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 15	100.00 1	99.85 29

Gipuma		99.03 78	99.16 60	98.64 204	99.94 2	98.51 108	99.32 26	99.75 42	99.58 37	98.60 253	99.62 40	98.22 100	99.51 380	97.70 180	99.73 171	97.89 413
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 38	99.91 3	98.98 71	99.63 7	99.58 78	99.44 51	99.78 39	99.76 15	96.39 234	99.92 63	99.44 53	99.92 67	99.68 68

pmmvs6		99.67 3	99.70 3	99.60 15	99.90 4	99.27 27	99.53 9	99.76 39	99.64 27	99.84 30	99.83 4	99.50 9	99.87 132	99.36 56	99.92 67	99.64 81

PS-MVSNAJss		99.46 17	99.49 16	99.35 76	99.90 4	98.15 135	99.20 48	99.65 63	99.48 43	99.92 8	99.71 22	98.07 114	99.96 14	99.53 46	100.00 1	99.93 11

testf1		99.25 41	99.16 60	99.51 48	99.89 6	99.63 4	98.71 104	99.69 51	98.90 129	99.43 100	99.35 101	98.86 34	99.67 310	97.81 169	99.81 123	99.24 261

APD_test2		99.25 41	99.16 60	99.51 48	99.89 6	99.63 4	98.71 104	99.69 51	98.90 129	99.43 100	99.35 101	98.86 34	99.67 310	97.81 169	99.81 123	99.24 261

ANet_high		99.57 10	99.67 6	99.28 92	99.89 6	98.09 142	99.14 57	99.93 5	99.82 8	99.93 6	99.81 8	99.17 20	99.94 41	99.31 60	100.00 1	99.82 35

anonymousdsp		99.51 14	99.47 21	99.62 9	99.88 9	99.08 69	99.34 23	99.69 51	98.93 125	99.65 62	99.72 21	98.93 32	99.95 26	99.11 76	100.00 1	99.82 35

v7n		99.53 12	99.57 13	99.41 66	99.88 9	98.54 106	99.45 14	99.61 71	99.66 24	99.68 56	99.66 32	98.44 77	99.95 26	99.73 26	99.96 28	99.75 57

mvs_tets		99.63 6	99.67 6	99.49 54	99.88 9	98.61 98	99.34 23	99.71 46	99.27 72	99.90 14	99.74 18	99.68 4	99.97 7	99.55 41	99.99 5	99.88 20

test_fmvsmconf0.01_n		99.57 10	99.63 10	99.36 70	99.87 12	98.13 138	98.08 182	99.95 1	99.45 49	99.98 2	99.75 16	99.80 1	99.97 7	99.82 11	99.99 5	99.99 2

jajsoiax		99.58 9	99.61 11	99.48 56	99.87 12	98.61 98	99.28 40	99.66 60	99.09 104	99.89 18	99.68 25	99.53 7	99.97 7	99.50 49	99.99 5	99.87 21

test_djsdf		99.52 13	99.51 15	99.53 38	99.86 14	98.74 88	99.39 20	99.56 92	99.11 94	99.70 50	99.73 20	99.00 27	99.97 7	99.26 64	99.98 12	99.89 16

MIMVSNet1		99.38 28	99.32 39	99.55 28	99.86 14	99.19 42	99.41 17	99.59 76	99.59 35	99.71 48	99.57 49	97.12 191	99.90 79	99.21 69	99.87 95	99.54 134

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 26	99.85 16	99.11 64	99.90 1	99.78 36	99.63 29	99.78 39	99.67 30	99.48 10	99.81 216	99.30 61	99.97 21	99.77 48
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 78	99.90 3	99.86 24	99.78 13	99.58 6	99.95 26	99.00 86	99.95 38	99.78 45

SixPastTwentyTwo		98.75 123	98.62 135	99.16 114	99.83 18	97.96 162	99.28 40	98.20 360	99.37 59	99.70 50	99.65 36	92.65 339	99.93 52	99.04 83	99.84 107	99.60 97

sc_t1		99.62 7	99.66 8	99.53 38	99.82 19	99.09 68	99.50 11	99.63 66	99.88 4	99.86 24	99.80 11	99.03 24	99.89 95	99.48 51	99.93 54	99.60 97

Baseline_NR-MVSNet		98.98 86	98.86 102	99.36 70	99.82 19	98.55 103	97.47 282	99.57 85	99.37 59	99.21 151	99.61 43	96.76 216	99.83 190	98.06 149	99.83 114	99.71 60

pm-mvs1		99.44 19	99.48 18	99.33 85	99.80 21	98.63 95	99.29 36	99.63 66	99.30 69	99.65 62	99.60 45	99.16 22	99.82 200	99.07 79	99.83 114	99.56 123

TransMVSNet (Re)		99.44 19	99.47 21	99.36 70	99.80 21	98.58 101	99.27 42	99.57 85	99.39 57	99.75 44	99.62 40	99.17 20	99.83 190	99.06 81	99.62 225	99.66 75

K. test v3		98.00 233	97.66 258	99.03 141	99.79 23	97.56 198	99.19 52	92.47 446	99.62 32	99.52 82	99.66 32	89.61 370	99.96 14	99.25 66	99.81 123	99.56 123

test_fmvsmconf0.1_n		99.49 15	99.54 14	99.34 79	99.78 24	98.11 139	97.77 237	99.90 11	99.33 64	99.97 3	99.66 32	99.71 3	99.96 14	99.79 18	99.99 5	99.96 8

APD_test1		98.83 107	98.66 128	99.34 79	99.78 24	99.47 9	98.42 144	99.45 137	98.28 181	98.98 184	99.19 142	97.76 141	99.58 355	96.57 269	99.55 252	98.97 315

test_vis3_rt		99.14 60	99.17 58	99.07 131	99.78 24	98.38 115	98.92 82	99.94 2	97.80 222	99.91 12	99.67 30	97.15 190	98.91 439	99.76 22	99.56 248	99.92 12

EGC-MVSNET		85.24 426	80.54 429	99.34 79	99.77 27	99.20 39	99.08 61	99.29 217	12.08 464	20.84 465	99.42 87	97.55 160	99.85 154	97.08 221	99.72 179	98.96 317

Anonymous20240521		98.69 134	98.87 99	98.16 278	99.77 27	95.11 319	99.08 61	99.44 145	99.34 63	99.33 123	99.55 57	94.10 314	99.94 41	99.25 66	99.96 28	99.42 195

FC-MVSNet-test		99.27 38	99.25 51	99.34 79	99.77 27	98.37 117	99.30 35	99.57 85	99.61 34	99.40 109	99.50 67	97.12 191	99.85 154	99.02 85	99.94 49	99.80 40

test_vis1_n		98.31 198	98.50 154	97.73 312	99.76 30	94.17 347	98.68 107	99.91 9	96.31 331	99.79 38	99.57 49	92.85 335	99.42 400	99.79 18	99.84 107	99.60 97

test_fmvs3		99.12 67	99.41 26	98.25 267	99.76 30	95.07 320	99.05 67	99.94 2	97.78 225	99.82 33	99.84 3	98.56 68	99.71 287	99.96 1	99.96 28	99.97 4

XXY-MVS		99.14 60	99.15 65	99.10 124	99.76 30	97.74 187	98.85 92	99.62 68	98.48 164	99.37 114	99.49 73	98.75 46	99.86 141	98.20 139	99.80 134	99.71 60

TDRefinement		99.42 24	99.38 29	99.55 28	99.76 30	99.33 21	99.68 6	99.71 46	99.38 58	99.53 80	99.61 43	98.64 56	99.80 224	98.24 134	99.84 107	99.52 146

fmvsm_s_conf0.1_n_a		99.17 52	99.30 44	98.80 176	99.75 34	96.59 256	97.97 211	99.86 16	98.22 184	99.88 21	99.71 22	98.59 62	99.84 172	99.73 26	99.98 12	99.98 3

tt0805		98.69 134	98.62 135	98.90 166	99.75 34	99.30 22	99.15 56	96.97 397	98.86 134	98.87 216	97.62 375	98.63 58	98.96 436	99.41 55	98.29 388	98.45 379

test_vis1_n_1920		98.40 182	98.92 92	96.81 374	99.74 36	90.76 425	98.15 170	99.91 9	98.33 172	99.89 18	99.55 57	95.07 285	99.88 113	99.76 22	99.93 54	99.79 42

FOURS1					99.73 37	99.67 3	99.43 15	99.54 101	99.43 53	99.26 140

PEN-MVS		99.41 25	99.34 36	99.62 9	99.73 37	99.14 57	99.29 36	99.54 101	99.62 32	99.56 71	99.42 87	98.16 108	99.96 14	98.78 100	99.93 54	99.77 48

lessismore_v0				98.97 153	99.73 37	97.53 200		86.71 461		99.37 114	99.52 66	89.93 366	99.92 63	98.99 87	99.72 179	99.44 188

SteuartSystems-ACMMP		98.79 116	98.54 148	99.54 31	99.73 37	99.16 48	98.23 160	99.31 201	97.92 213	98.90 205	98.90 225	98.00 120	99.88 113	96.15 301	99.72 179	99.58 112
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 219	98.15 211	98.22 272	99.73 37	95.15 316	97.36 293	99.68 56	94.45 387	98.99 183	99.27 120	96.87 205	99.94 41	97.13 218	99.91 76	99.57 117

Vis-MVSNet		99.34 30	99.36 33	99.27 95	99.73 37	98.26 124	99.17 53	99.78 36	99.11 94	99.27 136	99.48 74	98.82 37	99.95 26	98.94 90	99.93 54	99.59 104
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 53	99.72 43	98.98 71	99.51 10	99.85 18	99.86 6	99.88 21	99.82 5	99.02 26	99.90 79	99.54 42	99.95 38	99.61 95

SSC-MVS		98.71 127	98.74 112	98.62 210	99.72 43	96.08 279	98.74 97	98.64 340	99.74 13	99.67 58	99.24 132	94.57 300	99.95 26	99.11 76	99.24 312	99.82 35

test_f		98.67 142	98.87 99	98.05 287	99.72 43	95.59 293	98.51 128	99.81 31	96.30 333	99.78 39	99.82 5	96.14 244	98.63 446	99.82 11	99.93 54	99.95 9

ACMH	96.65 7	99.25 41	99.24 52	99.26 97	99.72 43	98.38 115	99.07 64	99.55 96	98.30 176	99.65 62	99.45 83	99.22 17	99.76 260	98.44 125	99.77 151	99.64 81
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0320		99.61 8	99.65 9	99.48 56	99.71 47	98.94 78	99.54 8	99.83 25	99.87 5	99.89 18	99.82 5	98.75 46	99.90 79	99.54 42	99.95 38	99.59 104

fmvsm_s_conf0.1_n		99.16 56	99.33 37	98.64 204	99.71 47	96.10 274	97.87 223	99.85 18	98.56 160	99.90 14	99.68 25	98.69 52	99.85 154	99.72 28	99.98 12	99.97 4

PS-CasMVS		99.40 26	99.33 37	99.62 9	99.71 47	99.10 65	99.29 36	99.53 104	99.53 40	99.46 95	99.41 91	98.23 97	99.95 26	98.89 94	99.95 38	99.81 38

DTE-MVSNet		99.43 23	99.35 34	99.66 7	99.71 47	99.30 22	99.31 30	99.51 109	99.64 27	99.56 71	99.46 79	98.23 97	99.97 7	98.78 100	99.93 54	99.72 59

WR-MVS_H		99.33 31	99.22 53	99.65 8	99.71 47	99.24 30	99.32 26	99.55 96	99.46 48	99.50 88	99.34 105	97.30 180	99.93 52	98.90 92	99.93 54	99.77 48

HPM-MVS_fast		99.01 80	98.82 105	99.57 21	99.71 47	99.35 17	99.00 72	99.50 112	97.33 269	98.94 200	98.86 235	98.75 46	99.82 200	97.53 192	99.71 188	99.56 123

ACMH+	96.62 9	99.08 74	99.00 84	99.33 85	99.71 47	98.83 83	98.60 114	99.58 78	99.11 94	99.53 80	99.18 146	98.81 38	99.67 310	96.71 258	99.77 151	99.50 152

PMVS	91.26 20	97.86 247	97.94 235	97.65 319	99.71 47	97.94 164	98.52 123	98.68 336	98.99 117	97.52 344	99.35 101	97.41 173	98.18 452	91.59 415	99.67 209	96.82 441
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
KinetiMVS		99.03 78	99.02 80	99.03 141	99.70 55	97.48 203	98.43 141	99.29 217	99.70 16	99.60 69	99.07 173	96.13 245	99.94 41	99.42 54	99.87 95	99.68 68

FIs		99.14 60	99.09 73	99.29 91	99.70 55	98.28 123	99.13 58	99.52 108	99.48 43	99.24 145	99.41 91	96.79 213	99.82 200	98.69 110	99.88 91	99.76 53

VPNet		98.87 100	98.83 104	99.01 145	99.70 55	97.62 196	98.43 141	99.35 182	99.47 46	99.28 134	99.05 181	96.72 219	99.82 200	98.09 146	99.36 292	99.59 104

fmvsm_s_conf0.1_n_2		99.20 50	99.38 29	98.65 202	99.69 58	96.08 279	97.49 279	99.90 11	99.53 40	99.88 21	99.64 37	98.51 71	99.90 79	99.83 9	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 195	98.68 125	97.27 350	99.69 58	92.29 399	98.03 192	99.85 18	97.62 234	99.96 4	99.62 40	93.98 315	99.74 273	99.52 48	99.86 101	99.79 42

MP-MVS-pluss		98.57 157	98.23 199	99.60 15	99.69 58	99.35 17	97.16 312	99.38 168	94.87 377	98.97 188	98.99 202	98.01 119	99.88 113	97.29 206	99.70 195	99.58 112
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 46	99.32 39	98.96 154	99.68 61	97.35 211	98.84 94	99.48 121	99.69 18	99.63 65	99.68 25	99.03 24	99.96 14	97.97 158	99.92 67	99.57 117

sd_testset		99.28 37	99.31 41	99.19 108	99.68 61	98.06 151	99.41 17	99.30 209	99.69 18	99.63 65	99.68 25	99.25 16	99.96 14	97.25 209	99.92 67	99.57 117

test_fmvs1_n		98.09 224	98.28 190	97.52 336	99.68 61	93.47 378	98.63 110	99.93 5	95.41 365	99.68 56	99.64 37	91.88 349	99.48 387	99.82 11	99.87 95	99.62 87

