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 13	100.00 1	99.85 26

Gipuma		99.03 68	99.16 53	98.64 190	99.94 2	98.51 104	99.32 23	99.75 38	99.58 29	98.60 224	99.62 37	98.22 86	99.51 350	97.70 156	99.73 152	97.89 382
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 26	99.31 36	99.53 37	99.91 3	98.98 69	99.63 7	99.58 65	99.44 42	99.78 32	99.76 12	96.39 210	99.92 55	99.44 43	99.92 58	99.68 63

pmmvs6		99.67 3	99.70 3	99.60 14	99.90 4	99.27 26	99.53 8	99.76 35	99.64 19	99.84 24	99.83 4	99.50 9	99.87 114	99.36 45	99.92 58	99.64 73

PS-MVSNAJss		99.46 14	99.49 13	99.35 72	99.90 4	98.15 131	99.20 45	99.65 55	99.48 34	99.92 8	99.71 19	98.07 99	99.96 12	99.53 37	100.00 1	99.93 11

testf1		99.25 37	99.16 53	99.51 46	99.89 6	99.63 4	98.71 99	99.69 46	98.90 111	99.43 86	99.35 93	98.86 30	99.67 282	97.81 147	99.81 106	99.24 236

APD_test2		99.25 37	99.16 53	99.51 46	99.89 6	99.63 4	98.71 99	99.69 46	98.90 111	99.43 86	99.35 93	98.86 30	99.67 282	97.81 147	99.81 106	99.24 236

ANet_high		99.57 7	99.67 5	99.28 88	99.89 6	98.09 138	99.14 54	99.93 5	99.82 5	99.93 6	99.81 6	99.17 19	99.94 39	99.31 48	100.00 1	99.82 31

anonymousdsp		99.51 11	99.47 18	99.62 9	99.88 9	99.08 67	99.34 20	99.69 46	98.93 109	99.65 52	99.72 18	98.93 28	99.95 24	99.11 62	100.00 1	99.82 31

v7n		99.53 9	99.57 10	99.41 62	99.88 9	98.54 102	99.45 11	99.61 61	99.66 17	99.68 46	99.66 29	98.44 67	99.95 24	99.73 23	99.96 27	99.75 52

mvs_tets		99.63 5	99.67 5	99.49 51	99.88 9	98.61 94	99.34 20	99.71 42	99.27 63	99.90 13	99.74 15	99.68 4	99.97 5	99.55 36	99.99 5	99.88 19

test_fmvsmconf0.01_n		99.57 7	99.63 7	99.36 66	99.87 12	98.13 134	98.08 170	99.95 1	99.45 40	99.98 2	99.75 13	99.80 1	99.97 5	99.82 9	99.99 5	99.99 2

jajsoiax		99.58 6	99.61 8	99.48 53	99.87 12	98.61 94	99.28 37	99.66 54	99.09 91	99.89 16	99.68 22	99.53 7	99.97 5	99.50 40	99.99 5	99.87 20

test_djsdf		99.52 10	99.51 12	99.53 37	99.86 14	98.74 84	99.39 17	99.56 79	99.11 81	99.70 42	99.73 17	99.00 23	99.97 5	99.26 52	99.98 12	99.89 16

MIMVSNet1		99.38 25	99.32 34	99.55 27	99.86 14	99.19 41	99.41 14	99.59 63	99.59 27	99.71 40	99.57 46	97.12 170	99.90 70	99.21 57	99.87 83	99.54 120

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 25	99.85 16	99.11 63	99.90 1	99.78 33	99.63 21	99.78 32	99.67 27	99.48 10	99.81 194	99.30 49	99.97 20	99.77 43
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 19	99.69 5	99.58 65	99.90 3	99.86 20	99.78 10	99.58 6	99.95 24	99.00 71	99.95 34	99.78 40

SixPastTwentyTwo		98.75 106	98.62 117	99.16 108	99.83 18	97.96 158	99.28 37	98.20 333	99.37 50	99.70 42	99.65 33	92.65 313	99.93 46	99.04 68	99.84 92	99.60 86

Baseline_NR-MVSNet		98.98 75	98.86 85	99.36 66	99.82 19	98.55 99	97.47 259	99.57 72	99.37 50	99.21 130	99.61 40	96.76 194	99.83 170	98.06 131	99.83 99	99.71 55

pm-mvs1		99.44 16	99.48 15	99.33 81	99.80 20	98.63 91	99.29 33	99.63 57	99.30 60	99.65 52	99.60 42	99.16 21	99.82 180	99.07 65	99.83 99	99.56 109

TransMVSNet (Re)		99.44 16	99.47 18	99.36 66	99.80 20	98.58 97	99.27 39	99.57 72	99.39 48	99.75 36	99.62 37	99.17 19	99.83 170	99.06 66	99.62 200	99.66 67

K. test v3		98.00 204	97.66 228	99.03 133	99.79 22	97.56 190	99.19 49	92.47 415	99.62 24	99.52 69	99.66 29	89.61 339	99.96 12	99.25 54	99.81 106	99.56 109

test_fmvsmconf0.1_n		99.49 12	99.54 11	99.34 75	99.78 23	98.11 135	97.77 217	99.90 11	99.33 55	99.97 3	99.66 29	99.71 3	99.96 12	99.79 16	99.99 5	99.96 8

APD_test1		98.83 93	98.66 111	99.34 75	99.78 23	99.47 9	98.42 136	99.45 120	98.28 157	98.98 160	99.19 130	97.76 123	99.58 325	96.57 239	99.55 227	98.97 284

test_vis3_rt		99.14 52	99.17 51	99.07 123	99.78 23	98.38 111	98.92 79	99.94 2	97.80 194	99.91 12	99.67 27	97.15 169	98.91 408	99.76 19	99.56 223	99.92 12

EGC-MVSNET		85.24 395	80.54 398	99.34 75	99.77 26	99.20 38	99.08 58	99.29 192	12.08 433	20.84 434	99.42 80	97.55 141	99.85 135	97.08 191	99.72 160	98.96 286

Anonymous20240521		98.69 117	98.87 82	98.16 254	99.77 26	95.11 296	99.08 58	99.44 124	99.34 54	99.33 106	99.55 54	94.10 289	99.94 39	99.25 54	99.96 27	99.42 175

FC-MVSNet-test		99.27 34	99.25 45	99.34 75	99.77 26	98.37 113	99.30 32	99.57 72	99.61 26	99.40 94	99.50 64	97.12 170	99.85 135	99.02 70	99.94 42	99.80 36

test_vis1_n		98.31 176	98.50 133	97.73 287	99.76 29	94.17 321	98.68 102	99.91 9	96.31 301	99.79 31	99.57 46	92.85 309	99.42 369	99.79 16	99.84 92	99.60 86

test_fmvs3		99.12 58	99.41 22	98.25 246	99.76 29	95.07 297	99.05 64	99.94 2	97.78 196	99.82 26	99.84 3	98.56 58	99.71 262	99.96 1	99.96 27	99.97 4

XXY-MVS		99.14 52	99.15 58	99.10 117	99.76 29	97.74 179	98.85 87	99.62 58	98.48 142	99.37 99	99.49 70	98.75 40	99.86 122	98.20 121	99.80 117	99.71 55

TDRefinement		99.42 21	99.38 25	99.55 27	99.76 29	99.33 20	99.68 6	99.71 42	99.38 49	99.53 67	99.61 40	98.64 48	99.80 201	98.24 118	99.84 92	99.52 131

fmvsm_s_conf0.1_n_a		99.17 47	99.30 39	98.80 165	99.75 33	96.59 244	97.97 192	99.86 16	98.22 160	99.88 18	99.71 19	98.59 54	99.84 153	99.73 23	99.98 12	99.98 3

tt0805		98.69 117	98.62 117	98.90 155	99.75 33	99.30 21	99.15 53	96.97 368	98.86 115	98.87 189	97.62 344	98.63 50	98.96 405	99.41 44	98.29 357	98.45 348

test_vis1_n_1920		98.40 163	98.92 77	96.81 343	99.74 35	90.76 394	98.15 160	99.91 9	98.33 148	99.89 16	99.55 54	95.07 260	99.88 97	99.76 19	99.93 47	99.79 37

FOURS1					99.73 36	99.67 3	99.43 12	99.54 87	99.43 44	99.26 122

PEN-MVS		99.41 22	99.34 31	99.62 9	99.73 36	99.14 56	99.29 33	99.54 87	99.62 24	99.56 59	99.42 80	98.16 94	99.96 12	98.78 85	99.93 47	99.77 43

lessismore_v0				98.97 142	99.73 36	97.53 192		86.71 430		99.37 99	99.52 63	89.93 337	99.92 55	98.99 72	99.72 160	99.44 168

SteuartSystems-ACMMP		98.79 99	98.54 128	99.54 30	99.73 36	99.16 47	98.23 150	99.31 176	97.92 185	98.90 180	98.90 203	98.00 105	99.88 97	96.15 271	99.72 160	99.58 98
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 194	98.15 185	98.22 249	99.73 36	95.15 293	97.36 267	99.68 51	94.45 356	98.99 159	99.27 111	96.87 184	99.94 39	97.13 188	99.91 66	99.57 103

Vis-MVSNet		99.34 27	99.36 28	99.27 91	99.73 36	98.26 120	99.17 50	99.78 33	99.11 81	99.27 118	99.48 71	98.82 33	99.95 24	98.94 75	99.93 47	99.59 92
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
SSC-MVS		98.71 110	98.74 95	98.62 196	99.72 42	96.08 261	98.74 92	98.64 313	99.74 10	99.67 48	99.24 121	94.57 275	99.95 24	99.11 62	99.24 281	99.82 31

test_f		98.67 125	98.87 82	98.05 263	99.72 42	95.59 273	98.51 123	99.81 28	96.30 303	99.78 32	99.82 5	96.14 220	98.63 415	99.82 9	99.93 47	99.95 9

ACMH	96.65 7	99.25 37	99.24 46	99.26 93	99.72 42	98.38 111	99.07 61	99.55 83	98.30 152	99.65 52	99.45 77	99.22 16	99.76 237	98.44 109	99.77 133	99.64 73
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
fmvsm_s_conf0.1_n		99.16 50	99.33 32	98.64 190	99.71 45	96.10 256	97.87 204	99.85 18	98.56 138	99.90 13	99.68 22	98.69 45	99.85 135	99.72 25	99.98 12	99.97 4

PS-CasMVS		99.40 23	99.33 32	99.62 9	99.71 45	99.10 64	99.29 33	99.53 90	99.53 31	99.46 81	99.41 84	98.23 83	99.95 24	98.89 79	99.95 34	99.81 34

DTE-MVSNet		99.43 20	99.35 29	99.66 7	99.71 45	99.30 21	99.31 27	99.51 94	99.64 19	99.56 59	99.46 73	98.23 83	99.97 5	98.78 85	99.93 47	99.72 54

WR-MVS_H		99.33 28	99.22 47	99.65 8	99.71 45	99.24 29	99.32 23	99.55 83	99.46 39	99.50 75	99.34 97	97.30 159	99.93 46	98.90 77	99.93 47	99.77 43

HPM-MVS_fast		99.01 69	98.82 88	99.57 20	99.71 45	99.35 16	99.00 69	99.50 96	97.33 239	98.94 175	98.86 213	98.75 40	99.82 180	97.53 166	99.71 165	99.56 109

ACMH+	96.62 9	99.08 65	99.00 70	99.33 81	99.71 45	98.83 79	98.60 109	99.58 65	99.11 81	99.53 67	99.18 134	98.81 34	99.67 282	96.71 228	99.77 133	99.50 137

PMVS	91.26 20	97.86 217	97.94 207	97.65 291	99.71 45	97.94 160	98.52 118	98.68 309	98.99 102	97.52 314	99.35 93	97.41 154	98.18 421	91.59 385	99.67 186	96.82 410
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FIs		99.14 52	99.09 63	99.29 87	99.70 52	98.28 119	99.13 55	99.52 93	99.48 34	99.24 127	99.41 84	96.79 191	99.82 180	98.69 95	99.88 80	99.76 48

VPNet		98.87 88	98.83 87	99.01 136	99.70 52	97.62 188	98.43 134	99.35 157	99.47 37	99.28 116	99.05 164	96.72 197	99.82 180	98.09 128	99.36 261	99.59 92

fmvsm_s_conf0.1_n_2		99.20 45	99.38 25	98.65 188	99.69 54	96.08 261	97.49 256	99.90 11	99.53 31	99.88 18	99.64 34	98.51 61	99.90 70	99.83 8	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 173	98.68 108	97.27 320	99.69 54	92.29 369	98.03 178	99.85 18	97.62 205	99.96 4	99.62 37	93.98 290	99.74 249	99.52 39	99.86 87	99.79 37

