This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

(*) 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 Infoallhigh-res
multi-view
indooroutdoorbotani.boulde.bridgedoorexhibi.lectur.living.loungeobserv.old co.statueterrac.
sort bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
LCM-MVSNet99.93 199.92 199.94 199.99 199.97 199.90 199.89 1399.98 199.99 199.96 199.77 2100.00 199.81 16100.00 199.85 29
Gipumacopyleft99.03 7999.16 6198.64 21499.94 298.51 11199.32 2699.75 4299.58 3898.60 26399.62 4098.22 10399.51 39297.70 18699.73 17797.89 425
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-099.37 2999.31 4199.53 3999.91 398.98 7299.63 799.58 8599.44 5299.78 3999.76 1596.39 24499.92 6499.44 5499.92 6899.68 70
pmmvs699.67 399.70 399.60 1699.90 499.27 2899.53 999.76 3999.64 2799.84 3099.83 499.50 999.87 13399.36 5799.92 6899.64 83
PS-MVSNAJss99.46 1799.49 1699.35 7999.90 498.15 13899.20 4899.65 6799.48 4499.92 899.71 2298.07 11799.96 1499.53 47100.00 199.93 11
testf199.25 4199.16 6199.51 4999.89 699.63 498.71 10499.69 5498.90 13299.43 10499.35 10398.86 3499.67 31797.81 17499.81 12799.24 273
APD_test299.25 4199.16 6199.51 4999.89 699.63 498.71 10499.69 5498.90 13299.43 10499.35 10398.86 3499.67 31797.81 17499.81 12799.24 273
ANet_high99.57 1099.67 699.28 9599.89 698.09 14599.14 5799.93 599.82 899.93 699.81 899.17 2099.94 4299.31 61100.00 199.82 35
anonymousdsp99.51 1499.47 2199.62 1099.88 999.08 7099.34 2399.69 5498.93 12899.65 6399.72 2198.93 3299.95 2699.11 77100.00 199.82 35
v7n99.53 1299.57 1399.41 6999.88 998.54 10999.45 1499.61 7699.66 2499.68 5799.66 3298.44 7799.95 2699.73 2799.96 2899.75 59
mvs_tets99.63 699.67 699.49 5599.88 998.61 10199.34 2399.71 4799.27 7399.90 1499.74 1899.68 499.97 799.55 4299.99 599.88 20
test_fmvsmconf0.01_n99.57 1099.63 1099.36 7399.87 1298.13 14198.08 18599.95 199.45 5099.98 299.75 1699.80 199.97 799.82 1299.99 599.99 2
jajsoiax99.58 999.61 1199.48 5799.87 1298.61 10199.28 4099.66 6399.09 10799.89 1899.68 2599.53 799.97 799.50 5099.99 599.87 21
test_djsdf99.52 1399.51 1599.53 3999.86 1498.74 9199.39 2099.56 10099.11 9799.70 5199.73 2099.00 2799.97 799.26 6599.98 1299.89 16
MIMVSNet199.38 2899.32 3999.55 2999.86 1499.19 4399.41 1799.59 8399.59 3699.71 4999.57 4997.12 19999.90 8099.21 7099.87 9699.54 140
LTVRE_ROB98.40 199.67 399.71 299.56 2799.85 1699.11 6599.90 199.78 3699.63 2999.78 3999.67 3099.48 1099.81 22099.30 6299.97 2199.77 49
Andreas Kuhn, Heiko Hirschmüller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
UniMVSNet_ETH3D99.69 299.69 499.69 399.84 1799.34 2099.69 599.58 8599.90 399.86 2499.78 1399.58 699.95 2699.00 8799.95 3899.78 46
SixPastTwentyTwo98.75 12798.62 14199.16 11799.83 1897.96 16599.28 4098.20 37299.37 6099.70 5199.65 3692.65 35099.93 5399.04 8499.84 11099.60 99
sc_t199.62 799.66 899.53 3999.82 1999.09 6999.50 1199.63 7199.88 499.86 2499.80 1199.03 2499.89 9699.48 5299.93 5599.60 99
Baseline_NR-MVSNet98.98 8798.86 10599.36 7399.82 1998.55 10697.47 29099.57 9299.37 6099.21 15799.61 4396.76 22699.83 19198.06 15299.83 11799.71 62
pm-mvs199.44 1999.48 1899.33 8899.80 2198.63 9899.29 3699.63 7199.30 7099.65 6399.60 4599.16 2299.82 20399.07 8099.83 11799.56 127
TransMVSNet (Re)99.44 1999.47 2199.36 7399.80 2198.58 10499.27 4299.57 9299.39 5899.75 4499.62 4099.17 2099.83 19199.06 8299.62 23599.66 77
K. test v398.00 24497.66 26999.03 14499.79 2397.56 20199.19 5292.47 45899.62 3299.52 8699.66 3289.61 38199.96 1499.25 6799.81 12799.56 127
test_fmvsmconf0.1_n99.49 1599.54 1499.34 8299.78 2498.11 14297.77 24199.90 1199.33 6599.97 399.66 3299.71 399.96 1499.79 1999.99 599.96 8
APD_test198.83 11198.66 13499.34 8299.78 2499.47 998.42 14799.45 14898.28 18498.98 19299.19 14697.76 14799.58 36696.57 28199.55 26298.97 327
test_vis3_rt99.14 6199.17 5999.07 13499.78 2498.38 11898.92 8299.94 297.80 22899.91 1299.67 3097.15 19898.91 45199.76 2399.56 25899.92 12
EGC-MVSNET85.24 43780.54 44099.34 8299.77 2799.20 4099.08 6199.29 22812.08 47620.84 47799.42 8897.55 16699.85 15597.08 23099.72 18598.96 329
Anonymous2024052198.69 13998.87 10198.16 29099.77 2795.11 33199.08 6199.44 15699.34 6499.33 12799.55 5794.10 32599.94 4299.25 6799.96 2899.42 203
FC-MVSNet-test99.27 3899.25 5299.34 8299.77 2798.37 12099.30 3599.57 9299.61 3499.40 11399.50 6797.12 19999.85 15599.02 8699.94 4999.80 41
test_vis1_n98.31 20898.50 16197.73 32499.76 3094.17 35998.68 10799.91 996.31 34299.79 3899.57 4992.85 34699.42 41299.79 1999.84 11099.60 99
test_fmvs399.12 6899.41 2698.25 27899.76 3095.07 33299.05 6799.94 297.78 23199.82 3399.84 398.56 6899.71 29399.96 199.96 2899.97 4
XXY-MVS99.14 6199.15 6699.10 12799.76 3097.74 19098.85 9299.62 7398.48 16799.37 11899.49 7398.75 4699.86 14298.20 14299.80 13899.71 62
TDRefinement99.42 2499.38 2999.55 2999.76 3099.33 2199.68 699.71 4799.38 5999.53 8299.61 4398.64 5699.80 22898.24 13799.84 11099.52 152
fmvsm_s_conf0.1_n_a99.17 5299.30 4498.80 18199.75 3496.59 26597.97 21599.86 1698.22 18799.88 2199.71 2298.59 6299.84 17399.73 2799.98 1299.98 3
tt080598.69 13998.62 14198.90 16999.75 3499.30 2399.15 5696.97 40998.86 13798.87 22597.62 38798.63 5898.96 44899.41 5698.29 40098.45 391
test_vis1_n_192098.40 19198.92 9496.81 38699.74 3690.76 43798.15 17399.91 998.33 17599.89 1899.55 5795.07 29699.88 11499.76 2399.93 5599.79 43
FOURS199.73 3799.67 399.43 1599.54 10999.43 5499.26 145
PEN-MVS99.41 2599.34 3699.62 1099.73 3799.14 5899.29 3699.54 10999.62 3299.56 7399.42 8898.16 11199.96 1498.78 10199.93 5599.77 49
lessismore_v098.97 15699.73 3797.53 20386.71 47399.37 11899.52 6689.93 37799.92 6498.99 8899.72 18599.44 195
SteuartSystems-ACMMP98.79 12098.54 15499.54 3299.73 3799.16 4998.23 16399.31 21297.92 21998.90 21498.90 23298.00 12399.88 11496.15 31399.72 18599.58 114
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu98.17 22998.15 22198.22 28499.73 3795.15 32897.36 30499.68 5994.45 39998.99 19199.27 12296.87 21599.94 4297.13 22799.91 7799.57 121
Vis-MVSNetpermissive99.34 3099.36 3399.27 9899.73 3798.26 12799.17 5399.78 3699.11 9799.27 14199.48 7498.82 3799.95 2698.94 9199.93 5599.59 106
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
tt0320-xc99.64 599.68 599.50 5499.72 4398.98 7299.51 1099.85 1899.86 699.88 2199.82 599.02 2699.90 8099.54 4399.95 3899.61 97
SSC-MVS98.71 13198.74 11698.62 22099.72 4396.08 28998.74 9798.64 35299.74 1399.67 5999.24 13594.57 31199.95 2699.11 7799.24 32499.82 35
test_f98.67 14898.87 10198.05 29999.72 4395.59 30498.51 13199.81 3196.30 34499.78 3999.82 596.14 25598.63 45899.82 1299.93 5599.95 9
ACMH96.65 799.25 4199.24 5399.26 10099.72 4398.38 11899.07 6499.55 10498.30 17999.65 6399.45 8399.22 1799.76 26498.44 12799.77 15599.64 83
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt032099.61 899.65 999.48 5799.71 4798.94 7999.54 899.83 2599.87 599.89 1899.82 598.75 4699.90 8099.54 4399.95 3899.59 106
fmvsm_s_conf0.1_n99.16 5699.33 3798.64 21499.71 4796.10 28497.87 22799.85 1898.56 16399.90 1499.68 2598.69 5299.85 15599.72 2999.98 1299.97 4
PS-CasMVS99.40 2699.33 3799.62 1099.71 4799.10 6699.29 3699.53 11399.53 4199.46 9999.41 9298.23 10099.95 2698.89 9599.95 3899.81 39
DTE-MVSNet99.43 2399.35 3499.66 799.71 4799.30 2399.31 3099.51 11999.64 2799.56 7399.46 7998.23 10099.97 798.78 10199.93 5599.72 61
WR-MVS_H99.33 3199.22 5499.65 899.71 4799.24 3199.32 2699.55 10499.46 4999.50 9299.34 10797.30 18899.93 5398.90 9399.93 5599.77 49
HPM-MVS_fast99.01 8198.82 10999.57 2299.71 4799.35 1799.00 7299.50 12297.33 27698.94 20998.86 24298.75 4699.82 20397.53 19899.71 19499.56 127
ACMH+96.62 999.08 7599.00 8699.33 8899.71 4798.83 8698.60 11799.58 8599.11 9799.53 8299.18 15098.81 3899.67 31796.71 26899.77 15599.50 158
PMVScopyleft91.26 2097.86 25897.94 24597.65 33199.71 4797.94 16798.52 12698.68 34898.99 12097.52 35699.35 10397.41 18198.18 46491.59 42799.67 21596.82 453
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
KinetiMVS99.03 7999.02 8299.03 14499.70 5597.48 20698.43 14499.29 22899.70 1699.60 7099.07 17996.13 25699.94 4299.42 5599.87 9699.68 70
FIs99.14 6199.09 7499.29 9499.70 5598.28 12699.13 5899.52 11899.48 4499.24 15199.41 9296.79 22399.82 20398.69 11199.88 9299.76 55
VPNet98.87 10298.83 10899.01 14899.70 5597.62 19998.43 14499.35 19399.47 4799.28 13999.05 18796.72 22999.82 20398.09 14999.36 30399.59 106
fmvsm_s_conf0.1_n_299.20 5099.38 2998.65 21299.69 5896.08 28997.49 28699.90 1199.53 4199.88 2199.64 3798.51 7199.90 8099.83 1099.98 1299.97 4
test_cas_vis1_n_192098.33 20598.68 13097.27 36299.69 5892.29 41198.03 19699.85 1897.62 24199.96 499.62 4093.98 32699.74 27799.52 4999.86 10399.79 43
MP-MVS-pluss98.57 16598.23 20999.60 1699.69 5899.35 1797.16 32599.38 17994.87 38998.97 19698.99 20998.01 12299.88 11497.29 21499.70 20199.58 114
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet99.23 4699.32 3998.96 15799.68 6197.35 21498.84 9499.48 13199.69 1899.63 6699.68 2599.03 2499.96 1497.97 16299.92 6899.57 121
sd_testset99.28 3799.31 4199.19 11199.68 6198.06 15499.41 1799.30 22099.69 1899.63 6699.68 2599.25 1699.96 1497.25 21799.92 6899.57 121