CHOSEN 1792x2688		97.49 276	97.14 291	98.54 232	99.68 61	96.09 277	96.50 348	99.62 68	91.58 425	98.84 219	98.97 209	92.36 341	99.88 113	96.76 251	99.95 38	99.67 73

tfpnnormal		98.90 96	98.90 94	98.91 163	99.67 65	97.82 179	99.00 72	99.44 145	99.45 49	99.51 87	99.24 132	98.20 103	99.86 141	95.92 310	99.69 198	99.04 302

MTAPA		98.88 99	98.64 131	99.61 13	99.67 65	99.36 16	98.43 141	99.20 241	98.83 138	98.89 208	98.90 225	96.98 201	99.92 63	97.16 213	99.70 195	99.56 123

test_fmvsmvis_n_1920		99.26 40	99.49 16	98.54 232	99.66 67	96.97 236	98.00 199	99.85 18	99.24 74	99.92 8	99.50 67	99.39 12	99.95 26	99.89 3	99.98 12	98.71 356

mvs5depth		99.30 34	99.59 12	98.44 246	99.65 68	95.35 308	99.82 3	99.94 2	99.83 7	99.42 104	99.94 2	98.13 111	99.96 14	99.63 34	99.96 28	100.00 1

fmvsm_l_conf0.5_n_a		99.19 51	99.27 47	98.94 157	99.65 68	97.05 232	97.80 232	99.76 39	98.70 143	99.78 39	99.11 165	98.79 42	99.95 26	99.85 5	99.96 28	99.83 32

WB-MVS		98.52 170	98.55 146	98.43 247	99.65 68	95.59 293	98.52 123	98.77 325	99.65 26	99.52 82	99.00 200	94.34 306	99.93 52	98.65 112	98.83 360	99.76 53

CP-MVSNet		99.21 48	99.09 73	99.56 26	99.65 68	98.96 77	99.13 58	99.34 188	99.42 54	99.33 123	99.26 125	97.01 199	99.94 41	98.74 105	99.93 54	99.79 42

HPM-MVS		98.79 116	98.53 150	99.59 19	99.65 68	99.29 24	99.16 54	99.43 151	96.74 313	98.61 251	98.38 320	98.62 59	99.87 132	96.47 281	99.67 209	99.59 104
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 151	98.36 179	99.42 64	99.65 68	99.42 11	98.55 119	99.57 85	97.72 228	98.90 205	99.26 125	96.12 247	99.52 375	95.72 321	99.71 188	99.32 239

NormalMVS		98.26 205	97.97 232	99.15 117	99.64 74	97.83 174	98.28 154	99.43 151	99.24 74	98.80 226	98.85 238	89.76 368	99.94 41	98.04 151	99.67 209	99.68 68

lecture		99.25 41	99.12 68	99.62 9	99.64 74	99.40 12	98.89 87	99.51 109	99.19 85	99.37 114	99.25 130	98.36 81	99.88 113	98.23 136	99.67 209	99.59 104

fmvsm_l_conf0.5_n		99.21 48	99.28 46	99.02 144	99.64 74	97.28 215	97.82 228	99.76 39	98.73 140	99.82 33	99.09 172	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 90	99.64 74	98.10 141	97.68 249	99.84 22	99.29 70	99.92 8	99.57 49	99.60 5	99.96 14	99.74 25	99.98 12	99.89 16

TSAR-MVS + MP.		98.63 148	98.49 158	99.06 137	99.64 74	97.90 168	98.51 128	98.94 290	96.96 300	99.24 145	98.89 231	97.83 133	99.81 216	96.88 241	99.49 272	99.48 169
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 110	98.72 116	99.12 120	99.64 74	98.54 106	97.98 207	99.68 56	97.62 234	99.34 121	99.18 146	97.54 161	99.77 254	97.79 171	99.74 168	99.04 302

Elysia		99.15 57	99.14 66	99.18 109	99.63 80	97.92 165	98.50 130	99.43 151	99.67 21	99.70 50	99.13 161	96.66 222	99.98 4	99.54 42	99.96 28	99.64 81

StellarMVS		99.15 57	99.14 66	99.18 109	99.63 80	97.92 165	98.50 130	99.43 151	99.67 21	99.70 50	99.13 161	96.66 222	99.98 4	99.54 42	99.96 28	99.64 81

KD-MVS_self_test		99.25 41	99.18 57	99.44 63	99.63 80	99.06 70	98.69 106	99.54 101	99.31 67	99.62 68	99.53 63	97.36 177	99.86 141	99.24 68	99.71 188	99.39 208

EU-MVSNet		97.66 264	98.50 154	95.13 416	99.63 80	85.84 447	98.35 150	98.21 359	98.23 183	99.54 76	99.46 79	95.02 286	99.68 306	98.24 134	99.87 95	99.87 21

HyFIR lowres test		97.19 302	96.60 326	98.96 154	99.62 84	97.28 215	95.17 413	99.50 112	94.21 392	99.01 180	98.32 328	86.61 388	99.99 2	97.10 220	99.84 107	99.60 97

fmvsm_l_conf0.5_n_9		99.32 33	99.43 24	98.98 151	99.59 85	97.18 225	97.44 285	99.83 25	99.56 38	99.91 12	99.34 105	99.36 13	99.93 52	99.83 9	99.98 12	99.85 29

fmvsm_l_conf0.5_n_3		99.45 18	99.48 18	99.34 79	99.59 85	98.21 132	97.82 228	99.84 22	99.41 56	99.92 8	99.41 91	99.51 8	99.95 26	99.84 8	99.97 21	99.87 21

mmtdpeth		99.30 34	99.42 25	98.92 162	99.58 87	96.89 243	99.48 13	99.92 7	99.92 2	98.26 288	99.80 11	98.33 87	99.91 72	99.56 39	99.95 38	99.97 4

ACMMP_NAP		98.75 123	98.48 159	99.57 21	99.58 87	99.29 24	97.82 228	99.25 230	96.94 302	98.78 228	99.12 164	98.02 118	99.84 172	97.13 218	99.67 209	99.59 104

nrg030		99.40 26	99.35 34	99.54 31	99.58 87	99.13 60	98.98 75	99.48 121	99.68 20	99.46 95	99.26 125	98.62 59	99.73 279	99.17 73	99.92 67	99.76 53

VDDNet		98.21 212	97.95 233	99.01 145	99.58 87	97.74 187	99.01 70	97.29 388	99.67 21	98.97 188	99.50 67	90.45 363	99.80 224	97.88 164	99.20 320	99.48 169

COLMAP_ROB	96.50 10	98.99 83	98.85 103	99.41 66	99.58 87	99.10 65	98.74 97	99.56 92	99.09 104	99.33 123	99.19 142	98.40 79	99.72 286	95.98 308	99.76 164	99.42 195
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	98.99 147	99.57 92	97.73 189	97.93 212	99.83 25	99.22 77	99.93 6	99.30 114	99.42 11	99.96 14	99.85 5	99.99 5	99.29 248

ZNCC-MVS		98.68 139	98.40 171	99.54 31	99.57 92	99.21 33	98.46 138	99.29 217	97.28 275	98.11 300	98.39 318	98.00 120	99.87 132	96.86 244	99.64 219	99.55 130

MSP-MVS		98.40 182	98.00 227	99.61 13	99.57 92	99.25 29	98.57 117	99.35 182	97.55 245	99.31 131	97.71 368	94.61 299	99.88 113	96.14 302	99.19 323	99.70 65
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		98.32 196	98.39 174	98.13 279	99.57 92	95.54 296	97.78 234	99.49 119	97.37 266	99.19 153	97.65 372	98.96 29	99.49 384	96.50 280	98.99 348	99.34 231

MP-MVS		98.46 176	98.09 216	99.54 31	99.57 92	99.22 32	98.50 130	99.19 245	97.61 237	97.58 338	98.66 281	97.40 174	99.88 113	94.72 347	99.60 232	99.54 134
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 127	98.46 163	99.47 60	99.57 92	98.97 73	98.23 160	99.48 121	96.60 318	99.10 163	99.06 174	98.71 50	99.83 190	95.58 328	99.78 145	99.62 87

LGP-MVS_train				99.47 60	99.57 92	98.97 73		99.48 121	96.60 318	99.10 163	99.06 174	98.71 50	99.83 190	95.58 328	99.78 145	99.62 87

IS-MVSNet		98.19 215	97.90 240	99.08 129	99.57 92	97.97 159	99.31 30	98.32 355	99.01 116	98.98 184	99.03 185	91.59 351	99.79 237	95.49 330	99.80 134	99.48 169

viewmsd2359difaftdt		98.84 105	99.04 78	98.24 269	99.56 100	95.51 298	97.38 289	99.70 50	99.16 90	99.57 70	99.40 94	98.26 94	99.71 287	98.55 121	99.82 118	99.50 152

dcpmvs_2		98.78 118	99.11 69	97.78 302	99.56 100	93.67 373	99.06 65	99.86 16	99.50 42	99.66 59	99.26 125	97.21 188	99.99 2	98.00 156	99.91 76	99.68 68

test_0402		98.76 122	98.71 119	98.93 159	99.56 100	98.14 137	98.45 140	99.34 188	99.28 71	98.95 193	98.91 222	98.34 86	99.79 237	95.63 325	99.91 76	98.86 334

EPP-MVSNet		98.30 199	98.04 223	99.07 131	99.56 100	97.83 174	99.29 36	98.07 366	99.03 114	98.59 255	99.13 161	92.16 345	99.90 79	96.87 242	99.68 203	99.49 158

ACMMP		98.75 123	98.50 154	99.52 44	99.56 100	99.16 48	98.87 88	99.37 172	97.16 290	98.82 223	99.01 197	97.71 144	99.87 132	96.29 293	99.69 198	99.54 134
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 69	99.20 56	98.78 182	99.55 105	96.59 256	97.79 233	99.82 30	98.21 185	99.81 36	99.53 63	98.46 75	99.84 172	99.70 31	99.97 21	99.90 15

fmvsm_s_conf0.5_n		99.09 70	99.26 49	98.61 213	99.55 105	96.09 277	97.74 243	99.81 31	98.55 161	99.85 27	99.55 57	98.60 61	99.84 172	99.69 33	99.98 12	99.89 16

FMVSNet1		99.17 52	99.17 58	99.17 111	99.55 105	98.24 126	99.20 48	99.44 145	99.21 79	99.43 100	99.55 57	97.82 136	99.86 141	98.42 127	99.89 89	99.41 198

Vis-MVSNet (Re-imp)		97.46 278	97.16 288	98.34 259	99.55 105	96.10 274	98.94 80	98.44 349	98.32 174	98.16 294	98.62 290	88.76 375	99.73 279	93.88 373	99.79 140	99.18 281

ACMM	96.08 12	98.91 94	98.73 114	99.48 56	99.55 105	99.14 57	98.07 185	99.37 172	97.62 234	99.04 176	98.96 212	98.84 36	99.79 237	97.43 200	99.65 217	99.49 158
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 131	98.97 88	97.89 295	99.54 110	94.05 350	98.55 119	99.92 7	96.78 311	99.72 46	99.78 13	96.60 226	99.67 310	99.91 2	99.90 83	99.94 10

mPP-MVS		98.64 146	98.34 182	99.54 31	99.54 110	99.17 44	98.63 110	99.24 235	97.47 253	98.09 302	98.68 276	97.62 153	99.89 95	96.22 296	99.62 225	99.57 117

XVG-ACMP-BASELINE		98.56 158	98.34 182	99.22 105	99.54 110	98.59 100	97.71 246	99.46 133	97.25 278	98.98 184	98.99 202	97.54 161	99.84 172	95.88 311	99.74 168	99.23 263

region2R		98.69 134	98.40 171	99.54 31	99.53 113	99.17 44	98.52 123	99.31 201	97.46 258	98.44 273	98.51 304	97.83 133	99.88 113	96.46 282	99.58 241	99.58 112

PGM-MVS		98.66 143	98.37 178	99.55 28	99.53 113	99.18 43	98.23 160	99.49 119	97.01 299	98.69 239	98.88 232	98.00 120	99.89 95	95.87 314	99.59 236	99.58 112

Patchmatch-RL test		97.26 295	97.02 296	97.99 291	99.52 115	95.53 297	96.13 373	99.71 46	97.47 253	99.27 136	99.16 152	84.30 409	99.62 335	97.89 161	99.77 151	98.81 342

ACMMPR		98.70 131	98.42 169	99.54 31	99.52 115	99.14 57	98.52 123	99.31 201	97.47 253	98.56 260	98.54 299	97.75 142	99.88 113	96.57 269	99.59 236	99.58 112

fmvsm_s_conf0.5_n_9		99.17 52	99.38 29	98.53 234	99.51 117	95.82 289	97.62 260	99.78 36	99.72 15	99.90 14	99.48 74	98.66 54	99.89 95	99.85 5	99.93 54	99.89 16

AstraMVS		98.16 221	98.07 221	98.41 249	99.51 117	95.86 286	98.00 199	95.14 429	98.97 120	99.43 100	99.24 132	93.25 323	99.84 172	99.21 69	99.87 95	99.54 134

fmvsm_s_conf0.5_n_8		99.13 64	99.26 49	98.74 193	99.51 117	96.44 266	97.65 255	99.65 63	99.66 24	99.78 39	99.48 74	97.92 127	99.93 52	99.72 28	99.95 38	99.87 21

GST-MVS		98.61 152	98.30 188	99.52 44	99.51 117	99.20 39	98.26 158	99.25 230	97.44 261	98.67 242	98.39 318	97.68 145	99.85 154	96.00 306	99.51 263	99.52 146

Anonymous20231206		98.21 212	98.21 200	98.20 273	99.51 117	95.43 306	98.13 172	99.32 196	96.16 337	98.93 201	98.82 248	96.00 252	99.83 190	97.32 205	99.73 171	99.36 225