MP-MVS-pluss		98.57 139	98.23 175	99.60 14	99.69 54	99.35 16	97.16 285	99.38 144	94.87 346	98.97 164	98.99 182	98.01 104	99.88 97	97.29 176	99.70 172	99.58 98
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 41	99.32 34	98.96 143	99.68 57	97.35 201	98.84 89	99.48 105	99.69 13	99.63 55	99.68 22	99.03 22	99.96 12	97.97 138	99.92 58	99.57 103

sd_testset		99.28 33	99.31 36	99.19 104	99.68 57	98.06 147	99.41 14	99.30 184	99.69 13	99.63 55	99.68 22	99.25 15	99.96 12	97.25 179	99.92 58	99.57 103

test_fmvs1_n		98.09 198	98.28 167	97.52 306	99.68 57	93.47 348	98.63 105	99.93 5	95.41 334	99.68 46	99.64 34	91.88 322	99.48 357	99.82 9	99.87 83	99.62 77

CHOSEN 1792x2688		97.49 246	97.14 261	98.54 214	99.68 57	96.09 259	96.50 318	99.62 58	91.58 394	98.84 192	98.97 188	92.36 315	99.88 97	96.76 221	99.95 34	99.67 66

tfpnnormal		98.90 85	98.90 79	98.91 152	99.67 61	97.82 171	99.00 69	99.44 124	99.45 40	99.51 74	99.24 121	98.20 89	99.86 122	95.92 280	99.69 175	99.04 271

MTAPA		98.88 87	98.64 114	99.61 12	99.67 61	99.36 15	98.43 134	99.20 215	98.83 119	98.89 182	98.90 203	96.98 180	99.92 55	97.16 183	99.70 172	99.56 109

test_fmvsmvis_n_1920		99.26 36	99.49 13	98.54 214	99.66 63	96.97 224	98.00 184	99.85 18	99.24 65	99.92 8	99.50 64	99.39 12	99.95 24	99.89 3	99.98 12	98.71 325

mvs5depth		99.30 30	99.59 9	98.44 227	99.65 64	95.35 285	99.82 3	99.94 2	99.83 4	99.42 89	99.94 2	98.13 97	99.96 12	99.63 30	99.96 27	100.00 1

fmvsm_l_conf0.5_n_a		99.19 46	99.27 42	98.94 146	99.65 64	97.05 220	97.80 213	99.76 35	98.70 123	99.78 32	99.11 150	98.79 38	99.95 24	99.85 5	99.96 27	99.83 28

WB-MVS		98.52 152	98.55 126	98.43 228	99.65 64	95.59 273	98.52 118	98.77 299	99.65 18	99.52 69	99.00 181	94.34 281	99.93 46	98.65 97	98.83 329	99.76 48

CP-MVSNet		99.21 43	99.09 63	99.56 25	99.65 64	98.96 74	99.13 55	99.34 163	99.42 45	99.33 106	99.26 116	97.01 178	99.94 39	98.74 90	99.93 47	99.79 37

HPM-MVS		98.79 99	98.53 129	99.59 18	99.65 64	99.29 23	99.16 51	99.43 130	96.74 283	98.61 222	98.38 290	98.62 51	99.87 114	96.47 251	99.67 186	99.59 92
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 134	98.36 157	99.42 60	99.65 64	99.42 11	98.55 114	99.57 72	97.72 199	98.90 180	99.26 116	96.12 222	99.52 345	95.72 291	99.71 165	99.32 217

fmvsm_l_conf0.5_n		99.21 43	99.28 41	99.02 135	99.64 70	97.28 205	97.82 209	99.76 35	98.73 120	99.82 26	99.09 156	98.81 34	99.95 24	99.86 4	99.96 27	99.83 28

test_fmvsmconf_n		99.44 16	99.48 15	99.31 86	99.64 70	98.10 137	97.68 229	99.84 21	99.29 61	99.92 8	99.57 46	99.60 5	99.96 12	99.74 22	99.98 12	99.89 16

TSAR-MVS + MP.		98.63 131	98.49 137	99.06 129	99.64 70	97.90 162	98.51 123	98.94 264	96.96 270	99.24 127	98.89 209	97.83 116	99.81 194	96.88 211	99.49 246	99.48 151
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 95	98.72 99	99.12 113	99.64 70	98.54 102	97.98 189	99.68 51	97.62 205	99.34 105	99.18 134	97.54 142	99.77 231	97.79 149	99.74 149	99.04 271

KD-MVS_self_test		99.25 37	99.18 50	99.44 59	99.63 74	99.06 68	98.69 101	99.54 87	99.31 58	99.62 58	99.53 60	97.36 157	99.86 122	99.24 56	99.71 165	99.39 188

EU-MVSNet		97.66 234	98.50 133	95.13 385	99.63 74	85.84 416	98.35 142	98.21 332	98.23 159	99.54 63	99.46 73	95.02 261	99.68 279	98.24 118	99.87 83	99.87 20

HyFIR lowres test		97.19 272	96.60 296	98.96 143	99.62 76	97.28 205	95.17 382	99.50 96	94.21 361	99.01 157	98.32 298	86.61 357	99.99 2	97.10 190	99.84 92	99.60 86

fmvsm_l_conf0.5_n_3		99.45 15	99.48 15	99.34 75	99.59 77	98.21 128	97.82 209	99.84 21	99.41 47	99.92 8	99.41 84	99.51 8	99.95 24	99.84 7	99.97 20	99.87 20

mmtdpeth		99.30 30	99.42 21	98.92 151	99.58 78	96.89 231	99.48 10	99.92 7	99.92 2	98.26 259	99.80 9	98.33 76	99.91 64	99.56 35	99.95 34	99.97 4

ACMMP_NAP		98.75 106	98.48 138	99.57 20	99.58 78	99.29 23	97.82 209	99.25 204	96.94 272	98.78 199	99.12 149	98.02 103	99.84 153	97.13 188	99.67 186	99.59 92

nrg030		99.40 23	99.35 29	99.54 30	99.58 78	99.13 59	98.98 72	99.48 105	99.68 15	99.46 81	99.26 116	98.62 51	99.73 254	99.17 60	99.92 58	99.76 48

VDDNet		98.21 189	97.95 205	99.01 136	99.58 78	97.74 179	99.01 67	97.29 359	99.67 16	98.97 164	99.50 64	90.45 334	99.80 201	97.88 144	99.20 289	99.48 151

COLMAP_ROB	96.50 10	98.99 72	98.85 86	99.41 62	99.58 78	99.10 64	98.74 92	99.56 79	99.09 91	99.33 106	99.19 130	98.40 69	99.72 261	95.98 278	99.76 145	99.42 175
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 28	99.45 20	98.99 138	99.57 83	97.73 181	97.93 193	99.83 24	99.22 66	99.93 6	99.30 105	99.42 11	99.96 12	99.85 5	99.99 5	99.29 226

ZNCC-MVS		98.68 122	98.40 150	99.54 30	99.57 83	99.21 32	98.46 131	99.29 192	97.28 245	98.11 271	98.39 288	98.00 105	99.87 114	96.86 214	99.64 194	99.55 116

MSP-MVS		98.40 163	98.00 200	99.61 12	99.57 83	99.25 28	98.57 112	99.35 157	97.55 216	99.31 114	97.71 337	94.61 274	99.88 97	96.14 272	99.19 292	99.70 60
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		98.32 174	98.39 153	98.13 255	99.57 83	95.54 276	97.78 215	99.49 103	97.37 236	99.19 132	97.65 341	98.96 25	99.49 354	96.50 250	98.99 317	99.34 210

MP-MVS		98.46 157	98.09 190	99.54 30	99.57 83	99.22 31	98.50 125	99.19 219	97.61 208	97.58 308	98.66 251	97.40 155	99.88 97	94.72 317	99.60 207	99.54 120
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 110	98.46 142	99.47 56	99.57 83	98.97 70	98.23 150	99.48 105	96.60 288	99.10 142	99.06 157	98.71 43	99.83 170	95.58 298	99.78 127	99.62 77

LGP-MVS_train				99.47 56	99.57 83	98.97 70		99.48 105	96.60 288	99.10 142	99.06 157	98.71 43	99.83 170	95.58 298	99.78 127	99.62 77

IS-MVSNet		98.19 191	97.90 211	99.08 121	99.57 83	97.97 155	99.31 27	98.32 328	99.01 101	98.98 160	99.03 168	91.59 324	99.79 214	95.49 300	99.80 117	99.48 151

dcpmvs_2		98.78 101	99.11 59	97.78 277	99.56 91	93.67 343	99.06 62	99.86 16	99.50 33	99.66 49	99.26 116	97.21 167	99.99 2	98.00 136	99.91 66	99.68 63

test_0402		98.76 105	98.71 102	98.93 148	99.56 91	98.14 133	98.45 133	99.34 163	99.28 62	98.95 168	98.91 200	98.34 75	99.79 214	95.63 295	99.91 66	98.86 303

EPP-MVSNet		98.30 177	98.04 196	99.07 123	99.56 91	97.83 168	99.29 33	98.07 339	99.03 99	98.59 226	99.13 148	92.16 318	99.90 70	96.87 212	99.68 180	99.49 141

ACMMP		98.75 106	98.50 133	99.52 42	99.56 91	99.16 47	98.87 84	99.37 148	97.16 260	98.82 196	99.01 178	97.71 126	99.87 114	96.29 263	99.69 175	99.54 120
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 60	99.20 49	98.78 171	99.55 95	96.59 244	97.79 214	99.82 27	98.21 161	99.81 29	99.53 60	98.46 65	99.84 153	99.70 27	99.97 20	99.90 15

fmvsm_s_conf0.5_n		99.09 61	99.26 44	98.61 199	99.55 95	96.09 259	97.74 223	99.81 28	98.55 139	99.85 22	99.55 54	98.60 53	99.84 153	99.69 29	99.98 12	99.89 16

FMVSNet1		99.17 47	99.17 51	99.17 105	99.55 95	98.24 122	99.20 45	99.44 124	99.21 68	99.43 86	99.55 54	97.82 119	99.86 122	98.42 111	99.89 78	99.41 178

Vis-MVSNet (Re-imp)		97.46 248	97.16 258	98.34 239	99.55 95	96.10 256	98.94 77	98.44 322	98.32 150	98.16 265	98.62 260	88.76 344	99.73 254	93.88 343	99.79 122	99.18 251

ACMM	96.08 12	98.91 83	98.73 97	99.48 53	99.55 95	99.14 56	98.07 172	99.37 148	97.62 205	99.04 153	98.96 191	98.84 32	99.79 214	97.43 170	99.65 192	99.49 141
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 114	98.97 74	97.89 270	99.54 100	94.05 324	98.55 114	99.92 7	96.78 281	99.72 38	99.78 10	96.60 202	99.67 282	99.91 2	99.90 72	99.94 10

mPP-MVS		98.64 129	98.34 160	99.54 30	99.54 100	99.17 43	98.63 105	99.24 209	97.47 223	98.09 273	98.68 246	97.62 135	99.89 83	96.22 266	99.62 200	99.57 103

XVG-ACMP-BASELINE		98.56 140	98.34 160	99.22 101	99.54 100	98.59 96	97.71 226	99.46 116	97.25 248	98.98 160	98.99 182	97.54 142	99.84 153	95.88 281	99.74 149	99.23 238

region2R		98.69 117	98.40 150	99.54 30	99.53 103	99.17 43	98.52 118	99.31 176	97.46 228	98.44 244	98.51 274	97.83 116	99.88 97	96.46 252	99.58 216	99.58 98

PGM-MVS		98.66 126	98.37 156	99.55 27	99.53 103	99.18 42	98.23 150	99.49 103	97.01 269	98.69 210	98.88 210	98.00 105	99.89 83	95.87 284	99.59 211	99.58 98

Patchmatch-RL test		97.26 265	97.02 266	97.99 267	99.52 105	95.53 277	96.13 343	99.71 42	97.47 223	99.27 118	99.16 140	84.30 378	99.62 307	97.89 141	99.77 133	98.81 311

ACMMPR		98.70 114	98.42 148	99.54 30	99.52 105	99.14 56	98.52 118	99.31 176	97.47 223	98.56 231	98.54 269	97.75 124	99.88 97	96.57 239	99.59 211	99.58 98

GST-MVS		98.61 135	98.30 165	99.52 42	99.51 107	99.20 38	98.26 148	99.25 204	97.44 231	98.67 213	98.39 288	97.68 127	99.85 135	96.00 276	99.51 238	99.52 131

Anonymous20231206		98.21 189	98.21 176	98.20 250	99.51 107	95.43 283	98.13 162	99.32 171	96.16 306	98.93 176	98.82 222	96.00 227	99.83 170	97.32 175	99.73 152	99.36 204

ACMP	95.32 15	98.41 161	98.09 190	99.36 66	99.51 107	98.79 82	97.68 229	99.38 144	95.76 321	98.81 198	98.82 222	98.36 71	99.82 180	94.75 314	99.77 133	99.48 151
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DVP-MVS		98.77 104	98.52 130	99.52 42	99.50 110	99.21 32	98.02 180	98.84 288	97.97 179	99.08 144	99.02 169	97.61 136	99.88 97	96.99 198	99.63 197	99.48 151
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 14	99.50 110	99.23 30	98.02 180	99.32 171					99.88 97	96.99 198	99.63 197	99.68 63

test0726					99.50 110	99.21 32	98.17 158	99.35 157	97.97 179	99.26 122	99.06 157	97.61 136