test_fmvs1_n98.09 23598.28 20097.52 34899.68 6193.47 39098.63 11399.93 595.41 37799.68 5799.64 3791.88 36099.48 39999.82 1299.87 9699.62 89
CHOSEN 1792x268897.49 28797.14 30298.54 24299.68 6196.09 28796.50 36199.62 7391.58 43798.84 22898.97 21692.36 35299.88 11496.76 26199.95 3899.67 75
tfpnnormal98.90 9898.90 9698.91 16699.67 6597.82 18299.00 7299.44 15699.45 5099.51 9199.24 13598.20 10699.86 14295.92 32299.69 20499.04 314
MTAPA98.88 10198.64 13799.61 1499.67 6599.36 1698.43 14499.20 25298.83 14198.89 21798.90 23296.98 20999.92 6497.16 22299.70 20199.56 127
test_fmvsmvis_n_192099.26 4099.49 1698.54 24299.66 6796.97 24598.00 20399.85 1899.24 7599.92 899.50 6799.39 1299.95 2699.89 399.98 1298.71 368
mvs5depth99.30 3499.59 1298.44 25699.65 6895.35 32099.82 399.94 299.83 799.42 10899.94 298.13 11499.96 1499.63 3599.96 28100.00 1
fmvsm_l_conf0.5_n_a99.19 5199.27 4798.94 16099.65 6897.05 24097.80 23699.76 3998.70 14699.78 3999.11 16998.79 4299.95 2699.85 699.96 2899.83 32
WB-MVS98.52 17998.55 15298.43 25799.65 6895.59 30498.52 12698.77 33799.65 2699.52 8699.00 20794.34 31799.93 5398.65 11398.83 37299.76 55
CP-MVSNet99.21 4899.09 7499.56 2799.65 6898.96 7899.13 5899.34 19999.42 5599.33 12799.26 12897.01 20799.94 4298.74 10699.93 5599.79 43
HPM-MVScopyleft98.79 12098.53 15699.59 2099.65 6899.29 2599.16 5499.43 16296.74 32298.61 26198.38 33298.62 5999.87 13396.47 29399.67 21599.59 106
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF98.62 15798.36 18799.42 6799.65 6899.42 1198.55 12299.57 9297.72 23598.90 21499.26 12896.12 25899.52 38795.72 33399.71 19499.32 250
NormalMVS98.26 21597.97 24299.15 12099.64 7497.83 17798.28 15799.43 16299.24 7598.80 23698.85 24589.76 37999.94 4298.04 15499.67 21599.68 70
lecture99.25 4199.12 6999.62 1099.64 7499.40 1298.89 8799.51 11999.19 8799.37 11899.25 13398.36 8299.88 11498.23 13999.67 21599.59 106
fmvsm_l_conf0.5_n99.21 4899.28 4699.02 14799.64 7497.28 22197.82 23299.76 3998.73 14399.82 3399.09 17798.81 3899.95 2699.86 499.96 2899.83 32
test_fmvsmconf_n99.44 1999.48 1899.31 9399.64 7498.10 14497.68 25599.84 2299.29 7199.92 899.57 4999.60 599.96 1499.74 2699.98 1299.89 16
TSAR-MVS + MP.98.63 15498.49 16699.06 14099.64 7497.90 17198.51 13198.94 30296.96 30799.24 15198.89 23897.83 13999.81 22096.88 25199.49 28399.48 176
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS98.82 11498.72 12099.12 12399.64 7498.54 10997.98 21199.68 5997.62 24199.34 12599.18 15097.54 16899.77 25897.79 17699.74 17499.04 314
Elysia99.15 5799.14 6799.18 11299.63 8097.92 16898.50 13399.43 16299.67 2199.70 5199.13 16596.66 23299.98 499.54 4399.96 2899.64 83
StellarMVS99.15 5799.14 6799.18 11299.63 8097.92 16898.50 13399.43 16299.67 2199.70 5199.13 16596.66 23299.98 499.54 4399.96 2899.64 83
KD-MVS_self_test99.25 4199.18 5899.44 6599.63 8099.06 7198.69 10699.54 10999.31 6899.62 6999.53 6397.36 18599.86 14299.24 6999.71 19499.39 216
EU-MVSNet97.66 27598.50 16195.13 42899.63 8085.84 45998.35 15398.21 37198.23 18699.54 7899.46 7995.02 29799.68 31398.24 13799.87 9699.87 21
HyFIR lowres test97.19 31396.60 33798.96 15799.62 8497.28 22195.17 42699.50 12294.21 40499.01 18798.32 34086.61 39999.99 297.10 22999.84 11099.60 99
fmvsm_l_conf0.5_n_999.32 3399.43 2498.98 15499.59 8597.18 23297.44 29499.83 2599.56 3999.91 1299.34 10799.36 1399.93 5399.83 1099.98 1299.85 29
fmvsm_l_conf0.5_n_399.45 1899.48 1899.34 8299.59 8598.21 13597.82 23299.84 2299.41 5799.92 899.41 9299.51 899.95 2699.84 999.97 2199.87 21
MED-MVS test99.45 6499.58 8798.93 8098.68 10799.60 7796.46 33599.53 8298.77 26599.83 19196.67 27199.64 22699.58 114
TestfortrainingZip a98.95 9198.72 12099.64 999.58 8799.32 2298.68 10799.60 7796.46 33599.53 8298.77 26597.87 13799.83 19198.39 13099.64 22699.77 49
FE-MVSNET98.59 16298.50 16198.87 17099.58 8797.30 21998.08 18599.74 4396.94 30998.97 19699.10 17296.94 21199.74 27797.33 21299.86 10399.55 134
mmtdpeth99.30 3499.42 2598.92 16599.58 8796.89 25299.48 1399.92 799.92 298.26 29999.80 1198.33 8899.91 7399.56 4099.95 3899.97 4
ACMMP_NAP98.75 12798.48 16799.57 2299.58 8799.29 2597.82 23299.25 24196.94 30998.78 23899.12 16898.02 12199.84 17397.13 22799.67 21599.59 106
nrg03099.40 2699.35 3499.54 3299.58 8799.13 6198.98 7599.48 13199.68 2099.46 9999.26 12898.62 5999.73 28499.17 7499.92 6899.76 55
VDDNet98.21 22297.95 24399.01 14899.58 8797.74 19099.01 7097.29 40099.67 2198.97 19699.50 6790.45 37499.80 22897.88 16999.20 33299.48 176
COLMAP_ROBcopyleft96.50 1098.99 8498.85 10799.41 6999.58 8799.10 6698.74 9799.56 10099.09 10799.33 12799.19 14698.40 7999.72 29295.98 32099.76 16999.42 203
Johannes L. Schönberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_fmvsm_n_192099.33 3199.45 2398.99 15099.57 9597.73 19297.93 21699.83 2599.22 7899.93 699.30 11699.42 1199.96 1499.85 699.99 599.29 259
ZNCC-MVS98.68 14598.40 17999.54 3299.57 9599.21 3498.46 14199.29 22897.28 28298.11 31198.39 33098.00 12399.87 13396.86 25499.64 22699.55 134
MSP-MVS98.40 19198.00 23799.61 1499.57 9599.25 3098.57 12099.35 19397.55 25299.31 13597.71 38094.61 31099.88 11496.14 31499.19 33599.70 67
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
testgi98.32 20698.39 18298.13 29199.57 9595.54 30797.78 23899.49 12997.37 27399.19 15997.65 38498.96 2999.49 39696.50 29298.99 36099.34 241
MP-MVScopyleft98.46 18598.09 22699.54 3299.57 9599.22 3398.50 13399.19 25697.61 24497.58 35098.66 29297.40 18299.88 11494.72 35999.60 24299.54 140
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test98.71 13198.46 17199.47 6199.57 9598.97 7498.23 16399.48 13196.60 32799.10 16999.06 18098.71 5099.83 19195.58 34099.78 14999.62 89
LGP-MVS_train99.47 6199.57 9598.97 7499.48 13196.60 32799.10 16999.06 18098.71 5099.83 19195.58 34099.78 14999.62 89
IS-MVSNet98.19 22597.90 25199.08 13299.57 9597.97 16299.31 3098.32 36799.01 11998.98 19299.03 19191.59 36299.79 24195.49 34299.80 13899.48 176
viewdifsd2359ckpt1198.84 10899.04 7998.24 28099.56 10395.51 30997.38 29999.70 5299.16 9299.57 7199.40 9598.26 9699.71 29398.55 12299.82 12199.50 158
viewmsd2359difaftdt98.84 10899.04 7998.24 28099.56 10395.51 30997.38 29999.70 5299.16 9299.57 7199.40 9598.26 9699.71 29398.55 12299.82 12199.50 158
dcpmvs_298.78 12299.11 7097.78 31499.56 10393.67 38599.06 6599.86 1699.50 4399.66 6099.26 12897.21 19699.99 298.00 15999.91 7799.68 70
test_040298.76 12698.71 12498.93 16299.56 10398.14 14098.45 14399.34 19999.28 7298.95 20298.91 22998.34 8799.79 24195.63 33799.91 7798.86 346
EPP-MVSNet98.30 20998.04 23399.07 13499.56 10397.83 17799.29 3698.07 37899.03 11798.59 26599.13 16592.16 35699.90 8096.87 25299.68 20999.49 165
ACMMPcopyleft98.75 12798.50 16199.52 4599.56 10399.16 4998.87 8899.37 18397.16 29798.82 23299.01 20397.71 15099.87 13396.29 30599.69 20499.54 140
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
fmvsm_s_conf0.5_n_a99.10 7099.20 5798.78 18799.55 10996.59 26597.79 23799.82 3098.21 18999.81 3699.53 6398.46 7599.84 17399.70 3299.97 2199.90 15
fmvsm_s_conf0.5_n99.09 7199.26 5098.61 22399.55 10996.09 28797.74 24899.81 3198.55 16499.85 2799.55 5798.60 6199.84 17399.69 3499.98 1299.89 16
FMVSNet199.17 5299.17 5999.17 11499.55 10998.24 12999.20 4899.44 15699.21 8099.43 10499.55 5797.82 14299.86 14298.42 12999.89 9099.41 206
Vis-MVSNet (Re-imp)97.46 28997.16 29998.34 26999.55 10996.10 28498.94 8098.44 36198.32 17798.16 30598.62 30188.76 38699.73 28493.88 38599.79 14499.18 293
ACMM96.08 1298.91 9698.73 11899.48 5799.55 10999.14 5898.07 18999.37 18397.62 24199.04 18398.96 21998.84 3699.79 24197.43 20799.65 22499.49 165
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs298.70 13698.97 9097.89 30799.54 11494.05 36298.55 12299.92 796.78 32099.72 4799.78 1396.60 23699.67 31799.91 299.90 8499.94 10
mPP-MVS98.64 15298.34 19099.54 3299.54 11499.17 4598.63 11399.24 24697.47 26098.09 31398.68 28797.62 15999.89 9696.22 30899.62 23599.57 121
XVG-ACMP-BASELINE98.56 16698.34 19099.22 10899.54 11498.59 10397.71 25199.46 14497.25 28598.98 19298.99 20997.54 16899.84 17395.88 32399.74 17499.23 275
viewmacassd2359aftdt98.86 10598.87 10198.83 17599.53 11797.32 21897.70 25399.64 6998.22 18799.25 14999.27 12298.40 7999.61 35297.98 16199.87 9699.55 134
region2R98.69 13998.40 17999.54 3299.53 11799.17 4598.52 12699.31 21297.46 26598.44 28498.51 31597.83 13999.88 11496.46 29499.58 25199.58 114
PGM-MVS98.66 14998.37 18699.55 2999.53 11799.18 4498.23 16399.49 12997.01 30698.69 24998.88 23998.00 12399.89 9695.87 32699.59 24699.58 114
Patchmatch-RL test97.26 30697.02 30797.99 30399.52 12095.53 30896.13 38699.71 4797.47 26099.27 14199.16 15684.30 42099.62 34597.89 16699.77 15598.81 354
ACMMPR98.70 13698.42 17799.54 3299.52 12099.14 5898.52 12699.31 21297.47 26098.56 27198.54 31097.75 14899.88 11496.57 28199.59 24699.58 114
fmvsm_s_conf0.5_n_999.17 5299.38 2998.53 24499.51 12295.82 29997.62 26699.78 3699.72 1599.90 1499.48 7498.66 5499.89 9699.85 699.93 5599.89 16
AstraMVS98.16 23198.07 23198.41 25999.51 12295.86 29698.00 20395.14 44198.97 12399.43 10499.24 13593.25 33499.84 17399.21 7099.87 9699.54 140
fmvsm_s_conf0.5_n_899.13 6599.26 5098.74 20099.51 12296.44 27697.65 26199.65 6799.66 2499.78 3999.48 7497.92 13199.93 5399.72 2999.95 3899.87 21