ACMP	95.32 15	98.41 180	98.09 216	99.36 70	99.51 117	98.79 86	97.68 249	99.38 168	95.76 352	98.81 225	98.82 248	98.36 81	99.82 200	94.75 344	99.77 151	99.48 169
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LuminaMVS		98.39 188	98.20 201	98.98 151	99.50 123	97.49 201	97.78 234	97.69 375	98.75 139	99.49 89	99.25 130	92.30 343	99.94 41	99.14 74	99.88 91	99.50 152

DVP-MVS		98.77 121	98.52 151	99.52 44	99.50 123	99.21 33	98.02 195	98.84 314	97.97 207	99.08 165	99.02 186	97.61 155	99.88 113	96.99 228	99.63 222	99.48 169
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 15	99.50 123	99.23 31	98.02 195	99.32 196					99.88 113	96.99 228	99.63 222	99.68 68

test0726					99.50 123	99.21 33	98.17 168	99.35 182	97.97 207	99.26 140	99.06 174	97.61 155

AllTest		98.44 178	98.20 201	99.16 114	99.50 123	98.55 103	98.25 159	99.58 78	96.80 309	98.88 212	99.06 174	97.65 148	99.57 357	94.45 354	99.61 230	99.37 218

TestCases				99.16 114	99.50 123	98.55 103		99.58 78	96.80 309	98.88 212	99.06 174	97.65 148	99.57 357	94.45 354	99.61 230	99.37 218

XVG-OURS		98.53 166	98.34 182	99.11 122	99.50 123	98.82 85	95.97 379	99.50 112	97.30 273	99.05 174	98.98 207	99.35 14	99.32 414	95.72 321	99.68 203	99.18 281

EG-PatchMatch MVS		98.99 83	99.01 82	98.94 157	99.50 123	97.47 204	98.04 190	99.59 76	98.15 200	99.40 109	99.36 100	98.58 67	99.76 260	98.78 100	99.68 203	99.59 104

fmvsm_s_conf0.5_n_2		99.14 60	99.31 41	98.63 208	99.49 131	96.08 279	97.38 289	99.81 31	99.48 43	99.84 30	99.57 49	98.46 75	99.89 95	99.82 11	99.97 21	99.91 13

SED-MVS		98.91 94	98.72 116	99.49 54	99.49 131	99.17 44	98.10 179	99.31 201	98.03 203	99.66 59	99.02 186	98.36 81	99.88 113	96.91 234	99.62 225	99.41 198

IU-MVS					99.49 131	99.15 52		98.87 305	92.97 410	99.41 106				96.76 251	99.62 225	99.66 75

test_241102_ONE					99.49 131	99.17 44		99.31 201	97.98 206	99.66 59	98.90 225	98.36 81	99.48 387

UA-Net		99.47 16	99.40 27	99.70 2	99.49 131	99.29 24	99.80 4	99.72 44	99.82 8	99.04 176	99.81 8	98.05 117	99.96 14	98.85 96	99.99 5	99.86 27

HFP-MVS		98.71 127	98.44 166	99.51 48	99.49 131	99.16 48	98.52 123	99.31 201	97.47 253	98.58 257	98.50 308	97.97 124	99.85 154	96.57 269	99.59 236	99.53 143

VPA-MVSNet		99.30 34	99.30 44	99.28 92	99.49 131	98.36 120	99.00 72	99.45 137	99.63 29	99.52 82	99.44 84	98.25 95	99.88 113	99.09 78	99.84 107	99.62 87

XVG-OURS-SEG-HR		98.49 173	98.28 190	99.14 118	99.49 131	98.83 83	96.54 344	99.48 121	97.32 271	99.11 160	98.61 292	99.33 15	99.30 417	96.23 295	98.38 384	99.28 250

114514_t		96.50 335	95.77 344	98.69 198	99.48 139	97.43 208	97.84 227	99.55 96	81.42 457	96.51 397	98.58 296	95.53 272	99.67 310	93.41 386	99.58 241	98.98 312

IterMVS-LS		98.55 162	98.70 122	98.09 280	99.48 139	94.73 330	97.22 307	99.39 166	98.97 120	99.38 112	99.31 113	96.00 252	99.93 52	98.58 115	99.97 21	99.60 97
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
fmvsm_s_conf0.5_n_5		99.07 76	99.10 71	98.99 147	99.47 141	97.22 220	97.40 287	99.83 25	97.61 237	99.85 27	99.30 114	98.80 40	99.95 26	99.71 30	99.90 83	99.78 45

v8		99.01 80	99.16 60	98.57 220	99.47 141	96.31 271	98.90 83	99.47 129	99.03 114	99.52 82	99.57 49	96.93 202	99.81 216	99.60 35	99.98 12	99.60 97

SSC-MVS3.2		98.53 166	98.79 108	97.74 309	99.46 143	93.62 376	96.45 350	99.34 188	99.33 64	98.93 201	98.70 272	97.90 128	99.90 79	99.12 75	99.92 67	99.69 67

fmvsm_s_conf0.5_n_3		99.22 47	99.37 32	98.78 182	99.46 143	96.58 259	97.65 255	99.72 44	99.47 46	99.86 24	99.50 67	98.94 30	99.89 95	99.75 24	99.97 21	99.86 27

XVS		98.72 126	98.45 164	99.53 38	99.46 143	99.21 33	98.65 108	99.34 188	98.62 150	97.54 342	98.63 288	97.50 167	99.83 190	96.79 247	99.53 258	99.56 123

X-MVStestdata		94.32 384	92.59 403	99.53 38	99.46 143	99.21 33	98.65 108	99.34 188	98.62 150	97.54 342	45.85 462	97.50 167	99.83 190	96.79 247	99.53 258	99.56 123

test20.03		98.78 118	98.77 111	98.78 182	99.46 143	97.20 223	97.78 234	99.24 235	99.04 113	99.41 106	98.90 225	97.65 148	99.76 260	97.70 180	99.79 140	99.39 208

guyue		98.01 232	97.93 237	98.26 266	99.45 148	95.48 301	98.08 182	96.24 412	98.89 131	99.34 121	99.14 159	91.32 355	99.82 200	99.07 79	99.83 114	99.48 169

CSCG		98.68 139	98.50 154	99.20 106	99.45 148	98.63 95	98.56 118	99.57 85	97.87 217	98.85 217	98.04 349	97.66 147	99.84 172	96.72 256	99.81 123	99.13 291

GeoE		99.05 77	98.99 86	99.25 100	99.44 150	98.35 121	98.73 101	99.56 92	98.42 167	98.91 204	98.81 250	98.94 30	99.91 72	98.35 129	99.73 171	99.49 158

v148		98.45 177	98.60 140	98.00 290	99.44 150	94.98 322	97.44 285	99.06 271	98.30 176	99.32 129	98.97 209	96.65 224	99.62 335	98.37 128	99.85 102	99.39 208

v10		98.97 87	99.11 69	98.55 227	99.44 150	96.21 273	98.90 83	99.55 96	98.73 140	99.48 90	99.60 45	96.63 225	99.83 190	99.70 31	99.99 5	99.61 95

V42		98.78 118	98.78 110	98.76 187	99.44 150	97.04 233	98.27 157	99.19 245	97.87 217	99.25 144	99.16 152	96.84 206	99.78 248	99.21 69	99.84 107	99.46 179

MDA-MVSNet-bldmvs		97.94 238	97.91 239	98.06 285	99.44 150	94.96 323	96.63 340	99.15 261	98.35 170	98.83 220	99.11 165	94.31 307	99.85 154	96.60 266	98.72 366	99.37 218

casdiffmvs_mvg		99.12 67	99.16 60	98.99 147	99.43 155	97.73 189	98.00 199	99.62 68	99.22 77	99.55 74	99.22 138	98.93 32	99.75 268	98.66 111	99.81 123	99.50 152
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 96	99.01 82	98.57 220	99.42 156	96.59 256	98.13 172	99.66 60	99.09 104	99.30 132	99.02 186	98.79 42	99.89 95	97.87 166	99.80 134	99.23 263

test1111		96.49 336	96.82 310	95.52 409	99.42 156	87.08 444	99.22 45	87.14 460	99.11 94	99.46 95	99.58 47	88.69 376	99.86 141	98.80 98	99.95 38	99.62 87

v2v482		98.56 158	98.62 135	98.37 256	99.42 156	95.81 290	97.58 268	99.16 256	97.90 215	99.28 134	99.01 197	95.98 257	99.79 237	99.33 58	99.90 83	99.51 149

OPM-MVS		98.56 158	98.32 186	99.25 100	99.41 159	98.73 91	97.13 314	99.18 249	97.10 293	98.75 234	98.92 220	98.18 104	99.65 326	96.68 260	99.56 248	99.37 218
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 226	98.08 219	98.04 288	99.41 159	94.59 336	94.59 431	99.40 164	97.50 250	98.82 223	98.83 245	96.83 208	99.84 172	97.50 194	99.81 123	99.71 60

test_one_0601					99.39 161	99.20 39		99.31 201	98.49 163	98.66 244	99.02 186	97.64 151

mvsany_test3		98.87 100	98.92 92	98.74 193	99.38 162	96.94 240	98.58 116	99.10 266	96.49 323	99.96 4	99.81 8	98.18 104	99.45 395	98.97 88	99.79 140	99.83 32

patch_mono-2		98.51 171	98.63 133	98.17 276	99.38 162	94.78 327	97.36 293	99.69 51	98.16 195	98.49 269	99.29 117	97.06 194	99.97 7	98.29 133	99.91 76	99.76 53

test2506		92.39 415	91.89 417	93.89 430	99.38 162	82.28 461	99.32 26	66.03 468	99.08 108	98.77 231	99.57 49	66.26 456	99.84 172	98.71 108	99.95 38	99.54 134

ECVR-MVS		96.42 338	96.61 324	95.85 401	99.38 162	88.18 439	99.22 45	86.00 462	99.08 108	99.36 117	99.57 49	88.47 381	99.82 200	98.52 122	99.95 38	99.54 134

casdiffmvs		98.95 90	99.00 84	98.81 174	99.38 162	97.33 212	97.82 228	99.57 85	99.17 89	99.35 119	99.17 150	98.35 85	99.69 297	98.46 124	99.73 171	99.41 198
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 89	99.02 80	98.76 187	99.38 162	97.26 217	98.49 133	99.50 112	98.86 134	99.19 153	99.06 174	98.23 97	99.69 297	98.71 108	99.76 164	99.33 236

TranMVSNet+NR-MVSNet		99.17 52	99.07 76	99.46 62	99.37 168	98.87 81	98.39 146	99.42 157	99.42 54	99.36 117	99.06 174	98.38 80	99.95 26	98.34 130	99.90 83	99.57 117

fmvsm_s_conf0.5_n_6		99.08 74	99.21 55	98.69 198	99.36 169	96.51 261	97.62 260	99.68 56	98.43 166	99.85 27	99.10 168	99.12 23	99.88 113	99.77 21	99.92 67	99.67 73

tttt0517		95.64 363	94.98 373	97.64 322	99.36 169	93.81 368	98.72 102	90.47 454	98.08 202	98.67 242	98.34 325	73.88 442	99.92 63	97.77 173	99.51 263	99.20 273

test_part2					99.36 169	99.10 65				99.05 174

v1144		98.60 153	98.66 128	98.41 249	99.36 169	95.90 284	97.58 268	99.34 188	97.51 249	99.27 136	99.15 156	96.34 239	99.80 224	99.47 52	99.93 54	99.51 149

CP-MVS		98.70 131	98.42 169	99.52 44	99.36 169	99.12 62	98.72 102	99.36 176	97.54 247	98.30 282	98.40 317	97.86 132	99.89 95	96.53 278	99.72 179	99.56 123

diffmvs_AUTHOR		98.50 172	98.59 142	98.23 271	99.35 174	95.48 301	96.61 341	99.60 72	98.37 168	98.90 205	99.00 200	97.37 176	99.76 260	98.22 137	99.85 102	99.46 179

Test_1112_low_res		96.99 317	96.55 328	98.31 262	99.35 174	95.47 304	95.84 391	99.53 104	91.51 427	96.80 384	98.48 311	91.36 354	99.83 190	96.58 267	99.53 258	99.62 87

DeepC-MVS	97.60 4	98.97 87	98.93 91	99.10 124	99.35 174	97.98 158	98.01 198	99.46 133	97.56 243	99.54 76	99.50 67	98.97 28	99.84 172	98.06 149	99.92 67	99.49 158
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 294	96.86 306	98.58 217	99.34 177	96.32 270	96.75 333	99.58 78	93.14 408	96.89 379	97.48 382	92.11 346	99.86 141	96.91 234	99.54 254	99.57 117

reproduce_model		99.15 57	98.97 88	99.67 4	99.33 178	99.44 10	98.15 170	99.47 129	99.12 93	99.52 82	99.32 112	98.31 88	99.90 79	97.78 172	99.73 171	99.66 75

MVSMamba_PlusPlus		98.83 107	98.98 87	98.36 257	99.32 179	96.58 259	98.90 83	99.41 161	99.75 11	98.72 237	99.50 67	96.17 243	99.94 41	99.27 63	99.78 145	98.57 372

fmvsm_s_conf0.5_n_4		99.01 80	99.22 53	98.38 253	99.31 180	95.48 301	97.56 270	99.73 43	98.87 132	99.75 44	99.27 120	98.80 40	99.86 141	99.80 16	99.90 83	99.81 38

SF-MVS		98.53 166	98.27 193	99.32 87	99.31 180	98.75 87	98.19 164	99.41 161	96.77 312	98.83 220	98.90 225	97.80 138	99.82 200	95.68 324	99.52 261	99.38 216

CPTT-MVS		97.84 253	97.36 277	99.27 95	99.31 180	98.46 111	98.29 153	99.27 224	94.90 376	97.83 322	98.37 321	94.90 288	99.84 172	93.85 375	99.54 254	99.51 149

