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 21399.94 298.51 11199.32 2699.75 4299.58 3898.60 26299.62 4098.22 10399.51 39197.70 18599.73 17697.89 424
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 24399.92 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 12799.24 272
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 12799.24 272
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 9999.11 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 19899.90 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 14099.16 11799.83 1897.96 16599.28 4098.20 37199.37 6099.70 5199.65 3692.65 34999.93 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 28999.57 9299.37 6099.21 15799.61 4396.76 22599.83 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 23499.66 77
K. test v398.00 24397.66 26899.03 14499.79 2397.56 20199.19 5292.47 45799.62 3299.52 8699.66 3289.61 38099.96 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 13399.34 8299.78 2499.47 998.42 14799.45 14798.28 18498.98 19199.19 14597.76 14699.58 36596.57 28099.55 26198.97 326
test_vis3_rt99.14 6199.17 5999.07 13499.78 2498.38 11898.92 8299.94 297.80 22799.91 1299.67 3097.15 19798.91 45099.76 2399.56 25799.92 12
EGC-MVSNET85.24 43680.54 43999.34 8299.77 2799.20 4099.08 6199.29 22712.08 47520.84 47699.42 8897.55 16599.85 15597.08 22999.72 18498.96 328
Anonymous2024052198.69 13998.87 10198.16 28999.77 2795.11 33099.08 6199.44 15599.34 6499.33 12799.55 5794.10 32499.94 4299.25 6799.96 2899.42 202
FC-MVSNet-test99.27 3899.25 5299.34 8299.77 2798.37 12099.30 3599.57 9299.61 3499.40 11399.50 6797.12 19899.85 15599.02 8699.94 4999.80 41
test_vis1_n98.31 20798.50 16097.73 32399.76 3094.17 35898.68 10799.91 996.31 34199.79 3899.57 4992.85 34599.42 41199.79 1999.84 11099.60 99
test_fmvs399.12 6899.41 2698.25 27799.76 3095.07 33199.05 6799.94 297.78 23099.82 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 26497.97 21599.86 1698.22 18799.88 2199.71 2298.59 6299.84 17399.73 2799.98 1299.98 3
tt080598.69 13998.62 14098.90 16999.75 3499.30 2399.15 5696.97 40898.86 13798.87 22497.62 38698.63 5898.96 44799.41 5698.29 39998.45 390
test_vis1_n_192098.40 19098.92 9496.81 38599.74 3690.76 43698.15 17399.91 998.33 17599.89 1899.55 5795.07 29599.88 11499.76 2399.93 5599.79 43
FOURS199.73 3799.67 399.43 1599.54 10899.43 5499.26 145
PEN-MVS99.41 2599.34 3699.62 1099.73 3799.14 5899.29 3699.54 10899.62 3299.56 7399.42 8898.16 11199.96 1498.78 10199.93 5599.77 49
lessismore_v098.97 15699.73 3797.53 20386.71 47299.37 11899.52 6689.93 37699.92 6498.99 8899.72 18499.44 195
SteuartSystems-ACMMP98.79 12098.54 15399.54 3299.73 3799.16 4998.23 16399.31 21197.92 21898.90 21398.90 23198.00 12399.88 11496.15 31299.72 18499.58 114
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu98.17 22898.15 22098.22 28399.73 3795.15 32797.36 30399.68 5994.45 39898.99 19099.27 12296.87 21499.94 4297.13 22699.91 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 21999.72 4396.08 28898.74 9798.64 35199.74 1399.67 5999.24 13594.57 31099.95 2699.11 7799.24 32399.82 35
test_f98.67 14798.87 10198.05 29899.72 4395.59 30398.51 13199.81 3196.30 34399.78 3999.82 596.14 25498.63 45799.82 1299.93 5599.95 9
ACMH96.65 799.25 4199.24 5399.26 10099.72 4398.38 11899.07 6499.55 10398.30 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 21399.71 4796.10 28397.87 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 11299.53 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 11899.64 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 10399.46 4999.50 9299.34 10797.30 18799.93 5398.90 9399.93 5599.77 49
HPM-MVS_fast99.01 8198.82 10999.57 2299.71 4799.35 1799.00 7299.50 12197.33 27598.94 20898.86 24198.75 4699.82 20397.53 19799.71 19399.56 127
ACMH+96.62 999.08 7599.00 8699.33 8899.71 4798.83 8698.60 11799.58 8599.11 9799.53 8299.18 14998.81 3899.67 31796.71 26799.77 15599.50 158
PMVScopyleft91.26 2097.86 25797.94 24497.65 33099.71 4797.94 16798.52 12698.68 34798.99 12097.52 35599.35 10397.41 18098.18 46391.59 42699.67 21496.82 452
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 22799.70 1699.60 7099.07 17896.13 25599.94 4299.42 5599.87 9699.68 70
FIs99.14 6199.09 7499.29 9499.70 5598.28 12699.13 5899.52 11799.48 4499.24 15199.41 9296.79 22299.82 20398.69 11199.88 9299.76 55
VPNet98.87 10298.83 10899.01 14899.70 5597.62 19998.43 14499.35 19299.47 4799.28 13999.05 18696.72 22899.82 20398.09 14999.36 30299.59 106
fmvsm_s_conf0.1_n_299.20 5099.38 2998.65 21199.69 5896.08 28897.49 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 20498.68 13097.27 36199.69 5892.29 41098.03 19699.85 1897.62 24099.96 499.62 4093.98 32599.74 27799.52 4999.86 10399.79 43
MP-MVS-pluss98.57 16498.23 20899.60 1699.69 5899.35 1797.16 32499.38 17894.87 38898.97 19598.99 20898.01 12299.88 11497.29 21399.70 20099.58 114
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet99.23 4699.32 3998.96 15799.68 6197.35 21498.84 9499.48 13099.69 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 21999.69 1899.63 6699.68 2599.25 1699.96 1497.25 21699.92 6899.57 121
test_fmvs1_n98.09 23498.28 19997.52 34799.68 6193.47 38998.63 11399.93 595.41 37699.68 5799.64 3791.88 35999.48 39899.82 1299.87 9699.62 89
CHOSEN 1792x268897.49 28697.14 30198.54 24199.68 6196.09 28696.50 36099.62 7391.58 43698.84 22798.97 21592.36 35199.88 11496.76 26099.95 3899.67 75
tfpnnormal98.90 9898.90 9698.91 16699.67 6597.82 18299.00 7299.44 15599.45 5099.51 9199.24 13598.20 10699.86 14295.92 32199.69 20399.04 313
MTAPA98.88 10198.64 13699.61 1499.67 6599.36 1698.43 14499.20 25198.83 14198.89 21698.90 23196.98 20899.92 6497.16 22199.70 20099.56 127
test_fmvsmvis_n_192099.26 4099.49 1698.54 24199.66 6796.97 24498.00 20399.85 1899.24 7599.92 899.50 6799.39 1299.95 2699.89 399.98 1298.71 367
mvs5depth99.30 3499.59 1298.44 25599.65 6895.35 31999.82 399.94 299.83 799.42 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 23997.80 23699.76 3998.70 14699.78 3999.11 16898.79 4299.95 2699.85 699.96 2899.83 32
WB-MVS98.52 17898.55 15198.43 25699.65 6895.59 30398.52 12698.77 33699.65 2699.52 8699.00 20694.34 31699.93 5398.65 11398.83 37199.76 55
CP-MVSNet99.21 4899.09 7499.56 2799.65 6898.96 7899.13 5899.34 19899.42 5599.33 12799.26 12897.01 20699.94 4298.74 10699.93 5599.79 43
HPM-MVScopyleft98.79 12098.53 15599.59 2099.65 6899.29 2599.16 5499.43 16196.74 32198.61 26098.38 33198.62 5999.87 13396.47 29299.67 21499.59 106
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF98.62 15698.36 18699.42 6799.65 6899.42 1198.55 12299.57 9297.72 23498.90 21399.26 12896.12 25799.52 38695.72 33299.71 19399.32 249
NormalMVS98.26 21497.97 24199.15 12099.64 7497.83 17798.28 15799.43 16199.24 7598.80 23598.85 24489.76 37899.94 4298.04 15499.67 21499.68 70
lecture99.25 4199.12 6999.62 1099.64 7499.40 1298.89 8799.51 11899.19 8799.37 11899.25 13398.36 8299.88 11498.23 13999.67 21499.59 106
fmvsm_l_conf0.5_n99.21 4899.28 4699.02 14799.64 7497.28 22197.82 23299.76 3998.73 14399.82 3399.09 17698.81 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 15398.49 16599.06 14099.64 7497.90 17198.51 13198.94 30196.96 30699.24 15198.89 23797.83 13899.81 22096.88 25099.49 28299.48 176
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 24099.34 12599.18 14997.54 16799.77 25897.79 17699.74 17399.04 313
Elysia99.15 5799.14 6799.18 11299.63 8097.92 16898.50 13399.43 16199.67 2199.70 5199.13 16496.66 23199.98 499.54 4399.96 2899.64 83
StellarMVS99.15 5799.14 6799.18 11299.63 8097.92 16898.50 13399.43 16199.67 2199.70 5199.13 16496.66 23199.98 499.54 4399.96 2899.64 83
KD-MVS_self_test99.25 4199.18 5899.44 6599.63 8099.06 7198.69 10699.54 10899.31 6899.62 6999.53 6397.36 18499.86 14299.24 6999.71 19399.39 215
EU-MVSNet97.66 27498.50 16095.13 42799.63 8085.84 45898.35 15398.21 37098.23 18699.54 7899.46 7995.02 29699.68 31398.24 13799.87 9699.87 21
HyFIR lowres test97.19 31296.60 33698.96 15799.62 8497.28 22195.17 42599.50 12194.21 40399.01 18798.32 33986.61 39899.99 297.10 22899.84 11099.60 99
fmvsm_l_conf0.5_n_999.32 3399.43 2498.98 15499.59 8597.18 23297.44 29399.83 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 33499.53 8298.77 26499.83 19196.67 27099.64 22599.58 114
TestfortrainingZip a98.95 9198.72 12099.64 999.58 8799.32 2298.68 10799.60 7796.46 33499.53 8298.77 26497.87 13699.83 19198.39 13099.64 22599.77 49
FE-MVSNET98.59 16198.50 16098.87 17099.58 8797.30 21998.08 18599.74 4396.94 30898.97 19599.10 17196.94 21099.74 27797.33 21199.86 10399.55 134
mmtdpeth99.30 3499.42 2598.92 16599.58 8796.89 25199.48 1399.92 799.92 298.26 29899.80 1198.33 8899.91 7399.56 4099.95 3899.97 4
