	94.76 454	96.83 327	92.90 472	92.87 476	57.92 487	99.55 386	86.93 466	97.52 435	98.00 432

PatchT		96.65 349	96.35 353	97.54 357	97.40 449	95.32 331	97.98 216	96.64 429	99.33 66	96.89 400	99.42 90	84.32 429	99.81 222	97.69 194	97.49 436	97.48 454

tpm cat1		93.29 424	93.13 421	93.75 454	97.39 450	84.74 474	97.39 305	97.65 401	83.39 478	94.16 460	98.41 336	82.86 440	99.39 427	91.56 439	95.35 470	97.14 460

PatchmatchNet		95.58 385	95.67 369	95.30 438	97.34 451	87.32 466	97.65 267	96.65 428	95.30 389	97.07 387	98.69 293	84.77 424	99.75 275	94.97 363	98.64 396	98.83 359
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 308	96.97 318	98.50 258	97.31 452	96.47 283	98.18 173	98.92 318	98.95 128	98.78 245	99.37 102	85.44 421	99.85 156	95.96 332	99.83 121	99.17 305

LS3D		98.63 161	98.38 191	99.36 74	97.25 453	99.38 13	99.12 60	99.32 216	99.21 81	98.44 292	98.88 246	97.31 194	99.80 231	96.58 290	99.34 316	98.92 347

IB-MVS	91.63 19	92.24 440	90.90 444	96.27 412	97.22 454	91.24 440	94.36 460	93.33 467	92.37 441	92.24 476	94.58 465	66.20 478	99.89 97	93.16 413	94.63 473	97.66 449
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		92.38 437	91.76 440	94.21 449	97.16 455	84.65 475	95.42 429	88.45 481	95.96 368	96.17 426	95.84 443	66.36 476	99.71 299	91.87 432	98.64 396	98.28 417

tpmrst		95.07 395	95.46 378	93.91 452	97.11 456	84.36 478	97.62 272	96.96 421	94.98 396	96.35 424	98.80 266	85.46 420	99.59 370	95.60 349	96.23 461	97.79 444

Syy-MVS		96.04 370	95.56 376	97.49 362	97.10 457	94.48 360	96.18 392	96.58 430	95.65 377	94.77 452	92.29 479	91.27 376	99.36 430	98.17 149	98.05 424	98.63 389

myMVS_eth3d		91.92 444	90.45 445	96.30 410	97.10 457	90.90 445	96.18 392	96.58 430	95.65 377	94.77 452	92.29 479	53.88 488	99.36 430	89.59 458	98.05 424	98.63 389

MDTV_nov1_ep13			95.22 389		97.06 459	83.20 481	97.74 254	96.16 436	94.37 412	96.99 392	98.83 259	83.95 433	99.53 394	93.90 394	97.95 428

MVS		93.19 426	92.09 431	96.50 405	96.91 460	94.03 376	98.07 194	98.06 390	68.01 483	94.56 457	96.48 428	95.96 278	99.30 440	83.84 472	96.89 454	96.17 470

E-PMN		94.17 409	94.37 404	93.58 456	96.86 461	85.71 472	90.11 481	97.07 417	98.17 202	97.82 345	97.19 414	84.62 426	98.94 460	89.77 456	97.68 433	96.09 474

JIA-IIPM		95.52 387	95.03 393	97.00 385	96.85 462	94.03 376	96.93 345	95.82 444	99.20 83	94.63 456	99.71 22	83.09 438	99.60 366	94.42 379	94.64 472	97.36 458

EMVS		93.83 415	94.02 407	93.23 461	96.83 463	84.96 473	89.77 482	96.32 434	97.92 227	97.43 374	96.36 433	86.17 412	98.93 461	87.68 463	97.73 432	95.81 475

blend_shiyan4		92.09 442	90.16 449	97.88 318	96.78 464	94.93 345	95.24 434	98.58 365	96.22 355	96.07 430	91.42 481	63.46 485	99.73 288	96.70 277	76.98 484	98.98 334

cl22		95.79 379	95.39 383	96.98 387	96.77 465	92.79 411	94.40 459	98.53 368	94.59 405	97.89 337	98.17 358	82.82 441	99.24 446	96.37 310	99.03 362	98.92 347

WB-MVSnew		95.73 381	95.57 375	96.23 415	96.70 466	90.70 449	96.07 398	93.86 464	95.60 379	97.04 389	95.45 454	96.00 271	99.55 386	91.04 447	98.31 408	98.43 407

dp		93.47 421	93.59 414	93.13 462	96.64 467	81.62 487	97.66 265	96.42 433	92.80 437	96.11 428	98.64 305	78.55 458	99.59 370	93.31 410	92.18 480	98.16 422