UnsupCasMVSNet_eth		97.89 242	97.60 263	98.75 189	99.31 180	97.17 227	97.62 260	99.35 182	98.72 142	98.76 233	98.68 276	92.57 340	99.74 273	97.76 177	95.60 446	99.34 231

fmvsm_s_conf0.5_n_7		98.83 107	99.04 78	98.20 273	99.30 184	94.83 325	97.23 303	99.36 176	98.64 145	99.84 30	99.43 86	98.10 113	99.91 72	99.56 39	99.96 28	99.87 21

pmmvs-eth3d		98.47 175	98.34 182	98.86 168	99.30 184	97.76 185	97.16 312	99.28 221	95.54 358	99.42 104	99.19 142	97.27 183	99.63 332	97.89 161	99.97 21	99.20 273

mamv4		99.44 19	99.39 28	99.58 20	99.30 184	99.74 2	99.04 68	99.81 31	99.77 10	99.82 33	99.57 49	97.82 136	99.98 4	99.53 46	99.89 89	99.01 306

SymmetryMVS		98.05 228	97.71 253	99.09 128	99.29 187	97.83 174	98.28 154	97.64 380	99.24 74	98.80 226	98.85 238	89.76 368	99.94 41	98.04 151	99.50 270	99.49 158

Anonymous20231211		99.27 38	99.27 47	99.26 97	99.29 187	98.18 133	99.49 12	99.51 109	99.70 16	99.80 37	99.68 25	96.84 206	99.83 190	99.21 69	99.91 76	99.77 48

viewmanbaseed2359cas		98.58 156	98.54 148	98.70 197	99.28 189	97.13 231	97.47 282	99.55 96	97.55 245	98.96 192	98.92 220	97.77 140	99.59 348	97.59 188	99.77 151	99.39 208

UnsupCasMVSNet_bld		97.30 292	96.92 302	98.45 244	99.28 189	96.78 250	96.20 367	99.27 224	95.42 362	98.28 286	98.30 329	93.16 326	99.71 287	94.99 338	97.37 422	98.87 333

EC-MVSNet		99.09 70	99.05 77	99.20 106	99.28 189	98.93 79	99.24 44	99.84 22	99.08 108	98.12 299	98.37 321	98.72 49	99.90 79	99.05 82	99.77 151	98.77 350

mamba_0408		98.80 114	98.88 97	98.55 227	99.27 192	96.50 262	98.00 199	99.60 72	98.93 125	99.22 148	98.84 243	98.59 62	99.89 95	97.74 178	99.72 179	99.27 251

SSM_04072		98.80 114	98.88 97	98.56 225	99.27 192	96.50 262	98.00 199	99.60 72	98.93 125	99.22 148	98.84 243	98.59 62	99.90 79	97.74 178	99.72 179	99.27 251

SSM_0407		98.86 103	98.96 90	98.55 227	99.27 192	96.50 262	98.04 190	99.66 60	99.09 104	99.22 148	99.02 186	98.79 42	99.87 132	97.87 166	99.72 179	99.27 251

reproduce-ours		99.09 70	98.90 94	99.67 4	99.27 192	99.49 6	98.00 199	99.42 157	99.05 111	99.48 90	99.27 120	98.29 90	99.89 95	97.61 185	99.71 188	99.62 87

our_new_method		99.09 70	98.90 94	99.67 4	99.27 192	99.49 6	98.00 199	99.42 157	99.05 111	99.48 90	99.27 120	98.29 90	99.89 95	97.61 185	99.71 188	99.62 87

DPE-MVS		98.59 155	98.26 194	99.57 21	99.27 192	99.15 52	97.01 317	99.39 166	97.67 230	99.44 99	98.99 202	97.53 163	99.89 95	95.40 332	99.68 203	99.66 75
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 252	98.18 206	96.87 370	99.27 192	91.16 419	95.53 401	99.25 230	99.10 101	99.41 106	99.35 101	93.10 328	99.96 14	98.65 112	99.94 49	99.49 158

v1192		98.60 153	98.66 128	98.41 249	99.27 192	95.88 285	97.52 275	99.36 176	97.41 262	99.33 123	99.20 141	96.37 237	99.82 200	99.57 37	99.92 67	99.55 130

N_pmnet		97.63 266	97.17 287	98.99 147	99.27 192	97.86 171	95.98 378	93.41 443	95.25 367	99.47 94	98.90 225	95.63 269	99.85 154	96.91 234	99.73 171	99.27 251

FPMVS		93.44 401	92.23 408	97.08 358	99.25 201	97.86 171	95.61 398	97.16 392	92.90 412	93.76 445	98.65 283	75.94 440	95.66 459	79.30 457	97.49 415	97.73 423

new-patchmatchnet		98.35 190	98.74 112	97.18 353	99.24 202	92.23 401	96.42 354	99.48 121	98.30 176	99.69 54	99.53 63	97.44 172	99.82 200	98.84 97	99.77 151	99.49 158

MCST-MVS		98.00 233	97.63 261	99.10 124	99.24 202	98.17 134	96.89 326	98.73 333	95.66 353	97.92 313	97.70 370	97.17 189	99.66 321	96.18 300	99.23 315	99.47 177

UniMVSNet (Re)		98.87 100	98.71 119	99.35 76	99.24 202	98.73 91	97.73 245	99.38 168	98.93 125	99.12 159	98.73 262	96.77 214	99.86 141	98.63 114	99.80 134	99.46 179

jason		97.45 280	97.35 278	97.76 306	99.24 202	93.93 362	95.86 388	98.42 351	94.24 391	98.50 268	98.13 339	94.82 292	99.91 72	97.22 210	99.73 171	99.43 192
jason: jason.
IterMVS		97.73 258	98.11 215	96.57 380	99.24 202	90.28 428	95.52 403	99.21 239	98.86 134	99.33 123	99.33 108	93.11 327	99.94 41	98.49 123	99.94 49	99.48 169
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 162	98.62 135	98.32 260	99.22 207	95.58 295	97.51 277	99.45 137	97.16 290	99.45 98	99.24 132	96.12 247	99.85 154	99.60 35	99.88 91	99.55 130

ITE_SJBPF				98.87 167	99.22 207	98.48 110		99.35 182	97.50 250	98.28 286	98.60 294	97.64 151	99.35 410	93.86 374	99.27 307	98.79 348

h-mvs33		97.77 256	97.33 280	99.10 124	99.21 209	97.84 173	98.35 150	98.57 343	99.11 94	98.58 257	99.02 186	88.65 379	99.96 14	98.11 144	96.34 438	99.49 158

v144192		98.54 164	98.57 144	98.45 244	99.21 209	95.98 282	97.63 259	99.36 176	97.15 292	99.32 129	99.18 146	95.84 264	99.84 172	99.50 49	99.91 76	99.54 134

APDe-MVS		98.99 83	98.79 108	99.60 15	99.21 209	99.15 52	98.87 88	99.48 121	97.57 241	99.35 119	99.24 132	97.83 133	99.89 95	97.88 164	99.70 195	99.75 57
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 92	98.81 107	99.28 92	99.21 209	98.45 112	98.46 138	99.33 194	99.63 29	99.48 90	99.15 156	97.23 186	99.75 268	97.17 212	99.66 216	99.63 86

SR-MVS-dyc-post		98.81 112	98.55 146	99.57 21	99.20 213	99.38 13	98.48 136	99.30 209	98.64 145	98.95 193	98.96 212	97.49 170	99.86 141	96.56 273	99.39 288	99.45 184

RE-MVS-def			98.58 143		99.20 213	99.38 13	98.48 136	99.30 209	98.64 145	98.95 193	98.96 212	97.75 142		96.56 273	99.39 288	99.45 184

v1921920		98.54 164	98.60 140	98.38 253	99.20 213	95.76 292	97.56 270	99.36 176	97.23 284	99.38 112	99.17 150	96.02 250	99.84 172	99.57 37	99.90 83	99.54 134

thisisatest0530		95.27 370	94.45 381	97.74 309	99.19 216	94.37 340	97.86 224	90.20 455	97.17 289	98.22 289	97.65 372	73.53 443	99.90 79	96.90 239	99.35 294	98.95 318

Anonymous20240529		98.93 92	98.87 99	99.12 120	99.19 216	98.22 131	99.01 70	98.99 288	99.25 73	99.54 76	99.37 96	97.04 195	99.80 224	97.89 161	99.52 261	99.35 229

APD-MVS_3200maxsize		98.84 105	98.61 139	99.53 38	99.19 216	99.27 27	98.49 133	99.33 194	98.64 145	99.03 179	98.98 207	97.89 130	99.85 154	96.54 277	99.42 285	99.46 179

HQP_MVS		97.99 236	97.67 255	98.93 159	99.19 216	97.65 193	97.77 237	99.27 224	98.20 189	97.79 325	97.98 353	94.90 288	99.70 293	94.42 356	99.51 263	99.45 184

plane_prior7					99.19 216	97.87 170

ab-mvs		98.41 180	98.36 179	98.59 216	99.19 216	97.23 218	99.32 26	98.81 319	97.66 231	98.62 249	99.40 94	96.82 209	99.80 224	95.88 311	99.51 263	98.75 353

F-COLMAP		97.30 292	96.68 319	99.14 118	99.19 216	98.39 114	97.27 302	99.30 209	92.93 411	96.62 390	98.00 351	95.73 267	99.68 306	92.62 402	98.46 383	99.35 229

SR-MVS		98.71 127	98.43 167	99.57 21	99.18 223	99.35 17	98.36 149	99.29 217	98.29 179	98.88 212	98.85 238	97.53 163	99.87 132	96.14 302	99.31 300	99.48 169

UniMVSNet_NR-MVSNet		98.86 103	98.68 125	99.40 68	99.17 224	98.74 88	97.68 249	99.40 164	99.14 92	99.06 167	98.59 295	96.71 220	99.93 52	98.57 117	99.77 151	99.53 143

LF4IMVS		97.90 240	97.69 254	98.52 235	99.17 224	97.66 192	97.19 311	99.47 129	96.31 331	97.85 321	98.20 336	96.71 220	99.52 375	94.62 348	99.72 179	98.38 389

SMA-MVS		98.40 182	98.03 224	99.51 48	99.16 226	99.21 33	98.05 188	99.22 238	94.16 393	98.98 184	99.10 168	97.52 165	99.79 237	96.45 283	99.64 219	99.53 143
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		98.82 110	98.63 133	99.39 69	99.16 226	98.74 88	97.54 273	99.25 230	98.84 137	99.06 167	98.76 259	96.76 216	99.93 52	98.57 117	99.77 151	99.50 152

NR-MVSNet		98.95 90	98.82 105	99.36 70	99.16 226	98.72 93	99.22 45	99.20 241	99.10 101	99.72 46	98.76 259	96.38 236	99.86 141	98.00 156	99.82 118	99.50 152

MVS_111021_LR		98.30 199	98.12 214	98.83 171	99.16 226	98.03 153	96.09 375	99.30 209	97.58 240	98.10 301	98.24 332	98.25 95	99.34 411	96.69 259	99.65 217	99.12 292

DSMNet-mixed		97.42 283	97.60 263	96.87 370	99.15 230	91.46 408	98.54 121	99.12 263	92.87 413	97.58 338	99.63 39	96.21 242	99.90 79	95.74 320	99.54 254	99.27 251

D2MVS		97.84 253	97.84 244	97.83 298	99.14 231	94.74 329	96.94 321	98.88 303	95.84 350	98.89 208	98.96 212	94.40 304	99.69 297	97.55 189	99.95 38	99.05 298

pmmvs5		97.64 265	97.49 269	98.08 283	99.14 231	95.12 318	96.70 336	99.05 274	93.77 400	98.62 249	98.83 245	93.23 324	99.75 268	98.33 132	99.76 164	99.36 225

SPE-MVS-test		99.13 64	99.09 73	99.26 97	99.13 233	98.97 73	99.31 30	99.88 14	99.44 51	98.16 294	98.51 304	98.64 56	99.93 52	98.91 91	99.85 102	98.88 332

VDD-MVS		98.56 158	98.39 174	99.07 131	99.13 233	98.07 148	98.59 115	97.01 395	99.59 35	99.11 160	99.27 120	94.82 292	99.79 237	98.34 130	99.63 222	99.34 231

save fliter					99.11 235	97.97 159	96.53 346	99.02 282	98.24 182

APD-MVS		98.10 222	97.67 255	99.42 64	99.11 235	98.93 79	97.76 240	99.28 221	94.97 374	98.72 237	98.77 257	97.04 195	99.85 154	93.79 376	99.54 254	99.49 158
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 134	98.71 119	98.62 210	99.10 237	96.37 268	97.23 303	98.87 305	99.20 81	99.19 153	98.99 202	97.30 180	99.85 154	98.77 103	99.79 140	99.65 80

EI-MVSNet		98.40 182	98.51 152	98.04 288	99.10 237	94.73 330	97.20 308	98.87 305	98.97 120	99.06 167	99.02 186	96.00 252	99.80 224	98.58 115	99.82 118	99.60 97

CVMVSNet		96.25 344	97.21 286	93.38 437	99.10 237	80.56 465	97.20 308	98.19 362	96.94 302	99.00 181	99.02 186	89.50 372	99.80 224	96.36 289	99.59 236	99.78 45

EI-MVSNet-Vis-set		98.68 139	98.70 122	98.63 208	99.09 240	96.40 267	97.23 303	98.86 310	99.20 81	99.18 157	98.97 209	97.29 182	99.85 154	98.72 107	99.78 145	99.64 81

HPM-MVS++		98.10 222	97.64 260	99.48 56	99.09 240	99.13 60	97.52 275	98.75 330	97.46 258	96.90 378	97.83 363	96.01 251	99.84 172	95.82 318	99.35 294	99.46 179

DP-MVS Recon		97.33 290	96.92 302	98.57 220	99.09 240	97.99 155	96.79 329	99.35 182	93.18 407	97.71 329	98.07 347	95.00 287	99.31 415	93.97 369	99.13 331	98.42 386

MVS_111021_HR		98.25 208	98.08 219	98.75 189	99.09 240	97.46 205	95.97 379	99.27 224	97.60 239	97.99 311	98.25 331	98.15 110	99.38 406	96.87 242	99.57 245	99.42 195