AllTest		98.44 159	98.20 177	99.16 108	99.50 110	98.55 99	98.25 149	99.58 65	96.80 279	98.88 185	99.06 157	97.65 130	99.57 327	94.45 324	99.61 205	99.37 197

TestCases				99.16 108	99.50 110	98.55 99		99.58 65	96.80 279	98.88 185	99.06 157	97.65 130	99.57 327	94.45 324	99.61 205	99.37 197

XVG-OURS		98.53 148	98.34 160	99.11 115	99.50 110	98.82 81	95.97 349	99.50 96	97.30 243	99.05 151	98.98 186	99.35 13	99.32 383	95.72 291	99.68 180	99.18 251

EG-PatchMatch MVS		98.99 72	99.01 69	98.94 146	99.50 110	97.47 194	98.04 177	99.59 63	98.15 172	99.40 94	99.36 92	98.58 57	99.76 237	98.78 85	99.68 180	99.59 92

fmvsm_s_conf0.5_n_2		99.14 52	99.31 36	98.63 194	99.49 117	96.08 261	97.38 264	99.81 28	99.48 34	99.84 24	99.57 46	98.46 65	99.89 83	99.82 9	99.97 20	99.91 13

SED-MVS		98.91 83	98.72 99	99.49 51	99.49 117	99.17 43	98.10 168	99.31 176	98.03 175	99.66 49	99.02 169	98.36 71	99.88 97	96.91 204	99.62 200	99.41 178

IU-MVS					99.49 117	99.15 51		98.87 279	92.97 379	99.41 91				96.76 221	99.62 200	99.66 67

test_241102_ONE					99.49 117	99.17 43		99.31 176	97.98 178	99.66 49	98.90 203	98.36 71	99.48 357

UA-Net		99.47 13	99.40 23	99.70 2	99.49 117	99.29 23	99.80 4	99.72 40	99.82 5	99.04 153	99.81 6	98.05 102	99.96 12	98.85 81	99.99 5	99.86 24

HFP-MVS		98.71 110	98.44 145	99.51 46	99.49 117	99.16 47	98.52 118	99.31 176	97.47 223	98.58 228	98.50 278	97.97 109	99.85 135	96.57 239	99.59 211	99.53 128

VPA-MVSNet		99.30 30	99.30 39	99.28 88	99.49 117	98.36 116	99.00 69	99.45 120	99.63 21	99.52 69	99.44 78	98.25 81	99.88 97	99.09 64	99.84 92	99.62 77

XVG-OURS-SEG-HR		98.49 154	98.28 167	99.14 111	99.49 117	98.83 79	96.54 314	99.48 105	97.32 241	99.11 139	98.61 262	99.33 14	99.30 386	96.23 265	98.38 353	99.28 228

114514_t		96.50 305	95.77 313	98.69 185	99.48 125	97.43 198	97.84 208	99.55 83	81.42 426	96.51 366	98.58 266	95.53 247	99.67 282	93.41 356	99.58 216	98.98 281

IterMVS-LS		98.55 144	98.70 105	98.09 256	99.48 125	94.73 305	97.22 280	99.39 142	98.97 105	99.38 97	99.31 104	96.00 227	99.93 46	98.58 100	99.97 20	99.60 86
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 66	99.10 61	98.99 138	99.47 127	97.22 210	97.40 262	99.83 24	97.61 208	99.85 22	99.30 105	98.80 36	99.95 24	99.71 26	99.90 72	99.78 40

v8		99.01 69	99.16 53	98.57 206	99.47 127	96.31 253	98.90 80	99.47 113	99.03 99	99.52 69	99.57 46	96.93 181	99.81 194	99.60 31	99.98 12	99.60 86

SSC-MVS3.2		98.53 148	98.79 91	97.74 284	99.46 129	93.62 346	96.45 320	99.34 163	99.33 55	98.93 176	98.70 242	97.90 112	99.90 70	99.12 61	99.92 58	99.69 62

fmvsm_s_conf0.5_n_3		99.22 42	99.37 27	98.78 171	99.46 129	96.58 246	97.65 235	99.72 40	99.47 37	99.86 20	99.50 64	98.94 26	99.89 83	99.75 21	99.97 20	99.86 24

XVS		98.72 109	98.45 143	99.53 37	99.46 129	99.21 32	98.65 103	99.34 163	98.62 128	97.54 312	98.63 258	97.50 148	99.83 170	96.79 217	99.53 233	99.56 109

X-MVStestdata		94.32 353	92.59 372	99.53 37	99.46 129	99.21 32	98.65 103	99.34 163	98.62 128	97.54 312	45.85 431	97.50 148	99.83 170	96.79 217	99.53 233	99.56 109

test20.03		98.78 101	98.77 94	98.78 171	99.46 129	97.20 213	97.78 215	99.24 209	99.04 98	99.41 91	98.90 203	97.65 130	99.76 237	97.70 156	99.79 122	99.39 188

CSCG		98.68 122	98.50 133	99.20 102	99.45 134	98.63 91	98.56 113	99.57 72	97.87 189	98.85 190	98.04 319	97.66 129	99.84 153	96.72 226	99.81 106	99.13 260

GeoE		99.05 67	98.99 72	99.25 96	99.44 135	98.35 117	98.73 96	99.56 79	98.42 144	98.91 179	98.81 224	98.94 26	99.91 64	98.35 113	99.73 152	99.49 141

v148		98.45 158	98.60 122	98.00 266	99.44 135	94.98 298	97.44 261	99.06 245	98.30 152	99.32 112	98.97 188	96.65 200	99.62 307	98.37 112	99.85 88	99.39 188

v10		98.97 76	99.11 59	98.55 211	99.44 135	96.21 255	98.90 80	99.55 83	98.73 120	99.48 76	99.60 42	96.63 201	99.83 170	99.70 27	99.99 5	99.61 85

V42		98.78 101	98.78 93	98.76 176	99.44 135	97.04 221	98.27 147	99.19 219	97.87 189	99.25 126	99.16 140	96.84 185	99.78 225	99.21 57	99.84 92	99.46 160

MDA-MVSNet-bldmvs		97.94 208	97.91 210	98.06 261	99.44 135	94.96 299	96.63 312	99.15 235	98.35 146	98.83 193	99.11 150	94.31 282	99.85 135	96.60 236	98.72 335	99.37 197

casdiffmvs_mvg		99.12 58	99.16 53	98.99 138	99.43 140	97.73 181	98.00 184	99.62 58	99.22 66	99.55 62	99.22 126	98.93 28	99.75 244	98.66 96	99.81 106	99.50 137
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test1111		96.49 306	96.82 280	95.52 378	99.42 141	87.08 413	99.22 42	87.14 429	99.11 81	99.46 81	99.58 44	88.69 345	99.86 122	98.80 83	99.95 34	99.62 77

v2v482		98.56 140	98.62 117	98.37 236	99.42 141	95.81 270	97.58 245	99.16 230	97.90 187	99.28 116	99.01 178	95.98 232	99.79 214	99.33 47	99.90 72	99.51 134

OPM-MVS		98.56 140	98.32 164	99.25 96	99.41 143	98.73 87	97.13 287	99.18 223	97.10 263	98.75 205	98.92 199	98.18 90	99.65 298	96.68 230	99.56 223	99.37 197
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 200	98.08 193	98.04 264	99.41 143	94.59 311	94.59 400	99.40 140	97.50 220	98.82 196	98.83 219	96.83 187	99.84 153	97.50 168	99.81 106	99.71 55

test_one_0601					99.39 145	99.20 38		99.31 176	98.49 141	98.66 215	99.02 169	97.64 133

mvsany_test3		98.87 88	98.92 77	98.74 182	99.38 146	96.94 228	98.58 111	99.10 240	96.49 293	99.96 4	99.81 6	98.18 90	99.45 364	98.97 73	99.79 122	99.83 28

patch_mono-2		98.51 153	98.63 115	98.17 252	99.38 146	94.78 302	97.36 267	99.69 46	98.16 171	98.49 240	99.29 108	97.06 173	99.97 5	98.29 117	99.91 66	99.76 48

test2506		92.39 384	91.89 386	93.89 399	99.38 146	82.28 430	99.32 23	66.03 437	99.08 93	98.77 202	99.57 46	66.26 425	99.84 153	98.71 93	99.95 34	99.54 120

ECVR-MVS		96.42 308	96.61 294	95.85 370	99.38 146	88.18 408	99.22 42	86.00 431	99.08 93	99.36 101	99.57 46	88.47 350	99.82 180	98.52 106	99.95 34	99.54 120

casdiffmvs		98.95 79	99.00 70	98.81 163	99.38 146	97.33 202	97.82 209	99.57 72	99.17 77	99.35 103	99.17 138	98.35 74	99.69 270	98.46 108	99.73 152	99.41 178
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 78	99.02 68	98.76 176	99.38 146	97.26 207	98.49 126	99.50 96	98.86 115	99.19 132	99.06 157	98.23 83	99.69 270	98.71 93	99.76 145	99.33 215

TranMVSNet+NR-MVSNet		99.17 47	99.07 66	99.46 58	99.37 152	98.87 77	98.39 138	99.42 133	99.42 45	99.36 101	99.06 157	98.38 70	99.95 24	98.34 114	99.90 72	99.57 103

tttt0517		95.64 332	94.98 342	97.64 293	99.36 153	93.81 338	98.72 97	90.47 423	98.08 174	98.67 213	98.34 295	73.88 411	99.92 55	97.77 151	99.51 238	99.20 243

test_part2					99.36 153	99.10 64				99.05 151

v1144		98.60 136	98.66 111	98.41 230	99.36 153	95.90 266	97.58 245	99.34 163	97.51 219	99.27 118	99.15 144	96.34 215	99.80 201	99.47 42	99.93 47	99.51 134

CP-MVS		98.70 114	98.42 148	99.52 42	99.36 153	99.12 61	98.72 97	99.36 152	97.54 217	98.30 253	98.40 287	97.86 115	99.89 83	96.53 248	99.72 160	99.56 109

Test_1112_low_res		96.99 287	96.55 298	98.31 242	99.35 157	95.47 281	95.84 361	99.53 90	91.51 396	96.80 354	98.48 281	91.36 326	99.83 170	96.58 237	99.53 233	99.62 77

DeepC-MVS	97.60 4	98.97 76	98.93 76	99.10 117	99.35 157	97.98 154	98.01 183	99.46 116	97.56 214	99.54 63	99.50 64	98.97 24	99.84 153	98.06 131	99.92 58	99.49 141
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 264	96.86 276	98.58 203	99.34 159	96.32 252	96.75 306	99.58 65	93.14 377	96.89 349	97.48 351	92.11 319	99.86 122	96.91 204	99.54 229	99.57 103

reproduce_model		99.15 51	98.97 74	99.67 4	99.33 160	99.44 10	98.15 160	99.47 113	99.12 80	99.52 69	99.32 103	98.31 77	99.90 70	97.78 150	99.73 152	99.66 67

MVSMamba_PlusPlus		98.83 93	98.98 73	98.36 237	99.32 161	96.58 246	98.90 80	99.41 137	99.75 8	98.72 208	99.50 64	96.17 219	99.94 39	99.27 51	99.78 127	98.57 341

fmvsm_s_conf0.5_n_4		99.01 69	99.22 47	98.38 233	99.31 162	95.48 280	97.56 247	99.73 39	98.87 113	99.75 36	99.27 111	98.80 36	99.86 122	99.80 14	99.90 72	99.81 34

SF-MVS		98.53 148	98.27 170	99.32 83	99.31 162	98.75 83	98.19 154	99.41 137	96.77 282	98.83 193	98.90 203	97.80 121	99.82 180	95.68 294	99.52 236	99.38 195

CPTT-MVS		97.84 223	97.36 247	99.27 91	99.31 162	98.46 107	98.29 145	99.27 198	94.90 345	97.83 292	98.37 291	94.90 263	99.84 153	93.85 345	99.54 229	99.51 134

UnsupCasMVSNet_eth		97.89 212	97.60 233	98.75 178	99.31 162	97.17 216	97.62 239	99.35 157	98.72 122	98.76 204	98.68 246	92.57 314	99.74 249	97.76 155	95.60 415	99.34 210

pmmvs-eth3d		98.47 156	98.34 160	98.86 157	99.30 166	97.76 177	97.16 285	99.28 195	95.54 327	99.42 89	99.19 130	97.27 162	99.63 304	97.89 141	99.97 20	99.20 243

mamv4		99.44 16	99.39 24	99.58 19	99.30 166	99.74 2	99.04 65	99.81 28	99.77 7	99.82 26	99.57 46	97.82 119	99.98 4	99.53 37	99.89 78	99.01 275

Anonymous20231211		99.27 34	99.27 42	99.26 93	99.29 168	98.18 129	99.49 9	99.51 94	99.70 12	99.80 30	99.68 22	96.84 185	99.83 170	99.21 57	99.91 66	99.77 43