ACMMP_NAP98.75 12798.48 16699.57 2299.58 8799.29 2597.82 23299.25 24096.94 30898.78 23799.12 16798.02 12199.84 17397.13 22699.67 21499.59 106
nrg03099.40 2699.35 3499.54 3299.58 8799.13 6198.98 7599.48 13099.68 2099.46 9999.26 12898.62 5999.73 28499.17 7499.92 6899.76 55
VDDNet98.21 22197.95 24299.01 14899.58 8797.74 19099.01 7097.29 39999.67 2198.97 19599.50 6790.45 37399.80 22897.88 16999.20 33199.48 176
COLMAP_ROBcopyleft96.50 1098.99 8498.85 10799.41 6999.58 8799.10 6698.74 9799.56 9999.09 10799.33 12799.19 14598.40 7999.72 29295.98 31999.76 16899.42 202
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 1499.85 699.99 599.29 258
ZNCC-MVS98.68 14498.40 17899.54 3299.57 9599.21 3498.46 14199.29 22797.28 28198.11 31098.39 32998.00 12399.87 13396.86 25399.64 22599.55 134
MSP-MVS98.40 19098.00 23699.61 1499.57 9599.25 3098.57 12099.35 19297.55 25199.31 13597.71 37994.61 30999.88 11496.14 31399.19 33499.70 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 20598.39 18198.13 29099.57 9595.54 30697.78 23899.49 12897.37 27299.19 15997.65 38398.96 2999.49 39596.50 29198.99 35999.34 240
MP-MVScopyleft98.46 18498.09 22599.54 3299.57 9599.22 3398.50 13399.19 25597.61 24397.58 34998.66 29197.40 18199.88 11494.72 35899.60 24199.54 140
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test98.71 13198.46 17099.47 6199.57 9598.97 7498.23 16399.48 13096.60 32699.10 16999.06 17998.71 5099.83 19195.58 33999.78 14999.62 89
LGP-MVS_train99.47 6199.57 9598.97 7499.48 13096.60 32699.10 16999.06 17998.71 5099.83 19195.58 33999.78 14999.62 89
IS-MVSNet98.19 22497.90 25099.08 13299.57 9597.97 16299.31 3098.32 36699.01 11998.98 19199.03 19091.59 36199.79 24195.49 34199.80 13899.48 176
viewdifsd2359ckpt1198.84 10899.04 7998.24 27999.56 10395.51 30897.38 29899.70 5299.16 9299.57 7199.40 9598.26 9699.71 29398.55 12299.82 12199.50 158
viewmsd2359difaftdt98.84 10899.04 7998.24 27999.56 10395.51 30897.38 29899.70 5299.16 9299.57 7199.40 9598.26 9699.71 29398.55 12299.82 12199.50 158
dcpmvs_298.78 12299.11 7097.78 31399.56 10393.67 38499.06 6599.86 1699.50 4399.66 6099.26 12897.21 19599.99 298.00 15999.91 7799.68 70
test_040298.76 12698.71 12498.93 16299.56 10398.14 14098.45 14399.34 19899.28 7298.95 20198.91 22898.34 8799.79 24195.63 33699.91 7798.86 345
EPP-MVSNet98.30 20898.04 23299.07 13499.56 10397.83 17799.29 3698.07 37799.03 11798.59 26499.13 16492.16 35599.90 8096.87 25199.68 20899.49 165
ACMMPcopyleft98.75 12798.50 16099.52 4599.56 10399.16 4998.87 8899.37 18297.16 29698.82 23199.01 20297.71 14999.87 13396.29 30499.69 20399.54 140
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 26497.79 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 22299.55 10996.09 28697.74 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 15599.21 8099.43 10499.55 5797.82 14199.86 14298.42 12999.89 9099.41 205
Vis-MVSNet (Re-imp)97.46 28897.16 29898.34 26899.55 10996.10 28398.94 8098.44 36098.32 17798.16 30498.62 30088.76 38599.73 28493.88 38499.79 14499.18 292
ACMM96.08 1298.91 9698.73 11899.48 5799.55 10999.14 5898.07 18999.37 18297.62 24099.04 18398.96 21898.84 3699.79 24197.43 20699.65 22399.49 165
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs298.70 13698.97 9097.89 30699.54 11494.05 36198.55 12299.92 796.78 31999.72 4799.78 1396.60 23599.67 31799.91 299.90 8499.94 10
mPP-MVS98.64 15198.34 18999.54 3299.54 11499.17 4598.63 11399.24 24597.47 25998.09 31298.68 28697.62 15899.89 9696.22 30799.62 23499.57 121
XVG-ACMP-BASELINE98.56 16598.34 18999.22 10899.54 11498.59 10397.71 25199.46 14397.25 28498.98 19198.99 20897.54 16799.84 17395.88 32299.74 17399.23 274
viewmacassd2359aftdt98.86 10598.87 10198.83 17599.53 11797.32 21897.70 25399.64 6998.22 18799.25 14999.27 12298.40 7999.61 35197.98 16199.87 9699.55 134
region2R98.69 13998.40 17899.54 3299.53 11799.17 4598.52 12699.31 21197.46 26498.44 28398.51 31497.83 13899.88 11496.46 29399.58 25099.58 114
PGM-MVS98.66 14898.37 18599.55 2999.53 11799.18 4498.23 16399.49 12897.01 30598.69 24898.88 23898.00 12399.89 9695.87 32599.59 24599.58 114
Patchmatch-RL test97.26 30597.02 30697.99 30299.52 12095.53 30796.13 38599.71 4797.47 25999.27 14199.16 15584.30 41999.62 34497.89 16699.77 15598.81 353
ACMMPR98.70 13698.42 17699.54 3299.52 12099.14 5898.52 12699.31 21197.47 25998.56 27098.54 30997.75 14799.88 11496.57 28099.59 24599.58 114
fmvsm_s_conf0.5_n_999.17 5299.38 2998.53 24399.51 12295.82 29897.62 26699.78 3699.72 1599.90 1499.48 7498.66 5499.89 9699.85 699.93 5599.89 16
AstraMVS98.16 23098.07 23098.41 25899.51 12295.86 29598.00 20395.14 44098.97 12399.43 10499.24 13593.25 33399.84 17399.21 7099.87 9699.54 140
fmvsm_s_conf0.5_n_899.13 6599.26 5098.74 20099.51 12296.44 27597.65 26199.65 6799.66 2499.78 3999.48 7497.92 13199.93 5399.72 2999.95 3899.87 21
GST-MVS98.61 15798.30 19699.52 4599.51 12299.20 4098.26 16199.25 24097.44 26798.67 25198.39 32997.68 15099.85 15596.00 31799.51 27299.52 152
Anonymous2023120698.21 22198.21 20998.20 28499.51 12295.43 31798.13 17599.32 20696.16 34798.93 20998.82 25496.00 26299.83 19197.32 21299.73 17699.36 233
ACMP95.32 1598.41 18898.09 22599.36 7399.51 12298.79 8997.68 25599.38 17895.76 36398.81 23398.82 25498.36 8299.82 20394.75 35599.77 15599.48 176
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LuminaMVS98.39 19698.20 21098.98 15499.50 12897.49 20497.78 23897.69 38698.75 14299.49 9399.25 13392.30 35399.94 4299.14 7599.88 9299.50 158
DVP-MVScopyleft98.77 12598.52 15699.52 4599.50 12899.21 3498.02 19998.84 32597.97 21299.08 17199.02 19197.61 16099.88 11496.99 23799.63 23199.48 176
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 20699.88 11496.99 23799.63 23199.68 70
test072699.50 12899.21 3498.17 17199.35 19297.97 21299.26 14599.06 17997.61 160
AllTest98.44 18698.20 21099.16 11799.50 12898.55 10698.25 16299.58 8596.80 31798.88 22099.06 17997.65 15399.57 36794.45 36599.61 23999.37 226
TestCases99.16 11799.50 12898.55 10699.58 8596.80 31798.88 22099.06 17997.65 15399.57 36794.45 36599.61 23999.37 226
XVG-OURS98.53 17498.34 18999.11 12599.50 12898.82 8895.97 39199.50 12197.30 27999.05 18198.98 21399.35 1499.32 42595.72 33299.68 20899.18 292
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 20899.59 106
fmvsm_s_conf0.5_n_299.14 6199.31 4198.63 21799.49 13696.08 28897.38 29899.81 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 21198.03 20899.66 6099.02 19198.36 8299.88 11496.91 24399.62 23499.41 205
IU-MVS99.49 13699.15 5398.87 31692.97 42199.41 11096.76 26099.62 23499.66 77
test_241102_ONE99.49 13699.17 4599.31 21197.98 21199.66 6098.90 23198.36 8299.48 398
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 17399.51 4999.49 13699.16 4998.52 12699.31 21197.47 25998.58 26698.50 31897.97 12799.85 15596.57 28099.59 24599.53 149
VPA-MVSNet99.30 3499.30 4499.28 9599.49 13698.36 12399.00 7299.45 14799.63 2999.52 8699.44 8498.25 9899.88 11499.09 7999.84 11099.62 89
XVG-OURS-SEG-HR98.49 18198.28 19999.14 12199.49 13698.83 8696.54 35699.48 13097.32 27799.11 16698.61 30299.33 1599.30 42896.23 30698.38 39599.28 261
114514_t96.50 34595.77 35498.69 20699.48 14497.43 21197.84 23199.55 10381.42 46896.51 40898.58 30695.53 28299.67 31793.41 39799.58 25098.98 323
IterMVS-LS98.55 16998.70 12798.09 29199.48 14494.73 34197.22 31899.39 17698.97 12399.38 11699.31 11596.00 26299.93 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 26997.75 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 29599.83 2597.61 24399.85 2799.30 11698.80 4099.95 2699.71 3199.90 8499.78 46
v899.01 8199.16 6198.57 22999.47 14696.31 28098.90 8399.47 13999.03 11799.52 8699.57 4996.93 21199.81 22099.60 3699.98 1299.60 99
SSC-MVS3.298.53 17498.79 11297.74 32099.46 14993.62 38796.45 36299.34 19899.33 6598.93 20998.70 28297.90 13299.90 8099.12 7699.92 6899.69 69
fmvsm_s_conf0.5_n_399.22 4799.37 3298.78 18799.46 14996.58 26797.65 26199.72 4599.47 4799.86 2499.50 6798.94 3099.89 9699.75 2599.97 2199.86 27
XVS98.72 13098.45 17199.53 3999.46 14999.21 3498.65 11199.34 19898.62 15397.54 35398.63 29897.50 17399.83 19196.79 25699.53 26799.56 127
X-MVStestdata94.32 39492.59 41399.53 3999.46 14999.21 3498.65 11199.34 19898.62 15397.54 35345.85 47397.50 17399.83 19196.79 25699.53 26799.56 127
test20.0398.78 12298.77 11598.78 18799.46 14997.20 22997.78 23899.24 24599.04 11699.41 11098.90 23197.65 15399.76 26497.70 18599.79 14499.39 215
guyue98.01 24297.93 24698.26 27599.45 15495.48 31298.08 18596.24 42398.89 13499.34 12599.14 16291.32 36599.82 20399.07 8099.83 11799.48 176