BP-MVS1		97.40 285	96.97 298	98.71 196	99.07 244	96.81 246	98.34 152	97.18 390	98.58 156	98.17 291	98.61 292	84.01 411	99.94 41	98.97 88	99.78 145	99.37 218

9.14			97.78 246		99.07 244		97.53 274	99.32 196	95.53 359	98.54 264	98.70 272	97.58 157	99.76 260	94.32 361	99.46 275

PAPM_NR		96.82 324	96.32 335	98.30 263	99.07 244	96.69 254	97.48 280	98.76 327	95.81 351	96.61 391	96.47 408	94.12 313	99.17 428	90.82 429	97.78 409	99.06 297

TAMVS		98.24 209	98.05 222	98.80 176	99.07 244	97.18 225	97.88 220	98.81 319	96.66 317	99.17 158	99.21 139	94.81 294	99.77 254	96.96 232	99.88 91	99.44 188

CLD-MVS		97.49 276	97.16 288	98.48 241	99.07 244	97.03 234	94.71 424	99.21 239	94.46 385	98.06 304	97.16 394	97.57 158	99.48 387	94.46 353	99.78 145	98.95 318
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 64	99.10 71	99.24 102	99.06 249	99.15 52	99.36 22	99.88 14	99.36 62	98.21 290	98.46 312	98.68 53	99.93 52	99.03 84	99.85 102	98.64 365

thres100view900		94.19 387	93.67 392	95.75 404	99.06 249	91.35 412	98.03 192	94.24 438	98.33 172	97.40 354	94.98 438	79.84 427	99.62 335	83.05 450	98.08 400	96.29 445

thres600view7		94.45 382	93.83 389	96.29 388	99.06 249	91.53 407	97.99 206	94.24 438	98.34 171	97.44 352	95.01 436	79.84 427	99.67 310	84.33 448	98.23 389	97.66 426

plane_prior1					99.05 252

YYNet1		97.60 267	97.67 255	97.39 346	99.04 253	93.04 385	95.27 410	98.38 354	97.25 278	98.92 203	98.95 216	95.48 276	99.73 279	96.99 228	98.74 364	99.41 198

MDA-MVSNet_test_wron		97.60 267	97.66 258	97.41 345	99.04 253	93.09 381	95.27 410	98.42 351	97.26 277	98.88 212	98.95 216	95.43 277	99.73 279	97.02 225	98.72 366	99.41 198

MIMVSNet		96.62 331	96.25 339	97.71 313	99.04 253	94.66 333	99.16 54	96.92 401	97.23 284	97.87 318	99.10 168	86.11 394	99.65 326	91.65 413	99.21 319	98.82 337

icg_test_0407_2		98.20 214	98.38 176	97.65 319	99.03 256	94.03 353	95.78 393	99.45 137	98.16 195	99.06 167	98.71 265	98.27 92	99.68 306	97.50 194	99.45 277	99.22 268

IMVS_0407		98.39 188	98.64 131	97.66 317	99.03 256	94.03 353	98.10 179	99.45 137	98.16 195	99.06 167	98.71 265	98.27 92	99.71 287	97.50 194	99.45 277	99.22 268

IMVS_0404		98.07 226	98.20 201	97.69 314	99.03 256	94.03 353	96.67 337	99.45 137	98.16 195	98.03 308	98.71 265	96.80 212	99.82 200	97.50 194	99.45 277	99.22 268

IMVS_0403		98.34 191	98.56 145	97.66 317	99.03 256	94.03 353	97.98 207	99.45 137	98.16 195	98.89 208	98.71 265	97.90 128	99.74 273	97.50 194	99.45 277	99.22 268

PatchMatch-RL		97.24 298	96.78 313	98.61 213	99.03 256	97.83 174	96.36 357	99.06 271	93.49 405	97.36 358	97.78 364	95.75 266	99.49 384	93.44 385	98.77 363	98.52 374

viewmambaseed2359dif		98.19 215	98.26 194	97.99 291	99.02 261	95.03 321	96.59 343	99.53 104	96.21 334	99.00 181	98.99 202	97.62 153	99.61 342	97.62 184	99.72 179	99.33 236

GDP-MVS		97.50 273	97.11 292	98.67 201	99.02 261	96.85 244	98.16 169	99.71 46	98.32 174	98.52 267	98.54 299	83.39 415	99.95 26	98.79 99	99.56 248	99.19 278

ZD-MVS					99.01 263	98.84 82		99.07 270	94.10 395	98.05 306	98.12 341	96.36 238	99.86 141	92.70 401	99.19 323

CDPH-MVS		97.26 295	96.66 322	99.07 131	99.00 264	98.15 135	96.03 377	99.01 285	91.21 431	97.79 325	97.85 362	96.89 204	99.69 297	92.75 399	99.38 291	99.39 208

diffmvs		98.22 210	98.24 198	98.17 276	99.00 264	95.44 305	96.38 356	99.58 78	97.79 224	98.53 265	98.50 308	96.76 216	99.74 273	97.95 160	99.64 219	99.34 231
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		98.40 182	98.19 205	99.03 141	99.00 264	97.65 193	96.85 327	98.94 290	98.57 157	98.89 208	98.50 308	95.60 270	99.85 154	97.54 191	99.85 102	99.59 104

plane_prior6					98.99 267	97.70 191						94.90 288

xiu_mvs_v1_base_debu		97.86 247	98.17 207	96.92 367	98.98 268	93.91 363	96.45 350	99.17 253	97.85 219	98.41 276	97.14 396	98.47 72	99.92 63	98.02 153	99.05 337	96.92 438

xiu_mvs_v1_base		97.86 247	98.17 207	96.92 367	98.98 268	93.91 363	96.45 350	99.17 253	97.85 219	98.41 276	97.14 396	98.47 72	99.92 63	98.02 153	99.05 337	96.92 438

xiu_mvs_v1_base_debi		97.86 247	98.17 207	96.92 367	98.98 268	93.91 363	96.45 350	99.17 253	97.85 219	98.41 276	97.14 396	98.47 72	99.92 63	98.02 153	99.05 337	96.92 438

MVP-Stereo		98.08 225	97.92 238	98.57 220	98.96 271	96.79 247	97.90 218	99.18 249	96.41 327	98.46 271	98.95 216	95.93 261	99.60 344	96.51 279	98.98 351	99.31 243
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 182	98.68 125	97.54 334	98.96 271	97.99 155	97.88 220	99.36 176	98.20 189	99.63 65	99.04 183	98.76 45	95.33 461	96.56 273	99.74 168	99.31 243
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				98.91 163	98.94 273	97.76 185		98.76 327	87.58 448	96.75 386	98.10 343	94.80 295	99.78 248	92.73 400	99.00 346	99.20 273

USDC		97.41 284	97.40 273	97.44 343	98.94 273	93.67 373	95.17 413	99.53 104	94.03 397	98.97 188	99.10 168	95.29 279	99.34 411	95.84 317	99.73 171	99.30 246

tfpn200view9		94.03 391	93.44 394	95.78 403	98.93 275	91.44 410	97.60 265	94.29 436	97.94 211	97.10 364	94.31 445	79.67 429	99.62 335	83.05 450	98.08 400	96.29 445

testdata				98.09 280	98.93 275	95.40 307		98.80 321	90.08 439	97.45 351	98.37 321	95.26 280	99.70 293	93.58 381	98.95 354	99.17 285

thres400		94.14 389	93.44 394	96.24 391	98.93 275	91.44 410	97.60 265	94.29 436	97.94 211	97.10 364	94.31 445	79.67 429	99.62 335	83.05 450	98.08 400	97.66 426

TAPA-MVS	96.21 11	96.63 330	95.95 341	98.65 202	98.93 275	98.09 142	96.93 323	99.28 221	83.58 454	98.13 298	97.78 364	96.13 245	99.40 402	93.52 382	99.29 305	98.45 379
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 279	96.93 241	95.54 400	98.78 324	85.72 451	96.86 381	98.11 342	94.43 302			99.10 336	99.23 263

PVSNet_BlendedMVS		97.55 272	97.53 266	97.60 326	98.92 279	93.77 370	96.64 339	99.43 151	94.49 383	97.62 334	99.18 146	96.82 209	99.67 310	94.73 345	99.93 54	99.36 225

PVSNet_Blended		96.88 320	96.68 319	97.47 341	98.92 279	93.77 370	94.71 424	99.43 151	90.98 433	97.62 334	97.36 390	96.82 209	99.67 310	94.73 345	99.56 248	98.98 312

MSDG		97.71 260	97.52 267	98.28 265	98.91 282	96.82 245	94.42 434	99.37 172	97.65 232	98.37 281	98.29 330	97.40 174	99.33 413	94.09 367	99.22 316	98.68 363

Anonymous202405211		97.90 240	97.50 268	99.08 129	98.90 283	98.25 125	98.53 122	96.16 413	98.87 132	99.11 160	98.86 235	90.40 364	99.78 248	97.36 203	99.31 300	99.19 278

原ACMM1				98.35 258	98.90 283	96.25 272		98.83 318	92.48 417	96.07 408	98.10 343	95.39 278	99.71 287	92.61 403	98.99 348	99.08 294

GBi-Net		98.65 144	98.47 161	99.17 111	98.90 283	98.24 126	99.20 48	99.44 145	98.59 153	98.95 193	99.55 57	94.14 310	99.86 141	97.77 173	99.69 198	99.41 198

test1		98.65 144	98.47 161	99.17 111	98.90 283	98.24 126	99.20 48	99.44 145	98.59 153	98.95 193	99.55 57	94.14 310	99.86 141	97.77 173	99.69 198	99.41 198

FMVSNet2		98.49 173	98.40 171	98.75 189	98.90 283	97.14 230	98.61 113	99.13 262	98.59 153	99.19 153	99.28 118	94.14 310	99.82 200	97.97 158	99.80 134	99.29 248

OMC-MVS		97.88 244	97.49 269	99.04 140	98.89 288	98.63 95	96.94 321	99.25 230	95.02 372	98.53 265	98.51 304	97.27 183	99.47 390	93.50 384	99.51 263	99.01 306

VortexMVS		97.98 237	98.31 187	97.02 361	98.88 289	91.45 409	98.03 192	99.47 129	98.65 144	99.55 74	99.47 77	91.49 353	99.81 216	99.32 59	99.91 76	99.80 40

MVSFormer		98.26 205	98.43 167	97.77 303	98.88 289	93.89 366	99.39 20	99.56 92	99.11 94	98.16 294	98.13 339	93.81 318	99.97 7	99.26 64	99.57 245	99.43 192

lupinMVS		97.06 310	96.86 306	97.65 319	98.88 289	93.89 366	95.48 404	97.97 368	93.53 403	98.16 294	97.58 376	93.81 318	99.91 72	96.77 250	99.57 245	99.17 285

dmvs_re		95.98 352	95.39 362	97.74 309	98.86 292	97.45 206	98.37 148	95.69 425	97.95 209	96.56 392	95.95 417	90.70 361	97.68 455	88.32 438	96.13 442	98.11 401

DELS-MVS		98.27 203	98.20 201	98.48 241	98.86 292	96.70 253	95.60 399	99.20 241	97.73 227	98.45 272	98.71 265	97.50 167	99.82 200	98.21 138	99.59 236	98.93 323
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		97.89 242	97.98 229	97.60 326	98.86 292	94.35 341	96.21 366	99.44 145	97.45 260	99.06 167	98.88 232	97.99 123	99.28 421	94.38 360	99.58 241	99.18 281

LCM-MVSNet-Re		98.64 146	98.48 159	99.11 122	98.85 295	98.51 108	98.49 133	99.83 25	98.37 168	99.69 54	99.46 79	98.21 102	99.92 63	94.13 366	99.30 303	98.91 327

pmmvs4		97.58 270	97.28 281	98.51 236	98.84 296	96.93 241	95.40 408	98.52 346	93.60 402	98.61 251	98.65 283	95.10 284	99.60 344	96.97 231	99.79 140	98.99 311

NP-MVS					98.84 296	97.39 210					96.84 399

sss		97.21 300	96.93 300	98.06 285	98.83 298	95.22 314	96.75 333	98.48 348	94.49 383	97.27 360	97.90 359	92.77 336	99.80 224	96.57 269	99.32 298	99.16 288

PVSNet	93.40 17	95.67 361	95.70 347	95.57 408	98.83 298	88.57 435	92.50 451	97.72 373	92.69 415	96.49 400	96.44 409	93.72 321	99.43 398	93.61 379	99.28 306	98.71 356

MVE	83.40 22	92.50 414	91.92 416	94.25 424	98.83 298	91.64 406	92.71 450	83.52 464	95.92 348	86.46 462	95.46 430	95.20 281	95.40 460	80.51 455	98.64 375	95.73 453
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 395	93.91 387	93.39 436	98.82 301	81.72 463	97.76 240	95.28 427	98.60 152	96.54 393	96.66 403	65.85 459	99.62 335	96.65 262	98.99 348	98.82 337

ambc				98.24 269	98.82 301	95.97 283	98.62 112	99.00 287		99.27 136	99.21 139	96.99 200	99.50 381	96.55 276	99.50 270	99.26 257

旧先验1					98.82 301	97.45 206		98.76 327			98.34 325	95.50 275			99.01 345	99.23 263

test_vis1_rt		97.75 257	97.72 252	97.83 298	98.81 304	96.35 269	97.30 298	99.69 51	94.61 381	97.87 318	98.05 348	96.26 241	98.32 449	98.74 105	98.18 392	98.82 337

WTY-MVS		96.67 328	96.27 338	97.87 296	98.81 304	94.61 335	96.77 331	97.92 370	94.94 375	97.12 363	97.74 367	91.11 357	99.82 200	93.89 372	98.15 396	99.18 281

3Dnovator+	97.89 3	98.69 134	98.51 152	99.24 102	98.81 304	98.40 113	99.02 69	99.19 245	98.99 117	98.07 303	99.28 118	97.11 193	99.84 172	96.84 245	99.32 298	99.47 177

QAPM		97.31 291	96.81 312	98.82 172	98.80 307	97.49 201	99.06 65	99.19 245	90.22 437	97.69 331	99.16 152	96.91 203	99.90 79	90.89 428	99.41 286	99.07 296