UnsupCasMVSNet_bld		97.30 262	96.92 272	98.45 225	99.28 169	96.78 238	96.20 337	99.27 198	95.42 331	98.28 257	98.30 299	93.16 300	99.71 262	94.99 308	97.37 391	98.87 302

EC-MVSNet		99.09 61	99.05 67	99.20 102	99.28 169	98.93 75	99.24 41	99.84 21	99.08 93	98.12 270	98.37 291	98.72 42	99.90 70	99.05 67	99.77 133	98.77 319

reproduce-ours		99.09 61	98.90 79	99.67 4	99.27 171	99.49 6	98.00 184	99.42 133	99.05 96	99.48 76	99.27 111	98.29 79	99.89 83	97.61 160	99.71 165	99.62 77

our_new_method		99.09 61	98.90 79	99.67 4	99.27 171	99.49 6	98.00 184	99.42 133	99.05 96	99.48 76	99.27 111	98.29 79	99.89 83	97.61 160	99.71 165	99.62 77

DPE-MVS		98.59 138	98.26 171	99.57 20	99.27 171	99.15 51	97.01 290	99.39 142	97.67 201	99.44 85	98.99 182	97.53 144	99.89 83	95.40 302	99.68 180	99.66 67
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 222	98.18 180	96.87 339	99.27 171	91.16 388	95.53 370	99.25 204	99.10 88	99.41 91	99.35 93	93.10 302	99.96 12	98.65 97	99.94 42	99.49 141

v1192		98.60 136	98.66 111	98.41 230	99.27 171	95.88 267	97.52 252	99.36 152	97.41 232	99.33 106	99.20 129	96.37 213	99.82 180	99.57 33	99.92 58	99.55 116

N_pmnet		97.63 236	97.17 257	98.99 138	99.27 171	97.86 165	95.98 348	93.41 412	95.25 336	99.47 80	98.90 203	95.63 244	99.85 135	96.91 204	99.73 152	99.27 229

FPMVS		93.44 370	92.23 377	97.08 328	99.25 177	97.86 165	95.61 367	97.16 363	92.90 381	93.76 414	98.65 253	75.94 409	95.66 428	79.30 427	97.49 384	97.73 392

new-patchmatchnet		98.35 169	98.74 95	97.18 323	99.24 178	92.23 371	96.42 324	99.48 105	98.30 152	99.69 44	99.53 60	97.44 153	99.82 180	98.84 82	99.77 133	99.49 141

MCST-MVS		98.00 204	97.63 231	99.10 117	99.24 178	98.17 130	96.89 299	98.73 306	95.66 322	97.92 283	97.70 339	97.17 168	99.66 293	96.18 270	99.23 284	99.47 158

UniMVSNet (Re)		98.87 88	98.71 102	99.35 72	99.24 178	98.73 87	97.73 225	99.38 144	98.93 109	99.12 138	98.73 236	96.77 192	99.86 122	98.63 99	99.80 117	99.46 160

jason		97.45 250	97.35 248	97.76 281	99.24 178	93.93 332	95.86 358	98.42 324	94.24 360	98.50 239	98.13 309	94.82 267	99.91 64	97.22 180	99.73 152	99.43 172
jason: jason.
IterMVS		97.73 228	98.11 189	96.57 349	99.24 178	90.28 397	95.52 372	99.21 213	98.86 115	99.33 106	99.33 99	93.11 301	99.94 39	98.49 107	99.94 42	99.48 151
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 144	98.62 117	98.32 240	99.22 183	95.58 275	97.51 254	99.45 120	97.16 260	99.45 84	99.24 121	96.12 222	99.85 135	99.60 31	99.88 80	99.55 116

ITE_SJBPF				98.87 156	99.22 183	98.48 106		99.35 157	97.50 220	98.28 257	98.60 264	97.64 133	99.35 379	93.86 344	99.27 276	98.79 317

h-mvs33		97.77 226	97.33 250	99.10 117	99.21 185	97.84 167	98.35 142	98.57 316	99.11 81	98.58 228	99.02 169	88.65 348	99.96 12	98.11 126	96.34 407	99.49 141

v144192		98.54 146	98.57 125	98.45 225	99.21 185	95.98 264	97.63 238	99.36 152	97.15 262	99.32 112	99.18 134	95.84 239	99.84 153	99.50 40	99.91 66	99.54 120

APDe-MVS		98.99 72	98.79 91	99.60 14	99.21 185	99.15 51	98.87 84	99.48 105	97.57 212	99.35 103	99.24 121	97.83 116	99.89 83	97.88 144	99.70 172	99.75 52
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 81	98.81 90	99.28 88	99.21 185	98.45 108	98.46 131	99.33 169	99.63 21	99.48 76	99.15 144	97.23 165	99.75 244	97.17 182	99.66 191	99.63 76

SR-MVS-dyc-post		98.81 97	98.55 126	99.57 20	99.20 189	99.38 12	98.48 129	99.30 184	98.64 124	98.95 168	98.96 191	97.49 151	99.86 122	96.56 243	99.39 257	99.45 164

RE-MVS-def			98.58 124		99.20 189	99.38 12	98.48 129	99.30 184	98.64 124	98.95 168	98.96 191	97.75 124		96.56 243	99.39 257	99.45 164

v1921920		98.54 146	98.60 122	98.38 233	99.20 189	95.76 272	97.56 247	99.36 152	97.23 254	99.38 97	99.17 138	96.02 225	99.84 153	99.57 33	99.90 72	99.54 120

thisisatest0530		95.27 339	94.45 350	97.74 284	99.19 192	94.37 315	97.86 205	90.20 424	97.17 259	98.22 260	97.65 341	73.53 412	99.90 70	96.90 209	99.35 263	98.95 287

Anonymous20240529		98.93 81	98.87 82	99.12 113	99.19 192	98.22 127	99.01 67	98.99 262	99.25 64	99.54 63	99.37 88	97.04 174	99.80 201	97.89 141	99.52 236	99.35 208

APD-MVS_3200maxsize		98.84 92	98.61 121	99.53 37	99.19 192	99.27 26	98.49 126	99.33 169	98.64 124	99.03 156	98.98 186	97.89 113	99.85 135	96.54 247	99.42 254	99.46 160

HQP_MVS		97.99 207	97.67 225	98.93 148	99.19 192	97.65 185	97.77 217	99.27 198	98.20 165	97.79 295	97.98 322	94.90 263	99.70 266	94.42 326	99.51 238	99.45 164

plane_prior7					99.19 192	97.87 164

ab-mvs		98.41 161	98.36 157	98.59 202	99.19 192	97.23 208	99.32 23	98.81 293	97.66 202	98.62 220	99.40 87	96.82 188	99.80 201	95.88 281	99.51 238	98.75 322

F-COLMAP		97.30 262	96.68 289	99.14 111	99.19 192	98.39 110	97.27 276	99.30 184	92.93 380	96.62 360	98.00 320	95.73 242	99.68 279	92.62 372	98.46 352	99.35 208

SR-MVS		98.71 110	98.43 146	99.57 20	99.18 199	99.35 16	98.36 141	99.29 192	98.29 155	98.88 185	98.85 216	97.53 144	99.87 114	96.14 272	99.31 269	99.48 151

UniMVSNet_NR-MVSNet		98.86 91	98.68 108	99.40 64	99.17 200	98.74 84	97.68 229	99.40 140	99.14 79	99.06 146	98.59 265	96.71 198	99.93 46	98.57 102	99.77 133	99.53 128

LF4IMVS		97.90 210	97.69 224	98.52 216	99.17 200	97.66 184	97.19 284	99.47 113	96.31 301	97.85 291	98.20 306	96.71 198	99.52 345	94.62 318	99.72 160	98.38 358

SMA-MVS		98.40 163	98.03 197	99.51 46	99.16 202	99.21 32	98.05 175	99.22 212	94.16 362	98.98 160	99.10 153	97.52 146	99.79 214	96.45 253	99.64 194	99.53 128
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 95	98.63 115	99.39 65	99.16 202	98.74 84	97.54 250	99.25 204	98.84 118	99.06 146	98.76 233	96.76 194	99.93 46	98.57 102	99.77 133	99.50 137

NR-MVSNet		98.95 79	98.82 88	99.36 66	99.16 202	98.72 89	99.22 42	99.20 215	99.10 88	99.72 38	98.76 233	96.38 212	99.86 122	98.00 136	99.82 102	99.50 137

MVS_111021_LR		98.30 177	98.12 188	98.83 160	99.16 202	98.03 149	96.09 345	99.30 184	97.58 211	98.10 272	98.24 302	98.25 81	99.34 380	96.69 229	99.65 192	99.12 261

DSMNet-mixed		97.42 253	97.60 233	96.87 339	99.15 206	91.46 378	98.54 116	99.12 237	92.87 382	97.58 308	99.63 36	96.21 218	99.90 70	95.74 290	99.54 229	99.27 229

D2MVS		97.84 223	97.84 215	97.83 273	99.14 207	94.74 304	96.94 294	98.88 277	95.84 319	98.89 182	98.96 191	94.40 279	99.69 270	97.55 163	99.95 34	99.05 267

pmmvs5		97.64 235	97.49 239	98.08 259	99.14 207	95.12 295	96.70 309	99.05 248	93.77 369	98.62 220	98.83 219	93.23 298	99.75 244	98.33 116	99.76 145	99.36 204

SPE-MVS-test		99.13 56	99.09 63	99.26 93	99.13 209	98.97 70	99.31 27	99.88 14	99.44 42	98.16 265	98.51 274	98.64 48	99.93 46	98.91 76	99.85 88	98.88 301

VDD-MVS		98.56 140	98.39 153	99.07 123	99.13 209	98.07 144	98.59 110	97.01 366	99.59 27	99.11 139	99.27 111	94.82 267	99.79 214	98.34 114	99.63 197	99.34 210

save fliter					99.11 211	97.97 155	96.53 316	99.02 256	98.24 158

APD-MVS		98.10 196	97.67 225	99.42 60	99.11 211	98.93 75	97.76 220	99.28 195	94.97 343	98.72 208	98.77 231	97.04 174	99.85 135	93.79 346	99.54 229	99.49 141
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 117	98.71 102	98.62 196	99.10 213	96.37 250	97.23 277	98.87 279	99.20 70	99.19 132	98.99 182	97.30 159	99.85 135	98.77 88	99.79 122	99.65 72

EI-MVSNet		98.40 163	98.51 131	98.04 264	99.10 213	94.73 305	97.20 281	98.87 279	98.97 105	99.06 146	99.02 169	96.00 227	99.80 201	98.58 100	99.82 102	99.60 86

CVMVSNet		96.25 313	97.21 256	93.38 406	99.10 213	80.56 434	97.20 281	98.19 335	96.94 272	99.00 158	99.02 169	89.50 341	99.80 201	96.36 259	99.59 211	99.78 40

EI-MVSNet-Vis-set		98.68 122	98.70 105	98.63 194	99.09 216	96.40 249	97.23 277	98.86 284	99.20 70	99.18 136	98.97 188	97.29 161	99.85 135	98.72 92	99.78 127	99.64 73

HPM-MVS++		98.10 196	97.64 230	99.48 53	99.09 216	99.13 59	97.52 252	98.75 303	97.46 228	96.90 348	97.83 332	96.01 226	99.84 153	95.82 288	99.35 263	99.46 160

DP-MVS Recon		97.33 260	96.92 272	98.57 206	99.09 216	97.99 151	96.79 302	99.35 157	93.18 376	97.71 299	98.07 317	95.00 262	99.31 384	93.97 339	99.13 300	98.42 355

MVS_111021_HR		98.25 185	98.08 193	98.75 178	99.09 216	97.46 195	95.97 349	99.27 198	97.60 210	97.99 281	98.25 301	98.15 96	99.38 375	96.87 212	99.57 220	99.42 175

BP-MVS1		97.40 255	96.97 268	98.71 184	99.07 220	96.81 234	98.34 144	97.18 361	98.58 134	98.17 262	98.61 262	84.01 380	99.94 39	98.97 73	99.78 127	99.37 197

9.14			97.78 217		99.07 220		97.53 251	99.32 171	95.53 328	98.54 235	98.70 242	97.58 138	99.76 237	94.32 331	99.46 248

PAPM_NR		96.82 294	96.32 305	98.30 243	99.07 220	96.69 242	97.48 257	98.76 300	95.81 320	96.61 361	96.47 377	94.12 288	99.17 397	90.82 399	97.78 378	99.06 266

TAMVS		98.24 186	98.05 195	98.80 165	99.07 220	97.18 215	97.88 201	98.81 293	96.66 287	99.17 137	99.21 127	94.81 269	99.77 231	96.96 202	99.88 80	99.44 168