CSCG98.68 14498.50 16099.20 10999.45 15498.63 9898.56 12199.57 9297.87 22298.85 22598.04 36097.66 15299.84 17396.72 26599.81 12799.13 302
GeoE99.05 7898.99 8899.25 10399.44 15698.35 12498.73 10199.56 9998.42 17098.91 21298.81 25798.94 3099.91 7398.35 13299.73 17699.49 165
v14898.45 18598.60 14598.00 30199.44 15694.98 33397.44 29399.06 28198.30 17999.32 13398.97 21596.65 23399.62 34498.37 13199.85 10599.39 215
v1098.97 8899.11 7098.55 23699.44 15696.21 28298.90 8399.55 10398.73 14399.48 9499.60 4596.63 23499.83 19199.70 3299.99 599.61 97
V4298.78 12298.78 11498.76 19499.44 15697.04 24098.27 16099.19 25597.87 22299.25 14999.16 15596.84 21599.78 25299.21 7099.84 11099.46 186
MDA-MVSNet-bldmvs97.94 24897.91 24998.06 29699.44 15694.96 33496.63 35299.15 27198.35 17398.83 22899.11 16894.31 31799.85 15596.60 27798.72 37799.37 226
viewdifsd2359ckpt0798.71 13198.86 10598.26 27599.43 16195.65 30297.20 31999.66 6399.20 8299.29 13799.01 20298.29 9199.73 28497.92 16599.75 17299.39 215
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 22999.42 16396.59 26498.13 17599.66 6399.09 10799.30 13699.02 19198.79 4299.89 9697.87 17199.80 13899.23 274
test111196.49 34696.82 32095.52 42099.42 16387.08 45599.22 4587.14 47199.11 9799.46 9999.58 4788.69 38699.86 14298.80 9999.95 3899.62 89
v2v48298.56 16598.62 14098.37 26599.42 16395.81 29997.58 27499.16 26697.90 22099.28 13999.01 20295.98 26799.79 24199.33 5999.90 8499.51 155
OPM-MVS98.56 16598.32 19499.25 10399.41 16698.73 9497.13 32699.18 25997.10 29998.75 24398.92 22698.18 10799.65 33596.68 26999.56 25799.37 226
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS298.07 23698.08 22898.04 29999.41 16694.59 34794.59 44399.40 17497.50 25698.82 23198.83 25196.83 21799.84 17397.50 20099.81 12799.71 62
test_one_060199.39 16899.20 4099.31 21198.49 16698.66 25399.02 19197.64 156
mvsany_test398.87 10298.92 9498.74 20099.38 16996.94 24898.58 11999.10 27696.49 33199.96 499.81 898.18 10799.45 40698.97 8999.79 14499.83 32
patch_mono-298.51 17998.63 13898.17 28799.38 16994.78 33897.36 30399.69 5498.16 19998.49 27999.29 11997.06 20199.97 798.29 13699.91 7799.76 55
test250692.39 42591.89 42793.89 44199.38 16982.28 47299.32 2666.03 47999.08 11198.77 24099.57 4966.26 46699.84 17398.71 10999.95 3899.54 140
ECVR-MVScopyleft96.42 34896.61 33495.85 41299.38 16988.18 45099.22 4586.00 47399.08 11199.36 12199.57 4988.47 39199.82 20398.52 12499.95 3899.54 140
casdiffmvspermissive98.95 9199.00 8698.81 17999.38 16997.33 21697.82 23299.57 9299.17 9199.35 12399.17 15398.35 8699.69 30498.46 12699.73 17699.41 205
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 16997.26 22398.49 13699.50 12198.86 13799.19 15999.06 17998.23 10099.69 30498.71 10999.76 16899.33 246
TranMVSNet+NR-MVSNet99.17 5299.07 7799.46 6399.37 17598.87 8498.39 14999.42 16799.42 5599.36 12199.06 17998.38 8199.95 2698.34 13399.90 8499.57 121
fmvsm_s_conf0.5_n_699.08 7599.21 5698.69 20699.36 17696.51 27097.62 26699.68 5998.43 16999.85 2799.10 17199.12 2399.88 11499.77 2299.92 6899.67 75
tttt051795.64 37394.98 38397.64 33399.36 17693.81 37998.72 10290.47 46598.08 20798.67 25198.34 33673.88 45299.92 6497.77 17899.51 27299.20 284
test_part299.36 17699.10 6699.05 181
v114498.60 15998.66 13398.41 25899.36 17695.90 29397.58 27499.34 19897.51 25599.27 14199.15 15996.34 24899.80 22899.47 5399.93 5599.51 155
CP-MVS98.70 13698.42 17699.52 4599.36 17699.12 6398.72 10299.36 18697.54 25398.30 29298.40 32897.86 13799.89 9696.53 28999.72 18499.56 127
diffmvs_AUTHOR98.50 18098.59 14798.23 28299.35 18195.48 31296.61 35399.60 7798.37 17198.90 21399.00 20697.37 18399.76 26498.22 14099.85 10599.46 186
Test_1112_low_res96.99 32796.55 33898.31 27199.35 18195.47 31595.84 40399.53 11291.51 43896.80 39598.48 32191.36 36499.83 19196.58 27899.53 26799.62 89
DeepC-MVS97.60 498.97 8898.93 9399.10 12799.35 18197.98 16198.01 20299.46 14397.56 24999.54 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 30496.86 31698.58 22699.34 18496.32 27996.75 34599.58 8593.14 41996.89 39097.48 39392.11 35699.86 14296.91 24399.54 26399.57 121
reproduce_model99.15 5798.97 9099.67 499.33 18599.44 1098.15 17399.47 13999.12 9699.52 8699.32 11498.31 8999.90 8097.78 17799.73 17699.66 77
MVSMamba_PlusPlus98.83 11198.98 8998.36 26699.32 18696.58 26798.90 8399.41 17199.75 1198.72 24699.50 6796.17 25399.94 4299.27 6499.78 14998.57 383
fmvsm_s_conf0.5_n_499.01 8199.22 5498.38 26299.31 18795.48 31297.56 27699.73 4498.87 13599.75 4499.27 12298.80 4099.86 14299.80 1799.90 8499.81 39
SF-MVS98.53 17498.27 20299.32 9099.31 18798.75 9098.19 16799.41 17196.77 32098.83 22898.90 23197.80 14399.82 20395.68 33599.52 27099.38 224
CPTT-MVS97.84 26397.36 28799.27 9899.31 18798.46 11498.29 15699.27 23494.90 38797.83 33398.37 33294.90 29899.84 17393.85 38699.54 26399.51 155
UnsupCasMVSNet_eth97.89 25297.60 27398.75 19699.31 18797.17 23497.62 26699.35 19298.72 14598.76 24298.68 28692.57 35099.74 27797.76 18295.60 45799.34 240
fmvsm_s_conf0.5_n_798.83 11199.04 7998.20 28499.30 19194.83 33697.23 31499.36 18698.64 14899.84 3099.43 8798.10 11699.91 7399.56 4099.96 2899.87 21
pmmvs-eth3d98.47 18398.34 18998.86 17299.30 19197.76 18897.16 32499.28 23195.54 36999.42 10899.19 14597.27 19099.63 34197.89 16699.97 2199.20 284
mamv499.44 1999.39 2899.58 2199.30 19199.74 299.04 6899.81 3199.77 1099.82 3399.57 4997.82 14199.98 499.53 4799.89 9099.01 317
viewcassd2359sk1198.55 16998.51 15798.67 20999.29 19496.99 24397.39 29699.54 10897.73 23298.81 23399.08 17797.55 16599.66 32897.52 19999.67 21499.36 233
SymmetryMVS98.05 23897.71 26399.09 13199.29 19497.83 17798.28 15797.64 39199.24 7598.80 23598.85 24489.76 37899.94 4298.04 15499.50 28099.49 165
Anonymous2023121199.27 3899.27 4799.26 10099.29 19498.18 13699.49 1299.51 11899.70 1699.80 3799.68 2596.84 21599.83 19199.21 7099.91 7799.77 49
viewmanbaseed2359cas98.58 16398.54 15398.70 20499.28 19797.13 23897.47 28999.55 10397.55 25198.96 20098.92 22697.77 14599.59 35897.59 19399.77 15599.39 215
UnsupCasMVSNet_bld97.30 30296.92 31298.45 25399.28 19796.78 25896.20 37999.27 23495.42 37398.28 29698.30 34093.16 33699.71 29394.99 34997.37 43398.87 344
EC-MVSNet99.09 7199.05 7899.20 10999.28 19798.93 8099.24 4499.84 2299.08 11198.12 30998.37 33298.72 4999.90 8099.05 8399.77 15598.77 361
mamba_040898.80 11898.88 9998.55 23699.27 20096.50 27198.00 20399.60 7798.93 12899.22 15498.84 24998.59 6299.89 9697.74 18399.72 18499.27 262
SSM_0407298.80 11898.88 9998.56 23499.27 20096.50 27198.00 20399.60 7798.93 12899.22 15498.84 24998.59 6299.90 8097.74 18399.72 18499.27 262
SSM_040798.86 10598.96 9298.55 23699.27 20096.50 27198.04 19499.66 6399.09 10799.22 15499.02 19198.79 4299.87 13397.87 17199.72 18499.27 262
reproduce-ours99.09 7198.90 9699.67 499.27 20099.49 698.00 20399.42 16799.05 11499.48 9499.27 12298.29 9199.89 9697.61 19099.71 19399.62 89
our_new_method99.09 7198.90 9699.67 499.27 20099.49 698.00 20399.42 16799.05 11499.48 9499.27 12298.29 9199.89 9697.61 19099.71 19399.62 89
DPE-MVScopyleft98.59 16198.26 20399.57 2299.27 20099.15 5397.01 32999.39 17697.67 23699.44 10398.99 20897.53 16999.89 9695.40 34399.68 20899.66 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 26298.18 21596.87 38199.27 20091.16 43095.53 41399.25 24099.10 10499.41 11099.35 10393.10 33899.96 1498.65 11399.94 4999.49 165
v119298.60 15998.66 13398.41 25899.27 20095.88 29497.52 28199.36 18697.41 26899.33 12799.20 14496.37 24699.82 20399.57 3899.92 6899.55 134
N_pmnet97.63 27697.17 29798.99 15099.27 20097.86 17495.98 39093.41 45495.25 37899.47 9898.90 23195.63 27999.85 15596.91 24399.73 17699.27 262
viewdifsd2359ckpt1398.39 19698.29 19898.70 20499.26 20997.19 23097.51 28399.48 13096.94 30898.58 26698.82 25497.47 17899.55 37497.21 21899.33 30799.34 240
FPMVS93.44 41192.23 41897.08 36999.25 21097.86 17495.61 41097.16 40392.90 42393.76 45698.65 29375.94 45095.66 47079.30 46897.49 42697.73 434
ME-MVS98.61 15798.33 19399.44 6599.24 21198.93 8097.45 29199.06 28198.14 20599.06 17398.77 26496.97 20999.82 20396.67 27099.64 22599.58 114
new-patchmatchnet98.35 19998.74 11697.18 36499.24 21192.23 41296.42 36699.48 13098.30 17999.69 5599.53 6397.44 17999.82 20398.84 9899.77 15599.49 165
MCST-MVS98.00 24397.63 27199.10 12799.24 21198.17 13796.89 33898.73 34495.66 36497.92 32497.70 38197.17 19699.66 32896.18 31199.23 32699.47 184
UniMVSNet (Re)98.87 10298.71 12499.35 7999.24 21198.73 9497.73 25099.38 17898.93 12899.12 16598.73 27296.77 22399.86 14298.63 11599.80 13899.46 186
jason97.45 29097.35 28897.76 31799.24 21193.93 37395.86 40098.42 36294.24 40298.50 27898.13 35094.82 30299.91 7397.22 21799.73 17699.43 199
jason: jason.