VNet		98.42 179	98.30 188	98.79 179	98.79 308	97.29 214	98.23 160	98.66 337	99.31 67	98.85 217	98.80 251	94.80 295	99.78 248	98.13 143	99.13 331	99.31 243

DPM-MVS		96.32 340	95.59 353	98.51 236	98.76 309	97.21 222	94.54 433	98.26 357	91.94 422	96.37 401	97.25 392	93.06 330	99.43 398	91.42 418	98.74 364	98.89 329

3Dnovator	98.27 2	98.81 112	98.73 114	99.05 138	98.76 309	97.81 182	99.25 43	99.30 209	98.57 157	98.55 262	99.33 108	97.95 125	99.90 79	97.16 213	99.67 209	99.44 188

PLC	94.65 16	96.51 333	95.73 346	98.85 169	98.75 311	97.91 167	96.42 354	99.06 271	90.94 434	95.59 414	97.38 388	94.41 303	99.59 348	90.93 426	98.04 405	99.05 298
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 322	96.75 315	97.08 358	98.74 312	93.33 379	96.71 335	98.26 357	96.72 314	98.44 273	97.37 389	95.20 281	99.47 390	91.89 408	97.43 419	98.44 382

hse-mvs2		97.46 278	97.07 293	98.64 204	98.73 313	97.33 212	97.45 284	97.64 380	99.11 94	98.58 257	97.98 353	88.65 379	99.79 237	98.11 144	97.39 421	98.81 342

CDS-MVSNet		97.69 261	97.35 278	98.69 198	98.73 313	97.02 235	96.92 325	98.75 330	95.89 349	98.59 255	98.67 278	92.08 347	99.74 273	96.72 256	99.81 123	99.32 239
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SD_0403		96.28 342	95.83 343	97.64 322	98.72 315	94.30 342	98.87 88	98.77 325	97.80 222	96.53 394	98.02 350	97.34 178	99.47 390	76.93 459	99.48 273	99.16 288

EIA-MVS		98.00 233	97.74 249	98.80 176	98.72 315	98.09 142	98.05 188	99.60 72	97.39 264	96.63 389	95.55 425	97.68 145	99.80 224	96.73 255	99.27 307	98.52 374

LFMVS		97.20 301	96.72 316	98.64 204	98.72 315	96.95 239	98.93 81	94.14 440	99.74 13	98.78 228	99.01 197	84.45 406	99.73 279	97.44 199	99.27 307	99.25 258

new_pmnet		96.99 317	96.76 314	97.67 315	98.72 315	94.89 324	95.95 383	98.20 360	92.62 416	98.55 262	98.54 299	94.88 291	99.52 375	93.96 370	99.44 284	98.59 371

Fast-Effi-MVS+		97.67 263	97.38 275	98.57 220	98.71 319	97.43 208	97.23 303	99.45 137	94.82 378	96.13 405	96.51 405	98.52 70	99.91 72	96.19 298	98.83 360	98.37 391

TEST9					98.71 319	98.08 146	95.96 381	99.03 279	91.40 428	95.85 411	97.53 378	96.52 229	99.76 260

train_agg		97.10 307	96.45 332	99.07 131	98.71 319	98.08 146	95.96 381	99.03 279	91.64 423	95.85 411	97.53 378	96.47 231	99.76 260	93.67 378	99.16 326	99.36 225

TSAR-MVS + GP.		98.18 217	97.98 229	98.77 186	98.71 319	97.88 169	96.32 360	98.66 337	96.33 329	99.23 147	98.51 304	97.48 171	99.40 402	97.16 213	99.46 275	99.02 305

FA-MVS(test-final)		96.99 317	96.82 310	97.50 338	98.70 323	94.78 327	99.34 23	96.99 396	95.07 371	98.48 270	99.33 108	88.41 382	99.65 326	96.13 304	98.92 357	98.07 404

AUN-MVS		96.24 346	95.45 358	98.60 215	98.70 323	97.22 220	97.38 289	97.65 378	95.95 347	95.53 421	97.96 357	82.11 423	99.79 237	96.31 291	97.44 418	98.80 347

our_test_3		97.39 286	97.73 251	96.34 386	98.70 323	89.78 431	94.61 430	98.97 289	96.50 322	99.04 176	98.85 238	95.98 257	99.84 172	97.26 208	99.67 209	99.41 198

ppachtmachnet_test		97.50 273	97.74 249	96.78 376	98.70 323	91.23 418	94.55 432	99.05 274	96.36 328	99.21 151	98.79 253	96.39 234	99.78 248	96.74 253	99.82 118	99.34 231

PCF-MVS	92.86 18	94.36 383	93.00 401	98.42 248	98.70 323	97.56 198	93.16 449	99.11 265	79.59 458	97.55 341	97.43 385	92.19 344	99.73 279	79.85 456	99.45 277	97.97 410
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 239	98.02 225	97.58 328	98.69 328	94.10 349	98.13 172	98.90 299	97.95 209	97.32 359	99.58 47	95.95 260	98.75 444	96.41 285	99.22 316	99.87 21

ETV-MVS		98.03 229	97.86 243	98.56 225	98.69 328	98.07 148	97.51 277	99.50 112	98.10 201	97.50 346	95.51 426	98.41 78	99.88 113	96.27 294	99.24 312	97.71 425

test_prior				98.95 156	98.69 328	97.95 163		99.03 279					99.59 348			99.30 246

mvsmamba		97.57 271	97.26 282	98.51 236	98.69 328	96.73 252	98.74 97	97.25 389	97.03 298	97.88 317	99.23 137	90.95 358	99.87 132	96.61 265	99.00 346	98.91 327

agg_prior					98.68 332	97.99 155		99.01 285		95.59 414			99.77 254

test_8					98.67 333	98.01 154	95.91 387	99.02 282	91.64 423	95.79 413	97.50 381	96.47 231	99.76 260

HQP-NCC					98.67 333		96.29 362		96.05 340	95.55 417

ACMP_Plane					98.67 333		96.29 362		96.05 340	95.55 417

CNVR-MVS		98.17 219	97.87 242	99.07 131	98.67 333	98.24 126	97.01 317	98.93 293	97.25 278	97.62 334	98.34 325	97.27 183	99.57 357	96.42 284	99.33 297	99.39 208

HQP-MVS		97.00 316	96.49 331	98.55 227	98.67 333	96.79 247	96.29 362	99.04 277	96.05 340	95.55 417	96.84 399	93.84 316	99.54 369	92.82 396	99.26 310	99.32 239

MM		98.22 210	97.99 228	98.91 163	98.66 338	96.97 236	97.89 219	94.44 434	99.54 39	98.95 193	99.14 159	93.50 322	99.92 63	99.80 16	99.96 28	99.85 29

test_fmvs1		97.72 259	97.94 235	97.07 360	98.66 338	92.39 396	97.68 249	99.81 31	95.20 370	99.54 76	99.44 84	91.56 352	99.41 401	99.78 20	99.77 151	99.40 207

balanced_conf03		98.63 148	98.72 116	98.38 253	98.66 338	96.68 255	98.90 83	99.42 157	98.99 117	98.97 188	99.19 142	95.81 265	99.85 154	98.77 103	99.77 151	98.60 368

thres200		93.72 397	93.14 399	95.46 412	98.66 338	91.29 414	96.61 341	94.63 433	97.39 264	96.83 382	93.71 448	79.88 426	99.56 360	82.40 453	98.13 397	95.54 454

wuyk23d		96.06 348	97.62 262	91.38 441	98.65 342	98.57 102	98.85 92	96.95 399	96.86 307	99.90 14	99.16 152	99.18 19	98.40 448	89.23 436	99.77 151	77.18 461

NCCC		97.86 247	97.47 272	99.05 138	98.61 343	98.07 148	96.98 319	98.90 299	97.63 233	97.04 368	97.93 358	95.99 256	99.66 321	95.31 333	98.82 362	99.43 192

DeepC-MVS_fast	96.85 6	98.30 199	98.15 211	98.75 189	98.61 343	97.23 218	97.76 240	99.09 268	97.31 272	98.75 234	98.66 281	97.56 159	99.64 329	96.10 305	99.55 252	99.39 208
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 399	92.09 410	97.75 307	98.60 345	94.40 339	97.32 296	95.26 428	97.56 243	96.79 385	95.50 427	53.57 467	99.77 254	95.26 334	98.97 352	99.08 294

thisisatest0515		94.12 390	93.16 398	96.97 365	98.60 345	92.90 386	93.77 445	90.61 453	94.10 395	96.91 375	95.87 420	74.99 441	99.80 224	94.52 351	99.12 334	98.20 397

GA-MVS		95.86 355	95.32 365	97.49 339	98.60 345	94.15 348	93.83 444	97.93 369	95.49 360	96.68 387	97.42 386	83.21 416	99.30 417	96.22 296	98.55 381	99.01 306

dmvs_testset		92.94 409	92.21 409	95.13 416	98.59 348	90.99 421	97.65 255	92.09 449	96.95 301	94.00 441	93.55 449	92.34 342	96.97 458	72.20 460	92.52 456	97.43 433

OPU-MVS				98.82 172	98.59 348	98.30 122	98.10 179				98.52 303	98.18 104	98.75 444	94.62 348	99.48 273	99.41 198

MSLP-MVS++		98.02 230	98.14 213	97.64 322	98.58 350	95.19 315	97.48 280	99.23 237	97.47 253	97.90 315	98.62 290	97.04 195	98.81 442	97.55 189	99.41 286	98.94 322

test12				98.93 159	98.58 350	97.83 174		98.66 337		96.53 394		95.51 274	99.69 297		99.13 331	99.27 251

CL-MVSNet_self_test		97.44 281	97.22 285	98.08 283	98.57 352	95.78 291	94.30 437	98.79 322	96.58 320	98.60 253	98.19 337	94.74 298	99.64 329	96.41 285	98.84 359	98.82 337

PS-MVSNAJ		97.08 309	97.39 274	96.16 397	98.56 353	92.46 394	95.24 412	98.85 313	97.25 278	97.49 347	95.99 416	98.07 114	99.90 79	96.37 287	98.67 374	96.12 450

CNLPA		97.17 304	96.71 317	98.55 227	98.56 353	98.05 152	96.33 359	98.93 293	96.91 304	97.06 367	97.39 387	94.38 305	99.45 395	91.66 412	99.18 325	98.14 400

xiu_mvs_v2_base		97.16 305	97.49 269	96.17 395	98.54 355	92.46 394	95.45 405	98.84 314	97.25 278	97.48 348	96.49 406	98.31 88	99.90 79	96.34 290	98.68 373	96.15 449

alignmvs		97.35 288	96.88 305	98.78 182	98.54 355	98.09 142	97.71 246	97.69 375	99.20 81	97.59 337	95.90 419	88.12 384	99.55 364	98.18 140	98.96 353	98.70 359

FE-MVS		95.66 362	94.95 375	97.77 303	98.53 357	95.28 311	99.40 19	96.09 416	93.11 409	97.96 312	99.26 125	79.10 433	99.77 254	92.40 405	98.71 368	98.27 395

Effi-MVS+		98.02 230	97.82 245	98.62 210	98.53 357	97.19 224	97.33 295	99.68 56	97.30 273	96.68 387	97.46 384	98.56 68	99.80 224	96.63 263	98.20 391	98.86 334

baseline1		95.96 353	95.44 359	97.52 336	98.51 359	93.99 360	98.39 146	96.09 416	98.21 185	98.40 280	97.76 366	86.88 386	99.63 332	95.42 331	89.27 459	98.95 318

MVS_Test		98.18 217	98.36 179	97.67 315	98.48 360	94.73 330	98.18 165	99.02 282	97.69 229	98.04 307	99.11 165	97.22 187	99.56 360	98.57 117	98.90 358	98.71 356

MGCFI-Net		98.34 191	98.28 190	98.51 236	98.47 361	97.59 197	98.96 77	99.48 121	99.18 88	97.40 354	95.50 427	98.66 54	99.50 381	98.18 140	98.71 368	98.44 382

BH-RMVSNet		96.83 322	96.58 327	97.58 328	98.47 361	94.05 350	96.67 337	97.36 384	96.70 316	97.87 318	97.98 353	95.14 283	99.44 397	90.47 431	98.58 380	99.25 258

sasdasda		98.34 191	98.26 194	98.58 217	98.46 363	97.82 179	98.96 77	99.46 133	99.19 85	97.46 349	95.46 430	98.59 62	99.46 393	98.08 147	98.71 368	98.46 376

canonicalmvs		98.34 191	98.26 194	98.58 217	98.46 363	97.82 179	98.96 77	99.46 133	99.19 85	97.46 349	95.46 430	98.59 62	99.46 393	98.08 147	98.71 368	98.46 376

MVS-HIRNet		94.32 384	95.62 350	90.42 442	98.46 363	75.36 466	96.29 362	89.13 457	95.25 367	95.38 423	99.75 16	92.88 333	99.19 427	94.07 368	99.39 288	96.72 443

PHI-MVS		98.29 202	97.95 233	99.34 79	98.44 366	99.16 48	98.12 176	99.38 168	96.01 344	98.06 304	98.43 315	97.80 138	99.67 310	95.69 323	99.58 241	99.20 273

DVP-MVS++		98.90 96	98.70 122	99.51 48	98.43 367	99.15 52	99.43 15	99.32 196	98.17 192	99.26 140	99.02 186	98.18 104	99.88 113	97.07 222	99.45 277	99.49 158

MSC_two_6792asdad				99.32 87	98.43 367	98.37 117		98.86 310					99.89 95	97.14 216	99.60 232	99.71 60

No_MVS				99.32 87	98.43 367	98.37 117		98.86 310					99.89 95	97.14 216	99.60 232	99.71 60

Fast-Effi-MVS+-dtu		98.27 203	98.09 216	98.81 174	98.43 367	98.11 139	97.61 264	99.50 112	98.64 145	97.39 356	97.52 380	98.12 112	99.95 26	96.90 239	98.71 368	98.38 389