CLD-MVS		97.49 246	97.16 258	98.48 222	99.07 220	97.03 222	94.71 393	99.21 213	94.46 354	98.06 275	97.16 363	97.57 139	99.48 357	94.46 323	99.78 127	98.95 287
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 56	99.10 61	99.24 98	99.06 225	99.15 51	99.36 19	99.88 14	99.36 53	98.21 261	98.46 282	98.68 46	99.93 46	99.03 69	99.85 88	98.64 334

thres100view900		94.19 356	93.67 361	95.75 373	99.06 225	91.35 381	98.03 178	94.24 407	98.33 148	97.40 324	94.98 407	79.84 396	99.62 307	83.05 420	98.08 369	96.29 414

thres600view7		94.45 351	93.83 358	96.29 357	99.06 225	91.53 377	97.99 188	94.24 407	98.34 147	97.44 322	95.01 405	79.84 396	99.67 282	84.33 418	98.23 358	97.66 395

plane_prior1					99.05 228

YYNet1		97.60 237	97.67 225	97.39 316	99.04 229	93.04 355	95.27 379	98.38 327	97.25 248	98.92 178	98.95 195	95.48 251	99.73 254	96.99 198	98.74 333	99.41 178

MDA-MVSNet_test_wron		97.60 237	97.66 228	97.41 315	99.04 229	93.09 351	95.27 379	98.42 324	97.26 247	98.88 185	98.95 195	95.43 252	99.73 254	97.02 195	98.72 335	99.41 178

MIMVSNet		96.62 301	96.25 309	97.71 288	99.04 229	94.66 308	99.16 51	96.92 372	97.23 254	97.87 288	99.10 153	86.11 363	99.65 298	91.65 383	99.21 288	98.82 306

PatchMatch-RL		97.24 268	96.78 283	98.61 199	99.03 232	97.83 168	96.36 327	99.06 245	93.49 374	97.36 328	97.78 333	95.75 241	99.49 354	93.44 355	98.77 332	98.52 343

GDP-MVS		97.50 243	97.11 262	98.67 187	99.02 233	96.85 232	98.16 159	99.71 42	98.32 150	98.52 238	98.54 269	83.39 384	99.95 24	98.79 84	99.56 223	99.19 248

ZD-MVS					99.01 234	98.84 78		99.07 244	94.10 364	98.05 277	98.12 311	96.36 214	99.86 122	92.70 371	99.19 292

CDPH-MVS		97.26 265	96.66 292	99.07 123	99.00 235	98.15 131	96.03 347	99.01 259	91.21 400	97.79 295	97.85 331	96.89 183	99.69 270	92.75 369	99.38 260	99.39 188

diffmvs		98.22 187	98.24 174	98.17 252	99.00 235	95.44 282	96.38 326	99.58 65	97.79 195	98.53 236	98.50 278	96.76 194	99.74 249	97.95 140	99.64 194	99.34 210
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WR-MVS		98.40 163	98.19 179	99.03 133	99.00 235	97.65 185	96.85 300	98.94 264	98.57 135	98.89 182	98.50 278	95.60 245	99.85 135	97.54 165	99.85 88	99.59 92

plane_prior6					98.99 238	97.70 183						94.90 263

xiu_mvs_v1_base_debu		97.86 217	98.17 181	96.92 336	98.98 239	93.91 333	96.45 320	99.17 227	97.85 191	98.41 247	97.14 365	98.47 62	99.92 55	98.02 133	99.05 306	96.92 407

xiu_mvs_v1_base		97.86 217	98.17 181	96.92 336	98.98 239	93.91 333	96.45 320	99.17 227	97.85 191	98.41 247	97.14 365	98.47 62	99.92 55	98.02 133	99.05 306	96.92 407

xiu_mvs_v1_base_debi		97.86 217	98.17 181	96.92 336	98.98 239	93.91 333	96.45 320	99.17 227	97.85 191	98.41 247	97.14 365	98.47 62	99.92 55	98.02 133	99.05 306	96.92 407

MVP-Stereo		98.08 199	97.92 209	98.57 206	98.96 242	96.79 235	97.90 199	99.18 223	96.41 297	98.46 242	98.95 195	95.93 236	99.60 315	96.51 249	98.98 320	99.31 221
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 163	98.68 108	97.54 304	98.96 242	97.99 151	97.88 201	99.36 152	98.20 165	99.63 55	99.04 166	98.76 39	95.33 430	96.56 243	99.74 149	99.31 221
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				98.91 152	98.94 244	97.76 177		98.76 300	87.58 417	96.75 356	98.10 313	94.80 270	99.78 225	92.73 370	99.00 315	99.20 243

USDC		97.41 254	97.40 243	97.44 313	98.94 244	93.67 343	95.17 382	99.53 90	94.03 366	98.97 164	99.10 153	95.29 254	99.34 380	95.84 287	99.73 152	99.30 224

tfpn200view9		94.03 360	93.44 363	95.78 372	98.93 246	91.44 379	97.60 242	94.29 405	97.94 183	97.10 334	94.31 414	79.67 398	99.62 307	83.05 420	98.08 369	96.29 414

testdata				98.09 256	98.93 246	95.40 284		98.80 295	90.08 408	97.45 321	98.37 291	95.26 255	99.70 266	93.58 351	98.95 323	99.17 255

thres400		94.14 358	93.44 363	96.24 360	98.93 246	91.44 379	97.60 242	94.29 405	97.94 183	97.10 334	94.31 414	79.67 398	99.62 307	83.05 420	98.08 369	97.66 395

TAPA-MVS	96.21 11	96.63 300	95.95 311	98.65 188	98.93 246	98.09 138	96.93 296	99.28 195	83.58 423	98.13 269	97.78 333	96.13 221	99.40 371	93.52 352	99.29 274	98.45 348
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 250	96.93 229	95.54 369	98.78 298	85.72 420	96.86 351	98.11 312	94.43 277			99.10 305	99.23 238

PVSNet_BlendedMVS		97.55 242	97.53 236	97.60 296	98.92 250	93.77 340	96.64 311	99.43 130	94.49 352	97.62 304	99.18 134	96.82 188	99.67 282	94.73 315	99.93 47	99.36 204

PVSNet_Blended		96.88 290	96.68 289	97.47 311	98.92 250	93.77 340	94.71 393	99.43 130	90.98 402	97.62 304	97.36 359	96.82 188	99.67 282	94.73 315	99.56 223	98.98 281

MSDG		97.71 230	97.52 237	98.28 245	98.91 253	96.82 233	94.42 403	99.37 148	97.65 203	98.37 252	98.29 300	97.40 155	99.33 382	94.09 337	99.22 285	98.68 332

Anonymous202405211		97.90 210	97.50 238	99.08 121	98.90 254	98.25 121	98.53 117	96.16 383	98.87 113	99.11 139	98.86 213	90.40 335	99.78 225	97.36 173	99.31 269	99.19 248

原ACMM1				98.35 238	98.90 254	96.25 254		98.83 292	92.48 386	96.07 377	98.10 313	95.39 253	99.71 262	92.61 373	98.99 317	99.08 263

GBi-Net		98.65 127	98.47 140	99.17 105	98.90 254	98.24 122	99.20 45	99.44 124	98.59 131	98.95 168	99.55 54	94.14 285	99.86 122	97.77 151	99.69 175	99.41 178

test1		98.65 127	98.47 140	99.17 105	98.90 254	98.24 122	99.20 45	99.44 124	98.59 131	98.95 168	99.55 54	94.14 285	99.86 122	97.77 151	99.69 175	99.41 178

FMVSNet2		98.49 154	98.40 150	98.75 178	98.90 254	97.14 219	98.61 108	99.13 236	98.59 131	99.19 132	99.28 109	94.14 285	99.82 180	97.97 138	99.80 117	99.29 226

OMC-MVS		97.88 214	97.49 239	99.04 132	98.89 259	98.63 91	96.94 294	99.25 204	95.02 341	98.53 236	98.51 274	97.27 162	99.47 360	93.50 354	99.51 238	99.01 275

MVSFormer		98.26 183	98.43 146	97.77 278	98.88 260	93.89 336	99.39 17	99.56 79	99.11 81	98.16 265	98.13 309	93.81 293	99.97 5	99.26 52	99.57 220	99.43 172

lupinMVS		97.06 280	96.86 276	97.65 291	98.88 260	93.89 336	95.48 373	97.97 341	93.53 372	98.16 265	97.58 345	93.81 293	99.91 64	96.77 220	99.57 220	99.17 255

dmvs_re		95.98 321	95.39 331	97.74 284	98.86 262	97.45 196	98.37 140	95.69 395	97.95 181	96.56 362	95.95 386	90.70 332	97.68 424	88.32 408	96.13 411	98.11 370

DELS-MVS		98.27 181	98.20 177	98.48 222	98.86 262	96.70 241	95.60 368	99.20 215	97.73 198	98.45 243	98.71 239	97.50 148	99.82 180	98.21 120	99.59 211	98.93 292
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		97.89 212	97.98 202	97.60 296	98.86 262	94.35 316	96.21 336	99.44 124	97.45 230	99.06 146	98.88 210	97.99 108	99.28 390	94.38 330	99.58 216	99.18 251

LCM-MVSNet-Re		98.64 129	98.48 138	99.11 115	98.85 265	98.51 104	98.49 126	99.83 24	98.37 145	99.69 44	99.46 73	98.21 88	99.92 55	94.13 336	99.30 272	98.91 296

pmmvs4		97.58 240	97.28 251	98.51 217	98.84 266	96.93 229	95.40 377	98.52 319	93.60 371	98.61 222	98.65 253	95.10 259	99.60 315	96.97 201	99.79 122	98.99 280

NP-MVS					98.84 266	97.39 200					96.84 368

sss		97.21 270	96.93 270	98.06 261	98.83 268	95.22 291	96.75 306	98.48 321	94.49 352	97.27 330	97.90 328	92.77 310	99.80 201	96.57 239	99.32 267	99.16 258

PVSNet	93.40 17	95.67 330	95.70 316	95.57 377	98.83 268	88.57 404	92.50 420	97.72 346	92.69 384	96.49 369	96.44 378	93.72 296	99.43 367	93.61 349	99.28 275	98.71 325

MVE	83.40 22	92.50 383	91.92 385	94.25 393	98.83 268	91.64 376	92.71 419	83.52 433	95.92 317	86.46 431	95.46 399	95.20 256	95.40 429	80.51 425	98.64 344	95.73 422
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 364	93.91 356	93.39 405	98.82 271	81.72 432	97.76 220	95.28 397	98.60 130	96.54 363	96.66 372	65.85 428	99.62 307	96.65 232	98.99 317	98.82 306

ambc				98.24 248	98.82 271	95.97 265	98.62 107	99.00 261		99.27 118	99.21 127	96.99 179	99.50 351	96.55 246	99.50 245	99.26 232

旧先验1					98.82 271	97.45 196		98.76 300			98.34 295	95.50 250			99.01 314	99.23 238

test_vis1_rt		97.75 227	97.72 223	97.83 273	98.81 274	96.35 251	97.30 272	99.69 46	94.61 350	97.87 288	98.05 318	96.26 217	98.32 418	98.74 90	98.18 361	98.82 306

WTY-MVS		96.67 298	96.27 308	97.87 271	98.81 274	94.61 310	96.77 304	97.92 343	94.94 344	97.12 333	97.74 336	91.11 328	99.82 180	93.89 342	98.15 365	99.18 251

3Dnovator+	97.89 3	98.69 117	98.51 131	99.24 98	98.81 274	98.40 109	99.02 66	99.19 219	98.99 102	98.07 274	99.28 109	97.11 172	99.84 153	96.84 215	99.32 267	99.47 158

QAPM		97.31 261	96.81 282	98.82 161	98.80 277	97.49 193	99.06 62	99.19 219	90.22 406	97.69 301	99.16 140	96.91 182	99.90 70	90.89 398	99.41 255	99.07 265

VNet		98.42 160	98.30 165	98.79 168	98.79 278	97.29 204	98.23 150	98.66 310	99.31 58	98.85 190	98.80 225	94.80 270	99.78 225	98.13 125	99.13 300	99.31 221

DPM-MVS		96.32 310	95.59 322	98.51 217	98.76 279	97.21 212	94.54 402	98.26 330	91.94 391	96.37 370	97.25 361	93.06 304	99.43 367	91.42 388	98.74 333	98.89 298

3Dnovator	98.27 2	98.81 97	98.73 97	99.05 130	98.76 279	97.81 174	99.25 40	99.30 184	98.57 135	98.55 233	99.33 99	97.95 110	99.90 70	97.16 183	99.67 186	99.44 168

PLC	94.65 16	96.51 303	95.73 315	98.85 158	98.75 281	97.91 161	96.42 324	99.06 245	90.94 403	95.59 383	97.38 357	94.41 278	99.59 319	90.93 396	98.04 374	99.05 267
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 292	96.75 285	97.08 328	98.74 282	93.33 349	96.71 308	98.26 330	96.72 284	98.44 244	97.37 358	95.20 256	99.47 360	91.89 378	97.43 388	98.44 351

hse-mvs2		97.46 248	97.07 263	98.64 190	98.73 283	97.33 202	97.45 260	97.64 352	99.11 81	98.58 228	97.98 322	88.65 348	99.79 214	98.11 126	97.39 390	98.81 311