GST-MVS98.61 15898.30 19799.52 4599.51 12299.20 4098.26 16199.25 24197.44 26898.67 25298.39 33097.68 15199.85 15596.00 31899.51 27399.52 152
Anonymous2023120698.21 22298.21 21098.20 28599.51 12295.43 31898.13 17599.32 20796.16 34898.93 21098.82 25596.00 26399.83 19197.32 21399.73 17799.36 234
ACMP95.32 1598.41 18998.09 22699.36 7399.51 12298.79 8997.68 25599.38 17995.76 36498.81 23498.82 25598.36 8299.82 20394.75 35699.77 15599.48 176
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LuminaMVS98.39 19798.20 21198.98 15499.50 12897.49 20497.78 23897.69 38798.75 14299.49 9399.25 13392.30 35499.94 4299.14 7599.88 9299.50 158
DVP-MVScopyleft98.77 12598.52 15799.52 4599.50 12899.21 3498.02 19998.84 32697.97 21399.08 17199.02 19297.61 16199.88 11496.99 23899.63 23299.48 176
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND99.60 1699.50 12899.23 3298.02 19999.32 20799.88 11496.99 23899.63 23299.68 70
test072699.50 12899.21 3498.17 17199.35 19397.97 21399.26 14599.06 18097.61 161
AllTest98.44 18798.20 21199.16 11799.50 12898.55 10698.25 16299.58 8596.80 31898.88 22199.06 18097.65 15499.57 36894.45 36699.61 24099.37 227
TestCases99.16 11799.50 12898.55 10699.58 8596.80 31898.88 22199.06 18097.65 15499.57 36894.45 36699.61 24099.37 227
XVG-OURS98.53 17598.34 19099.11 12599.50 12898.82 8895.97 39299.50 12297.30 28099.05 18198.98 21499.35 1499.32 42695.72 33399.68 20999.18 293
EG-PatchMatch MVS98.99 8499.01 8498.94 16099.50 12897.47 20798.04 19499.59 8398.15 20499.40 11399.36 10298.58 6799.76 26498.78 10199.68 20999.59 106
fmvsm_s_conf0.5_n_299.14 6199.31 4198.63 21899.49 13696.08 28997.38 29999.81 3199.48 4499.84 3099.57 4998.46 7599.89 9699.82 1299.97 2199.91 13
SED-MVS98.91 9698.72 12099.49 5599.49 13699.17 4598.10 18299.31 21298.03 20999.66 6099.02 19298.36 8299.88 11496.91 24499.62 23599.41 206
IU-MVS99.49 13699.15 5398.87 31792.97 42299.41 11096.76 26199.62 23599.66 77
test_241102_ONE99.49 13699.17 4599.31 21297.98 21299.66 6098.90 23298.36 8299.48 399
UA-Net99.47 1699.40 2799.70 299.49 13699.29 2599.80 499.72 4599.82 899.04 18399.81 898.05 12099.96 1498.85 9799.99 599.86 27
HFP-MVS98.71 13198.44 17499.51 4999.49 13699.16 4998.52 12699.31 21297.47 26098.58 26798.50 31997.97 12799.85 15596.57 28199.59 24699.53 149
VPA-MVSNet99.30 3499.30 4499.28 9599.49 13698.36 12399.00 7299.45 14899.63 2999.52 8699.44 8498.25 9899.88 11499.09 7999.84 11099.62 89
XVG-OURS-SEG-HR98.49 18298.28 20099.14 12199.49 13698.83 8696.54 35799.48 13197.32 27899.11 16698.61 30399.33 1599.30 42996.23 30798.38 39699.28 262
114514_t96.50 34695.77 35598.69 20799.48 14497.43 21197.84 23199.55 10481.42 46996.51 40998.58 30795.53 28399.67 31793.41 39899.58 25198.98 324
IterMVS-LS98.55 17098.70 12798.09 29299.48 14494.73 34297.22 31999.39 17798.97 12399.38 11699.31 11596.00 26399.93 5398.58 11699.97 2199.60 99
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
fmvsm_s_conf0.5_n_1099.15 5799.27 4798.78 18799.47 14696.56 27097.75 24799.71 4799.60 3599.74 4699.44 8497.96 12899.95 2699.86 499.94 4999.82 35
fmvsm_s_conf0.5_n_599.07 7799.10 7298.99 15099.47 14697.22 22697.40 29699.83 2597.61 24499.85 2799.30 11698.80 4099.95 2699.71 3199.90 8499.78 46
v899.01 8199.16 6198.57 23099.47 14696.31 28198.90 8399.47 14099.03 11799.52 8699.57 4996.93 21299.81 22099.60 3699.98 1299.60 99
SSC-MVS3.298.53 17598.79 11297.74 32199.46 14993.62 38896.45 36399.34 19999.33 6598.93 21098.70 28397.90 13299.90 8099.12 7699.92 6899.69 69
fmvsm_s_conf0.5_n_399.22 4799.37 3298.78 18799.46 14996.58 26897.65 26199.72 4599.47 4799.86 2499.50 6798.94 3099.89 9699.75 2599.97 2199.86 27
XVS98.72 13098.45 17299.53 3999.46 14999.21 3498.65 11199.34 19998.62 15397.54 35498.63 29997.50 17499.83 19196.79 25799.53 26899.56 127
X-MVStestdata94.32 39592.59 41499.53 3999.46 14999.21 3498.65 11199.34 19998.62 15397.54 35445.85 47497.50 17499.83 19196.79 25799.53 26899.56 127
test20.0398.78 12298.77 11598.78 18799.46 14997.20 22997.78 23899.24 24699.04 11699.41 11098.90 23297.65 15499.76 26497.70 18699.79 14499.39 216
guyue98.01 24397.93 24798.26 27699.45 15495.48 31398.08 18596.24 42498.89 13499.34 12599.14 16391.32 36699.82 20399.07 8099.83 11799.48 176
CSCG98.68 14598.50 16199.20 10999.45 15498.63 9898.56 12199.57 9297.87 22398.85 22698.04 36197.66 15399.84 17396.72 26699.81 12799.13 303
GeoE99.05 7898.99 8899.25 10399.44 15698.35 12498.73 10199.56 10098.42 17098.91 21398.81 25898.94 3099.91 7398.35 13299.73 17799.49 165
v14898.45 18698.60 14698.00 30299.44 15694.98 33497.44 29499.06 28298.30 17999.32 13398.97 21696.65 23499.62 34598.37 13199.85 10599.39 216
v1098.97 8899.11 7098.55 23799.44 15696.21 28398.90 8399.55 10498.73 14399.48 9499.60 4596.63 23599.83 19199.70 3299.99 599.61 97
V4298.78 12298.78 11498.76 19499.44 15697.04 24198.27 16099.19 25697.87 22399.25 14999.16 15696.84 21699.78 25299.21 7099.84 11099.46 186
MDA-MVSNet-bldmvs97.94 24997.91 25098.06 29799.44 15694.96 33596.63 35399.15 27298.35 17398.83 22999.11 16994.31 31899.85 15596.60 27898.72 37899.37 227
viewdifsd2359ckpt0798.71 13198.86 10598.26 27699.43 16195.65 30397.20 32099.66 6399.20 8299.29 13799.01 20398.29 9199.73 28497.92 16599.75 17399.39 216
casdiffmvs_mvgpermissive99.12 6899.16 6198.99 15099.43 16197.73 19298.00 20399.62 7399.22 7899.55 7699.22 14198.93 3299.75 27298.66 11299.81 12799.50 158
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SSM_040498.90 9899.01 8498.57 23099.42 16396.59 26598.13 17599.66 6399.09 10799.30 13699.02 19298.79 4299.89 9697.87 17199.80 13899.23 275
test111196.49 34796.82 32195.52 42199.42 16387.08 45699.22 4587.14 47299.11 9799.46 9999.58 4788.69 38799.86 14298.80 9999.95 3899.62 89
v2v48298.56 16698.62 14198.37 26699.42 16395.81 30097.58 27499.16 26797.90 22199.28 13999.01 20395.98 26899.79 24199.33 5999.90 8499.51 155
OPM-MVS98.56 16698.32 19599.25 10399.41 16698.73 9497.13 32799.18 26097.10 30098.75 24498.92 22798.18 10799.65 33696.68 27099.56 25899.37 227
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS298.07 23798.08 22998.04 30099.41 16694.59 34894.59 44499.40 17597.50 25798.82 23298.83 25296.83 21899.84 17397.50 20199.81 12799.71 62
E398.69 13998.68 13098.73 20299.40 16897.10 23997.48 28799.57 9298.09 20799.00 18899.20 14497.90 13299.67 31797.73 18599.77 15599.43 199
test_one_060199.39 16999.20 4099.31 21298.49 16698.66 25499.02 19297.64 157
mvsany_test398.87 10298.92 9498.74 20099.38 17096.94 24998.58 11999.10 27796.49 33299.96 499.81 898.18 10799.45 40798.97 8999.79 14499.83 32
patch_mono-298.51 18098.63 13998.17 28899.38 17094.78 33997.36 30499.69 5498.16 19998.49 28099.29 11997.06 20299.97 798.29 13699.91 7799.76 55
test250692.39 42691.89 42893.89 44299.38 17082.28 47399.32 2666.03 48099.08 11198.77 24199.57 4966.26 46799.84 17398.71 10999.95 3899.54 140
ECVR-MVScopyleft96.42 34996.61 33595.85 41399.38 17088.18 45199.22 4586.00 47499.08 11199.36 12199.57 4988.47 39299.82 20398.52 12499.95 3899.54 140
casdiffmvspermissive98.95 9199.00 8698.81 17999.38 17097.33 21697.82 23299.57 9299.17 9199.35 12399.17 15498.35 8699.69 30498.46 12699.73 17799.41 206
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline98.96 9099.02 8298.76 19499.38 17097.26 22398.49 13699.50 12298.86 13799.19 15999.06 18098.23 10099.69 30498.71 10999.76 16999.33 247
TranMVSNet+NR-MVSNet99.17 5299.07 7799.46 6399.37 17698.87 8498.39 14999.42 16899.42 5599.36 12199.06 18098.38 8199.95 2698.34 13399.90 8499.57 121
fmvsm_s_conf0.5_n_699.08 7599.21 5698.69 20799.36 17796.51 27197.62 26699.68 5998.43 16999.85 2799.10 17299.12 2399.88 11499.77 2299.92 6899.67 75
tttt051795.64 37494.98 38497.64 33499.36 17793.81 38098.72 10290.47 46698.08 20898.67 25298.34 33773.88 45399.92 6497.77 17899.51 27399.20 285
test_part299.36 17799.10 6699.05 181
v114498.60 16098.66 13498.41 25999.36 17795.90 29497.58 27499.34 19997.51 25699.27 14199.15 16096.34 24999.80 22899.47 5399.93 5599.51 155
CP-MVS98.70 13698.42 17799.52 4599.36 17799.12 6398.72 10299.36 18797.54 25498.30 29398.40 32997.86 13899.89 9696.53 29099.72 18599.56 127
diffmvs_AUTHOR98.50 18198.59 14898.23 28399.35 18295.48 31396.61 35499.60 7798.37 17198.90 21499.00 20797.37 18499.76 26498.22 14099.85 10599.46 186
Test_1112_low_res96.99 32896.55 33998.31 27299.35 18295.47 31695.84 40499.53 11391.51 43996.80 39698.48 32291.36 36599.83 19196.58 27999.53 26899.62 89
DeepC-MVS97.60 498.97 8898.93 9399.10 12799.35 18297.98 16198.01 20299.46 14497.56 25099.54 7899.50 6798.97 2899.84 17398.06 15299.92 6899.49 165
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss97.29 30596.86 31798.58 22799.34 18596.32 28096.75 34699.58 8593.14 42096.89 39197.48 39492.11 35799.86 14296.91 24499.54 26499.57 121
reproduce_model99.15 5798.97 9099.67 499.33 18699.44 1098.15 17399.47 14099.12 9699.52 8699.32 11498.31 8999.90 8097.78 17799.73 17799.66 77
MVSMamba_PlusPlus98.83 11198.98 8998.36 26799.32 18796.58 26898.90 8399.41 17299.75 1198.72 24799.50 6796.17 25499.94 4299.27 6499.78 14998.57 384
fmvsm_s_conf0.5_n_499.01 8199.22 5498.38 26399.31 18895.48 31397.56 27699.73 4498.87 13599.75 4499.27 12298.80 4099.86 14299.80 1799.90 8499.81 39