IterMVS97.73 26898.11 22496.57 39199.24 21190.28 43995.52 41599.21 24998.86 13799.33 12799.33 11093.11 33799.94 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 16998.62 14098.32 26999.22 21795.58 30597.51 28399.45 14797.16 29699.45 10299.24 13596.12 25799.85 15599.60 3699.88 9299.55 134
ITE_SJBPF98.87 17099.22 21798.48 11399.35 19297.50 25698.28 29698.60 30497.64 15699.35 42193.86 38599.27 31898.79 359
h-mvs3397.77 26697.33 29099.10 12799.21 21997.84 17698.35 15398.57 35499.11 9798.58 26699.02 19188.65 38999.96 1498.11 14796.34 44999.49 165
v14419298.54 17298.57 14998.45 25399.21 21995.98 29197.63 26599.36 18697.15 29899.32 13399.18 14995.84 27499.84 17399.50 5099.91 7799.54 140
APDe-MVScopyleft98.99 8498.79 11299.60 1699.21 21999.15 5398.87 8899.48 13097.57 24799.35 12399.24 13597.83 13899.89 9697.88 16999.70 20099.75 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 21998.45 11598.46 14199.33 20499.63 2999.48 9499.15 15997.23 19399.75 27297.17 22099.66 22299.63 88
SR-MVS-dyc-post98.81 11698.55 15199.57 2299.20 22399.38 1398.48 13999.30 21998.64 14898.95 20198.96 21897.49 17699.86 14296.56 28499.39 29899.45 191
RE-MVS-def98.58 14899.20 22399.38 1398.48 13999.30 21998.64 14898.95 20198.96 21897.75 14796.56 28499.39 29899.45 191
v192192098.54 17298.60 14598.38 26299.20 22395.76 30197.56 27699.36 18697.23 29099.38 11699.17 15396.02 26099.84 17399.57 3899.90 8499.54 140
thisisatest053095.27 38094.45 39197.74 32099.19 22694.37 35197.86 22890.20 46697.17 29598.22 29997.65 38373.53 45399.90 8096.90 24899.35 30498.95 329
Anonymous2024052998.93 9498.87 10199.12 12399.19 22698.22 13499.01 7098.99 29999.25 7499.54 7899.37 9897.04 20299.80 22897.89 16699.52 27099.35 238
APD-MVS_3200maxsize98.84 10898.61 14499.53 3999.19 22699.27 2898.49 13699.33 20498.64 14899.03 18698.98 21397.89 13499.85 15596.54 28899.42 29599.46 186
HQP_MVS97.99 24697.67 26598.93 16299.19 22697.65 19697.77 24199.27 23498.20 19397.79 33697.98 36494.90 29899.70 30094.42 36799.51 27299.45 191
plane_prior799.19 22697.87 173
ab-mvs98.41 18898.36 18698.59 22599.19 22697.23 22499.32 2698.81 33097.66 23798.62 25899.40 9596.82 21899.80 22895.88 32299.51 27298.75 364
F-COLMAP97.30 30296.68 32999.14 12199.19 22698.39 11797.27 31399.30 21992.93 42296.62 40198.00 36295.73 27799.68 31392.62 41398.46 39499.35 238
viewdifsd2359ckpt0998.13 23197.92 24798.77 19299.18 23397.35 21497.29 30999.53 11295.81 36198.09 31298.47 32296.34 24899.66 32897.02 23399.51 27299.29 258
SR-MVS98.71 13198.43 17499.57 2299.18 23399.35 1798.36 15299.29 22798.29 18298.88 22098.85 24497.53 16999.87 13396.14 31399.31 31199.48 176
UniMVSNet_NR-MVSNet98.86 10598.68 13099.40 7199.17 23598.74 9197.68 25599.40 17499.14 9599.06 17398.59 30596.71 22999.93 5398.57 11899.77 15599.53 149
LF4IMVS97.90 25097.69 26498.52 24499.17 23597.66 19597.19 32399.47 13996.31 34197.85 33298.20 34796.71 22999.52 38694.62 35999.72 18498.38 400
SMA-MVScopyleft98.40 19098.03 23399.51 4999.16 23799.21 3498.05 19299.22 24894.16 40498.98 19199.10 17197.52 17199.79 24196.45 29499.64 22599.53 149
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 13899.39 7299.16 23798.74 9197.54 27999.25 24098.84 14099.06 17398.76 26996.76 22599.93 5398.57 11899.77 15599.50 158
NR-MVSNet98.95 9198.82 10999.36 7399.16 23798.72 9699.22 4599.20 25199.10 10499.72 4798.76 26996.38 24599.86 14298.00 15999.82 12199.50 158
MVS_111021_LR98.30 20898.12 22398.83 17599.16 23798.03 15696.09 38799.30 21997.58 24698.10 31198.24 34398.25 9899.34 42296.69 26899.65 22399.12 303
DSMNet-mixed97.42 29397.60 27396.87 38199.15 24191.46 41998.54 12499.12 27392.87 42497.58 34999.63 3996.21 25299.90 8095.74 33199.54 26399.27 262
D2MVS97.84 26397.84 25497.83 30999.14 24294.74 34096.94 33398.88 31495.84 36098.89 21698.96 21894.40 31499.69 30497.55 19499.95 3899.05 309
pmmvs597.64 27597.49 27998.08 29499.14 24295.12 32996.70 34899.05 28593.77 41198.62 25898.83 25193.23 33499.75 27298.33 13599.76 16899.36 233
SPE-MVS-test99.13 6599.09 7499.26 10099.13 24498.97 7499.31 3099.88 1499.44 5298.16 30498.51 31498.64 5699.93 5398.91 9299.85 10598.88 343
VDD-MVS98.56 16598.39 18199.07 13499.13 24498.07 15198.59 11897.01 40699.59 3699.11 16699.27 12294.82 30299.79 24198.34 13399.63 23199.34 240
save fliter99.11 24697.97 16296.53 35899.02 29398.24 185
APD-MVScopyleft98.10 23297.67 26599.42 6799.11 24698.93 8097.76 24499.28 23194.97 38598.72 24698.77 26497.04 20299.85 15593.79 38799.54 26399.49 165
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 21999.10 24896.37 27797.23 31498.87 31699.20 8299.19 15998.99 20897.30 18799.85 15598.77 10499.79 14499.65 82
EI-MVSNet98.40 19098.51 15798.04 29999.10 24894.73 34197.20 31998.87 31698.97 12399.06 17399.02 19196.00 26299.80 22898.58 11699.82 12199.60 99
CVMVSNet96.25 35497.21 29693.38 44899.10 24880.56 47697.20 31998.19 37396.94 30899.00 18899.02 19189.50 38299.80 22896.36 30099.59 24599.78 46
EI-MVSNet-Vis-set98.68 14498.70 12798.63 21799.09 25196.40 27697.23 31498.86 32199.20 8299.18 16398.97 21597.29 18999.85 15598.72 10899.78 14999.64 83
HPM-MVS++copyleft98.10 23297.64 27099.48 5799.09 25199.13 6197.52 28198.75 34197.46 26496.90 38997.83 37496.01 26199.84 17395.82 32999.35 30499.46 186
DP-MVS Recon97.33 30096.92 31298.57 22999.09 25197.99 15896.79 34199.35 19293.18 41897.71 34098.07 35895.00 29799.31 42693.97 38099.13 34298.42 397
MVS_111021_HR98.25 21798.08 22898.75 19699.09 25197.46 20895.97 39199.27 23497.60 24597.99 32298.25 34298.15 11399.38 41796.87 25199.57 25499.42 202
BP-MVS197.40 29596.97 30898.71 20399.07 25596.81 25498.34 15597.18 40198.58 15998.17 30198.61 30284.01 42199.94 4298.97 8999.78 14999.37 226
9.1497.78 25699.07 25597.53 28099.32 20695.53 37098.54 27498.70 28297.58 16299.76 26494.32 37299.46 285
PAPM_NR96.82 33496.32 34598.30 27299.07 25596.69 26297.48 28798.76 33895.81 36196.61 40296.47 41994.12 32399.17 43990.82 44097.78 42099.06 308
TAMVS98.24 21898.05 23198.80 18199.07 25597.18 23297.88 22498.81 33096.66 32599.17 16499.21 14294.81 30499.77 25896.96 24199.88 9299.44 195
CLD-MVS97.49 28697.16 29898.48 25099.07 25597.03 24194.71 43699.21 24994.46 39698.06 31597.16 40597.57 16399.48 39894.46 36499.78 14998.95 329
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 26099.15 5399.36 2299.88 1499.36 6398.21 30098.46 32398.68 5399.93 5399.03 8599.85 10598.64 376
thres100view90094.19 39793.67 40295.75 41599.06 26091.35 42398.03 19694.24 44998.33 17597.40 36594.98 44979.84 43799.62 34483.05 46198.08 41196.29 456
thres600view794.45 39293.83 39996.29 39999.06 26091.53 41897.99 21094.24 44998.34 17497.44 36395.01 44779.84 43799.67 31784.33 45998.23 40097.66 437
plane_prior199.05 263
YYNet197.60 27797.67 26597.39 35799.04 26493.04 39695.27 42298.38 36597.25 28498.92 21198.95 22295.48 28699.73 28496.99 23798.74 37599.41 205
MDA-MVSNet_test_wron97.60 27797.66 26897.41 35699.04 26493.09 39295.27 42298.42 36297.26 28398.88 22098.95 22295.43 28799.73 28497.02 23398.72 37799.41 205
MIMVSNet96.62 34196.25 34997.71 32499.04 26494.66 34499.16 5496.92 41297.23 29097.87 32999.10 17186.11 40499.65 33591.65 42499.21 33098.82 348
icg_test_0407_298.20 22398.38 18397.65 33099.03 26794.03 36495.78 40599.45 14798.16 19999.06 17398.71 27598.27 9499.68 31397.50 20099.45 28799.22 279
IMVS_040798.39 19698.64 13697.66 32899.03 26794.03 36498.10 18299.45 14798.16 19999.06 17398.71 27598.27 9499.71 29397.50 20099.45 28799.22 279
IMVS_040498.07 23698.20 21097.69 32599.03 26794.03 36496.67 34999.45 14798.16 19998.03 31998.71 27596.80 22199.82 20397.50 20099.45 28799.22 279
IMVS_040398.34 20098.56 15097.66 32899.03 26794.03 36497.98 21199.45 14798.16 19998.89 21698.71 27597.90 13299.74 27797.50 20099.45 28799.22 279
PatchMatch-RL97.24 30896.78 32398.61 22299.03 26797.83 17796.36 36999.06 28193.49 41697.36 36997.78 37595.75 27699.49 39593.44 39698.77 37498.52 385
viewmambaseed2359dif98.19 22498.26 20397.99 30299.02 27295.03 33296.59 35599.53 11296.21 34499.00 18898.99 20897.62 15899.61 35197.62 18999.72 18499.33 246
GDP-MVS97.50 28397.11 30298.67 20999.02 27296.85 25298.16 17299.71 4798.32 17798.52 27798.54 30983.39 42599.95 2698.79 10099.56 25799.19 289
ZD-MVS99.01 27498.84 8599.07 28094.10 40698.05 31798.12 35296.36 24799.86 14292.70 41299.19 334