OpenMVS_ROB	95.38 14	95.84 357	95.18 370	97.81 300	98.41 371	97.15 229	97.37 292	98.62 341	83.86 453	98.65 245	98.37 321	94.29 308	99.68 306	88.41 437	98.62 378	96.60 444

DeepPCF-MVS	96.93 5	98.32 196	98.01 226	99.23 104	98.39 372	98.97 73	95.03 417	99.18 249	96.88 305	99.33 123	98.78 255	98.16 108	99.28 421	96.74 253	99.62 225	99.44 188

Patchmatch-test		96.55 332	96.34 334	97.17 355	98.35 373	93.06 382	98.40 145	97.79 371	97.33 269	98.41 276	98.67 278	83.68 414	99.69 297	95.16 336	99.31 300	98.77 350

AdaColmap		97.14 306	96.71 317	98.46 243	98.34 374	97.80 183	96.95 320	98.93 293	95.58 357	96.92 373	97.66 371	95.87 263	99.53 371	90.97 425	99.14 329	98.04 405

OpenMVS	96.65 7	97.09 308	96.68 319	98.32 260	98.32 375	97.16 228	98.86 91	99.37 172	89.48 441	96.29 403	99.15 156	96.56 227	99.90 79	92.90 393	99.20 320	97.89 413

MG-MVS		96.77 325	96.61 324	97.26 351	98.31 376	93.06 382	95.93 384	98.12 365	96.45 326	97.92 313	98.73 262	93.77 320	99.39 404	91.19 423	99.04 340	99.33 236

test_yl		96.69 326	96.29 336	97.90 293	98.28 377	95.24 312	97.29 299	97.36 384	98.21 185	98.17 291	97.86 360	86.27 390	99.55 364	94.87 342	98.32 385	98.89 329

DCV-MVSNet		96.69 326	96.29 336	97.90 293	98.28 377	95.24 312	97.29 299	97.36 384	98.21 185	98.17 291	97.86 360	86.27 390	99.55 364	94.87 342	98.32 385	98.89 329

CHOSEN 280x420		95.51 367	95.47 356	95.65 407	98.25 379	88.27 438	93.25 448	98.88 303	93.53 403	94.65 432	97.15 395	86.17 392	99.93 52	97.41 201	99.93 54	98.73 355

SCA		96.41 339	96.66 322	95.67 405	98.24 380	88.35 437	95.85 390	96.88 402	96.11 338	97.67 332	98.67 278	93.10 328	99.85 154	94.16 362	99.22 316	98.81 342

DeepMVS_CX				93.44 435	98.24 380	94.21 345		94.34 435	64.28 461	91.34 455	94.87 442	89.45 373	92.77 462	77.54 458	93.14 455	93.35 457

MS-PatchMatch		97.68 262	97.75 248	97.45 342	98.23 382	93.78 369	97.29 299	98.84 314	96.10 339	98.64 246	98.65 283	96.04 249	99.36 407	96.84 245	99.14 329	99.20 273

BH-w/o		95.13 373	94.89 377	95.86 400	98.20 383	91.31 413	95.65 397	97.37 383	93.64 401	96.52 396	95.70 423	93.04 331	99.02 433	88.10 439	95.82 445	97.24 436

mvs_anonymous		97.83 255	98.16 210	96.87 370	98.18 384	91.89 403	97.31 297	98.90 299	97.37 266	98.83 220	99.46 79	96.28 240	99.79 237	98.90 92	98.16 395	98.95 318

miper_lstm_enhance		97.18 303	97.16 288	97.25 352	98.16 385	92.85 387	95.15 415	99.31 201	97.25 278	98.74 236	98.78 255	90.07 365	99.78 248	97.19 211	99.80 134	99.11 293

RRT-MVS		97.88 244	97.98 229	97.61 325	98.15 386	93.77 370	98.97 76	99.64 65	99.16 90	98.69 239	99.42 87	91.60 350	99.89 95	97.63 183	98.52 382	99.16 288

ET-MVSNet_ETH3D		94.30 386	93.21 397	97.58 328	98.14 387	94.47 338	94.78 423	93.24 445	94.72 379	89.56 457	95.87 420	78.57 436	99.81 216	96.91 234	97.11 430	98.46 376

ADS-MVSNet2		95.43 368	94.98 373	96.76 377	98.14 387	91.74 404	97.92 215	97.76 372	90.23 435	96.51 397	98.91 222	85.61 397	99.85 154	92.88 394	96.90 431	98.69 360

ADS-MVSNet		95.24 371	94.93 376	96.18 394	98.14 387	90.10 430	97.92 215	97.32 387	90.23 435	96.51 397	98.91 222	85.61 397	99.74 273	92.88 394	96.90 431	98.69 360

c3_l		97.36 287	97.37 276	97.31 347	98.09 390	93.25 380	95.01 418	99.16 256	97.05 295	98.77 231	98.72 264	92.88 333	99.64 329	96.93 233	99.76 164	99.05 298

FMVSNet3		97.50 273	97.24 284	98.29 264	98.08 391	95.83 288	97.86 224	98.91 298	97.89 216	98.95 193	98.95 216	87.06 385	99.81 216	97.77 173	99.69 198	99.23 263

PAPM		91.88 423	90.34 426	96.51 381	98.06 392	92.56 392	92.44 452	97.17 391	86.35 449	90.38 456	96.01 415	86.61 388	99.21 426	70.65 462	95.43 447	97.75 422

Effi-MVS+-dtu		98.26 205	97.90 240	99.35 76	98.02 393	99.49 6	98.02 195	99.16 256	98.29 179	97.64 333	97.99 352	96.44 233	99.95 26	96.66 261	98.93 356	98.60 368

eth_miper_zixun_eth		97.23 299	97.25 283	97.17 355	98.00 394	92.77 389	94.71 424	99.18 249	97.27 276	98.56 260	98.74 261	91.89 348	99.69 297	97.06 224	99.81 123	99.05 298

HY-MVS	95.94 13	95.90 354	95.35 364	97.55 333	97.95 395	94.79 326	98.81 96	96.94 400	92.28 420	95.17 425	98.57 297	89.90 367	99.75 268	91.20 422	97.33 426	98.10 402

UGNet		98.53 166	98.45 164	98.79 179	97.94 396	96.96 238	99.08 61	98.54 344	99.10 101	96.82 383	99.47 77	96.55 228	99.84 172	98.56 120	99.94 49	99.55 130
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		96.47 337	95.70 347	98.79 179	97.92 397	99.12 62	98.28 154	98.60 342	92.16 421	95.54 420	96.17 413	94.77 297	99.52 375	89.62 434	98.23 389	97.72 424
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		96.86 321	96.55 328	97.79 301	97.91 398	94.21 345	97.56 270	98.87 305	97.49 252	99.06 167	99.05 181	80.72 424	99.80 224	98.44 125	99.82 118	99.37 218

API-MVS		97.04 312	96.91 304	97.42 344	97.88 399	98.23 130	98.18 165	98.50 347	97.57 241	97.39 356	96.75 401	96.77 214	99.15 430	90.16 432	99.02 344	94.88 455

myMVS_eth3d28		92.92 410	92.31 406	94.77 419	97.84 400	87.59 442	96.19 368	96.11 415	97.08 294	94.27 435	93.49 451	66.07 458	98.78 443	91.78 410	97.93 408	97.92 412

miper_ehance_all_eth		97.06 310	97.03 295	97.16 357	97.83 401	93.06 382	94.66 427	99.09 268	95.99 345	98.69 239	98.45 313	92.73 338	99.61 342	96.79 247	99.03 341	98.82 337

cl____		97.02 313	96.83 309	97.58 328	97.82 402	94.04 352	94.66 427	99.16 256	97.04 296	98.63 247	98.71 265	88.68 378	99.69 297	97.00 226	99.81 123	99.00 310

DIV-MVS_self_test		97.02 313	96.84 308	97.58 328	97.82 402	94.03 353	94.66 427	99.16 256	97.04 296	98.63 247	98.71 265	88.69 376	99.69 297	97.00 226	99.81 123	99.01 306

CANet		97.87 246	97.76 247	98.19 275	97.75 404	95.51 298	96.76 332	99.05 274	97.74 226	96.93 372	98.21 335	95.59 271	99.89 95	97.86 168	99.93 54	99.19 278

UBG		93.25 404	92.32 405	96.04 399	97.72 405	90.16 429	95.92 386	95.91 420	96.03 343	93.95 443	93.04 454	69.60 448	99.52 375	90.72 430	97.98 406	98.45 379

mvsany_test1		97.60 267	97.54 265	97.77 303	97.72 405	95.35 308	95.36 409	97.13 393	94.13 394	99.71 48	99.33 108	97.93 126	99.30 417	97.60 187	98.94 355	98.67 364

PVSNet_0	89.98 21	91.15 424	90.30 427	93.70 432	97.72 405	84.34 456	90.24 455	97.42 382	90.20 438	93.79 444	93.09 453	90.90 360	98.89 441	86.57 445	72.76 462	97.87 415

CR-MVSNet		96.28 342	95.95 341	97.28 349	97.71 408	94.22 343	98.11 177	98.92 296	92.31 419	96.91 375	99.37 96	85.44 400	99.81 216	97.39 202	97.36 424	97.81 418

RPMNet		97.02 313	96.93 300	97.30 348	97.71 408	94.22 343	98.11 177	99.30 209	99.37 59	96.91 375	99.34 105	86.72 387	99.87 132	97.53 192	97.36 424	97.81 418

ETVMVS		92.60 413	91.08 422	97.18 353	97.70 410	93.65 375	96.54 344	95.70 423	96.51 321	94.68 431	92.39 457	61.80 464	99.50 381	86.97 442	97.41 420	98.40 387

pmmvs3		95.03 375	94.40 382	96.93 366	97.70 410	92.53 393	95.08 416	97.71 374	88.57 445	97.71 329	98.08 346	79.39 431	99.82 200	96.19 298	99.11 335	98.43 384

baseline2		93.73 396	92.83 402	96.42 384	97.70 410	91.28 415	96.84 328	89.77 456	93.96 399	92.44 451	95.93 418	79.14 432	99.77 254	92.94 392	96.76 435	98.21 396

WBMVS		95.18 372	94.78 378	96.37 385	97.68 413	89.74 432	95.80 392	98.73 333	97.54 247	98.30 282	98.44 314	70.06 446	99.82 200	96.62 264	99.87 95	99.54 134

tpm		94.67 380	94.34 384	95.66 406	97.68 413	88.42 436	97.88 220	94.90 430	94.46 385	96.03 410	98.56 298	78.66 434	99.79 237	95.88 311	95.01 449	98.78 349

CANet_DTU		97.26 295	97.06 294	97.84 297	97.57 415	94.65 334	96.19 368	98.79 322	97.23 284	95.14 426	98.24 332	93.22 325	99.84 172	97.34 204	99.84 107	99.04 302

testing11		93.08 407	92.02 412	96.26 390	97.56 416	90.83 424	96.32 360	95.70 423	96.47 325	92.66 450	93.73 447	64.36 462	99.59 348	93.77 377	97.57 413	98.37 391

tpm2		93.09 406	92.58 404	94.62 421	97.56 416	86.53 445	97.66 253	95.79 422	86.15 450	94.07 440	98.23 334	75.95 439	99.53 371	90.91 427	96.86 434	97.81 418

testing91		93.32 402	92.27 407	96.47 383	97.54 418	91.25 416	96.17 372	96.76 404	97.18 288	93.65 446	93.50 450	65.11 461	99.63 332	93.04 391	97.45 417	98.53 373

TR-MVS		95.55 365	95.12 371	96.86 373	97.54 418	93.94 361	96.49 349	96.53 409	94.36 390	97.03 370	96.61 404	94.26 309	99.16 429	86.91 444	96.31 439	97.47 432

testing99		93.04 408	91.98 415	96.23 392	97.53 420	90.70 426	96.35 358	95.94 419	96.87 306	93.41 447	93.43 452	63.84 463	99.59 348	93.24 389	97.19 427	98.40 387

1314		95.74 359	95.60 351	96.17 395	97.53 420	92.75 390	98.07 185	98.31 356	91.22 430	94.25 436	96.68 402	95.53 272	99.03 432	91.64 414	97.18 428	96.74 442

CostFormer		93.97 392	93.78 390	94.51 422	97.53 420	85.83 448	97.98 207	95.96 418	89.29 443	94.99 428	98.63 288	78.63 435	99.62 335	94.54 350	96.50 436	98.09 403

FMVSNet5		96.01 350	95.20 369	98.41 249	97.53 420	96.10 274	98.74 97	99.50 112	97.22 287	98.03 308	99.04 183	69.80 447	99.88 113	97.27 207	99.71 188	99.25 258

PMMVS		96.51 333	95.98 340	98.09 280	97.53 420	95.84 287	94.92 420	98.84 314	91.58 425	96.05 409	95.58 424	95.68 268	99.66 321	95.59 327	98.09 399	98.76 352

reproduce_monomvs		95.00 377	95.25 366	94.22 425	97.51 425	83.34 457	97.86 224	98.44 349	98.51 162	99.29 133	99.30 114	67.68 452	99.56 360	98.89 94	99.81 123	99.77 48

PAPR		95.29 369	94.47 380	97.75 307	97.50 426	95.14 317	94.89 421	98.71 335	91.39 429	95.35 424	95.48 429	94.57 300	99.14 431	84.95 447	97.37 422	98.97 315

testing222		91.96 421	90.37 425	96.72 378	97.47 427	92.59 391	96.11 374	94.76 431	96.83 308	92.90 449	92.87 455	57.92 465	99.55 364	86.93 443	97.52 414	98.00 409

PatchT		96.65 329	96.35 333	97.54 334	97.40 428	95.32 310	97.98 207	96.64 406	99.33 64	96.89 379	99.42 87	84.32 408	99.81 216	97.69 182	97.49 415	97.48 431

tpm cat1		93.29 403	93.13 400	93.75 431	97.39 429	84.74 451	97.39 288	97.65 378	83.39 455	94.16 437	98.41 316	82.86 419	99.39 404	91.56 416	95.35 448	97.14 437