SF-MVS98.53 17598.27 20399.32 9099.31 18898.75 9098.19 16799.41 17296.77 32198.83 22998.90 23297.80 14499.82 20395.68 33699.52 27199.38 225
CPTT-MVS97.84 26497.36 28899.27 9899.31 18898.46 11498.29 15699.27 23594.90 38897.83 33498.37 33394.90 29999.84 17393.85 38799.54 26499.51 155
UnsupCasMVSNet_eth97.89 25397.60 27498.75 19699.31 18897.17 23497.62 26699.35 19398.72 14598.76 24398.68 28792.57 35199.74 27797.76 18295.60 45899.34 241
fmvsm_s_conf0.5_n_798.83 11199.04 7998.20 28599.30 19294.83 33797.23 31599.36 18798.64 14899.84 3099.43 8798.10 11699.91 7399.56 4099.96 2899.87 21
pmmvs-eth3d98.47 18498.34 19098.86 17299.30 19297.76 18897.16 32599.28 23295.54 37099.42 10899.19 14697.27 19199.63 34297.89 16699.97 2199.20 285
mamv499.44 1999.39 2899.58 2199.30 19299.74 299.04 6899.81 3199.77 1099.82 3399.57 4997.82 14299.98 499.53 4799.89 9099.01 318
viewcassd2359sk1198.55 17098.51 15898.67 21099.29 19596.99 24497.39 29799.54 10997.73 23398.81 23499.08 17897.55 16699.66 32997.52 20099.67 21599.36 234
SymmetryMVS98.05 23997.71 26499.09 13199.29 19597.83 17798.28 15797.64 39299.24 7598.80 23698.85 24589.76 37999.94 4298.04 15499.50 28199.49 165
Anonymous2023121199.27 3899.27 4799.26 10099.29 19598.18 13699.49 1299.51 11999.70 1699.80 3799.68 2596.84 21699.83 19199.21 7099.91 7799.77 49
viewmanbaseed2359cas98.58 16498.54 15498.70 20599.28 19897.13 23897.47 29099.55 10497.55 25298.96 20198.92 22797.77 14699.59 35997.59 19499.77 15599.39 216
UnsupCasMVSNet_bld97.30 30396.92 31398.45 25499.28 19896.78 25996.20 38099.27 23595.42 37498.28 29798.30 34193.16 33799.71 29394.99 35097.37 43498.87 345
EC-MVSNet99.09 7199.05 7899.20 10999.28 19898.93 8099.24 4499.84 2299.08 11198.12 31098.37 33398.72 4999.90 8099.05 8399.77 15598.77 362
mamba_040898.80 11898.88 9998.55 23799.27 20196.50 27298.00 20399.60 7798.93 12899.22 15498.84 25098.59 6299.89 9697.74 18399.72 18599.27 263
SSM_0407298.80 11898.88 9998.56 23599.27 20196.50 27298.00 20399.60 7798.93 12899.22 15498.84 25098.59 6299.90 8097.74 18399.72 18599.27 263
SSM_040798.86 10598.96 9298.55 23799.27 20196.50 27298.04 19499.66 6399.09 10799.22 15499.02 19298.79 4299.87 13397.87 17199.72 18599.27 263
reproduce-ours99.09 7198.90 9699.67 499.27 20199.49 698.00 20399.42 16899.05 11499.48 9499.27 12298.29 9199.89 9697.61 19199.71 19499.62 89
our_new_method99.09 7198.90 9699.67 499.27 20199.49 698.00 20399.42 16899.05 11499.48 9499.27 12298.29 9199.89 9697.61 19199.71 19499.62 89
DPE-MVScopyleft98.59 16298.26 20499.57 2299.27 20199.15 5397.01 33099.39 17797.67 23799.44 10398.99 20997.53 17099.89 9695.40 34499.68 20999.66 77
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT97.85 26398.18 21696.87 38299.27 20191.16 43195.53 41499.25 24199.10 10499.41 11099.35 10393.10 33999.96 1498.65 11399.94 4999.49 165
v119298.60 16098.66 13498.41 25999.27 20195.88 29597.52 28199.36 18797.41 26999.33 12799.20 14496.37 24799.82 20399.57 3899.92 6899.55 134
N_pmnet97.63 27797.17 29898.99 15099.27 20197.86 17495.98 39193.41 45595.25 37999.47 9898.90 23295.63 28099.85 15596.91 24499.73 17799.27 263
viewdifsd2359ckpt1398.39 19798.29 19998.70 20599.26 21097.19 23097.51 28399.48 13196.94 30998.58 26798.82 25597.47 17999.55 37597.21 21999.33 30899.34 241
FPMVS93.44 41292.23 41997.08 37099.25 21197.86 17495.61 41197.16 40492.90 42493.76 45798.65 29475.94 45195.66 47179.30 46997.49 42797.73 435
ME-MVS98.61 15898.33 19499.44 6599.24 21298.93 8097.45 29299.06 28298.14 20599.06 17398.77 26596.97 21099.82 20396.67 27199.64 22699.58 114
new-patchmatchnet98.35 20098.74 11697.18 36599.24 21292.23 41396.42 36799.48 13198.30 17999.69 5599.53 6397.44 18099.82 20398.84 9899.77 15599.49 165
MCST-MVS98.00 24497.63 27299.10 12799.24 21298.17 13796.89 33998.73 34595.66 36597.92 32597.70 38297.17 19799.66 32996.18 31299.23 32799.47 184
UniMVSNet (Re)98.87 10298.71 12499.35 7999.24 21298.73 9497.73 25099.38 17998.93 12899.12 16598.73 27396.77 22499.86 14298.63 11599.80 13899.46 186
jason97.45 29197.35 28997.76 31899.24 21293.93 37495.86 40198.42 36394.24 40398.50 27998.13 35194.82 30399.91 7397.22 21899.73 17799.43 199
jason: jason.
IterMVS97.73 26998.11 22596.57 39299.24 21290.28 44095.52 41699.21 25098.86 13799.33 12799.33 11093.11 33899.94 4298.49 12599.94 4999.48 176
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v124098.55 17098.62 14198.32 27099.22 21895.58 30697.51 28399.45 14897.16 29799.45 10299.24 13596.12 25899.85 15599.60 3699.88 9299.55 134
ITE_SJBPF98.87 17099.22 21898.48 11399.35 19397.50 25798.28 29798.60 30597.64 15799.35 42293.86 38699.27 31998.79 360
h-mvs3397.77 26797.33 29199.10 12799.21 22097.84 17698.35 15398.57 35599.11 9798.58 26799.02 19288.65 39099.96 1498.11 14796.34 45099.49 165
v14419298.54 17398.57 15098.45 25499.21 22095.98 29297.63 26599.36 18797.15 29999.32 13399.18 15095.84 27599.84 17399.50 5099.91 7799.54 140
APDe-MVScopyleft98.99 8498.79 11299.60 1699.21 22099.15 5398.87 8899.48 13197.57 24899.35 12399.24 13597.83 13999.89 9697.88 16999.70 20199.75 59
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS98.93 9498.81 11199.28 9599.21 22098.45 11598.46 14199.33 20599.63 2999.48 9499.15 16097.23 19499.75 27297.17 22199.66 22399.63 88
SR-MVS-dyc-post98.81 11698.55 15299.57 2299.20 22499.38 1398.48 13999.30 22098.64 14898.95 20298.96 21997.49 17799.86 14296.56 28599.39 29999.45 191
RE-MVS-def98.58 14999.20 22499.38 1398.48 13999.30 22098.64 14898.95 20298.96 21997.75 14896.56 28599.39 29999.45 191
v192192098.54 17398.60 14698.38 26399.20 22495.76 30297.56 27699.36 18797.23 29199.38 11699.17 15496.02 26199.84 17399.57 3899.90 8499.54 140
thisisatest053095.27 38194.45 39297.74 32199.19 22794.37 35297.86 22890.20 46797.17 29698.22 30097.65 38473.53 45499.90 8096.90 24999.35 30598.95 330
Anonymous2024052998.93 9498.87 10199.12 12399.19 22798.22 13499.01 7098.99 30099.25 7499.54 7899.37 9897.04 20399.80 22897.89 16699.52 27199.35 239
APD-MVS_3200maxsize98.84 10898.61 14599.53 3999.19 22799.27 2898.49 13699.33 20598.64 14899.03 18698.98 21497.89 13599.85 15596.54 28999.42 29699.46 186
HQP_MVS97.99 24797.67 26698.93 16299.19 22797.65 19697.77 24199.27 23598.20 19397.79 33797.98 36594.90 29999.70 30094.42 36899.51 27399.45 191
plane_prior799.19 22797.87 173
ab-mvs98.41 18998.36 18798.59 22699.19 22797.23 22499.32 2698.81 33197.66 23898.62 25999.40 9596.82 21999.80 22895.88 32399.51 27398.75 365
F-COLMAP97.30 30396.68 33099.14 12199.19 22798.39 11797.27 31499.30 22092.93 42396.62 40298.00 36395.73 27899.68 31392.62 41498.46 39599.35 239
viewdifsd2359ckpt0998.13 23297.92 24898.77 19299.18 23497.35 21497.29 31099.53 11395.81 36298.09 31398.47 32396.34 24999.66 32997.02 23499.51 27399.29 259
SR-MVS98.71 13198.43 17599.57 2299.18 23499.35 1798.36 15299.29 22898.29 18298.88 22198.85 24597.53 17099.87 13396.14 31499.31 31299.48 176
UniMVSNet_NR-MVSNet98.86 10598.68 13099.40 7199.17 23698.74 9197.68 25599.40 17599.14 9599.06 17398.59 30696.71 23099.93 5398.57 11899.77 15599.53 149
LF4IMVS97.90 25197.69 26598.52 24599.17 23697.66 19597.19 32499.47 14096.31 34297.85 33398.20 34896.71 23099.52 38794.62 36099.72 18598.38 401
SMA-MVScopyleft98.40 19198.03 23499.51 4999.16 23899.21 3498.05 19299.22 24994.16 40598.98 19299.10 17297.52 17299.79 24196.45 29599.64 22699.53 149
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
DU-MVS98.82 11498.63 13999.39 7299.16 23898.74 9197.54 27999.25 24198.84 14099.06 17398.76 27096.76 22699.93 5398.57 11899.77 15599.50 158
NR-MVSNet98.95 9198.82 10999.36 7399.16 23898.72 9699.22 4599.20 25299.10 10499.72 4798.76 27096.38 24699.86 14298.00 15999.82 12199.50 158
MVS_111021_LR98.30 20998.12 22498.83 17599.16 23898.03 15696.09 38899.30 22097.58 24798.10 31298.24 34498.25 9899.34 42396.69 26999.65 22499.12 304
DSMNet-mixed97.42 29497.60 27496.87 38299.15 24291.46 42098.54 12499.12 27492.87 42597.58 35099.63 3996.21 25399.90 8095.74 33299.54 26499.27 263
D2MVS97.84 26497.84 25597.83 31099.14 24394.74 34196.94 33498.88 31595.84 36198.89 21798.96 21994.40 31599.69 30497.55 19599.95 3899.05 310
pmmvs597.64 27697.49 28098.08 29599.14 24395.12 33096.70 34999.05 28693.77 41298.62 25998.83 25293.23 33599.75 27298.33 13599.76 16999.36 234
SPE-MVS-test99.13 6599.09 7499.26 10099.13 24598.97 7499.31 3099.88 1499.44 5298.16 30598.51 31598.64 5699.93 5398.91 9299.85 10598.88 344
VDD-MVS98.56 16698.39 18299.07 13499.13 24598.07 15198.59 11897.01 40799.59 3699.11 16699.27 12294.82 30399.79 24198.34 13399.63 23299.34 241
save fliter99.11 24797.97 16296.53 35999.02 29498.24 185
APD-MVScopyleft98.10 23397.67 26699.42 6799.11 24798.93 8097.76 24499.28 23294.97 38698.72 24798.77 26597.04 20399.85 15593.79 38899.54 26499.49 165
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set98.69 13998.71 12498.62 22099.10 24996.37 27897.23 31598.87 31799.20 8299.19 15998.99 20997.30 18899.85 15598.77 10499.79 14499.65 82
EI-MVSNet98.40 19198.51 15898.04 30099.10 24994.73 34297.20 32098.87 31798.97 12399.06 17399.02 19296.00 26399.80 22898.58 11699.82 12199.60 99
CVMVSNet96.25 35597.21 29793.38 44999.10 24980.56 47797.20 32098.19 37496.94 30999.00 18899.02 19289.50 38399.80 22896.36 30199.59 24699.78 46