CDPH-MVS97.26 30596.66 33299.07 13499.00 27598.15 13896.03 38999.01 29691.21 44297.79 33697.85 37396.89 21399.69 30492.75 41099.38 30199.39 215
diffmvspermissive98.22 21998.24 20798.17 28799.00 27595.44 31696.38 36899.58 8597.79 22998.53 27598.50 31896.76 22599.74 27797.95 16499.64 22599.34 240
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 19098.19 21499.03 14499.00 27597.65 19696.85 33998.94 30198.57 16098.89 21698.50 31895.60 28099.85 15597.54 19699.85 10599.59 106
plane_prior698.99 27897.70 19494.90 298
xiu_mvs_v1_base_debu97.86 25798.17 21696.92 37898.98 27993.91 37496.45 36299.17 26397.85 22498.41 28697.14 40798.47 7299.92 6498.02 15699.05 34896.92 449
xiu_mvs_v1_base97.86 25798.17 21696.92 37898.98 27993.91 37496.45 36299.17 26397.85 22498.41 28697.14 40798.47 7299.92 6498.02 15699.05 34896.92 449
xiu_mvs_v1_base_debi97.86 25798.17 21696.92 37898.98 27993.91 37496.45 36299.17 26397.85 22498.41 28697.14 40798.47 7299.92 6498.02 15699.05 34896.92 449
MVP-Stereo98.08 23597.92 24798.57 22998.96 28296.79 25597.90 22299.18 25996.41 33798.46 28198.95 22295.93 27199.60 35496.51 29098.98 36299.31 253
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS98.40 19098.68 13097.54 34598.96 28297.99 15897.88 22499.36 18698.20 19399.63 6699.04 18898.76 4595.33 47296.56 28499.74 17399.31 253
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 28497.76 18898.76 33887.58 45996.75 39798.10 35494.80 30599.78 25292.73 41199.00 35799.20 284
USDC97.41 29497.40 28397.44 35498.94 28493.67 38495.17 42599.53 11294.03 40898.97 19599.10 17195.29 28999.34 42295.84 32899.73 17699.30 256
tfpn200view994.03 40193.44 40495.78 41498.93 28691.44 42197.60 27194.29 44797.94 21697.10 37594.31 45679.67 43999.62 34483.05 46198.08 41196.29 456
testdata98.09 29198.93 28695.40 31898.80 33290.08 45097.45 36298.37 33295.26 29099.70 30093.58 39298.95 36599.17 296
thres40094.14 39993.44 40496.24 40298.93 28691.44 42197.60 27194.29 44797.94 21697.10 37594.31 45679.67 43999.62 34483.05 46198.08 41197.66 437
TAPA-MVS96.21 1196.63 34095.95 35198.65 21198.93 28698.09 14596.93 33599.28 23183.58 46598.13 30897.78 37596.13 25599.40 41393.52 39399.29 31698.45 390
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test22298.92 29096.93 24995.54 41298.78 33585.72 46296.86 39298.11 35394.43 31299.10 34799.23 274
PVSNet_BlendedMVS97.55 28297.53 27697.60 33798.92 29093.77 38196.64 35199.43 16194.49 39497.62 34599.18 14996.82 21899.67 31794.73 35699.93 5599.36 233
PVSNet_Blended96.88 33096.68 32997.47 35298.92 29093.77 38194.71 43699.43 16190.98 44497.62 34597.36 40196.82 21899.67 31794.73 35699.56 25798.98 323
MSDG97.71 27097.52 27798.28 27498.91 29396.82 25394.42 44699.37 18297.65 23898.37 29198.29 34197.40 18199.33 42494.09 37899.22 32798.68 374
Anonymous20240521197.90 25097.50 27899.08 13298.90 29498.25 12898.53 12596.16 42498.87 13599.11 16698.86 24190.40 37499.78 25297.36 20999.31 31199.19 289
原ACMM198.35 26798.90 29496.25 28198.83 32992.48 42896.07 41998.10 35495.39 28899.71 29392.61 41498.99 35999.08 305
GBi-Net98.65 14998.47 16899.17 11498.90 29498.24 12999.20 4899.44 15598.59 15698.95 20199.55 5794.14 32099.86 14297.77 17899.69 20399.41 205
test198.65 14998.47 16899.17 11498.90 29498.24 12999.20 4899.44 15598.59 15698.95 20199.55 5794.14 32099.86 14297.77 17899.69 20399.41 205
FMVSNet298.49 18198.40 17898.75 19698.90 29497.14 23798.61 11699.13 27298.59 15699.19 15999.28 12094.14 32099.82 20397.97 16299.80 13899.29 258
OMC-MVS97.88 25497.49 27999.04 14398.89 29998.63 9896.94 33399.25 24095.02 38398.53 27598.51 31497.27 19099.47 40193.50 39599.51 27299.01 317
VortexMVS97.98 24798.31 19597.02 37298.88 30091.45 42098.03 19699.47 13998.65 14799.55 7699.47 7791.49 36399.81 22099.32 6099.91 7799.80 41
MVSFormer98.26 21498.43 17497.77 31498.88 30093.89 37799.39 2099.56 9999.11 9798.16 30498.13 35093.81 32899.97 799.26 6599.57 25499.43 199
lupinMVS97.06 32096.86 31697.65 33098.88 30093.89 37795.48 41697.97 37993.53 41498.16 30497.58 38793.81 32899.91 7396.77 25999.57 25499.17 296
dmvs_re95.98 36295.39 37297.74 32098.86 30397.45 20998.37 15195.69 43697.95 21496.56 40395.95 42890.70 37197.68 46688.32 44996.13 45398.11 412
DELS-MVS98.27 21298.20 21098.48 25098.86 30396.70 26195.60 41199.20 25197.73 23298.45 28298.71 27597.50 17399.82 20398.21 14199.59 24598.93 334
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 25297.98 23897.60 33798.86 30394.35 35296.21 37899.44 15597.45 26699.06 17398.88 23897.99 12699.28 43294.38 37199.58 25099.18 292
LCM-MVSNet-Re98.64 15198.48 16699.11 12598.85 30698.51 11198.49 13699.83 2598.37 17199.69 5599.46 7998.21 10599.92 6494.13 37799.30 31498.91 338
pmmvs497.58 28097.28 29198.51 24598.84 30796.93 24995.40 42098.52 35793.60 41398.61 26098.65 29395.10 29499.60 35496.97 24099.79 14498.99 322
NP-MVS98.84 30797.39 21396.84 410
sss97.21 31096.93 31098.06 29698.83 30995.22 32596.75 34598.48 35994.49 39497.27 37197.90 37092.77 34699.80 22896.57 28099.32 30999.16 299
PVSNet93.40 1795.67 37195.70 35795.57 41998.83 30988.57 44692.50 46397.72 38492.69 42696.49 41196.44 42093.72 33199.43 40993.61 39099.28 31798.71 367
MVEpermissive83.40 2292.50 42491.92 42694.25 43598.83 30991.64 41792.71 46283.52 47595.92 35886.46 47395.46 44195.20 29195.40 47180.51 46698.64 38695.73 464
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-293.78 40593.91 39793.39 44798.82 31281.72 47497.76 24495.28 43898.60 15596.54 40496.66 41465.85 46999.62 34496.65 27398.99 35998.82 348
ambc98.24 27998.82 31295.97 29298.62 11599.00 29899.27 14199.21 14296.99 20799.50 39296.55 28799.50 28099.26 268
旧先验198.82 31297.45 20998.76 33898.34 33695.50 28599.01 35699.23 274
test_vis1_rt97.75 26797.72 26297.83 30998.81 31596.35 27897.30 30899.69 5494.61 39297.87 32998.05 35996.26 25198.32 46098.74 10698.18 40398.82 348
WTY-MVS96.67 33896.27 34897.87 30798.81 31594.61 34696.77 34397.92 38194.94 38697.12 37497.74 37891.11 36799.82 20393.89 38398.15 40799.18 292
3Dnovator+97.89 398.69 13998.51 15799.24 10598.81 31598.40 11699.02 6999.19 25598.99 12098.07 31499.28 12097.11 20099.84 17396.84 25499.32 30999.47 184
QAPM97.31 30196.81 32298.82 17798.80 31897.49 20499.06 6599.19 25590.22 44897.69 34299.16 15596.91 21299.90 8090.89 43999.41 29699.07 307
VNet98.42 18798.30 19698.79 18498.79 31997.29 22098.23 16398.66 34899.31 6898.85 22598.80 25894.80 30599.78 25298.13 14699.13 34299.31 253
DPM-MVS96.32 35095.59 36398.51 24598.76 32097.21 22894.54 44598.26 36891.94 43396.37 41297.25 40393.06 34099.43 40991.42 42998.74 37598.89 340
3Dnovator98.27 298.81 11698.73 11899.05 14198.76 32097.81 18599.25 4399.30 21998.57 16098.55 27299.33 11097.95 12999.90 8097.16 22199.67 21499.44 195
PLCcopyleft94.65 1696.51 34395.73 35698.85 17398.75 32297.91 17096.42 36699.06 28190.94 44595.59 42597.38 39994.41 31399.59 35890.93 43798.04 41699.05 309
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned96.83 33296.75 32597.08 36998.74 32393.33 39096.71 34798.26 36896.72 32298.44 28397.37 40095.20 29199.47 40191.89 41997.43 43098.44 393
hse-mvs297.46 28897.07 30398.64 21398.73 32497.33 21697.45 29197.64 39199.11 9798.58 26697.98 36488.65 38999.79 24198.11 14797.39 43298.81 353
CDS-MVSNet97.69 27197.35 28898.69 20698.73 32497.02 24296.92 33798.75 34195.89 35998.59 26498.67 28892.08 35799.74 27796.72 26599.81 12799.32 249
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SD_040396.28 35295.83 35397.64 33398.72 32694.30 35398.87 8898.77 33697.80 22796.53 40598.02 36197.34 18599.47 40176.93 47099.48 28399.16 299
EIA-MVS98.00 24397.74 25998.80 18198.72 32698.09 14598.05 19299.60 7797.39 27096.63 40095.55 43697.68 15099.80 22896.73 26499.27 31898.52 385
LFMVS97.20 31196.72 32698.64 21398.72 32696.95 24798.93 8194.14 45199.74 1398.78 23799.01 20284.45 41699.73 28497.44 20599.27 31899.25 269
new_pmnet96.99 32796.76 32497.67 32698.72 32694.89 33595.95 39598.20 37192.62 42798.55 27298.54 30994.88 30199.52 38693.96 38199.44 29498.59 382
Fast-Effi-MVS+97.67 27397.38 28598.57 22998.71 33097.43 21197.23 31499.45 14794.82 38996.13 41696.51 41698.52 7099.91 7396.19 30998.83 37198.37 402
TEST998.71 33098.08 14995.96 39399.03 29091.40 43995.85 42297.53 38996.52 23899.76 264
train_agg97.10 31796.45 34299.07 13498.71 33098.08 14995.96 39399.03 29091.64 43495.85 42297.53 38996.47 24099.76 26493.67 38999.16 33799.36 233