CDS-MVSNet		97.69 231	97.35 248	98.69 185	98.73 283	97.02 223	96.92 298	98.75 303	95.89 318	98.59 226	98.67 248	92.08 320	99.74 249	96.72 226	99.81 106	99.32 217
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EIA-MVS		98.00 204	97.74 220	98.80 165	98.72 285	98.09 138	98.05 175	99.60 62	97.39 234	96.63 359	95.55 394	97.68 127	99.80 201	96.73 225	99.27 276	98.52 343

LFMVS		97.20 271	96.72 286	98.64 190	98.72 285	96.95 227	98.93 78	94.14 409	99.74 10	98.78 199	99.01 178	84.45 375	99.73 254	97.44 169	99.27 276	99.25 233

new_pmnet		96.99 287	96.76 284	97.67 289	98.72 285	94.89 300	95.95 353	98.20 333	92.62 385	98.55 233	98.54 269	94.88 266	99.52 345	93.96 340	99.44 253	98.59 340

Fast-Effi-MVS+		97.67 233	97.38 245	98.57 206	98.71 288	97.43 198	97.23 277	99.45 120	94.82 347	96.13 374	96.51 374	98.52 60	99.91 64	96.19 268	98.83 329	98.37 360

TEST9					98.71 288	98.08 142	95.96 351	99.03 253	91.40 397	95.85 380	97.53 347	96.52 205	99.76 237

train_agg		97.10 277	96.45 302	99.07 123	98.71 288	98.08 142	95.96 351	99.03 253	91.64 392	95.85 380	97.53 347	96.47 207	99.76 237	93.67 348	99.16 295	99.36 204

TSAR-MVS + GP.		98.18 192	97.98 202	98.77 175	98.71 288	97.88 163	96.32 330	98.66 310	96.33 299	99.23 129	98.51 274	97.48 152	99.40 371	97.16 183	99.46 248	99.02 274

FA-MVS(test-final)		96.99 287	96.82 280	97.50 308	98.70 292	94.78 302	99.34 20	96.99 367	95.07 340	98.48 241	99.33 99	88.41 351	99.65 298	96.13 274	98.92 326	98.07 373

AUN-MVS		96.24 315	95.45 327	98.60 201	98.70 292	97.22 210	97.38 264	97.65 350	95.95 316	95.53 390	97.96 326	82.11 392	99.79 214	96.31 261	97.44 387	98.80 316

our_test_3		97.39 256	97.73 222	96.34 355	98.70 292	89.78 400	94.61 399	98.97 263	96.50 292	99.04 153	98.85 216	95.98 232	99.84 153	97.26 178	99.67 186	99.41 178

ppachtmachnet_test		97.50 243	97.74 220	96.78 345	98.70 292	91.23 387	94.55 401	99.05 248	96.36 298	99.21 130	98.79 227	96.39 210	99.78 225	96.74 223	99.82 102	99.34 210

PCF-MVS	92.86 18	94.36 352	93.00 370	98.42 229	98.70 292	97.56 190	93.16 418	99.11 239	79.59 427	97.55 311	97.43 354	92.19 317	99.73 254	79.85 426	99.45 250	97.97 379
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 209	98.02 198	97.58 298	98.69 297	94.10 323	98.13 162	98.90 273	97.95 181	97.32 329	99.58 44	95.95 235	98.75 413	96.41 255	99.22 285	99.87 20

ETV-MVS		98.03 201	97.86 214	98.56 210	98.69 297	98.07 144	97.51 254	99.50 96	98.10 173	97.50 316	95.51 395	98.41 68	99.88 97	96.27 264	99.24 281	97.71 394

test_prior				98.95 145	98.69 297	97.95 159		99.03 253					99.59 319			99.30 224

mvsmamba		97.57 241	97.26 252	98.51 217	98.69 297	96.73 240	98.74 92	97.25 360	97.03 268	97.88 287	99.23 125	90.95 329	99.87 114	96.61 235	99.00 315	98.91 296

agg_prior					98.68 301	97.99 151		99.01 259		95.59 383			99.77 231

test_8					98.67 302	98.01 150	95.91 357	99.02 256	91.64 392	95.79 382	97.50 350	96.47 207	99.76 237

HQP-NCC					98.67 302		96.29 332		96.05 309	95.55 386

ACMP_Plane					98.67 302		96.29 332		96.05 309	95.55 386

CNVR-MVS		98.17 194	97.87 213	99.07 123	98.67 302	98.24 122	97.01 290	98.93 267	97.25 248	97.62 304	98.34 295	97.27 162	99.57 327	96.42 254	99.33 266	99.39 188

HQP-MVS		97.00 286	96.49 301	98.55 211	98.67 302	96.79 235	96.29 332	99.04 251	96.05 309	95.55 386	96.84 368	93.84 291	99.54 339	92.82 366	99.26 279	99.32 217

MM		98.22 187	97.99 201	98.91 152	98.66 307	96.97 224	97.89 200	94.44 403	99.54 30	98.95 168	99.14 147	93.50 297	99.92 55	99.80 14	99.96 27	99.85 26

test_fmvs1		97.72 229	97.94 207	97.07 330	98.66 307	92.39 366	97.68 229	99.81 28	95.20 339	99.54 63	99.44 78	91.56 325	99.41 370	99.78 18	99.77 133	99.40 187

balanced_conf03		98.63 131	98.72 99	98.38 233	98.66 307	96.68 243	98.90 80	99.42 133	98.99 102	98.97 164	99.19 130	95.81 240	99.85 135	98.77 88	99.77 133	98.60 337

thres200		93.72 366	93.14 368	95.46 381	98.66 307	91.29 383	96.61 313	94.63 402	97.39 234	96.83 352	93.71 417	79.88 395	99.56 330	82.40 423	98.13 366	95.54 423

wuyk23d		96.06 317	97.62 232	91.38 410	98.65 311	98.57 98	98.85 87	96.95 370	96.86 277	99.90 13	99.16 140	99.18 18	98.40 417	89.23 406	99.77 133	77.18 430

NCCC		97.86 217	97.47 242	99.05 130	98.61 312	98.07 144	96.98 292	98.90 273	97.63 204	97.04 338	97.93 327	95.99 231	99.66 293	95.31 303	98.82 331	99.43 172

DeepC-MVS_fast	96.85 6	98.30 177	98.15 185	98.75 178	98.61 312	97.23 208	97.76 220	99.09 242	97.31 242	98.75 205	98.66 251	97.56 140	99.64 301	96.10 275	99.55 227	99.39 188
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 368	92.09 379	97.75 282	98.60 314	94.40 314	97.32 270	95.26 398	97.56 214	96.79 355	95.50 396	53.57 436	99.77 231	95.26 304	98.97 321	99.08 263

thisisatest0515		94.12 359	93.16 367	96.97 334	98.60 314	92.90 356	93.77 414	90.61 422	94.10 364	96.91 345	95.87 389	74.99 410	99.80 201	94.52 321	99.12 303	98.20 366

GA-MVS		95.86 324	95.32 334	97.49 309	98.60 314	94.15 322	93.83 413	97.93 342	95.49 329	96.68 357	97.42 355	83.21 385	99.30 386	96.22 266	98.55 350	99.01 275

dmvs_testset		92.94 378	92.21 378	95.13 385	98.59 317	90.99 390	97.65 235	92.09 418	96.95 271	94.00 410	93.55 418	92.34 316	96.97 427	72.20 429	92.52 425	97.43 402

OPU-MVS				98.82 161	98.59 317	98.30 118	98.10 168				98.52 273	98.18 90	98.75 413	94.62 318	99.48 247	99.41 178

MSLP-MVS++		98.02 202	98.14 187	97.64 293	98.58 319	95.19 292	97.48 257	99.23 211	97.47 223	97.90 285	98.62 260	97.04 174	98.81 411	97.55 163	99.41 255	98.94 291

test12				98.93 148	98.58 319	97.83 168		98.66 310		96.53 364		95.51 249	99.69 270		99.13 300	99.27 229

CL-MVSNet_self_test		97.44 251	97.22 255	98.08 259	98.57 321	95.78 271	94.30 406	98.79 296	96.58 290	98.60 224	98.19 307	94.74 273	99.64 301	96.41 255	98.84 328	98.82 306

PS-MVSNAJ		97.08 279	97.39 244	96.16 366	98.56 322	92.46 364	95.24 381	98.85 287	97.25 248	97.49 317	95.99 385	98.07 99	99.90 70	96.37 257	98.67 343	96.12 419

CNLPA		97.17 274	96.71 287	98.55 211	98.56 322	98.05 148	96.33 329	98.93 267	96.91 274	97.06 337	97.39 356	94.38 280	99.45 364	91.66 382	99.18 294	98.14 369

xiu_mvs_v2_base		97.16 275	97.49 239	96.17 364	98.54 324	92.46 364	95.45 374	98.84 288	97.25 248	97.48 318	96.49 375	98.31 77	99.90 70	96.34 260	98.68 342	96.15 418

alignmvs		97.35 258	96.88 275	98.78 171	98.54 324	98.09 138	97.71 226	97.69 348	99.20 70	97.59 307	95.90 388	88.12 353	99.55 334	98.18 122	98.96 322	98.70 328

FE-MVS		95.66 331	94.95 344	97.77 278	98.53 326	95.28 288	99.40 16	96.09 386	93.11 378	97.96 282	99.26 116	79.10 402	99.77 231	92.40 375	98.71 337	98.27 364

Effi-MVS+		98.02 202	97.82 216	98.62 196	98.53 326	97.19 214	97.33 269	99.68 51	97.30 243	96.68 357	97.46 353	98.56 58	99.80 201	96.63 233	98.20 360	98.86 303

baseline1		95.96 322	95.44 328	97.52 306	98.51 328	93.99 330	98.39 138	96.09 386	98.21 161	98.40 251	97.76 335	86.88 355	99.63 304	95.42 301	89.27 428	98.95 287

MVS_Test		98.18 192	98.36 157	97.67 289	98.48 329	94.73 305	98.18 155	99.02 256	97.69 200	98.04 278	99.11 150	97.22 166	99.56 330	98.57 102	98.90 327	98.71 325

MGCFI-Net		98.34 170	98.28 167	98.51 217	98.47 330	97.59 189	98.96 74	99.48 105	99.18 76	97.40 324	95.50 396	98.66 47	99.50 351	98.18 122	98.71 337	98.44 351

BH-RMVSNet		96.83 292	96.58 297	97.58 298	98.47 330	94.05 324	96.67 310	97.36 355	96.70 286	97.87 288	97.98 322	95.14 258	99.44 366	90.47 401	98.58 349	99.25 233

sasdasda		98.34 170	98.26 171	98.58 203	98.46 332	97.82 171	98.96 74	99.46 116	99.19 74	97.46 319	95.46 399	98.59 54	99.46 362	98.08 129	98.71 337	98.46 345

canonicalmvs		98.34 170	98.26 171	98.58 203	98.46 332	97.82 171	98.96 74	99.46 116	99.19 74	97.46 319	95.46 399	98.59 54	99.46 362	98.08 129	98.71 337	98.46 345

MVS-HIRNet		94.32 353	95.62 319	90.42 411	98.46 332	75.36 435	96.29 332	89.13 426	95.25 336	95.38 392	99.75 13	92.88 307	99.19 396	94.07 338	99.39 257	96.72 412

PHI-MVS		98.29 180	97.95 205	99.34 75	98.44 335	99.16 47	98.12 165	99.38 144	96.01 313	98.06 275	98.43 285	97.80 121	99.67 282	95.69 293	99.58 216	99.20 243

DVP-MVS++		98.90 85	98.70 105	99.51 46	98.43 336	99.15 51	99.43 12	99.32 171	98.17 168	99.26 122	99.02 169	98.18 90	99.88 97	97.07 192	99.45 250	99.49 141

MSC_two_6792asdad				99.32 83	98.43 336	98.37 113		98.86 284					99.89 83	97.14 186	99.60 207	99.71 55

No_MVS				99.32 83	98.43 336	98.37 113		98.86 284					99.89 83	97.14 186	99.60 207	99.71 55

Fast-Effi-MVS+-dtu		98.27 181	98.09 190	98.81 163	98.43 336	98.11 135	97.61 241	99.50 96	98.64 124	97.39 326	97.52 349	98.12 98	99.95 24	96.90 209	98.71 337	98.38 358

OpenMVS_ROB	95.38 14	95.84 326	95.18 339	97.81 275	98.41 340	97.15 218	97.37 266	98.62 314	83.86 422	98.65 216	98.37 291	94.29 283	99.68 279	88.41 407	98.62 347	96.60 413

DeepPCF-MVS	96.93 5	98.32 174	98.01 199	99.23 100	98.39 341	98.97 70	95.03 386	99.18 223	96.88 275	99.33 106	98.78 229	98.16 94	99.28 390	96.74 223	99.62 200	99.44 168

Patchmatch-test		96.55 302	96.34 304	97.17 325	98.35 342	93.06 352	98.40 137	97.79 344	97.33 239	98.41 247	98.67 248	83.68 383	99.69 270	95.16 306	99.31 269	98.77 319

AdaColmap		97.14 276	96.71 287	98.46 224	98.34 343	97.80 175	96.95 293	98.93 267	95.58 326	96.92 343	97.66 340	95.87 238	99.53 341	90.97 395	99.14 298	98.04 374