MonoMVSNet		96.25 364	96.53 350	95.39 436	96.57 468	91.01 443	98.82 96	97.68 400	98.57 166	98.03 328	99.37 102	90.92 379	97.78 477	94.99 361	93.88 476	97.38 457

usedtu_blend_shiyan5		96.20 367	95.62 370	97.94 314	96.53 469	94.93 345	98.83 95	99.59 89	98.89 135	96.71 408	91.16 482	86.05 415	99.73 288	96.70 277	96.09 464	99.17 305

test-LLR		93.90 414	93.85 409	94.04 450	96.53 469	84.62 476	94.05 465	92.39 470	96.17 357	94.12 461	95.07 455	82.30 442	99.67 326	95.87 337	98.18 413	97.82 439

test-mter		92.33 439	91.76 440	94.04 450	96.53 469	84.62 476	94.05 465	92.39 470	94.00 421	94.12 461	95.07 455	65.63 481	99.67 326	95.87 337	98.18 413	97.82 439

TESTMET0.1,1		92.19 441	91.77 439	93.46 457	96.48 472	82.80 483	94.05 465	91.52 475	94.45 410	94.00 464	94.88 461	66.65 475	99.56 382	95.78 342	98.11 419	98.02 429

MGCNet		97.44 300	97.01 317	98.72 210	96.42 473	96.74 267	97.20 329	91.97 473	98.46 174	98.30 301	98.79 268	92.74 356	99.91 74	99.30 63	99.94 50	99.52 156

miper_enhance_ethall		96.01 371	95.74 365	96.81 397	96.41 474	92.27 423	93.69 470	98.89 324	91.14 455	98.30 301	97.35 412	90.58 382	99.58 377	96.31 314	99.03 362	98.60 391

tpmvs		95.02 397	95.25 387	94.33 446	96.39 475	85.87 469	98.08 190	96.83 426	95.46 384	95.51 445	98.69 293	85.91 416	99.53 394	94.16 385	96.23 461	97.58 452

CMPMVS	75.91 23	96.29 361	95.44 380	98.84 178	96.25 476	98.69 98	97.02 338	99.12 283	88.90 467	97.83 343	98.86 249	89.51 391	98.90 463	91.92 430	99.51 281	98.92 347
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 402	93.69 412	96.99 386	96.05 477	93.61 400	94.97 442	93.49 465	96.17 357	97.57 361	94.88 461	82.30 442	99.01 458	93.60 403	94.17 475	98.37 414

EPMVS		93.72 418	93.27 417	95.09 441	96.04 478	87.76 463	98.13 180	85.01 486	94.69 403	96.92 394	98.64 305	78.47 459	99.31 438	95.04 360	96.46 458	98.20 420

cascas		94.79 400	94.33 406	96.15 421	96.02 479	92.36 421	92.34 477	99.26 249	85.34 475	95.08 450	94.96 460	92.96 351	98.53 470	94.41 382	98.59 400	97.56 453

MVStest1		95.86 376	95.60 372	96.63 402	95.87 480	91.70 428	97.93 222	98.94 312	98.03 217	99.56 74	99.66 32	71.83 465	98.26 473	99.35 59	99.24 333	99.91 13

gg-mvs-nofinetune		92.37 438	91.20 442	95.85 424	95.80 481	92.38 420	99.31 30	81.84 488	99.75 11	91.83 477	99.74 18	68.29 470	99.02 456	87.15 464	97.12 450	96.16 471

gm-plane-assit					94.83 482	81.97 485			88.07 470		94.99 458		99.60 366	91.76 434

GG-mvs-BLEND				94.76 443	94.54 483	92.13 425	99.31 30	80.47 489		88.73 483	91.01 483	67.59 474	98.16 476	82.30 477	94.53 474	93.98 479

UWE-MVS-28		90.22 447	89.28 450	93.02 463	94.50 484	82.87 482	96.52 369	87.51 482	95.21 392	92.36 475	96.04 435	71.57 466	98.25 474	72.04 484	97.77 431	97.94 434

EPNet_dtu		94.93 399	94.78 399	95.38 437	93.58 485	87.68 464	96.78 352	95.69 448	97.35 284	89.14 482	98.09 365	88.15 403	99.49 407	94.95 364	99.30 324	98.98 334
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 451	75.95 454	77.12 468	92.39 486	67.91 492	90.16 480	59.44 493	82.04 479	89.42 481	94.67 464	49.68 490	81.74 486	48.06 486	77.66 483	81.72 482

KD-MVS_2432*1600		92.87 432	91.99 434	95.51 433	91.37 487	89.27 456	94.07 463	98.14 386	95.42 385	97.25 382	96.44 430	67.86 471	99.24 446	91.28 443	96.08 465	98.02 429

miper_refine_blended		92.87 432	91.99 434	95.51 433	91.37 487	89.27 456	94.07 463	98.14 386	95.42 385	97.25 382	96.44 430	67.86 471	99.24 446	91.28 443	96.08 465	98.02 429