TSAR-MVS + GP.98.18 22697.98 23898.77 19298.71 33097.88 17296.32 37298.66 34896.33 33999.23 15398.51 31497.48 17799.40 41397.16 22199.46 28599.02 316
FA-MVS(test-final)96.99 32796.82 32097.50 34998.70 33494.78 33899.34 2396.99 40795.07 38298.48 28099.33 11088.41 39299.65 33596.13 31598.92 36898.07 415
AUN-MVS96.24 35695.45 36898.60 22498.70 33497.22 22697.38 29897.65 38995.95 35795.53 43297.96 36882.11 43399.79 24196.31 30297.44 42998.80 358
our_test_397.39 29697.73 26196.34 39798.70 33489.78 44294.61 44298.97 30096.50 33099.04 18398.85 24495.98 26799.84 17397.26 21599.67 21499.41 205
ppachtmachnet_test97.50 28397.74 25996.78 38798.70 33491.23 42994.55 44499.05 28596.36 33899.21 15798.79 26096.39 24399.78 25296.74 26299.82 12199.34 240
PCF-MVS92.86 1894.36 39393.00 41198.42 25798.70 33497.56 20193.16 46199.11 27579.59 46997.55 35297.43 39692.19 35499.73 28479.85 46799.45 28797.97 421
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth97.91 24998.02 23497.58 33998.69 33994.10 36098.13 17598.90 31097.95 21497.32 37099.58 4795.95 27098.75 45596.41 29699.22 32799.87 21
ETV-MVS98.03 23997.86 25398.56 23498.69 33998.07 15197.51 28399.50 12198.10 20697.50 35795.51 43798.41 7899.88 11496.27 30599.24 32397.71 436
test_prior98.95 15998.69 33997.95 16699.03 29099.59 35899.30 256
mvsmamba97.57 28197.26 29298.51 24598.69 33996.73 26098.74 9797.25 40097.03 30497.88 32899.23 14090.95 36899.87 13396.61 27699.00 35798.91 338
agg_prior98.68 34397.99 15899.01 29695.59 42599.77 258
test_898.67 34498.01 15795.91 39999.02 29391.64 43495.79 42497.50 39296.47 24099.76 264
HQP-NCC98.67 34496.29 37496.05 35095.55 428
ACMP_Plane98.67 34496.29 37496.05 35095.55 428
CNVR-MVS98.17 22897.87 25299.07 13498.67 34498.24 12997.01 32998.93 30497.25 28497.62 34598.34 33697.27 19099.57 36796.42 29599.33 30799.39 215
HQP-MVS97.00 32696.49 34198.55 23698.67 34496.79 25596.29 37499.04 28896.05 35095.55 42896.84 41093.84 32699.54 38092.82 40799.26 32199.32 249
MM98.22 21997.99 23798.91 16698.66 34996.97 24497.89 22394.44 44599.54 4098.95 20199.14 16293.50 33299.92 6499.80 1799.96 2899.85 29
test_fmvs197.72 26997.94 24497.07 37198.66 34992.39 40797.68 25599.81 3195.20 38199.54 7899.44 8491.56 36299.41 41299.78 2199.77 15599.40 214
balanced_conf0398.63 15398.72 12098.38 26298.66 34996.68 26398.90 8399.42 16798.99 12098.97 19599.19 14595.81 27599.85 15598.77 10499.77 15598.60 379
thres20093.72 40793.14 40995.46 42398.66 34991.29 42596.61 35394.63 44497.39 27096.83 39393.71 45979.88 43699.56 37082.40 46498.13 40895.54 465
wuyk23d96.06 35897.62 27291.38 45298.65 35398.57 10598.85 9296.95 41096.86 31599.90 1499.16 15599.18 1998.40 45989.23 44799.77 15577.18 472
NCCC97.86 25797.47 28299.05 14198.61 35498.07 15196.98 33198.90 31097.63 23997.04 37997.93 36995.99 26699.66 32895.31 34498.82 37399.43 199
DeepC-MVS_fast96.85 698.30 20898.15 22098.75 19698.61 35497.23 22497.76 24499.09 27897.31 27898.75 24398.66 29197.56 16499.64 33896.10 31699.55 26199.39 215
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing393.51 40992.09 42097.75 31898.60 35694.40 35097.32 30695.26 43997.56 24996.79 39695.50 43853.57 47799.77 25895.26 34598.97 36399.08 305
thisisatest051594.12 40093.16 40896.97 37698.60 35692.90 39793.77 45790.61 46494.10 40696.91 38695.87 43174.99 45199.80 22894.52 36299.12 34598.20 408
GA-MVS95.86 36595.32 37597.49 35098.60 35694.15 35993.83 45697.93 38095.49 37196.68 39897.42 39783.21 42699.30 42896.22 30798.55 39299.01 317
dmvs_testset92.94 41992.21 41995.13 42798.59 35990.99 43297.65 26192.09 46096.95 30794.00 45293.55 46092.34 35296.97 46972.20 47192.52 46797.43 444
OPU-MVS98.82 17798.59 35998.30 12598.10 18298.52 31398.18 10798.75 45594.62 35999.48 28399.41 205
MSLP-MVS++98.02 24098.14 22297.64 33398.58 36195.19 32697.48 28799.23 24797.47 25997.90 32698.62 30097.04 20298.81 45397.55 19499.41 29698.94 333
test1298.93 16298.58 36197.83 17798.66 34896.53 40595.51 28499.69 30499.13 34299.27 262
CL-MVSNet_self_test97.44 29197.22 29598.08 29498.57 36395.78 30094.30 44998.79 33396.58 32898.60 26298.19 34894.74 30899.64 33896.41 29698.84 37098.82 348
PS-MVSNAJ97.08 31997.39 28496.16 40898.56 36492.46 40595.24 42498.85 32497.25 28497.49 35895.99 42798.07 11799.90 8096.37 29898.67 38596.12 461
CNLPA97.17 31496.71 32798.55 23698.56 36498.05 15596.33 37198.93 30496.91 31297.06 37897.39 39894.38 31599.45 40691.66 42399.18 33698.14 411
xiu_mvs_v2_base97.16 31597.49 27996.17 40698.54 36692.46 40595.45 41798.84 32597.25 28497.48 35996.49 41798.31 8999.90 8096.34 30198.68 38496.15 460
alignmvs97.35 29896.88 31598.78 18798.54 36698.09 14597.71 25197.69 38699.20 8297.59 34895.90 43088.12 39499.55 37498.18 14398.96 36498.70 370
FE-MVS95.66 37294.95 38597.77 31498.53 36895.28 32299.40 1996.09 42793.11 42097.96 32399.26 12879.10 44399.77 25892.40 41698.71 37998.27 406
Effi-MVS+98.02 24097.82 25598.62 21998.53 36897.19 23097.33 30599.68 5997.30 27996.68 39897.46 39598.56 6899.80 22896.63 27498.20 40298.86 345
baseline195.96 36395.44 36997.52 34798.51 37093.99 37198.39 14996.09 42798.21 18998.40 29097.76 37786.88 39699.63 34195.42 34289.27 47098.95 329
MVS_Test98.18 22698.36 18697.67 32698.48 37194.73 34198.18 16899.02 29397.69 23598.04 31899.11 16897.22 19499.56 37098.57 11898.90 36998.71 367
MGCFI-Net98.34 20098.28 19998.51 24598.47 37297.59 20098.96 7799.48 13099.18 9097.40 36595.50 43898.66 5499.50 39298.18 14398.71 37998.44 393
BH-RMVSNet96.83 33296.58 33797.58 33998.47 37294.05 36196.67 34997.36 39596.70 32497.87 32997.98 36495.14 29399.44 40890.47 44298.58 39199.25 269
sasdasda98.34 20098.26 20398.58 22698.46 37497.82 18298.96 7799.46 14399.19 8797.46 36095.46 44198.59 6299.46 40498.08 15098.71 37998.46 387
canonicalmvs98.34 20098.26 20398.58 22698.46 37497.82 18298.96 7799.46 14399.19 8797.46 36095.46 44198.59 6299.46 40498.08 15098.71 37998.46 387
MVS-HIRNet94.32 39495.62 36090.42 45398.46 37475.36 47796.29 37489.13 46895.25 37895.38 43499.75 1692.88 34399.19 43894.07 37999.39 29896.72 454
PHI-MVS98.29 21197.95 24299.34 8298.44 37799.16 4998.12 17999.38 17896.01 35498.06 31598.43 32697.80 14399.67 31795.69 33499.58 25099.20 284
DVP-MVS++98.90 9898.70 12799.51 4998.43 37899.15 5399.43 1599.32 20698.17 19699.26 14599.02 19198.18 10799.88 11497.07 23099.45 28799.49 165
MSC_two_6792asdad99.32 9098.43 37898.37 12098.86 32199.89 9697.14 22499.60 24199.71 62
No_MVS99.32 9098.43 37898.37 12098.86 32199.89 9697.14 22499.60 24199.71 62
Fast-Effi-MVS+-dtu98.27 21298.09 22598.81 17998.43 37898.11 14297.61 27099.50 12198.64 14897.39 36797.52 39198.12 11599.95 2696.90 24898.71 37998.38 400
OpenMVS_ROBcopyleft95.38 1495.84 36795.18 38097.81 31198.41 38297.15 23697.37 30298.62 35283.86 46498.65 25498.37 33294.29 31899.68 31388.41 44898.62 38996.60 455
DeepPCF-MVS96.93 598.32 20598.01 23599.23 10798.39 38398.97 7495.03 42999.18 25996.88 31399.33 12798.78 26298.16 11199.28 43296.74 26299.62 23499.44 195
Patchmatch-test96.55 34296.34 34497.17 36698.35 38493.06 39398.40 14897.79 38297.33 27598.41 28698.67 28883.68 42499.69 30495.16 34799.31 31198.77 361
AdaColmapbinary97.14 31696.71 32798.46 25298.34 38597.80 18696.95 33298.93 30495.58 36896.92 38497.66 38295.87 27399.53 38290.97 43699.14 34098.04 416
OpenMVScopyleft96.65 797.09 31896.68 32998.32 26998.32 38697.16 23598.86 9199.37 18289.48 45296.29 41499.15 15996.56 23699.90 8092.90 40499.20 33197.89 424
MG-MVS96.77 33596.61 33497.26 36298.31 38793.06 39395.93 39698.12 37696.45 33697.92 32498.73 27293.77 33099.39 41591.19 43499.04 35199.33 246
test_yl96.69 33696.29 34697.90 30498.28 38895.24 32397.29 30997.36 39598.21 18998.17 30197.86 37186.27 40099.55 37494.87 35398.32 39698.89 340
DCV-MVSNet96.69 33696.29 34697.90 30498.28 38895.24 32397.29 30997.36 39598.21 18998.17 30197.86 37186.27 40099.55 37494.87 35398.32 39698.89 340
CHOSEN 280x42095.51 37795.47 36695.65 41898.25 39088.27 44993.25 46098.88 31493.53 41494.65 44397.15 40686.17 40299.93 5397.41 20799.93 5598.73 366
SCA96.41 34996.66 33295.67 41698.24 39188.35 44895.85 40296.88 41396.11 34897.67 34398.67 28893.10 33899.85 15594.16 37399.22 32798.81 353
DeepMVS_CXcopyleft93.44 44698.24 39194.21 35694.34 44664.28 47291.34 46694.87 45389.45 38392.77 47377.54 46993.14 46693.35 468