OpenMVS	96.65 7	97.09 278	96.68 289	98.32 240	98.32 344	97.16 217	98.86 86	99.37 148	89.48 410	96.29 372	99.15 144	96.56 203	99.90 70	92.90 363	99.20 289	97.89 382

MG-MVS		96.77 295	96.61 294	97.26 321	98.31 345	93.06 352	95.93 354	98.12 338	96.45 296	97.92 283	98.73 236	93.77 295	99.39 373	91.19 393	99.04 309	99.33 215

test_yl		96.69 296	96.29 306	97.90 268	98.28 346	95.24 289	97.29 273	97.36 355	98.21 161	98.17 262	97.86 329	86.27 359	99.55 334	94.87 312	98.32 354	98.89 298

DCV-MVSNet		96.69 296	96.29 306	97.90 268	98.28 346	95.24 289	97.29 273	97.36 355	98.21 161	98.17 262	97.86 329	86.27 359	99.55 334	94.87 312	98.32 354	98.89 298

CHOSEN 280x420		95.51 336	95.47 325	95.65 376	98.25 348	88.27 407	93.25 417	98.88 277	93.53 372	94.65 401	97.15 364	86.17 361	99.93 46	97.41 171	99.93 47	98.73 324

SCA		96.41 309	96.66 292	95.67 374	98.24 349	88.35 406	95.85 360	96.88 373	96.11 307	97.67 302	98.67 248	93.10 302	99.85 135	94.16 332	99.22 285	98.81 311

DeepMVS_CX				93.44 404	98.24 349	94.21 319		94.34 404	64.28 430	91.34 424	94.87 411	89.45 342	92.77 431	77.54 428	93.14 424	93.35 426

MS-PatchMatch		97.68 232	97.75 219	97.45 312	98.23 351	93.78 339	97.29 273	98.84 288	96.10 308	98.64 217	98.65 253	96.04 224	99.36 376	96.84 215	99.14 298	99.20 243

BH-w/o		95.13 342	94.89 346	95.86 369	98.20 352	91.31 382	95.65 366	97.37 354	93.64 370	96.52 365	95.70 392	93.04 305	99.02 402	88.10 409	95.82 414	97.24 405

mvs_anonymous		97.83 225	98.16 184	96.87 339	98.18 353	91.89 373	97.31 271	98.90 273	97.37 236	98.83 193	99.46 73	96.28 216	99.79 214	98.90 77	98.16 364	98.95 287

miper_lstm_enhance		97.18 273	97.16 258	97.25 322	98.16 354	92.85 357	95.15 384	99.31 176	97.25 248	98.74 207	98.78 229	90.07 336	99.78 225	97.19 181	99.80 117	99.11 262

RRT-MVS		97.88 214	97.98 202	97.61 295	98.15 355	93.77 340	98.97 73	99.64 56	99.16 78	98.69 210	99.42 80	91.60 323	99.89 83	97.63 159	98.52 351	99.16 258

ET-MVSNet_ETH3D		94.30 355	93.21 366	97.58 298	98.14 356	94.47 313	94.78 392	93.24 414	94.72 348	89.56 426	95.87 389	78.57 405	99.81 194	96.91 204	97.11 399	98.46 345

ADS-MVSNet2		95.43 337	94.98 342	96.76 346	98.14 356	91.74 374	97.92 196	97.76 345	90.23 404	96.51 366	98.91 200	85.61 366	99.85 135	92.88 364	96.90 400	98.69 329

ADS-MVSNet		95.24 340	94.93 345	96.18 363	98.14 356	90.10 399	97.92 196	97.32 358	90.23 404	96.51 366	98.91 200	85.61 366	99.74 249	92.88 364	96.90 400	98.69 329

c3_l		97.36 257	97.37 246	97.31 317	98.09 359	93.25 350	95.01 387	99.16 230	97.05 265	98.77 202	98.72 238	92.88 307	99.64 301	96.93 203	99.76 145	99.05 267

FMVSNet3		97.50 243	97.24 254	98.29 244	98.08 360	95.83 269	97.86 205	98.91 272	97.89 188	98.95 168	98.95 195	87.06 354	99.81 194	97.77 151	99.69 175	99.23 238

PAPM		91.88 392	90.34 395	96.51 350	98.06 361	92.56 362	92.44 421	97.17 362	86.35 418	90.38 425	96.01 384	86.61 357	99.21 395	70.65 431	95.43 416	97.75 391

Effi-MVS+-dtu		98.26 183	97.90 211	99.35 72	98.02 362	99.49 6	98.02 180	99.16 230	98.29 155	97.64 303	97.99 321	96.44 209	99.95 24	96.66 231	98.93 325	98.60 337

eth_miper_zixun_eth		97.23 269	97.25 253	97.17 325	98.00 363	92.77 359	94.71 393	99.18 223	97.27 246	98.56 231	98.74 235	91.89 321	99.69 270	97.06 194	99.81 106	99.05 267

HY-MVS	95.94 13	95.90 323	95.35 333	97.55 303	97.95 364	94.79 301	98.81 91	96.94 371	92.28 389	95.17 394	98.57 267	89.90 338	99.75 244	91.20 392	97.33 395	98.10 371

UGNet		98.53 148	98.45 143	98.79 168	97.94 365	96.96 226	99.08 58	98.54 317	99.10 88	96.82 353	99.47 72	96.55 204	99.84 153	98.56 105	99.94 42	99.55 116
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		96.47 307	95.70 316	98.79 168	97.92 366	99.12 61	98.28 146	98.60 315	92.16 390	95.54 389	96.17 382	94.77 272	99.52 345	89.62 404	98.23 358	97.72 393
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		96.86 291	96.55 298	97.79 276	97.91 367	94.21 319	97.56 247	98.87 279	97.49 222	99.06 146	99.05 164	80.72 393	99.80 201	98.44 109	99.82 102	99.37 197

API-MVS		97.04 282	96.91 274	97.42 314	97.88 368	98.23 126	98.18 155	98.50 320	97.57 212	97.39 326	96.75 370	96.77 192	99.15 399	90.16 402	99.02 313	94.88 424

myMVS_eth3d28		92.92 379	92.31 375	94.77 388	97.84 369	87.59 411	96.19 338	96.11 385	97.08 264	94.27 404	93.49 420	66.07 427	98.78 412	91.78 380	97.93 377	97.92 381

miper_ehance_all_eth		97.06 280	97.03 265	97.16 327	97.83 370	93.06 352	94.66 396	99.09 242	95.99 314	98.69 210	98.45 283	92.73 312	99.61 314	96.79 217	99.03 310	98.82 306

cl____		97.02 283	96.83 279	97.58 298	97.82 371	94.04 326	94.66 396	99.16 230	97.04 266	98.63 218	98.71 239	88.68 347	99.69 270	97.00 196	99.81 106	99.00 279

DIV-MVS_self_test		97.02 283	96.84 278	97.58 298	97.82 371	94.03 327	94.66 396	99.16 230	97.04 266	98.63 218	98.71 239	88.69 345	99.69 270	97.00 196	99.81 106	99.01 275

CANet		97.87 216	97.76 218	98.19 251	97.75 373	95.51 278	96.76 305	99.05 248	97.74 197	96.93 342	98.21 305	95.59 246	99.89 83	97.86 146	99.93 47	99.19 248

UBG		93.25 373	92.32 374	96.04 368	97.72 374	90.16 398	95.92 356	95.91 390	96.03 312	93.95 412	93.04 423	69.60 417	99.52 345	90.72 400	97.98 375	98.45 348

mvsany_test1		97.60 237	97.54 235	97.77 278	97.72 374	95.35 285	95.36 378	97.13 364	94.13 363	99.71 40	99.33 99	97.93 111	99.30 386	97.60 162	98.94 324	98.67 333

PVSNet_0	89.98 21	91.15 393	90.30 396	93.70 401	97.72 374	84.34 425	90.24 424	97.42 353	90.20 407	93.79 413	93.09 422	90.90 331	98.89 410	86.57 415	72.76 431	97.87 384

CR-MVSNet		96.28 312	95.95 311	97.28 319	97.71 377	94.22 317	98.11 166	98.92 270	92.31 388	96.91 345	99.37 88	85.44 369	99.81 194	97.39 172	97.36 393	97.81 387

RPMNet		97.02 283	96.93 270	97.30 318	97.71 377	94.22 317	98.11 166	99.30 184	99.37 50	96.91 345	99.34 97	86.72 356	99.87 114	97.53 166	97.36 393	97.81 387

ETVMVS		92.60 382	91.08 391	97.18 323	97.70 379	93.65 345	96.54 314	95.70 393	96.51 291	94.68 400	92.39 426	61.80 433	99.50 351	86.97 412	97.41 389	98.40 356

pmmvs3		95.03 344	94.40 351	96.93 335	97.70 379	92.53 363	95.08 385	97.71 347	88.57 414	97.71 299	98.08 316	79.39 400	99.82 180	96.19 268	99.11 304	98.43 353

baseline2		93.73 365	92.83 371	96.42 353	97.70 379	91.28 384	96.84 301	89.77 425	93.96 368	92.44 420	95.93 387	79.14 401	99.77 231	92.94 362	96.76 404	98.21 365

WBMVS		95.18 341	94.78 347	96.37 354	97.68 382	89.74 401	95.80 362	98.73 306	97.54 217	98.30 253	98.44 284	70.06 415	99.82 180	96.62 234	99.87 83	99.54 120

tpm		94.67 349	94.34 353	95.66 375	97.68 382	88.42 405	97.88 201	94.90 399	94.46 354	96.03 379	98.56 268	78.66 403	99.79 214	95.88 281	95.01 418	98.78 318

CANet_DTU		97.26 265	97.06 264	97.84 272	97.57 384	94.65 309	96.19 338	98.79 296	97.23 254	95.14 395	98.24 302	93.22 299	99.84 153	97.34 174	99.84 92	99.04 271

testing11		93.08 376	92.02 381	96.26 359	97.56 385	90.83 393	96.32 330	95.70 393	96.47 295	92.66 419	93.73 416	64.36 431	99.59 319	93.77 347	97.57 382	98.37 360

tpm2		93.09 375	92.58 373	94.62 390	97.56 385	86.53 414	97.66 233	95.79 392	86.15 419	94.07 409	98.23 304	75.95 408	99.53 341	90.91 397	96.86 403	97.81 387

testing91		93.32 371	92.27 376	96.47 352	97.54 387	91.25 385	96.17 342	96.76 375	97.18 258	93.65 415	93.50 419	65.11 430	99.63 304	93.04 361	97.45 386	98.53 342

TR-MVS		95.55 334	95.12 340	96.86 342	97.54 387	93.94 331	96.49 319	96.53 380	94.36 359	97.03 340	96.61 373	94.26 284	99.16 398	86.91 414	96.31 408	97.47 401

testing99		93.04 377	91.98 384	96.23 361	97.53 389	90.70 395	96.35 328	95.94 389	96.87 276	93.41 416	93.43 421	63.84 432	99.59 319	93.24 359	97.19 396	98.40 356

1314		95.74 328	95.60 320	96.17 364	97.53 389	92.75 360	98.07 172	98.31 329	91.22 399	94.25 405	96.68 371	95.53 247	99.03 401	91.64 384	97.18 397	96.74 411

CostFormer		93.97 361	93.78 359	94.51 391	97.53 389	85.83 417	97.98 189	95.96 388	89.29 412	94.99 397	98.63 258	78.63 404	99.62 307	94.54 320	96.50 405	98.09 372

FMVSNet5		96.01 319	95.20 338	98.41 230	97.53 389	96.10 256	98.74 92	99.50 96	97.22 257	98.03 279	99.04 166	69.80 416	99.88 97	97.27 177	99.71 165	99.25 233

PMMVS		96.51 303	95.98 310	98.09 256	97.53 389	95.84 268	94.92 389	98.84 288	91.58 394	96.05 378	95.58 393	95.68 243	99.66 293	95.59 297	98.09 368	98.76 321

reproduce_monomvs		95.00 346	95.25 335	94.22 394	97.51 394	83.34 426	97.86 205	98.44 322	98.51 140	99.29 115	99.30 105	67.68 421	99.56 330	98.89 79	99.81 106	99.77 43

PAPR		95.29 338	94.47 349	97.75 282	97.50 395	95.14 294	94.89 390	98.71 308	91.39 398	95.35 393	95.48 398	94.57 275	99.14 400	84.95 417	97.37 391	98.97 284

testing222		91.96 390	90.37 394	96.72 347	97.47 396	92.59 361	96.11 344	94.76 400	96.83 278	92.90 418	92.87 424	57.92 434	99.55 334	86.93 413	97.52 383	98.00 378

PatchT		96.65 299	96.35 303	97.54 304	97.40 397	95.32 287	97.98 189	96.64 377	99.33 55	96.89 349	99.42 80	84.32 377	99.81 194	97.69 158	97.49 384	97.48 400

tpm cat1		93.29 372	93.13 369	93.75 400	97.39 398	84.74 420	97.39 263	97.65 350	83.39 424	94.16 406	98.41 286	82.86 388	99.39 373	91.56 386	95.35 417	97.14 406