EI-MVSNet-Vis-set98.68 14598.70 12798.63 21899.09 25296.40 27797.23 31598.86 32299.20 8299.18 16398.97 21697.29 19099.85 15598.72 10899.78 14999.64 83
HPM-MVS++copyleft98.10 23397.64 27199.48 5799.09 25299.13 6197.52 28198.75 34297.46 26596.90 39097.83 37596.01 26299.84 17395.82 33099.35 30599.46 186
DP-MVS Recon97.33 30196.92 31398.57 23099.09 25297.99 15896.79 34299.35 19393.18 41997.71 34198.07 35995.00 29899.31 42793.97 38199.13 34398.42 398
MVS_111021_HR98.25 21898.08 22998.75 19699.09 25297.46 20895.97 39299.27 23597.60 24697.99 32398.25 34398.15 11399.38 41896.87 25299.57 25599.42 203
BP-MVS197.40 29696.97 30998.71 20499.07 25696.81 25598.34 15597.18 40298.58 15998.17 30298.61 30384.01 42299.94 4298.97 8999.78 14999.37 227
9.1497.78 25799.07 25697.53 28099.32 20795.53 37198.54 27598.70 28397.58 16399.76 26494.32 37399.46 286
PAPM_NR96.82 33596.32 34698.30 27399.07 25696.69 26397.48 28798.76 33995.81 36296.61 40396.47 42094.12 32499.17 44090.82 44197.78 42199.06 309
TAMVS98.24 21998.05 23298.80 18199.07 25697.18 23297.88 22498.81 33196.66 32699.17 16499.21 14294.81 30599.77 25896.96 24299.88 9299.44 195
CLD-MVS97.49 28797.16 29998.48 25199.07 25697.03 24294.71 43799.21 25094.46 39798.06 31697.16 40697.57 16499.48 39994.46 36599.78 14998.95 330
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CS-MVS99.13 6599.10 7299.24 10599.06 26199.15 5399.36 2299.88 1499.36 6398.21 30198.46 32498.68 5399.93 5399.03 8599.85 10598.64 377
thres100view90094.19 39893.67 40395.75 41699.06 26191.35 42498.03 19694.24 45098.33 17597.40 36694.98 45079.84 43899.62 34583.05 46298.08 41296.29 457
thres600view794.45 39393.83 40096.29 40099.06 26191.53 41997.99 21094.24 45098.34 17497.44 36495.01 44879.84 43899.67 31784.33 46098.23 40197.66 438
plane_prior199.05 264
YYNet197.60 27897.67 26697.39 35899.04 26593.04 39795.27 42398.38 36697.25 28598.92 21298.95 22395.48 28799.73 28496.99 23898.74 37699.41 206
MDA-MVSNet_test_wron97.60 27897.66 26997.41 35799.04 26593.09 39395.27 42398.42 36397.26 28498.88 22198.95 22395.43 28899.73 28497.02 23498.72 37899.41 206
MIMVSNet96.62 34296.25 35097.71 32599.04 26594.66 34599.16 5496.92 41397.23 29197.87 33099.10 17286.11 40599.65 33691.65 42599.21 33198.82 349
icg_test_0407_298.20 22498.38 18497.65 33199.03 26894.03 36595.78 40699.45 14898.16 19999.06 17398.71 27698.27 9499.68 31397.50 20199.45 28899.22 280
IMVS_040798.39 19798.64 13797.66 32999.03 26894.03 36598.10 18299.45 14898.16 19999.06 17398.71 27698.27 9499.71 29397.50 20199.45 28899.22 280
IMVS_040498.07 23798.20 21197.69 32699.03 26894.03 36596.67 35099.45 14898.16 19998.03 32098.71 27696.80 22299.82 20397.50 20199.45 28899.22 280
IMVS_040398.34 20198.56 15197.66 32999.03 26894.03 36597.98 21199.45 14898.16 19998.89 21798.71 27697.90 13299.74 27797.50 20199.45 28899.22 280
PatchMatch-RL97.24 30996.78 32498.61 22399.03 26897.83 17796.36 37099.06 28293.49 41797.36 37097.78 37695.75 27799.49 39693.44 39798.77 37598.52 386
viewmambaseed2359dif98.19 22598.26 20497.99 30399.02 27395.03 33396.59 35699.53 11396.21 34599.00 18898.99 20997.62 15999.61 35297.62 19099.72 18599.33 247
GDP-MVS97.50 28497.11 30398.67 21099.02 27396.85 25398.16 17299.71 4798.32 17798.52 27898.54 31083.39 42699.95 2698.79 10099.56 25899.19 290
ZD-MVS99.01 27598.84 8599.07 28194.10 40798.05 31898.12 35396.36 24899.86 14292.70 41399.19 335
CDPH-MVS97.26 30696.66 33399.07 13499.00 27698.15 13896.03 39099.01 29791.21 44397.79 33797.85 37496.89 21499.69 30492.75 41199.38 30299.39 216
diffmvspermissive98.22 22098.24 20898.17 28899.00 27695.44 31796.38 36999.58 8597.79 23098.53 27698.50 31996.76 22699.74 27797.95 16499.64 22699.34 241
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WR-MVS98.40 19198.19 21599.03 14499.00 27697.65 19696.85 34098.94 30298.57 16098.89 21798.50 31995.60 28199.85 15597.54 19799.85 10599.59 106
plane_prior698.99 27997.70 19494.90 299
xiu_mvs_v1_base_debu97.86 25898.17 21796.92 37998.98 28093.91 37596.45 36399.17 26497.85 22598.41 28797.14 40898.47 7299.92 6498.02 15699.05 34996.92 450
xiu_mvs_v1_base97.86 25898.17 21796.92 37998.98 28093.91 37596.45 36399.17 26497.85 22598.41 28797.14 40898.47 7299.92 6498.02 15699.05 34996.92 450
xiu_mvs_v1_base_debi97.86 25898.17 21796.92 37998.98 28093.91 37596.45 36399.17 26497.85 22598.41 28797.14 40898.47 7299.92 6498.02 15699.05 34996.92 450
MVP-Stereo98.08 23697.92 24898.57 23098.96 28396.79 25697.90 22299.18 26096.41 33898.46 28298.95 22395.93 27299.60 35596.51 29198.98 36399.31 254
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS98.40 19198.68 13097.54 34698.96 28397.99 15897.88 22499.36 18798.20 19399.63 6699.04 18998.76 4595.33 47396.56 28599.74 17499.31 254
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
新几何198.91 16698.94 28597.76 18898.76 33987.58 46096.75 39898.10 35594.80 30699.78 25292.73 41299.00 35899.20 285
USDC97.41 29597.40 28497.44 35598.94 28593.67 38595.17 42699.53 11394.03 40998.97 19699.10 17295.29 29099.34 42395.84 32999.73 17799.30 257
tfpn200view994.03 40293.44 40595.78 41598.93 28791.44 42297.60 27194.29 44897.94 21797.10 37694.31 45779.67 44099.62 34583.05 46298.08 41296.29 457
testdata98.09 29298.93 28795.40 31998.80 33390.08 45197.45 36398.37 33395.26 29199.70 30093.58 39398.95 36699.17 297
thres40094.14 40093.44 40596.24 40398.93 28791.44 42297.60 27194.29 44897.94 21797.10 37694.31 45779.67 44099.62 34583.05 46298.08 41297.66 438
TAPA-MVS96.21 1196.63 34195.95 35298.65 21298.93 28798.09 14596.93 33699.28 23283.58 46698.13 30997.78 37696.13 25699.40 41493.52 39499.29 31798.45 391
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test22298.92 29196.93 25095.54 41398.78 33685.72 46396.86 39398.11 35494.43 31399.10 34899.23 275
PVSNet_BlendedMVS97.55 28397.53 27797.60 33898.92 29193.77 38296.64 35299.43 16294.49 39597.62 34699.18 15096.82 21999.67 31794.73 35799.93 5599.36 234
PVSNet_Blended96.88 33196.68 33097.47 35398.92 29193.77 38294.71 43799.43 16290.98 44597.62 34697.36 40296.82 21999.67 31794.73 35799.56 25898.98 324
MSDG97.71 27197.52 27898.28 27598.91 29496.82 25494.42 44799.37 18397.65 23998.37 29298.29 34297.40 18299.33 42594.09 37999.22 32898.68 375
Anonymous20240521197.90 25197.50 27999.08 13298.90 29598.25 12898.53 12596.16 42598.87 13599.11 16698.86 24290.40 37599.78 25297.36 21099.31 31299.19 290
原ACMM198.35 26898.90 29596.25 28298.83 33092.48 42996.07 42098.10 35595.39 28999.71 29392.61 41598.99 36099.08 306
GBi-Net98.65 15098.47 16999.17 11498.90 29598.24 12999.20 4899.44 15698.59 15698.95 20299.55 5794.14 32199.86 14297.77 17899.69 20499.41 206
test198.65 15098.47 16999.17 11498.90 29598.24 12999.20 4899.44 15698.59 15698.95 20299.55 5794.14 32199.86 14297.77 17899.69 20499.41 206
FMVSNet298.49 18298.40 17998.75 19698.90 29597.14 23798.61 11699.13 27398.59 15699.19 15999.28 12094.14 32199.82 20397.97 16299.80 13899.29 259
OMC-MVS97.88 25597.49 28099.04 14398.89 30098.63 9896.94 33499.25 24195.02 38498.53 27698.51 31597.27 19199.47 40293.50 39699.51 27399.01 318
VortexMVS97.98 24898.31 19697.02 37398.88 30191.45 42198.03 19699.47 14098.65 14799.55 7699.47 7791.49 36499.81 22099.32 6099.91 7799.80 41
MVSFormer98.26 21598.43 17597.77 31598.88 30193.89 37899.39 2099.56 10099.11 9798.16 30598.13 35193.81 32999.97 799.26 6599.57 25599.43 199
lupinMVS97.06 32196.86 31797.65 33198.88 30193.89 37895.48 41797.97 38093.53 41598.16 30597.58 38893.81 32999.91 7396.77 26099.57 25599.17 297
dmvs_re95.98 36395.39 37397.74 32198.86 30497.45 20998.37 15195.69 43797.95 21596.56 40495.95 42990.70 37297.68 46788.32 45096.13 45498.11 413
DELS-MVS98.27 21398.20 21198.48 25198.86 30496.70 26295.60 41299.20 25297.73 23398.45 28398.71 27697.50 17499.82 20398.21 14199.59 24698.93 335
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
TinyColmap97.89 25397.98 23997.60 33898.86 30494.35 35396.21 37999.44 15697.45 26799.06 17398.88 23997.99 12699.28 43394.38 37299.58 25199.18 293
LCM-MVSNet-Re98.64 15298.48 16799.11 12598.85 30798.51 11198.49 13699.83 2598.37 17199.69 5599.46 7998.21 10599.92 6494.13 37899.30 31598.91 339
pmmvs497.58 28197.28 29298.51 24698.84 30896.93 25095.40 42198.52 35893.60 41498.61 26198.65 29495.10 29599.60 35596.97 24199.79 14498.99 323
NP-MVS98.84 30897.39 21396.84 411
sss97.21 31196.93 31198.06 29798.83 31095.22 32696.75 34698.48 36094.49 39597.27 37297.90 37192.77 34799.80 22896.57 28199.32 31099.16 300
PVSNet93.40 1795.67 37295.70 35895.57 42098.83 31088.57 44792.50 46497.72 38592.69 42796.49 41296.44 42193.72 33299.43 41093.61 39199.28 31898.71 368
MVEpermissive83.40 2292.50 42591.92 42794.25 43698.83 31091.64 41892.71 46383.52 47695.92 35986.46 47495.46 44295.20 29295.40 47280.51 46798.64 38795.73 465
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-293.78 40693.91 39893.39 44898.82 31381.72 47597.76 24495.28 43998.60 15596.54 40596.66 41565.85 47099.62 34596.65 27498.99 36098.82 349
ambc98.24 28098.82 31395.97 29398.62 11599.00 29999.27 14199.21 14296.99 20899.50 39396.55 28899.50 28199.26 269
旧先验198.82 31397.45 20998.76 33998.34 33795.50 28699.01 35799.23 275