MS-PatchMatch97.68 27297.75 25897.45 35398.23 39393.78 38097.29 30998.84 32596.10 34998.64 25598.65 29396.04 25999.36 41896.84 25499.14 34099.20 284
BH-w/o95.13 38394.89 38795.86 41198.20 39491.31 42495.65 40997.37 39493.64 41296.52 40795.70 43493.04 34199.02 44488.10 45095.82 45697.24 447
mvs_anonymous97.83 26598.16 21996.87 38198.18 39591.89 41497.31 30798.90 31097.37 27298.83 22899.46 7996.28 25099.79 24198.90 9398.16 40698.95 329
miper_lstm_enhance97.18 31397.16 29897.25 36398.16 39692.85 39895.15 42799.31 21197.25 28498.74 24598.78 26290.07 37599.78 25297.19 21999.80 13899.11 304
RRT-MVS97.88 25497.98 23897.61 33698.15 39793.77 38198.97 7699.64 6999.16 9298.69 24899.42 8891.60 36099.89 9697.63 18898.52 39399.16 299
ET-MVSNet_ETH3D94.30 39693.21 40797.58 33998.14 39894.47 34994.78 43593.24 45694.72 39089.56 46895.87 43178.57 44699.81 22096.91 24397.11 44198.46 387
ADS-MVSNet295.43 37894.98 38396.76 38898.14 39891.74 41597.92 21997.76 38390.23 44696.51 40898.91 22885.61 40799.85 15592.88 40596.90 44298.69 371
ADS-MVSNet95.24 38194.93 38696.18 40598.14 39890.10 44197.92 21997.32 39890.23 44696.51 40898.91 22885.61 40799.74 27792.88 40596.90 44298.69 371
c3_l97.36 29797.37 28697.31 35898.09 40193.25 39195.01 43099.16 26697.05 30198.77 24098.72 27492.88 34399.64 33896.93 24299.76 16899.05 309
FMVSNet397.50 28397.24 29498.29 27398.08 40295.83 29797.86 22898.91 30997.89 22198.95 20198.95 22287.06 39599.81 22097.77 17899.69 20399.23 274
PAPM91.88 43390.34 43696.51 39298.06 40392.56 40392.44 46497.17 40286.35 46090.38 46796.01 42686.61 39899.21 43770.65 47395.43 45897.75 433
Effi-MVS+-dtu98.26 21497.90 25099.35 7998.02 40499.49 698.02 19999.16 26698.29 18297.64 34497.99 36396.44 24299.95 2696.66 27298.93 36798.60 379
eth_miper_zixun_eth97.23 30997.25 29397.17 36698.00 40592.77 40094.71 43699.18 25997.27 28298.56 27098.74 27191.89 35899.69 30497.06 23299.81 12799.05 309
HY-MVS95.94 1395.90 36495.35 37497.55 34497.95 40694.79 33798.81 9696.94 41192.28 43195.17 43698.57 30789.90 37799.75 27291.20 43397.33 43798.10 413
UGNet98.53 17498.45 17198.79 18497.94 40796.96 24699.08 6198.54 35599.10 10496.82 39499.47 7796.55 23799.84 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 34795.70 35798.79 18497.92 40899.12 6398.28 15798.60 35392.16 43295.54 43196.17 42494.77 30799.52 38689.62 44598.23 40097.72 435
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 33196.55 33897.79 31297.91 40994.21 35697.56 27698.87 31697.49 25899.06 17399.05 18680.72 43499.80 22898.44 12799.82 12199.37 226
API-MVS97.04 32296.91 31497.42 35597.88 41098.23 13398.18 16898.50 35897.57 24797.39 36796.75 41296.77 22399.15 44190.16 44399.02 35594.88 466
myMVS_eth3d2892.92 42092.31 41694.77 43097.84 41187.59 45396.19 38096.11 42697.08 30094.27 44693.49 46266.07 46898.78 45491.78 42197.93 41997.92 423
miper_ehance_all_eth97.06 32097.03 30597.16 36897.83 41293.06 39394.66 43999.09 27895.99 35598.69 24898.45 32492.73 34899.61 35196.79 25699.03 35298.82 348
cl____97.02 32396.83 31997.58 33997.82 41394.04 36394.66 43999.16 26697.04 30298.63 25698.71 27588.68 38899.69 30497.00 23599.81 12799.00 321
DIV-MVS_self_test97.02 32396.84 31897.58 33997.82 41394.03 36494.66 43999.16 26697.04 30298.63 25698.71 27588.69 38699.69 30497.00 23599.81 12799.01 317
CANet97.87 25697.76 25798.19 28697.75 41595.51 30896.76 34499.05 28597.74 23196.93 38398.21 34695.59 28199.89 9697.86 17399.93 5599.19 289
UBG93.25 41492.32 41596.04 41097.72 41690.16 44095.92 39895.91 43196.03 35393.95 45493.04 46569.60 45899.52 38690.72 44197.98 41798.45 390
mvsany_test197.60 27797.54 27597.77 31497.72 41695.35 31995.36 42197.13 40494.13 40599.71 4999.33 11097.93 13099.30 42897.60 19298.94 36698.67 375
PVSNet_089.98 2191.15 43490.30 43793.70 44397.72 41684.34 46790.24 46797.42 39390.20 44993.79 45593.09 46490.90 37098.89 45286.57 45672.76 47397.87 426
CR-MVSNet96.28 35295.95 35197.28 36097.71 41994.22 35498.11 18098.92 30792.31 43096.91 38699.37 9885.44 41099.81 22097.39 20897.36 43597.81 429
RPMNet97.02 32396.93 31097.30 35997.71 41994.22 35498.11 18099.30 21999.37 6096.91 38699.34 10786.72 39799.87 13397.53 19797.36 43597.81 429
ETVMVS92.60 42391.08 43297.18 36497.70 42193.65 38696.54 35695.70 43496.51 32994.68 44292.39 46861.80 47499.50 39286.97 45397.41 43198.40 398
pmmvs395.03 38594.40 39296.93 37797.70 42192.53 40495.08 42897.71 38588.57 45697.71 34098.08 35779.39 44199.82 20396.19 30999.11 34698.43 395
baseline293.73 40692.83 41296.42 39597.70 42191.28 42696.84 34089.77 46793.96 41092.44 46295.93 42979.14 44299.77 25892.94 40396.76 44698.21 407
WBMVS95.18 38294.78 38896.37 39697.68 42489.74 44395.80 40498.73 34497.54 25398.30 29298.44 32570.06 45699.82 20396.62 27599.87 9699.54 140
tpm94.67 39094.34 39495.66 41797.68 42488.42 44797.88 22494.90 44194.46 39696.03 42198.56 30878.66 44499.79 24195.88 32295.01 46098.78 360
CANet_DTU97.26 30597.06 30497.84 30897.57 42694.65 34596.19 38098.79 33397.23 29095.14 43798.24 34393.22 33599.84 17397.34 21099.84 11099.04 313
testing1193.08 41792.02 42296.26 40197.56 42790.83 43596.32 37295.70 43496.47 33392.66 46193.73 45864.36 47299.59 35893.77 38897.57 42498.37 402
tpm293.09 41692.58 41494.62 43297.56 42786.53 45697.66 25995.79 43386.15 46194.07 45198.23 34575.95 44999.53 38290.91 43896.86 44597.81 429
testing9193.32 41292.27 41796.47 39497.54 42991.25 42796.17 38496.76 41597.18 29493.65 45793.50 46165.11 47199.63 34193.04 40297.45 42898.53 384
TR-MVS95.55 37595.12 38196.86 38497.54 42993.94 37296.49 36196.53 42094.36 40197.03 38196.61 41594.26 31999.16 44086.91 45596.31 45097.47 443
testing9993.04 41891.98 42596.23 40397.53 43190.70 43796.35 37095.94 43096.87 31493.41 45893.43 46363.84 47399.59 35893.24 40097.19 43898.40 398
131495.74 36995.60 36196.17 40697.53 43192.75 40198.07 18998.31 36791.22 44194.25 44796.68 41395.53 28299.03 44391.64 42597.18 43996.74 453
CostFormer93.97 40293.78 40094.51 43397.53 43185.83 45997.98 21195.96 42989.29 45494.99 43998.63 29878.63 44599.62 34494.54 36196.50 44798.09 414
FMVSNet596.01 36095.20 37998.41 25897.53 43196.10 28398.74 9799.50 12197.22 29398.03 31999.04 18869.80 45799.88 11497.27 21499.71 19399.25 269
PMMVS96.51 34395.98 35098.09 29197.53 43195.84 29694.92 43298.84 32591.58 43696.05 42095.58 43595.68 27899.66 32895.59 33898.09 41098.76 363
reproduce_monomvs95.00 38795.25 37694.22 43697.51 43683.34 46897.86 22898.44 36098.51 16599.29 13799.30 11667.68 46299.56 37098.89 9599.81 12799.77 49
PAPR95.29 37994.47 39097.75 31897.50 43795.14 32894.89 43398.71 34691.39 44095.35 43595.48 44094.57 31099.14 44284.95 45897.37 43398.97 326
testing22291.96 43190.37 43596.72 38997.47 43892.59 40296.11 38694.76 44296.83 31692.90 46092.87 46657.92 47599.55 37486.93 45497.52 42598.00 420
PatchT96.65 33996.35 34397.54 34597.40 43995.32 32197.98 21196.64 41799.33 6596.89 39099.42 8884.32 41899.81 22097.69 18797.49 42697.48 442
tpm cat193.29 41393.13 41093.75 44297.39 44084.74 46297.39 29697.65 38983.39 46694.16 44898.41 32782.86 42999.39 41591.56 42795.35 45997.14 448
PatchmatchNetpermissive95.58 37495.67 35995.30 42697.34 44187.32 45497.65 26196.65 41695.30 37797.07 37798.69 28484.77 41399.75 27294.97 35198.64 38698.83 347
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry97.35 29896.97 30898.50 24997.31 44296.47 27498.18 16898.92 30798.95 12798.78 23799.37 9885.44 41099.85 15595.96 32099.83 11799.17 296
LS3D98.63 15398.38 18399.36 7397.25 44399.38 1399.12 6099.32 20699.21 8098.44 28398.88 23897.31 18699.80 22896.58 27899.34 30698.92 335
IB-MVS91.63 1992.24 42990.90 43396.27 40097.22 44491.24 42894.36 44893.33 45592.37 42992.24 46494.58 45566.20 46799.89 9693.16 40194.63 46297.66 437
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 42691.76 42994.21 43797.16 44584.65 46395.42 41988.45 46995.96 35696.17 41595.84 43366.36 46599.71 29391.87 42098.64 38698.28 405
tpmrst95.07 38495.46 36793.91 44097.11 44684.36 46697.62 26696.96 40994.98 38496.35 41398.80 25885.46 40999.59 35895.60 33796.23 45197.79 432
Syy-MVS96.04 35995.56 36597.49 35097.10 44794.48 34896.18 38296.58 41895.65 36594.77 44092.29 46991.27 36699.36 41898.17 14598.05 41498.63 377
myMVS_eth3d91.92 43290.45 43496.30 39897.10 44790.90 43396.18 38296.58 41895.65 36594.77 44092.29 46953.88 47699.36 41889.59 44698.05 41498.63 377