PatchmatchNet		95.58 364	95.67 349	95.30 415	97.34 430	87.32 443	97.65 255	96.65 405	95.30 366	97.07 366	98.69 274	84.77 403	99.75 268	94.97 340	98.64 375	98.83 336
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 288	96.97 298	98.50 240	97.31 431	96.47 265	98.18 165	98.92 296	98.95 124	98.78 228	99.37 96	85.44 400	99.85 154	95.96 309	99.83 114	99.17 285

LS3D		98.63 148	98.38 176	99.36 70	97.25 432	99.38 13	99.12 60	99.32 196	99.21 79	98.44 273	98.88 232	97.31 179	99.80 224	96.58 267	99.34 296	98.92 324

IB-MVS	91.63 19	92.24 419	90.90 423	96.27 389	97.22 433	91.24 417	94.36 436	93.33 444	92.37 418	92.24 453	94.58 444	66.20 457	99.89 95	93.16 390	94.63 451	97.66 426
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		92.38 416	91.76 419	94.21 426	97.16 434	84.65 452	95.42 407	88.45 458	95.96 346	96.17 404	95.84 422	66.36 455	99.71 287	91.87 409	98.64 375	98.28 394

tpmrst		95.07 374	95.46 357	93.91 429	97.11 435	84.36 455	97.62 260	96.96 398	94.98 373	96.35 402	98.80 251	85.46 399	99.59 348	95.60 326	96.23 440	97.79 421

Syy-MVS		96.04 349	95.56 355	97.49 339	97.10 436	94.48 337	96.18 370	96.58 407	95.65 354	94.77 429	92.29 458	91.27 356	99.36 407	98.17 142	98.05 403	98.63 366

myMVS_eth3d		91.92 422	90.45 424	96.30 387	97.10 436	90.90 422	96.18 370	96.58 407	95.65 354	94.77 429	92.29 458	53.88 466	99.36 407	89.59 435	98.05 403	98.63 366

MDTV_nov1_ep13			95.22 368		97.06 438	83.20 458	97.74 243	96.16 413	94.37 389	96.99 371	98.83 245	83.95 412	99.53 371	93.90 371	97.95 407

MVS		93.19 405	92.09 410	96.50 382	96.91 439	94.03 353	98.07 185	98.06 367	68.01 460	94.56 434	96.48 407	95.96 259	99.30 417	83.84 449	96.89 433	96.17 447

E-PMN		94.17 388	94.37 383	93.58 433	96.86 440	85.71 449	90.11 457	97.07 394	98.17 192	97.82 324	97.19 393	84.62 405	98.94 437	89.77 433	97.68 412	96.09 451

JIA-IIPM		95.52 366	95.03 372	97.00 362	96.85 441	94.03 353	96.93 323	95.82 421	99.20 81	94.63 433	99.71 22	83.09 417	99.60 344	94.42 356	94.64 450	97.36 435

EMVS		93.83 394	94.02 386	93.23 438	96.83 442	84.96 450	89.77 458	96.32 411	97.92 213	97.43 353	96.36 412	86.17 392	98.93 438	87.68 440	97.73 411	95.81 452

cl22		95.79 358	95.39 362	96.98 364	96.77 443	92.79 388	94.40 435	98.53 345	94.59 382	97.89 316	98.17 338	82.82 420	99.24 423	96.37 287	99.03 341	98.92 324

WB-MVSnew		95.73 360	95.57 354	96.23 392	96.70 444	90.70 426	96.07 376	93.86 441	95.60 356	97.04 368	95.45 433	96.00 252	99.55 364	91.04 424	98.31 387	98.43 384

dp		93.47 400	93.59 393	93.13 439	96.64 445	81.62 464	97.66 253	96.42 410	92.80 414	96.11 406	98.64 286	78.55 437	99.59 348	93.31 387	92.18 458	98.16 399

MonoMVSNet		96.25 344	96.53 330	95.39 413	96.57 446	91.01 420	98.82 95	97.68 377	98.57 157	98.03 308	99.37 96	90.92 359	97.78 454	94.99 338	93.88 454	97.38 434

test-LLR		93.90 393	93.85 388	94.04 427	96.53 447	84.62 453	94.05 441	92.39 447	96.17 335	94.12 438	95.07 434	82.30 421	99.67 310	95.87 314	98.18 392	97.82 416

test-mter		92.33 418	91.76 419	94.04 427	96.53 447	84.62 453	94.05 441	92.39 447	94.00 398	94.12 438	95.07 434	65.63 460	99.67 310	95.87 314	98.18 392	97.82 416

TESTMET0.1,1		92.19 420	91.77 418	93.46 434	96.48 449	82.80 460	94.05 441	91.52 452	94.45 387	94.00 441	94.88 440	66.65 454	99.56 360	95.78 319	98.11 398	98.02 406

MVS_0304		97.44 281	97.01 297	98.72 195	96.42 450	96.74 251	97.20 308	91.97 450	98.46 165	98.30 282	98.79 253	92.74 337	99.91 72	99.30 61	99.94 49	99.52 146

miper_enhance_ethall		96.01 350	95.74 345	96.81 374	96.41 451	92.27 400	93.69 446	98.89 302	91.14 432	98.30 282	97.35 391	90.58 362	99.58 355	96.31 291	99.03 341	98.60 368

tpmvs		95.02 376	95.25 366	94.33 423	96.39 452	85.87 446	98.08 182	96.83 403	95.46 361	95.51 422	98.69 274	85.91 395	99.53 371	94.16 362	96.23 440	97.58 429

CMPMVS	75.91 23	96.29 341	95.44 359	98.84 170	96.25 453	98.69 94	97.02 316	99.12 263	88.90 444	97.83 322	98.86 235	89.51 371	98.90 440	91.92 407	99.51 263	98.92 324
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 381	93.69 391	96.99 363	96.05 454	93.61 377	94.97 419	93.49 442	96.17 335	97.57 340	94.88 440	82.30 421	99.01 435	93.60 380	94.17 453	98.37 391

EPMVS		93.72 397	93.27 396	95.09 418	96.04 455	87.76 440	98.13 172	85.01 463	94.69 380	96.92 373	98.64 286	78.47 438	99.31 415	95.04 337	96.46 437	98.20 397

cascas		94.79 379	94.33 385	96.15 398	96.02 456	92.36 398	92.34 453	99.26 229	85.34 452	95.08 427	94.96 439	92.96 332	98.53 447	94.41 359	98.59 379	97.56 430

MVStest1		95.86 355	95.60 351	96.63 379	95.87 457	91.70 405	97.93 212	98.94 290	98.03 203	99.56 71	99.66 32	71.83 444	98.26 450	99.35 57	99.24 312	99.91 13

gg-mvs-nofinetune		92.37 417	91.20 421	95.85 401	95.80 458	92.38 397	99.31 30	81.84 465	99.75 11	91.83 454	99.74 18	68.29 449	99.02 433	87.15 441	97.12 429	96.16 448

gm-plane-assit					94.83 459	81.97 462			88.07 447		94.99 437		99.60 344	91.76 411

GG-mvs-BLEND				94.76 420	94.54 460	92.13 402	99.31 30	80.47 466		88.73 460	91.01 460	67.59 453	98.16 453	82.30 454	94.53 452	93.98 456

UWE-MVS-28		90.22 425	89.28 428	93.02 440	94.50 461	82.87 459	96.52 347	87.51 459	95.21 369	92.36 452	96.04 414	71.57 445	98.25 451	72.04 461	97.77 410	97.94 411

EPNet_dtu		94.93 378	94.78 378	95.38 414	93.58 462	87.68 441	96.78 330	95.69 425	97.35 268	89.14 459	98.09 345	88.15 383	99.49 384	94.95 341	99.30 303	98.98 312
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 429	75.95 432	77.12 445	92.39 463	67.91 469	90.16 456	59.44 470	82.04 456	89.42 458	94.67 443	49.68 468	81.74 463	48.06 463	77.66 461	81.72 459

KD-MVS_2432*1600		92.87 411	91.99 413	95.51 410	91.37 464	89.27 433	94.07 439	98.14 363	95.42 362	97.25 361	96.44 409	67.86 450	99.24 423	91.28 420	96.08 443	98.02 406

miper_refine_blended		92.87 411	91.99 413	95.51 410	91.37 464	89.27 433	94.07 439	98.14 363	95.42 362	97.25 361	96.44 409	67.86 450	99.24 423	91.28 420	96.08 443	98.02 406

EPNet		96.14 347	95.44 359	98.25 267	90.76 466	95.50 300	97.92 215	94.65 432	98.97 120	92.98 448	98.85 238	89.12 374	99.87 132	95.99 307	99.68 203	99.39 208
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 430	68.95 433	70.34 446	87.68 467	65.00 470	91.11 454	59.90 469	69.02 459	74.46 464	88.89 461	48.58 469	68.03 465	28.61 464	72.33 463	77.99 460

test_method		79.78 427	79.50 430	80.62 443	80.21 468	45.76 471	70.82 459	98.41 353	31.08 463	80.89 463	97.71 368	84.85 402	97.37 456	91.51 417	80.03 460	98.75 353

tmp_tt		78.77 428	78.73 431	78.90 444	58.45 469	74.76 468	94.20 438	78.26 467	39.16 462	86.71 461	92.82 456	80.50 425	75.19 464	86.16 446	92.29 457	86.74 458

testmvs		17.12 432	20.53 435	6.87 448	12.05 470	4.20 473	93.62 447	6.73 471	4.62 466	10.41 466	24.33 463	8.28 471	3.56 467	9.69 466	15.07 464	12.86 463

test123		17.04 433	20.11 436	7.82 447	10.25 471	4.91 472	94.80 422	4.47 472	4.93 465	10.00 467	24.28 464	9.69 470	3.64 466	10.14 465	12.43 465	14.92 462

mmdepth		0.00 436	0.00 439	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	0.00 467	0.00 472	0.00 468	0.00 467	0.00 466	0.00 464

monomultidepth		0.00 436	0.00 439	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	0.00 467	0.00 472	0.00 468	0.00 467	0.00 466	0.00 464

test_blank		0.00 436	0.00 439	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	0.00 467	0.00 472	0.00 468	0.00 467	0.00 466	0.00 464

eth-test2					0.00 472

eth-test					0.00 472

uanet_test		0.00 436	0.00 439	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	0.00 467	0.00 472	0.00 468	0.00 467	0.00 466	0.00 464

DCPMVS		0.00 436	0.00 439	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	0.00 467	0.00 472	0.00 468	0.00 467	0.00 466	0.00 464

cdsmvs_eth3d_5k		24.66 431	32.88 434	0.00 449	0.00 472	0.00 474	0.00 460	99.10 266	0.00 467	0.00 468	97.58 376	99.21 18	0.00 468	0.00 467	0.00 466	0.00 464

pcd_1.5k_mvsjas		8.17 434	10.90 437	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	0.00 467	98.07 114	0.00 468	0.00 467	0.00 466	0.00 464

sosnet-low-res		0.00 436	0.00 439	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	0.00 467	0.00 472	0.00 468	0.00 467	0.00 466	0.00 464

sosnet		0.00 436	0.00 439	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	0.00 467	0.00 472	0.00 468	0.00 467	0.00 466	0.00 464

uncertanet		0.00 436	0.00 439	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	0.00 467	0.00 472	0.00 468	0.00 467	0.00 466	0.00 464

Regformer		0.00 436	0.00 439	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	0.00 467	0.00 472	0.00 468	0.00 467	0.00 466	0.00 464

ab-mvs-re		8.12 435	10.83 438	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	97.48 382	0.00 472	0.00 468	0.00 467	0.00 466	0.00 464

uanet		0.00 436	0.00 439	0.00 449	0.00 472	0.00 474	0.00 460	0.00 473	0.00 467	0.00 468	0.00 467	0.00 472	0.00 468	0.00 467	0.00 466	0.00 464

WAC-MVS						90.90 422								91.37 419

PC_three_1452									93.27 406	99.40 109	98.54 299	98.22 100	97.00 457	95.17 335	99.45 277	99.49 158

test_241102_TWO								99.30 209	98.03 203	99.26 140	99.02 186	97.51 166	99.88 113	96.91 234	99.60 232	99.66 75

test_0728_THIRD									98.17 192	99.08 165	99.02 186	97.89 130	99.88 113	97.07 222	99.71 188	99.70 65

GSMVS																98.81 342

sam_mvs1												84.74 404				98.81 342

sam_mvs												84.29 410

MTGPA								99.20 241

test_post1							97.59 267				20.48 466	83.07 418	99.66 321	94.16 362

test_post											21.25 465	83.86 413	99.70 293

patchmatchnet-post											98.77 257	84.37 407	99.85 154

MTMP							97.93 212	91.91 451

test9_res														93.28 388	99.15 328	99.38 216

agg_prior2														92.50 404	99.16 326	99.37 218

test_prior4						97.97 159	95.86 388

test_prior2							95.74 395		96.48 324	96.11 406	97.63 374	95.92 262		94.16 362	99.20 320

旧先验2							95.76 394		88.56 446	97.52 344			99.66 321	94.48 352

新几何2							95.93 384

无先验							95.74 395	98.74 332	89.38 442				99.73 279	92.38 406		99.22 268

原ACMM2							95.53 401

testdata2													99.79 237	92.80 398

segment_acmp												97.02 198

testdata1							95.44 406		96.32 330

plane_prior5								99.27 224					99.70 293	94.42 356	99.51 263	99.45 184

plane_prior4											97.98 353

plane_prior3						97.78 184			97.41 262	97.79 325

plane_prior2							97.77 237		98.20 189

plane_prior						97.65 193	97.07 315		96.72 314						99.36 292

n2								0.00 473

nn								0.00 473

door-mid								99.57 85

test11								98.87 305

door								99.41 161

HQP5-MVS						96.79 247

BP-MVS														92.82 396

HQP4-MVS										95.56 416			99.54 369			99.32 239

HQP3-MVS								99.04 277							99.26 310

HQP2-MVS												93.84 316

MDTV_nov1_ep13_2view						74.92 467	97.69 248		90.06 440	97.75 328		85.78 396		93.52 382		98.69 360

ACMMP++_ref															99.77 151

ACMMP++															99.68 203

Test By Simon												96.52 229

High-resolution multi-view benchmark