PatchmatchNet		95.58 333	95.67 318	95.30 384	97.34 399	87.32 412	97.65 235	96.65 376	95.30 335	97.07 336	98.69 244	84.77 372	99.75 244	94.97 310	98.64 344	98.83 305
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 258	96.97 268	98.50 221	97.31 400	96.47 248	98.18 155	98.92 270	98.95 108	98.78 199	99.37 88	85.44 369	99.85 135	95.96 279	99.83 99	99.17 255

LS3D		98.63 131	98.38 155	99.36 66	97.25 401	99.38 12	99.12 57	99.32 171	99.21 68	98.44 244	98.88 210	97.31 158	99.80 201	96.58 237	99.34 265	98.92 293

IB-MVS	91.63 19	92.24 388	90.90 392	96.27 358	97.22 402	91.24 386	94.36 405	93.33 413	92.37 387	92.24 422	94.58 413	66.20 426	99.89 83	93.16 360	94.63 420	97.66 395
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		92.38 385	91.76 388	94.21 395	97.16 403	84.65 421	95.42 376	88.45 427	95.96 315	96.17 373	95.84 391	66.36 424	99.71 262	91.87 379	98.64 344	98.28 363

tpmrst		95.07 343	95.46 326	93.91 398	97.11 404	84.36 424	97.62 239	96.96 369	94.98 342	96.35 371	98.80 225	85.46 368	99.59 319	95.60 296	96.23 409	97.79 390

Syy-MVS		96.04 318	95.56 324	97.49 309	97.10 405	94.48 312	96.18 340	96.58 378	95.65 323	94.77 398	92.29 427	91.27 327	99.36 376	98.17 124	98.05 372	98.63 335

myMVS_eth3d		91.92 391	90.45 393	96.30 356	97.10 405	90.90 391	96.18 340	96.58 378	95.65 323	94.77 398	92.29 427	53.88 435	99.36 376	89.59 405	98.05 372	98.63 335

MDTV_nov1_ep13			95.22 337		97.06 407	83.20 427	97.74 223	96.16 383	94.37 358	96.99 341	98.83 219	83.95 381	99.53 341	93.90 341	97.95 376

MVS		93.19 374	92.09 379	96.50 351	96.91 408	94.03 327	98.07 172	98.06 340	68.01 429	94.56 403	96.48 376	95.96 234	99.30 386	83.84 419	96.89 402	96.17 416

E-PMN		94.17 357	94.37 352	93.58 402	96.86 409	85.71 418	90.11 426	97.07 365	98.17 168	97.82 294	97.19 362	84.62 374	98.94 406	89.77 403	97.68 381	96.09 420

JIA-IIPM		95.52 335	95.03 341	97.00 331	96.85 410	94.03 327	96.93 296	95.82 391	99.20 70	94.63 402	99.71 19	83.09 386	99.60 315	94.42 326	94.64 419	97.36 404

EMVS		93.83 363	94.02 355	93.23 407	96.83 411	84.96 419	89.77 427	96.32 382	97.92 185	97.43 323	96.36 381	86.17 361	98.93 407	87.68 410	97.73 380	95.81 421

cl22		95.79 327	95.39 331	96.98 333	96.77 412	92.79 358	94.40 404	98.53 318	94.59 351	97.89 286	98.17 308	82.82 389	99.24 392	96.37 257	99.03 310	98.92 293

WB-MVSnew		95.73 329	95.57 323	96.23 361	96.70 413	90.70 395	96.07 346	93.86 410	95.60 325	97.04 338	95.45 402	96.00 227	99.55 334	91.04 394	98.31 356	98.43 353

dp		93.47 369	93.59 362	93.13 408	96.64 414	81.62 433	97.66 233	96.42 381	92.80 383	96.11 375	98.64 256	78.55 406	99.59 319	93.31 357	92.18 427	98.16 368

MonoMVSNet		96.25 313	96.53 300	95.39 382	96.57 415	91.01 389	98.82 90	97.68 349	98.57 135	98.03 279	99.37 88	90.92 330	97.78 423	94.99 308	93.88 423	97.38 403

test-LLR		93.90 362	93.85 357	94.04 396	96.53 416	84.62 422	94.05 410	92.39 416	96.17 304	94.12 407	95.07 403	82.30 390	99.67 282	95.87 284	98.18 361	97.82 385

test-mter		92.33 387	91.76 388	94.04 396	96.53 416	84.62 422	94.05 410	92.39 416	94.00 367	94.12 407	95.07 403	65.63 429	99.67 282	95.87 284	98.18 361	97.82 385

TESTMET0.1,1		92.19 389	91.77 387	93.46 403	96.48 418	82.80 429	94.05 410	91.52 421	94.45 356	94.00 410	94.88 409	66.65 423	99.56 330	95.78 289	98.11 367	98.02 375

MVS_0304		97.44 251	97.01 267	98.72 183	96.42 419	96.74 239	97.20 281	91.97 419	98.46 143	98.30 253	98.79 227	92.74 311	99.91 64	99.30 49	99.94 42	99.52 131

miper_enhance_ethall		96.01 319	95.74 314	96.81 343	96.41 420	92.27 370	93.69 415	98.89 276	91.14 401	98.30 253	97.35 360	90.58 333	99.58 325	96.31 261	99.03 310	98.60 337

tpmvs		95.02 345	95.25 335	94.33 392	96.39 421	85.87 415	98.08 170	96.83 374	95.46 330	95.51 391	98.69 244	85.91 364	99.53 341	94.16 332	96.23 409	97.58 398

CMPMVS	75.91 23	96.29 311	95.44 328	98.84 159	96.25 422	98.69 90	97.02 289	99.12 237	88.90 413	97.83 292	98.86 213	89.51 340	98.90 409	91.92 377	99.51 238	98.92 293
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 350	93.69 360	96.99 332	96.05 423	93.61 347	94.97 388	93.49 411	96.17 304	97.57 310	94.88 409	82.30 390	99.01 404	93.60 350	94.17 422	98.37 360

EPMVS		93.72 366	93.27 365	95.09 387	96.04 424	87.76 409	98.13 162	85.01 432	94.69 349	96.92 343	98.64 256	78.47 407	99.31 384	95.04 307	96.46 406	98.20 366

cascas		94.79 348	94.33 354	96.15 367	96.02 425	92.36 368	92.34 422	99.26 203	85.34 421	95.08 396	94.96 408	92.96 306	98.53 416	94.41 329	98.59 348	97.56 399

MVStest1		95.86 324	95.60 320	96.63 348	95.87 426	91.70 375	97.93 193	98.94 264	98.03 175	99.56 59	99.66 29	71.83 413	98.26 419	99.35 46	99.24 281	99.91 13

gg-mvs-nofinetune		92.37 386	91.20 390	95.85 370	95.80 427	92.38 367	99.31 27	81.84 434	99.75 8	91.83 423	99.74 15	68.29 418	99.02 402	87.15 411	97.12 398	96.16 417

gm-plane-assit					94.83 428	81.97 431			88.07 416		94.99 406		99.60 315	91.76 381

GG-mvs-BLEND				94.76 389	94.54 429	92.13 372	99.31 27	80.47 435		88.73 429	91.01 429	67.59 422	98.16 422	82.30 424	94.53 421	93.98 425

UWE-MVS-28		90.22 394	89.28 397	93.02 409	94.50 430	82.87 428	96.52 317	87.51 428	95.21 338	92.36 421	96.04 383	71.57 414	98.25 420	72.04 430	97.77 379	97.94 380

EPNet_dtu		94.93 347	94.78 347	95.38 383	93.58 431	87.68 410	96.78 303	95.69 395	97.35 238	89.14 428	98.09 315	88.15 352	99.49 354	94.95 311	99.30 272	98.98 281
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 398	75.95 401	77.12 414	92.39 432	67.91 438	90.16 425	59.44 439	82.04 425	89.42 427	94.67 412	49.68 437	81.74 432	48.06 432	77.66 430	81.72 428

KD-MVS_2432*1600		92.87 380	91.99 382	95.51 379	91.37 433	89.27 402	94.07 408	98.14 336	95.42 331	97.25 331	96.44 378	67.86 419	99.24 392	91.28 390	96.08 412	98.02 375

miper_refine_blended		92.87 380	91.99 382	95.51 379	91.37 433	89.27 402	94.07 408	98.14 336	95.42 331	97.25 331	96.44 378	67.86 419	99.24 392	91.28 390	96.08 412	98.02 375

EPNet		96.14 316	95.44 328	98.25 246	90.76 435	95.50 279	97.92 196	94.65 401	98.97 105	92.98 417	98.85 216	89.12 343	99.87 114	95.99 277	99.68 180	99.39 188
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 399	68.95 402	70.34 415	87.68 436	65.00 439	91.11 423	59.90 438	69.02 428	74.46 433	88.89 430	48.58 438	68.03 434	28.61 433	72.33 432	77.99 429

test_method		79.78 396	79.50 399	80.62 412	80.21 437	45.76 440	70.82 428	98.41 326	31.08 432	80.89 432	97.71 337	84.85 371	97.37 425	91.51 387	80.03 429	98.75 322

tmp_tt		78.77 397	78.73 400	78.90 413	58.45 438	74.76 437	94.20 407	78.26 436	39.16 431	86.71 430	92.82 425	80.50 394	75.19 433	86.16 416	92.29 426	86.74 427

testmvs		17.12 401	20.53 404	6.87 417	12.05 439	4.20 442	93.62 416	6.73 440	4.62 435	10.41 435	24.33 432	8.28 440	3.56 436	9.69 435	15.07 433	12.86 432

test123		17.04 402	20.11 405	7.82 416	10.25 440	4.91 441	94.80 391	4.47 441	4.93 434	10.00 436	24.28 433	9.69 439	3.64 435	10.14 434	12.43 434	14.92 431

mmdepth		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

monomultidepth		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

test_blank		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

eth-test2					0.00 441

eth-test					0.00 441

uanet_test		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

DCPMVS		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

cdsmvs_eth3d_5k		24.66 400	32.88 403	0.00 418	0.00 441	0.00 443	0.00 429	99.10 240	0.00 436	0.00 437	97.58 345	99.21 17	0.00 437	0.00 436	0.00 435	0.00 433

pcd_1.5k_mvsjas		8.17 403	10.90 406	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	98.07 99	0.00 437	0.00 436	0.00 435	0.00 433

sosnet-low-res		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

sosnet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uncertanet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

Regformer		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

ab-mvs-re		8.12 404	10.83 407	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	97.48 351	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uanet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

WAC-MVS						90.90 391								91.37 389

PC_three_1452									93.27 375	99.40 94	98.54 269	98.22 86	97.00 426	95.17 305	99.45 250	99.49 141

test_241102_TWO								99.30 184	98.03 175	99.26 122	99.02 169	97.51 147	99.88 97	96.91 204	99.60 207	99.66 67

test_0728_THIRD									98.17 168	99.08 144	99.02 169	97.89 113	99.88 97	97.07 192	99.71 165	99.70 60

GSMVS																98.81 311

sam_mvs1												84.74 373				98.81 311

sam_mvs												84.29 379

MTGPA								99.20 215

test_post1							97.59 244				20.48 435	83.07 387	99.66 293	94.16 332

test_post											21.25 434	83.86 382	99.70 266

patchmatchnet-post											98.77 231	84.37 376	99.85 135

MTMP							97.93 193	91.91 420

test9_res														93.28 358	99.15 297	99.38 195

agg_prior2														92.50 374	99.16 295	99.37 197

test_prior4						97.97 155	95.86 358

test_prior2							95.74 364		96.48 294	96.11 375	97.63 343	95.92 237		94.16 332	99.20 289

旧先验2							95.76 363		88.56 415	97.52 314			99.66 293	94.48 322

新几何2							95.93 354

无先验							95.74 364	98.74 305	89.38 411				99.73 254	92.38 376		99.22 242

原ACMM2							95.53 370

testdata2													99.79 214	92.80 368

segment_acmp												97.02 177

testdata1							95.44 375		96.32 300

plane_prior5								99.27 198					99.70 266	94.42 326	99.51 238	99.45 164

plane_prior4											97.98 322

plane_prior3						97.78 176			97.41 232	97.79 295

plane_prior2							97.77 217		98.20 165

plane_prior						97.65 185	97.07 288		96.72 284						99.36 261

n2								0.00 442

nn								0.00 442

door-mid								99.57 72

test11								98.87 279

door								99.41 137

HQP5-MVS						96.79 235

BP-MVS														92.82 366

HQP4-MVS										95.56 385			99.54 339			99.32 217

HQP3-MVS								99.04 251							99.26 279

HQP2-MVS												93.84 291

MDTV_nov1_ep13_2view						74.92 436	97.69 228		90.06 409	97.75 298		85.78 365		93.52 352		98.69 329

ACMMP++_ref															99.77 133

ACMMP++															99.68 180

Test By Simon												96.52 205

High-resolution multi-view benchmark