test_vis1_rt97.75 26897.72 26397.83 31098.81 31696.35 27997.30 30999.69 5494.61 39397.87 33098.05 36096.26 25298.32 46198.74 10698.18 40498.82 349
WTY-MVS96.67 33996.27 34997.87 30898.81 31694.61 34796.77 34497.92 38294.94 38797.12 37597.74 37991.11 36899.82 20393.89 38498.15 40899.18 293
3Dnovator+97.89 398.69 13998.51 15899.24 10598.81 31698.40 11699.02 6999.19 25698.99 12098.07 31599.28 12097.11 20199.84 17396.84 25599.32 31099.47 184
QAPM97.31 30296.81 32398.82 17798.80 31997.49 20499.06 6599.19 25690.22 44997.69 34399.16 15696.91 21399.90 8090.89 44099.41 29799.07 308
VNet98.42 18898.30 19798.79 18498.79 32097.29 22098.23 16398.66 34999.31 6898.85 22698.80 25994.80 30699.78 25298.13 14699.13 34399.31 254
DPM-MVS96.32 35195.59 36498.51 24698.76 32197.21 22894.54 44698.26 36991.94 43496.37 41397.25 40493.06 34199.43 41091.42 43098.74 37698.89 341
3Dnovator98.27 298.81 11698.73 11899.05 14198.76 32197.81 18599.25 4399.30 22098.57 16098.55 27399.33 11097.95 12999.90 8097.16 22299.67 21599.44 195
PLCcopyleft94.65 1696.51 34495.73 35798.85 17398.75 32397.91 17096.42 36799.06 28290.94 44695.59 42697.38 40094.41 31499.59 35990.93 43898.04 41799.05 310
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned96.83 33396.75 32697.08 37098.74 32493.33 39196.71 34898.26 36996.72 32398.44 28497.37 40195.20 29299.47 40291.89 42097.43 43198.44 394
hse-mvs297.46 28997.07 30498.64 21498.73 32597.33 21697.45 29297.64 39299.11 9798.58 26797.98 36588.65 39099.79 24198.11 14797.39 43398.81 354
CDS-MVSNet97.69 27297.35 28998.69 20798.73 32597.02 24396.92 33898.75 34295.89 36098.59 26598.67 28992.08 35899.74 27796.72 26699.81 12799.32 250
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SD_040396.28 35395.83 35497.64 33498.72 32794.30 35498.87 8898.77 33797.80 22896.53 40698.02 36297.34 18699.47 40276.93 47199.48 28499.16 300
EIA-MVS98.00 24497.74 26098.80 18198.72 32798.09 14598.05 19299.60 7797.39 27196.63 40195.55 43797.68 15199.80 22896.73 26599.27 31998.52 386
LFMVS97.20 31296.72 32798.64 21498.72 32796.95 24898.93 8194.14 45299.74 1398.78 23899.01 20384.45 41799.73 28497.44 20699.27 31999.25 270
new_pmnet96.99 32896.76 32597.67 32798.72 32794.89 33695.95 39698.20 37292.62 42898.55 27398.54 31094.88 30299.52 38793.96 38299.44 29598.59 383
Fast-Effi-MVS+97.67 27497.38 28698.57 23098.71 33197.43 21197.23 31599.45 14894.82 39096.13 41796.51 41798.52 7099.91 7396.19 31098.83 37298.37 403
TEST998.71 33198.08 14995.96 39499.03 29191.40 44095.85 42397.53 39096.52 23999.76 264
train_agg97.10 31896.45 34399.07 13498.71 33198.08 14995.96 39499.03 29191.64 43595.85 42397.53 39096.47 24199.76 26493.67 39099.16 33899.36 234
TSAR-MVS + GP.98.18 22797.98 23998.77 19298.71 33197.88 17296.32 37398.66 34996.33 34099.23 15398.51 31597.48 17899.40 41497.16 22299.46 28699.02 317
FA-MVS(test-final)96.99 32896.82 32197.50 35098.70 33594.78 33999.34 2396.99 40895.07 38398.48 28199.33 11088.41 39399.65 33696.13 31698.92 36998.07 416
AUN-MVS96.24 35795.45 36998.60 22598.70 33597.22 22697.38 29997.65 39095.95 35895.53 43397.96 36982.11 43499.79 24196.31 30397.44 43098.80 359
our_test_397.39 29797.73 26296.34 39898.70 33589.78 44394.61 44398.97 30196.50 33199.04 18398.85 24595.98 26899.84 17397.26 21699.67 21599.41 206
ppachtmachnet_test97.50 28497.74 26096.78 38898.70 33591.23 43094.55 44599.05 28696.36 33999.21 15798.79 26196.39 24499.78 25296.74 26399.82 12199.34 241
PCF-MVS92.86 1894.36 39493.00 41298.42 25898.70 33597.56 20193.16 46299.11 27679.59 47097.55 35397.43 39792.19 35599.73 28479.85 46899.45 28897.97 422
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth97.91 25098.02 23597.58 34098.69 34094.10 36198.13 17598.90 31197.95 21597.32 37199.58 4795.95 27198.75 45696.41 29799.22 32899.87 21
ETV-MVS98.03 24097.86 25498.56 23598.69 34098.07 15197.51 28399.50 12298.10 20697.50 35895.51 43898.41 7899.88 11496.27 30699.24 32497.71 437
test_prior98.95 15998.69 34097.95 16699.03 29199.59 35999.30 257
mvsmamba97.57 28297.26 29398.51 24698.69 34096.73 26198.74 9797.25 40197.03 30597.88 32999.23 14090.95 36999.87 13396.61 27799.00 35898.91 339
agg_prior98.68 34497.99 15899.01 29795.59 42699.77 258
test_898.67 34598.01 15795.91 40099.02 29491.64 43595.79 42597.50 39396.47 24199.76 264
HQP-NCC98.67 34596.29 37596.05 35195.55 429
ACMP_Plane98.67 34596.29 37596.05 35195.55 429
CNVR-MVS98.17 22997.87 25399.07 13498.67 34598.24 12997.01 33098.93 30597.25 28597.62 34698.34 33797.27 19199.57 36896.42 29699.33 30899.39 216
HQP-MVS97.00 32796.49 34298.55 23798.67 34596.79 25696.29 37599.04 28996.05 35195.55 42996.84 41193.84 32799.54 38192.82 40899.26 32299.32 250
MM98.22 22097.99 23898.91 16698.66 35096.97 24597.89 22394.44 44699.54 4098.95 20299.14 16393.50 33399.92 6499.80 1799.96 2899.85 29
test_fmvs197.72 27097.94 24597.07 37298.66 35092.39 40897.68 25599.81 3195.20 38299.54 7899.44 8491.56 36399.41 41399.78 2199.77 15599.40 215
balanced_conf0398.63 15498.72 12098.38 26398.66 35096.68 26498.90 8399.42 16898.99 12098.97 19699.19 14695.81 27699.85 15598.77 10499.77 15598.60 380
thres20093.72 40893.14 41095.46 42498.66 35091.29 42696.61 35494.63 44597.39 27196.83 39493.71 46079.88 43799.56 37182.40 46598.13 40995.54 466
wuyk23d96.06 35997.62 27391.38 45398.65 35498.57 10598.85 9296.95 41196.86 31699.90 1499.16 15699.18 1998.40 46089.23 44899.77 15577.18 473
NCCC97.86 25897.47 28399.05 14198.61 35598.07 15196.98 33298.90 31197.63 24097.04 38097.93 37095.99 26799.66 32995.31 34598.82 37499.43 199
DeepC-MVS_fast96.85 698.30 20998.15 22198.75 19698.61 35597.23 22497.76 24499.09 27997.31 27998.75 24498.66 29297.56 16599.64 33996.10 31799.55 26299.39 216
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing393.51 41092.09 42197.75 31998.60 35794.40 35197.32 30795.26 44097.56 25096.79 39795.50 43953.57 47899.77 25895.26 34698.97 36499.08 306
thisisatest051594.12 40193.16 40996.97 37798.60 35792.90 39893.77 45890.61 46594.10 40796.91 38795.87 43274.99 45299.80 22894.52 36399.12 34698.20 409
GA-MVS95.86 36695.32 37697.49 35198.60 35794.15 36093.83 45797.93 38195.49 37296.68 39997.42 39883.21 42799.30 42996.22 30898.55 39399.01 318
dmvs_testset92.94 42092.21 42095.13 42898.59 36090.99 43397.65 26192.09 46196.95 30894.00 45393.55 46192.34 35396.97 47072.20 47292.52 46897.43 445
OPU-MVS98.82 17798.59 36098.30 12598.10 18298.52 31498.18 10798.75 45694.62 36099.48 28499.41 206
MSLP-MVS++98.02 24198.14 22397.64 33498.58 36295.19 32797.48 28799.23 24897.47 26097.90 32798.62 30197.04 20398.81 45497.55 19599.41 29798.94 334
test1298.93 16298.58 36297.83 17798.66 34996.53 40695.51 28599.69 30499.13 34399.27 263
CL-MVSNet_self_test97.44 29297.22 29698.08 29598.57 36495.78 30194.30 45098.79 33496.58 32998.60 26398.19 34994.74 30999.64 33996.41 29798.84 37198.82 349
PS-MVSNAJ97.08 32097.39 28596.16 40998.56 36592.46 40695.24 42598.85 32597.25 28597.49 35995.99 42898.07 11799.90 8096.37 29998.67 38696.12 462
CNLPA97.17 31596.71 32898.55 23798.56 36598.05 15596.33 37298.93 30596.91 31397.06 37997.39 39994.38 31699.45 40791.66 42499.18 33798.14 412
xiu_mvs_v2_base97.16 31697.49 28096.17 40798.54 36792.46 40695.45 41898.84 32697.25 28597.48 36096.49 41898.31 8999.90 8096.34 30298.68 38596.15 461
alignmvs97.35 29996.88 31698.78 18798.54 36798.09 14597.71 25197.69 38799.20 8297.59 34995.90 43188.12 39599.55 37598.18 14398.96 36598.70 371
FE-MVS95.66 37394.95 38697.77 31598.53 36995.28 32399.40 1996.09 42893.11 42197.96 32499.26 12879.10 44499.77 25892.40 41798.71 38098.27 407
Effi-MVS+98.02 24197.82 25698.62 22098.53 36997.19 23097.33 30699.68 5997.30 28096.68 39997.46 39698.56 6899.80 22896.63 27598.20 40398.86 346
baseline195.96 36495.44 37097.52 34898.51 37193.99 37298.39 14996.09 42898.21 18998.40 29197.76 37886.88 39799.63 34295.42 34389.27 47198.95 330
MVS_Test98.18 22798.36 18797.67 32798.48 37294.73 34298.18 16899.02 29497.69 23698.04 31999.11 16997.22 19599.56 37198.57 11898.90 37098.71 368
MGCFI-Net98.34 20198.28 20098.51 24698.47 37397.59 20098.96 7799.48 13199.18 9097.40 36695.50 43998.66 5499.50 39398.18 14398.71 38098.44 394
BH-RMVSNet96.83 33396.58 33897.58 34098.47 37394.05 36296.67 35097.36 39696.70 32597.87 33097.98 36595.14 29499.44 40990.47 44398.58 39299.25 270
sasdasda98.34 20198.26 20498.58 22798.46 37597.82 18298.96 7799.46 14499.19 8797.46 36195.46 44298.59 6299.46 40598.08 15098.71 38098.46 388
canonicalmvs98.34 20198.26 20498.58 22798.46 37597.82 18298.96 7799.46 14499.19 8797.46 36195.46 44298.59 6299.46 40598.08 15098.71 38098.46 388
MVS-HIRNet94.32 39595.62 36190.42 45498.46 37575.36 47896.29 37589.13 46995.25 37995.38 43599.75 1692.88 34499.19 43994.07 38099.39 29996.72 455
PHI-MVS98.29 21297.95 24399.34 8298.44 37899.16 4998.12 17999.38 17996.01 35598.06 31698.43 32797.80 14499.67 31795.69 33599.58 25199.20 285
DVP-MVS++98.90 9898.70 12799.51 4998.43 37999.15 5399.43 1599.32 20798.17 19699.26 14599.02 19298.18 10799.88 11497.07 23199.45 28899.49 165
MSC_two_6792asdad99.32 9098.43 37998.37 12098.86 32299.89 9697.14 22599.60 24299.71 62
No_MVS99.32 9098.43 37998.37 12098.86 32299.89 9697.14 22599.60 24299.71 62
Fast-Effi-MVS+-dtu98.27 21398.09 22698.81 17998.43 37998.11 14297.61 27099.50 12298.64 14897.39 36897.52 39298.12 11599.95 2696.90 24998.71 38098.38 401