EPNet		96.14 368	95.44 380	98.25 286	90.76 489	95.50 320	97.92 225	94.65 455	98.97 124	92.98 471	98.85 252	89.12 394	99.87 134	95.99 330	99.68 215	99.39 223
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 452	68.95 455	70.34 469	87.68 490	65.00 493	91.11 478	59.90 492	69.02 482	74.46 487	88.89 484	48.58 491	68.03 488	28.61 487	72.33 486	77.99 483

test_method		79.78 449	79.50 452	80.62 466	80.21 491	45.76 494	70.82 483	98.41 376	31.08 486	80.89 486	97.71 389	84.85 423	97.37 479	91.51 440	80.03 482	98.75 376

tmp_tt		78.77 450	78.73 453	78.90 467	58.45 492	74.76 491	94.20 462	78.26 490	39.16 485	86.71 484	92.82 477	80.50 446	75.19 487	86.16 469	92.29 479	86.74 481

testmvs		17.12 454	20.53 457	6.87 471	12.05 493	4.20 496	93.62 471	6.73 494	4.62 489	10.41 489	24.33 486	8.28 493	3.56 490	9.69 489	15.07 487	12.86 486

test123		17.04 455	20.11 458	7.82 470	10.25 494	4.91 495	94.80 445	4.47 495	4.93 488	10.00 490	24.28 487	9.69 492	3.64 489	10.14 488	12.43 488	14.92 485

mmdepth		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

monomultidepth		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

test_blank		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

eth-test2					0.00 495

eth-test					0.00 495

uanet_test		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

DCPMVS		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

cdsmvs_eth3d_5k		24.66 453	32.88 456	0.00 472	0.00 495	0.00 497	0.00 484	99.10 286	0.00 490	0.00 491	97.58 397	99.21 18	0.00 491	0.00 490	0.00 489	0.00 487

pcd_1.5k_mvsjas		8.17 456	10.90 459	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	98.07 122	0.00 491	0.00 490	0.00 489	0.00 487

sosnet-low-res		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

sosnet		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

uncertanet		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

Regformer		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

ab-mvs-re		8.12 457	10.83 460	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	97.48 403	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

uanet		0.00 458	0.00 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.00 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

TestfortrainingZip							98.68 108

WAC-MVS						90.90 445								91.37 442

PC_three_1452									93.27 429	99.40 115	98.54 318	98.22 107	97.00 480	95.17 358	99.45 296	99.49 171

test_241102_TWO								99.30 229	98.03 217	99.26 148	99.02 198	97.51 180	99.88 115	96.91 252	99.60 249	99.66 78

test_0728_THIRD									98.17 202	99.08 177	99.02 198	97.89 141	99.88 115	97.07 239	99.71 200	99.70 68

GSMVS																98.81 365

sam_mvs1												84.74 425				98.81 365

sam_mvs												84.29 431

MTGPA								99.20 261

test_post1							97.59 280				20.48 489	83.07 439	99.66 339	94.16 385

test_post											21.25 488	83.86 434	99.70 306

patchmatchnet-post											98.77 272	84.37 428	99.85 156

MTMP							97.93 222	91.91 474

test9_res														93.28 411	99.15 349	99.38 232

agg_prior2														92.50 427	99.16 347	99.37 234

test_prior4						97.97 163	95.86 410

test_prior2							95.74 417		96.48 343	96.11 428	97.63 395	95.92 281		94.16 385	99.20 341

旧先验2							95.76 416		88.56 469	97.52 365			99.66 339	94.48 375

新几何2							95.93 406

无先验							95.74 417	98.74 354	89.38 465				99.73 288	92.38 429		99.22 288

原ACMM2							95.53 423

testdata2													99.79 244	92.80 421

segment_acmp												97.02 214

testdata1							95.44 428		96.32 351

plane_prior5								99.27 244					99.70 306	94.42 379	99.51 281	99.45 197

plane_prior4											97.98 373

plane_prior3						97.78 188			97.41 277	97.79 346

plane_prior2							97.77 247		98.20 199

plane_prior						97.65 197	97.07 337		96.72 333						99.36 312

n2								0.00 496

nn								0.00 496

door-mid								99.57 99

test11								98.87 327

door								99.41 181

HQP5-MVS						96.79 263

BP-MVS														92.82 419

HQP4-MVS										95.56 439			99.54 392			99.32 257

HQP3-MVS								99.04 298							99.26 331

HQP2-MVS												93.84 335

MDTV_nov1_ep13_2view						74.92 490	97.69 260		90.06 463	97.75 349		85.78 417		93.52 405		98.69 383

ACMMP++_ref															99.77 160

ACMMP++															99.68 215

Test By Simon												96.52 247

High-resolution multi-view benchmark