MDTV_nov1_ep1395.22 37897.06 44983.20 46997.74 24896.16 42494.37 40096.99 38298.83 25183.95 42299.53 38293.90 38297.95 418
MVS93.19 41592.09 42096.50 39396.91 45094.03 36498.07 18998.06 37868.01 47194.56 44596.48 41895.96 26999.30 42883.84 46096.89 44496.17 458
E-PMN94.17 39894.37 39393.58 44496.86 45185.71 46090.11 46997.07 40598.17 19697.82 33597.19 40484.62 41598.94 44889.77 44497.68 42396.09 462
JIA-IIPM95.52 37695.03 38297.00 37396.85 45294.03 36496.93 33595.82 43299.20 8294.63 44499.71 2283.09 42799.60 35494.42 36794.64 46197.36 446
EMVS93.83 40494.02 39693.23 44996.83 45384.96 46189.77 47096.32 42297.92 21897.43 36496.36 42386.17 40298.93 44987.68 45197.73 42295.81 463
cl2295.79 36895.39 37296.98 37596.77 45492.79 39994.40 44798.53 35694.59 39397.89 32798.17 34982.82 43099.24 43496.37 29899.03 35298.92 335
WB-MVSnew95.73 37095.57 36496.23 40396.70 45590.70 43796.07 38893.86 45295.60 36797.04 37995.45 44496.00 26299.55 37491.04 43598.31 39898.43 395
dp93.47 41093.59 40393.13 45096.64 45681.62 47597.66 25996.42 42192.80 42596.11 41798.64 29678.55 44799.59 35893.31 39892.18 46998.16 410
MonoMVSNet96.25 35496.53 34095.39 42496.57 45791.01 43198.82 9597.68 38898.57 16098.03 31999.37 9890.92 36997.78 46594.99 34993.88 46597.38 445
test-LLR93.90 40393.85 39894.04 43896.53 45884.62 46494.05 45392.39 45896.17 34594.12 44995.07 44582.30 43199.67 31795.87 32598.18 40397.82 427
test-mter92.33 42891.76 42994.04 43896.53 45884.62 46494.05 45392.39 45894.00 40994.12 44995.07 44565.63 47099.67 31795.87 32598.18 40397.82 427
TESTMET0.1,192.19 43091.77 42893.46 44596.48 46082.80 47194.05 45391.52 46394.45 39894.00 45294.88 45166.65 46499.56 37095.78 33098.11 40998.02 417
MGCNet97.44 29197.01 30798.72 20296.42 46196.74 25997.20 31991.97 46198.46 16898.30 29298.79 26092.74 34799.91 7399.30 6299.94 4999.52 152
miper_enhance_ethall96.01 36095.74 35596.81 38596.41 46292.27 41193.69 45898.89 31391.14 44398.30 29297.35 40290.58 37299.58 36596.31 30299.03 35298.60 379
tpmvs95.02 38695.25 37694.33 43496.39 46385.87 45798.08 18596.83 41495.46 37295.51 43398.69 28485.91 40599.53 38294.16 37396.23 45197.58 440
CMPMVSbinary75.91 2396.29 35195.44 36998.84 17496.25 46498.69 9797.02 32899.12 27388.90 45597.83 33398.86 24189.51 38198.90 45191.92 41899.51 27298.92 335
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 194.51 39193.69 40196.99 37496.05 46593.61 38894.97 43193.49 45396.17 34597.57 35194.88 45182.30 43199.01 44693.60 39194.17 46498.37 402
EPMVS93.72 40793.27 40695.09 42996.04 46687.76 45198.13 17585.01 47494.69 39196.92 38498.64 29678.47 44899.31 42695.04 34896.46 44898.20 408
cascas94.79 38994.33 39596.15 40996.02 46792.36 40992.34 46599.26 23985.34 46395.08 43894.96 45092.96 34298.53 45894.41 37098.59 39097.56 441
MVStest195.86 36595.60 36196.63 39095.87 46891.70 41697.93 21698.94 30198.03 20899.56 7399.66 3271.83 45498.26 46199.35 5899.24 32399.91 13
gg-mvs-nofinetune92.37 42791.20 43195.85 41295.80 46992.38 40899.31 3081.84 47699.75 1191.83 46599.74 1868.29 45999.02 44487.15 45297.12 44096.16 459
gm-plane-assit94.83 47081.97 47388.07 45894.99 44899.60 35491.76 422
GG-mvs-BLEND94.76 43194.54 47192.13 41399.31 3080.47 47788.73 47191.01 47167.59 46398.16 46482.30 46594.53 46393.98 467
UWE-MVS-2890.22 43589.28 43893.02 45194.50 47282.87 47096.52 35987.51 47095.21 38092.36 46396.04 42571.57 45598.25 46272.04 47297.77 42197.94 422
EPNet_dtu94.93 38894.78 38895.38 42593.58 47387.68 45296.78 34295.69 43697.35 27489.14 47098.09 35688.15 39399.49 39594.95 35299.30 31498.98 323
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai76.24 43975.95 44277.12 45692.39 47467.91 48090.16 46859.44 48182.04 46789.42 46994.67 45449.68 47881.74 47448.06 47477.66 47281.72 470
KD-MVS_2432*160092.87 42191.99 42395.51 42191.37 47589.27 44494.07 45198.14 37495.42 37397.25 37296.44 42067.86 46099.24 43491.28 43196.08 45498.02 417
miper_refine_blended92.87 42191.99 42395.51 42191.37 47589.27 44494.07 45198.14 37495.42 37397.25 37296.44 42067.86 46099.24 43491.28 43196.08 45498.02 417
EPNet96.14 35795.44 36998.25 27790.76 47795.50 31197.92 21994.65 44398.97 12392.98 45998.85 24489.12 38499.87 13395.99 31899.68 20899.39 215
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan69.30 44068.95 44370.34 45787.68 47865.00 48191.11 46659.90 48069.02 47074.46 47588.89 47248.58 47968.03 47628.61 47572.33 47477.99 471
test_method79.78 43779.50 44080.62 45480.21 47945.76 48270.82 47198.41 36431.08 47480.89 47497.71 37984.85 41297.37 46791.51 42880.03 47198.75 364
tmp_tt78.77 43878.73 44178.90 45558.45 48074.76 47994.20 45078.26 47839.16 47386.71 47292.82 46780.50 43575.19 47586.16 45792.29 46886.74 469
testmvs17.12 44220.53 4456.87 45912.05 4814.20 48493.62 4596.73 4824.62 47710.41 47724.33 4748.28 4813.56 4789.69 47715.07 47512.86 474
test12317.04 44320.11 4467.82 45810.25 4824.91 48394.80 4344.47 4834.93 47610.00 47824.28 4759.69 4803.64 47710.14 47612.43 47614.92 473
mmdepth0.00 4460.00 4490.00 4600.00 4830.00 4850.00 4720.00 4840.00 4780.00 4790.00 4780.00 4820.00 4790.00 4780.00 4770.00 475
monomultidepth0.00 4460.00 4490.00 4600.00 4830.00 4850.00 4720.00 4840.00 4780.00 4790.00 4780.00 4820.00 4790.00 4780.00 4770.00 475
test_blank0.00 4460.00 4490.00 4600.00 4830.00 4850.00 4720.00 4840.00 4780.00 4790.00 4780.00 4820.00 4790.00 4780.00 4770.00 475
eth-test20.00 483
eth-test0.00 483
uanet_test0.00 4460.00 4490.00 4600.00 4830.00 4850.00 4720.00 4840.00 4780.00 4790.00 4780.00 4820.00 4790.00 4780.00 4770.00 475
DCPMVS0.00 4460.00 4490.00 4600.00 4830.00 4850.00 4720.00 4840.00 4780.00 4790.00 4780.00 4820.00 4790.00 4780.00 4770.00 475
cdsmvs_eth3d_5k24.66 44132.88 4440.00 4600.00 4830.00 4850.00 47299.10 2760.00 4780.00 47997.58 38799.21 180.00 4790.00 4780.00 4770.00 475
pcd_1.5k_mvsjas8.17 44410.90 4470.00 4600.00 4830.00 4850.00 4720.00 4840.00 4780.00 4790.00 47898.07 1170.00 4790.00 4780.00 4770.00 475
sosnet-low-res0.00 4460.00 4490.00 4600.00 4830.00 4850.00 4720.00 4840.00 4780.00 4790.00 4780.00 4820.00 4790.00 4780.00 4770.00 475
sosnet0.00 4460.00 4490.00 4600.00 4830.00 4850.00 4720.00 4840.00 4780.00 4790.00 4780.00 4820.00 4790.00 4780.00 4770.00 475
uncertanet0.00 4460.00 4490.00 4600.00 4830.00 4850.00 4720.00 4840.00 4780.00 4790.00 4780.00 4820.00 4790.00 4780.00 4770.00 475
Regformer0.00 4460.00 4490.00 4600.00 4830.00 4850.00 4720.00 4840.00 4780.00 4790.00 4780.00 4820.00 4790.00 4780.00 4770.00 475
ab-mvs-re8.12 44510.83 4480.00 4600.00 4830.00 4850.00 4720.00 4840.00 4780.00 47997.48 3930.00 4820.00 4790.00 4780.00 4770.00 475
uanet0.00 4460.00 4490.00 4600.00 4830.00 4850.00 4720.00 4840.00 4780.00 4790.00 4780.00 4820.00 4790.00 4780.00 4770.00 475
TestfortrainingZip98.68 107
WAC-MVS90.90 43391.37 430
PC_three_145293.27 41799.40 11398.54 30998.22 10397.00 46895.17 34699.45 28799.49 165
test_241102_TWO99.30 21998.03 20899.26 14599.02 19197.51 17299.88 11496.91 24399.60 24199.66 77
test_0728_THIRD98.17 19699.08 17199.02 19197.89 13499.88 11497.07 23099.71 19399.70 67
GSMVS98.81 353
sam_mvs184.74 41498.81 353
sam_mvs84.29 420
MTGPAbinary99.20 251
test_post197.59 27320.48 47783.07 42899.66 32894.16 373
test_post21.25 47683.86 42399.70 300
patchmatchnet-post98.77 26484.37 41799.85 155
MTMP97.93 21691.91 462
test9_res93.28 39999.15 33999.38 224
agg_prior292.50 41599.16 33799.37 226
test_prior497.97 16295.86 400
test_prior295.74 40796.48 33296.11 41797.63 38595.92 27294.16 37399.20 331
旧先验295.76 40688.56 45797.52 35599.66 32894.48 363
新几何295.93 396
无先验95.74 40798.74 34389.38 45399.73 28492.38 41799.22 279
原ACMM295.53 413
testdata299.79 24192.80 409
segment_acmp97.02 205
testdata195.44 41896.32 340
plane_prior599.27 23499.70 30094.42 36799.51 27299.45 191
plane_prior497.98 364
plane_prior397.78 18797.41 26897.79 336
plane_prior297.77 24198.20 193
plane_prior97.65 19697.07 32796.72 32299.36 302
n20.00 484
nn0.00 484
door-mid99.57 92
test1198.87 316
door99.41 171
HQP5-MVS96.79 255
BP-MVS92.82 407
HQP4-MVS95.56 42799.54 38099.32 249
HQP3-MVS99.04 28899.26 321
HQP2-MVS93.84 326
MDTV_nov1_ep13_2view74.92 47897.69 25490.06 45197.75 33985.78 40693.52 39398.69 371
ACMMP++_ref99.77 155
ACMMP++99.68 208
Test By Simon96.52 238