OpenMVS_ROBcopyleft95.38 1495.84 36895.18 38197.81 31298.41 38397.15 23697.37 30398.62 35383.86 46598.65 25598.37 33394.29 31999.68 31388.41 44998.62 39096.60 456
DeepPCF-MVS96.93 598.32 20698.01 23699.23 10798.39 38498.97 7495.03 43099.18 26096.88 31499.33 12798.78 26398.16 11199.28 43396.74 26399.62 23599.44 195
Patchmatch-test96.55 34396.34 34597.17 36798.35 38593.06 39498.40 14897.79 38397.33 27698.41 28798.67 28983.68 42599.69 30495.16 34899.31 31298.77 362
AdaColmapbinary97.14 31796.71 32898.46 25398.34 38697.80 18696.95 33398.93 30595.58 36996.92 38597.66 38395.87 27499.53 38390.97 43799.14 34198.04 417
OpenMVScopyleft96.65 797.09 31996.68 33098.32 27098.32 38797.16 23598.86 9199.37 18389.48 45396.29 41599.15 16096.56 23799.90 8092.90 40599.20 33297.89 425
MG-MVS96.77 33696.61 33597.26 36398.31 38893.06 39495.93 39798.12 37796.45 33797.92 32598.73 27393.77 33199.39 41691.19 43599.04 35299.33 247
test_yl96.69 33796.29 34797.90 30598.28 38995.24 32497.29 31097.36 39698.21 18998.17 30297.86 37286.27 40199.55 37594.87 35498.32 39798.89 341
DCV-MVSNet96.69 33796.29 34797.90 30598.28 38995.24 32497.29 31097.36 39698.21 18998.17 30297.86 37286.27 40199.55 37594.87 35498.32 39798.89 341
CHOSEN 280x42095.51 37895.47 36795.65 41998.25 39188.27 45093.25 46198.88 31593.53 41594.65 44497.15 40786.17 40399.93 5397.41 20899.93 5598.73 367
SCA96.41 35096.66 33395.67 41798.24 39288.35 44995.85 40396.88 41496.11 34997.67 34498.67 28993.10 33999.85 15594.16 37499.22 32898.81 354
DeepMVS_CXcopyleft93.44 44798.24 39294.21 35794.34 44764.28 47391.34 46794.87 45489.45 38492.77 47477.54 47093.14 46793.35 469
MS-PatchMatch97.68 27397.75 25997.45 35498.23 39493.78 38197.29 31098.84 32696.10 35098.64 25698.65 29496.04 26099.36 41996.84 25599.14 34199.20 285
BH-w/o95.13 38494.89 38895.86 41298.20 39591.31 42595.65 41097.37 39593.64 41396.52 40895.70 43593.04 34299.02 44588.10 45195.82 45797.24 448
mvs_anonymous97.83 26698.16 22096.87 38298.18 39691.89 41597.31 30898.90 31197.37 27398.83 22999.46 7996.28 25199.79 24198.90 9398.16 40798.95 330
miper_lstm_enhance97.18 31497.16 29997.25 36498.16 39792.85 39995.15 42899.31 21297.25 28598.74 24698.78 26390.07 37699.78 25297.19 22099.80 13899.11 305
RRT-MVS97.88 25597.98 23997.61 33798.15 39893.77 38298.97 7699.64 6999.16 9298.69 24999.42 8891.60 36199.89 9697.63 18998.52 39499.16 300
ET-MVSNet_ETH3D94.30 39793.21 40897.58 34098.14 39994.47 35094.78 43693.24 45794.72 39189.56 46995.87 43278.57 44799.81 22096.91 24497.11 44298.46 388
ADS-MVSNet295.43 37994.98 38496.76 38998.14 39991.74 41697.92 21997.76 38490.23 44796.51 40998.91 22985.61 40899.85 15592.88 40696.90 44398.69 372
ADS-MVSNet95.24 38294.93 38796.18 40698.14 39990.10 44297.92 21997.32 39990.23 44796.51 40998.91 22985.61 40899.74 27792.88 40696.90 44398.69 372
c3_l97.36 29897.37 28797.31 35998.09 40293.25 39295.01 43199.16 26797.05 30298.77 24198.72 27592.88 34499.64 33996.93 24399.76 16999.05 310
FMVSNet397.50 28497.24 29598.29 27498.08 40395.83 29897.86 22898.91 31097.89 22298.95 20298.95 22387.06 39699.81 22097.77 17899.69 20499.23 275
PAPM91.88 43490.34 43796.51 39398.06 40492.56 40492.44 46597.17 40386.35 46190.38 46896.01 42786.61 39999.21 43870.65 47495.43 45997.75 434
Effi-MVS+-dtu98.26 21597.90 25199.35 7998.02 40599.49 698.02 19999.16 26798.29 18297.64 34597.99 36496.44 24399.95 2696.66 27398.93 36898.60 380
eth_miper_zixun_eth97.23 31097.25 29497.17 36798.00 40692.77 40194.71 43799.18 26097.27 28398.56 27198.74 27291.89 35999.69 30497.06 23399.81 12799.05 310
HY-MVS95.94 1395.90 36595.35 37597.55 34597.95 40794.79 33898.81 9696.94 41292.28 43295.17 43798.57 30889.90 37899.75 27291.20 43497.33 43898.10 414
UGNet98.53 17598.45 17298.79 18497.94 40896.96 24799.08 6198.54 35699.10 10496.82 39599.47 7796.55 23899.84 17398.56 12199.94 4999.55 134
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
MAR-MVS96.47 34895.70 35898.79 18497.92 40999.12 6398.28 15798.60 35492.16 43395.54 43296.17 42594.77 30899.52 38789.62 44698.23 40197.72 436
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
MVSTER96.86 33296.55 33997.79 31397.91 41094.21 35797.56 27698.87 31797.49 25999.06 17399.05 18780.72 43599.80 22898.44 12799.82 12199.37 227
API-MVS97.04 32396.91 31597.42 35697.88 41198.23 13398.18 16898.50 35997.57 24897.39 36896.75 41396.77 22499.15 44290.16 44499.02 35694.88 467
myMVS_eth3d2892.92 42192.31 41794.77 43197.84 41287.59 45496.19 38196.11 42797.08 30194.27 44793.49 46366.07 46998.78 45591.78 42297.93 42097.92 424
miper_ehance_all_eth97.06 32197.03 30697.16 36997.83 41393.06 39494.66 44099.09 27995.99 35698.69 24998.45 32592.73 34999.61 35296.79 25799.03 35398.82 349
cl____97.02 32496.83 32097.58 34097.82 41494.04 36494.66 44099.16 26797.04 30398.63 25798.71 27688.68 38999.69 30497.00 23699.81 12799.00 322
DIV-MVS_self_test97.02 32496.84 31997.58 34097.82 41494.03 36594.66 44099.16 26797.04 30398.63 25798.71 27688.69 38799.69 30497.00 23699.81 12799.01 318
CANet97.87 25797.76 25898.19 28797.75 41695.51 30996.76 34599.05 28697.74 23296.93 38498.21 34795.59 28299.89 9697.86 17399.93 5599.19 290
UBG93.25 41592.32 41696.04 41197.72 41790.16 44195.92 39995.91 43296.03 35493.95 45593.04 46669.60 45999.52 38790.72 44297.98 41898.45 391
mvsany_test197.60 27897.54 27697.77 31597.72 41795.35 32095.36 42297.13 40594.13 40699.71 4999.33 11097.93 13099.30 42997.60 19398.94 36798.67 376
PVSNet_089.98 2191.15 43590.30 43893.70 44497.72 41784.34 46890.24 46897.42 39490.20 45093.79 45693.09 46590.90 37198.89 45386.57 45772.76 47497.87 427
CR-MVSNet96.28 35395.95 35297.28 36197.71 42094.22 35598.11 18098.92 30892.31 43196.91 38799.37 9885.44 41199.81 22097.39 20997.36 43697.81 430
RPMNet97.02 32496.93 31197.30 36097.71 42094.22 35598.11 18099.30 22099.37 6096.91 38799.34 10786.72 39899.87 13397.53 19897.36 43697.81 430
ETVMVS92.60 42491.08 43397.18 36597.70 42293.65 38796.54 35795.70 43596.51 33094.68 44392.39 46961.80 47599.50 39386.97 45497.41 43298.40 399
pmmvs395.03 38694.40 39396.93 37897.70 42292.53 40595.08 42997.71 38688.57 45797.71 34198.08 35879.39 44299.82 20396.19 31099.11 34798.43 396
baseline293.73 40792.83 41396.42 39697.70 42291.28 42796.84 34189.77 46893.96 41192.44 46395.93 43079.14 44399.77 25892.94 40496.76 44798.21 408
WBMVS95.18 38394.78 38996.37 39797.68 42589.74 44495.80 40598.73 34597.54 25498.30 29398.44 32670.06 45799.82 20396.62 27699.87 9699.54 140
tpm94.67 39194.34 39595.66 41897.68 42588.42 44897.88 22494.90 44294.46 39796.03 42298.56 30978.66 44599.79 24195.88 32395.01 46198.78 361
CANet_DTU97.26 30697.06 30597.84 30997.57 42794.65 34696.19 38198.79 33497.23 29195.14 43898.24 34493.22 33699.84 17397.34 21199.84 11099.04 314
testing1193.08 41892.02 42396.26 40297.56 42890.83 43696.32 37395.70 43596.47 33492.66 46293.73 45964.36 47399.59 35993.77 38997.57 42598.37 403
tpm293.09 41792.58 41594.62 43397.56 42886.53 45797.66 25995.79 43486.15 46294.07 45298.23 34675.95 45099.53 38390.91 43996.86 44697.81 430
testing9193.32 41392.27 41896.47 39597.54 43091.25 42896.17 38596.76 41697.18 29593.65 45893.50 46265.11 47299.63 34293.04 40397.45 42998.53 385
TR-MVS95.55 37695.12 38296.86 38597.54 43093.94 37396.49 36296.53 42194.36 40297.03 38296.61 41694.26 32099.16 44186.91 45696.31 45197.47 444
testing9993.04 41991.98 42696.23 40497.53 43290.70 43896.35 37195.94 43196.87 31593.41 45993.43 46463.84 47499.59 35993.24 40197.19 43998.40 399
131495.74 37095.60 36296.17 40797.53 43292.75 40298.07 18998.31 36891.22 44294.25 44896.68 41495.53 28399.03 44491.64 42697.18 44096.74 454
CostFormer93.97 40393.78 40194.51 43497.53 43285.83 46097.98 21195.96 43089.29 45594.99 44098.63 29978.63 44699.62 34594.54 36296.50 44898.09 415
FMVSNet596.01 36195.20 38098.41 25997.53 43296.10 28498.74 9799.50 12297.22 29498.03 32099.04 18969.80 45899.88 11497.27 21599.71 19499.25 270
PMMVS96.51 34495.98 35198.09 29297.53 43295.84 29794.92 43398.84 32691.58 43796.05 42195.58 43695.68 27999.66 32995.59 33998.09 41198.76 364
reproduce_monomvs95.00 38895.25 37794.22 43797.51 43783.34 46997.86 22898.44 36198.51 16599.29 13799.30 11667.68 46399.56 37198.89 9599.81 12799.77 49
PAPR95.29 38094.47 39197.75 31997.50 43895.14 32994.89 43498.71 34791.39 44195.35 43695.48 44194.57 31199.14 44384.95 45997.37 43498.97 327
testing22291.96 43290.37 43696.72 39097.47 43992.59 40396.11 38794.76 44396.83 31792.90 46192.87 46757.92 47699.55 37586.93 45597.52 42698.00 421
PatchT96.65 34096.35 34497.54 34697.40 44095.32 32297.98 21196.64 41899.33 6596.89 39199.42 8884.32 41999.81 22097.69 18897.49 42797.48 443
tpm cat193.29 41493.13 41193.75 44397.39 44184.74 46397.39 29797.65 39083.39 46794.16 44998.41 32882.86 43099.39 41691.56 42895.35 46097.14 449
PatchmatchNetpermissive95.58 37595.67 36095.30 42797.34 44287.32 45597.65 26196.65 41795.30 37897.07 37898.69 28584.77 41499.75 27294.97 35298.64 38798.83 348
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry97.35 29996.97 30998.50 25097.31 44396.47 27598.18 16898.92 30898.95 12798.78 23899.37 9885.44 41199.85 15595.96 32199.83 11799.17 297
LS3D98.63 15498.38 18499.36 7397.25 44499.38 1399.12 6099.32 20799.21 8098.44 28498.88 23997.31 18799.80 22896.58 27999.34 30798.92 336
IB-MVS91.63 1992.24 43090.90 43496.27 40197.22 44591.24 42994.36 44993.33 45692.37 43092.24 46594.58 45666.20 46899.89 9693.16 40294.63 46397.66 438
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
UWE-MVS92.38 42791.76 43094.21 43897.16 44684.65 46495.42 42088.45 47095.96 35796.17 41695.84 43466.36 46699.71 29391.87 42198.64 38798.28 406
tpmrst95.07 38595.46 36893.91 44197.11 44784.36 46797.62 26696.96 41094.98 38596.35 41498.80 25985.46 41099.59 35995.60 33896.23 45297.79 433
Syy-MVS96.04 36095.56 36697.49 35197.10 44894.48 34996.18 38396.58 41995.65 36694.77 44192.29 47091.27 36799.36 41998.17 14598.05 41598.63 378
myMVS_eth3d91.92 43390.45 43596.30 39997.10 44890.90 43496.18 38396.58 41995.65 36694.77 44192.29 47053.88 47799.36 41989.59 44798.05 41598.63 378
MDTV_nov1_ep1395.22 37997.06 45083.20 47097.74 24896.16 42594.37 40196.99 38398.83 25283.95 42399.53 38393.90 38397.95 419
MVS93.19 41692.09 42196.50 39496.91 45194.03 36598.07 18998.06 37968.01 47294.56 44696.48 41995.96 27099.30 42983.84 46196.89 44596.17 459
E-PMN94.17 39994.37 39493.58 44596.86 45285.71 46190.11 47097.07 40698.17 19697.82 33697.19 40584.62 41698.94 44989.77 44597.68 42496.09 463
JIA-IIPM95.52 37795.03 38397.00 37496.85 45394.03 36596.93 33695.82 43399.20 8294.63 44599.71 2283.09 42899.60 35594.42 36894.64 46297.36 447
EMVS93.83 40594.02 39793.23 45096.83 45484.96 46289.77 47196.32 42397.92 21997.43 36596.36 42486.17 40398.93 45087.68 45297.73 42395.81 464
cl2295.79 36995.39 37396.98 37696.77 45592.79 40094.40 44898.53 35794.59 39497.89 32898.17 35082.82 43199.24 43596.37 29999.03 35398.92 336
WB-MVSnew95.73 37195.57 36596.23 40496.70 45690.70 43896.07 38993.86 45395.60 36897.04 38095.45 44596.00 26399.55 37591.04 43698.31 39998.43 396
dp93.47 41193.59 40493.13 45196.64 45781.62 47697.66 25996.42 42292.80 42696.11 41898.64 29778.55 44899.59 35993.31 39992.18 47098.16 411
MonoMVSNet96.25 35596.53 34195.39 42596.57 45891.01 43298.82 9597.68 38998.57 16098.03 32099.37 9890.92 37097.78 46694.99 35093.88 46697.38 446
test-LLR93.90 40493.85 39994.04 43996.53 45984.62 46594.05 45492.39 45996.17 34694.12 45095.07 44682.30 43299.67 31795.87 32698.18 40497.82 428
test-mter92.33 42991.76 43094.04 43996.53 45984.62 46594.05 45492.39 45994.00 41094.12 45095.07 44665.63 47199.67 31795.87 32698.18 40497.82 428
TESTMET0.1,192.19 43191.77 42993.46 44696.48 46182.80 47294.05 45491.52 46494.45 39994.00 45394.88 45266.65 46599.56 37195.78 33198.11 41098.02 418
MGCNet97.44 29297.01 30898.72 20396.42 46296.74 26097.20 32091.97 46298.46 16898.30 29398.79 26192.74 34899.91 7399.30 6299.94 4999.52 152
miper_enhance_ethall96.01 36195.74 35696.81 38696.41 46392.27 41293.69 45998.89 31491.14 44498.30 29397.35 40390.58 37399.58 36696.31 30399.03 35398.60 380
tpmvs95.02 38795.25 37794.33 43596.39 46485.87 45898.08 18596.83 41595.46 37395.51 43498.69 28585.91 40699.53 38394.16 37496.23 45297.58 441
CMPMVSbinary75.91 2396.29 35295.44 37098.84 17496.25 46598.69 9797.02 32999.12 27488.90 45697.83 33498.86 24289.51 38298.90 45291.92 41999.51 27398.92 336
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 194.51 39293.69 40296.99 37596.05 46693.61 38994.97 43293.49 45496.17 34697.57 35294.88 45282.30 43299.01 44793.60 39294.17 46598.37 403
EPMVS93.72 40893.27 40795.09 43096.04 46787.76 45298.13 17585.01 47594.69 39296.92 38598.64 29778.47 44999.31 42795.04 34996.46 44998.20 409
cascas94.79 39094.33 39696.15 41096.02 46892.36 41092.34 46699.26 24085.34 46495.08 43994.96 45192.96 34398.53 45994.41 37198.59 39197.56 442
MVStest195.86 36695.60 36296.63 39195.87 46991.70 41797.93 21698.94 30298.03 20999.56 7399.66 3271.83 45598.26 46299.35 5899.24 32499.91 13
gg-mvs-nofinetune92.37 42891.20 43295.85 41395.80 47092.38 40999.31 3081.84 47799.75 1191.83 46699.74 1868.29 46099.02 44587.15 45397.12 44196.16 460
gm-plane-assit94.83 47181.97 47488.07 45994.99 44999.60 35591.76 423
GG-mvs-BLEND94.76 43294.54 47292.13 41499.31 3080.47 47888.73 47291.01 47267.59 46498.16 46582.30 46694.53 46493.98 468
UWE-MVS-2890.22 43689.28 43993.02 45294.50 47382.87 47196.52 36087.51 47195.21 38192.36 46496.04 42671.57 45698.25 46372.04 47397.77 42297.94 423
EPNet_dtu94.93 38994.78 38995.38 42693.58 47487.68 45396.78 34395.69 43797.35 27589.14 47198.09 35788.15 39499.49 39694.95 35399.30 31598.98 324
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai76.24 44075.95 44377.12 45792.39 47567.91 48190.16 46959.44 48282.04 46889.42 47094.67 45549.68 47981.74 47548.06 47577.66 47381.72 471
KD-MVS_2432*160092.87 42291.99 42495.51 42291.37 47689.27 44594.07 45298.14 37595.42 37497.25 37396.44 42167.86 46199.24 43591.28 43296.08 45598.02 418
miper_refine_blended92.87 42291.99 42495.51 42291.37 47689.27 44594.07 45298.14 37595.42 37497.25 37396.44 42167.86 46199.24 43591.28 43296.08 45598.02 418
EPNet96.14 35895.44 37098.25 27890.76 47895.50 31297.92 21994.65 44498.97 12392.98 46098.85 24589.12 38599.87 13395.99 31999.68 20999.39 216
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan69.30 44168.95 44470.34 45887.68 47965.00 48291.11 46759.90 48169.02 47174.46 47688.89 47348.58 48068.03 47728.61 47672.33 47577.99 472
test_method79.78 43879.50 44180.62 45580.21 48045.76 48370.82 47298.41 36531.08 47580.89 47597.71 38084.85 41397.37 46891.51 42980.03 47298.75 365
tmp_tt78.77 43978.73 44278.90 45658.45 48174.76 48094.20 45178.26 47939.16 47486.71 47392.82 46880.50 43675.19 47686.16 45892.29 46986.74 470
testmvs17.12 44320.53 4466.87 46012.05 4824.20 48593.62 4606.73 4834.62 47810.41 47824.33 4758.28 4823.56 4799.69 47815.07 47612.86 475
test12317.04 44420.11 4477.82 45910.25 4834.91 48494.80 4354.47 4844.93 47710.00 47924.28 4769.69 4813.64 47810.14 47712.43 47714.92 474
mmdepth0.00 4470.00 4500.00 4610.00 4840.00 4860.00 4730.00 4850.00 4790.00 4800.00 4790.00 4830.00 4800.00 4790.00 4780.00 476
monomultidepth0.00 4470.00 4500.00 4610.00 4840.00 4860.00 4730.00 4850.00 4790.00 4800.00 4790.00 4830.00 4800.00 4790.00 4780.00 476
test_blank0.00 4470.00 4500.00 4610.00 4840.00 4860.00 4730.00 4850.00 4790.00 4800.00 4790.00 4830.00 4800.00 4790.00 4780.00 476
eth-test20.00 484
eth-test0.00 484
uanet_test0.00 4470.00 4500.00 4610.00 4840.00 4860.00 4730.00 4850.00 4790.00 4800.00 4790.00 4830.00 4800.00 4790.00 4780.00 476
DCPMVS0.00 4470.00 4500.00 4610.00 4840.00 4860.00 4730.00 4850.00 4790.00 4800.00 4790.00 4830.00 4800.00 4790.00 4780.00 476
cdsmvs_eth3d_5k24.66 44232.88 4450.00 4610.00 4840.00 4860.00 47399.10 2770.00 4790.00 48097.58 38899.21 180.00 4800.00 4790.00 4780.00 476
pcd_1.5k_mvsjas8.17 44510.90 4480.00 4610.00 4840.00 4860.00 4730.00 4850.00 4790.00 4800.00 47998.07 1170.00 4800.00 4790.00 4780.00 476
sosnet-low-res0.00 4470.00 4500.00 4610.00 4840.00 4860.00 4730.00 4850.00 4790.00 4800.00 4790.00 4830.00 4800.00 4790.00 4780.00 476
sosnet0.00 4470.00 4500.00 4610.00 4840.00 4860.00 4730.00 4850.00 4790.00 4800.00 4790.00 4830.00 4800.00 4790.00 4780.00 476
uncertanet0.00 4470.00 4500.00 4610.00 4840.00 4860.00 4730.00 4850.00 4790.00 4800.00 4790.00 4830.00 4800.00 4790.00 4780.00 476
Regformer0.00 4470.00 4500.00 4610.00 4840.00 4860.00 4730.00 4850.00 4790.00 4800.00 4790.00 4830.00 4800.00 4790.00 4780.00 476
ab-mvs-re8.12 44610.83 4490.00 4610.00 4840.00 4860.00 4730.00 4850.00 4790.00 48097.48 3940.00 4830.00 4800.00 4790.00 4780.00 476
uanet0.00 4470.00 4500.00 4610.00 4840.00 4860.00 4730.00 4850.00 4790.00 4800.00 4790.00 4830.00 4800.00 4790.00 4780.00 476
TestfortrainingZip98.68 107
WAC-MVS90.90 43491.37 431
PC_three_145293.27 41899.40 11398.54 31098.22 10397.00 46995.17 34799.45 28899.49 165
test_241102_TWO99.30 22098.03 20999.26 14599.02 19297.51 17399.88 11496.91 24499.60 24299.66 77
test_0728_THIRD98.17 19699.08 17199.02 19297.89 13599.88 11497.07 23199.71 19499.70 67
GSMVS98.81 354
sam_mvs184.74 41598.81 354
sam_mvs84.29 421
MTGPAbinary99.20 252
test_post197.59 27320.48 47883.07 42999.66 32994.16 374
test_post21.25 47783.86 42499.70 300
patchmatchnet-post98.77 26584.37 41899.85 155
MTMP97.93 21691.91 463
test9_res93.28 40099.15 34099.38 225
agg_prior292.50 41699.16 33899.37 227
test_prior497.97 16295.86 401
test_prior295.74 40896.48 33396.11 41897.63 38695.92 27394.16 37499.20 332
旧先验295.76 40788.56 45897.52 35699.66 32994.48 364
新几何295.93 397
无先验95.74 40898.74 34489.38 45499.73 28492.38 41899.22 280
原ACMM295.53 414
testdata299.79 24192.80 410
segment_acmp97.02 206
testdata195.44 41996.32 341
plane_prior599.27 23599.70 30094.42 36899.51 27399.45 191
plane_prior497.98 365
plane_prior397.78 18797.41 26997.79 337
plane_prior297.77 24198.20 193
plane_prior97.65 19697.07 32896.72 32399.36 303
n20.00 485
nn0.00 485
door-mid99.57 92
test1198.87 317
door99.41 172
HQP5-MVS96.79 256
BP-MVS92.82 408
HQP4-MVS95.56 42899.54 38199.32 250
HQP3-MVS99.04 28999.26 322
HQP2-MVS93.84 327
MDTV_nov1_ep13_2view74.92 47997.69 25490.06 45297.75 34085.78 40793.52 39498.69 372
ACMMP++_ref99.77 155
ACMMP++99.68 209
Test By Simon96.52 239