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 bysort bysort bysort bysort bysort bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort by
CS-MVS99.50 3199.48 2299.54 12599.76 8299.42 11899.90 199.55 10098.56 11899.78 8199.70 21298.65 7499.79 24199.65 4199.78 13499.41 260
mmtdpeth96.95 37696.71 37597.67 39699.33 28794.90 42399.89 299.28 34398.15 17599.72 10298.57 43286.56 43499.90 14899.82 2989.02 46098.20 427
SPE-MVS-test99.49 3399.48 2299.54 12599.78 7099.30 13899.89 299.58 7898.56 11899.73 9799.69 22398.55 8199.82 22399.69 3599.85 9499.48 239
MVSFormer99.17 10999.12 9799.29 20399.51 22598.94 19799.88 499.46 23397.55 27399.80 7499.65 24497.39 12599.28 36299.03 13099.85 9499.65 171
test_djsdf98.67 21098.57 21198.98 24198.70 41798.91 20499.88 499.46 23397.55 27399.22 25499.88 5395.73 21999.28 36299.03 13097.62 32198.75 331
OurMVSNet-221017-097.88 29297.77 28398.19 35598.71 41696.53 37699.88 499.00 38697.79 24398.78 33699.94 691.68 37199.35 35297.21 33996.99 35798.69 348
EC-MVSNet99.44 5099.39 4099.58 11699.56 20499.49 10999.88 499.58 7898.38 13799.73 9799.69 22398.20 10399.70 28299.64 4399.82 11799.54 215
DVP-MVS++99.59 1599.50 1999.88 1599.51 22599.88 1099.87 899.51 15298.99 6999.88 4399.81 13099.27 799.96 4198.85 16299.80 12599.81 79
FOURS199.91 199.93 199.87 899.56 9099.10 4899.81 69
K. test v397.10 37396.79 37398.01 36898.72 41496.33 38399.87 897.05 46497.59 26796.16 44099.80 14888.71 41199.04 40596.69 37196.55 36398.65 372
FC-MVSNet-test98.75 20398.62 20499.15 22599.08 35699.45 11599.86 1199.60 6798.23 16598.70 34899.82 11596.80 16299.22 37699.07 12596.38 36698.79 321
v7n97.87 29497.52 31298.92 25298.76 41098.58 24899.84 1299.46 23396.20 38998.91 31499.70 21294.89 25799.44 33296.03 38893.89 42498.75 331
DTE-MVSNet97.51 34997.19 35898.46 32698.63 42398.13 28199.84 1299.48 20096.68 35197.97 40299.67 23792.92 33498.56 43996.88 36492.60 44298.70 344
3Dnovator97.25 999.24 9799.05 11299.81 6099.12 34599.66 7199.84 1299.74 1399.09 5598.92 31399.90 3395.94 20699.98 2098.95 14299.92 3999.79 92
FIs98.78 19898.63 19999.23 21599.18 32999.54 9899.83 1599.59 7398.28 15098.79 33599.81 13096.75 16599.37 34599.08 12496.38 36698.78 323
MGCFI-Net99.01 16298.85 17099.50 14999.42 25999.26 14499.82 1699.48 20098.60 11599.28 23698.81 42197.04 14799.76 25399.29 9197.87 31099.47 245
test_fmvs392.10 43091.77 43393.08 44596.19 46186.25 46599.82 1698.62 43896.65 35495.19 44896.90 46555.05 47995.93 47296.63 37690.92 45197.06 461
jajsoiax98.43 22498.28 23198.88 26598.60 42798.43 26799.82 1699.53 12598.19 17098.63 36099.80 14893.22 32999.44 33299.22 10097.50 33398.77 327
OpenMVScopyleft96.50 1698.47 22198.12 24299.52 13999.04 36499.53 10199.82 1699.72 1494.56 42998.08 39599.88 5394.73 26999.98 2097.47 32499.76 14099.06 302
SDMVSNet99.11 13798.90 15699.75 7799.81 5799.59 8899.81 2099.65 3998.78 9899.64 14099.88 5394.56 28199.93 11099.67 3798.26 28899.72 133
nrg03098.64 21498.42 22199.28 20799.05 36299.69 6399.81 2099.46 23398.04 21299.01 29699.82 11596.69 16799.38 34299.34 8194.59 41198.78 323
HPM-MVScopyleft99.42 5599.28 6999.83 5699.90 499.72 5699.81 2099.54 10997.59 26799.68 11599.63 25698.91 3999.94 9298.58 20699.91 4699.84 53
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EPP-MVSNet99.13 12398.99 13499.53 13399.65 15699.06 17199.81 2099.33 31897.43 29099.60 15599.88 5397.14 13899.84 19699.13 11598.94 23799.69 150
3Dnovator+97.12 1399.18 10498.97 13899.82 5799.17 33799.68 6499.81 2099.51 15299.20 3398.72 34199.89 4295.68 22199.97 2998.86 16099.86 8799.81 79
sasdasda99.02 15898.86 16799.51 14499.42 25999.32 13199.80 2599.48 20098.63 11099.31 22898.81 42197.09 14399.75 25699.27 9597.90 30799.47 245
FA-MVS(test-final)98.75 20398.53 21599.41 17699.55 20899.05 17399.80 2599.01 38596.59 36499.58 15999.59 27095.39 23199.90 14897.78 29099.49 17799.28 277
GeoE98.85 18998.62 20499.53 13399.61 18599.08 16899.80 2599.51 15297.10 32299.31 22899.78 17295.23 24299.77 24998.21 24699.03 23199.75 109
canonicalmvs99.02 15898.86 16799.51 14499.42 25999.32 13199.80 2599.48 20098.63 11099.31 22898.81 42197.09 14399.75 25699.27 9597.90 30799.47 245
v897.95 28397.63 30298.93 25098.95 37998.81 22699.80 2599.41 26996.03 40399.10 27999.42 32894.92 25499.30 36096.94 35994.08 42198.66 370
Vis-MVSNet (Re-imp)98.87 17798.72 18599.31 19599.71 11798.88 20899.80 2599.44 25397.91 22599.36 21899.78 17295.49 22899.43 33697.91 27599.11 21899.62 186
Anonymous2024052196.20 39295.89 39597.13 41497.72 44894.96 42299.79 3199.29 34193.01 44597.20 42599.03 40089.69 40198.36 44391.16 45196.13 37298.07 434
PS-MVSNAJss98.92 17198.92 15198.90 25898.78 40398.53 25299.78 3299.54 10998.07 19899.00 30099.76 18599.01 2099.37 34599.13 11597.23 35098.81 320
PEN-MVS97.76 31597.44 32898.72 29198.77 40898.54 25199.78 3299.51 15297.06 32698.29 38599.64 25092.63 34798.89 43098.09 25993.16 43498.72 337
anonymousdsp98.44 22398.28 23198.94 24898.50 43398.96 18799.77 3499.50 17597.07 32498.87 32299.77 18194.76 26799.28 36298.66 19297.60 32298.57 398
SixPastTwentyTwo97.50 35097.33 34698.03 36598.65 42196.23 38899.77 3498.68 43497.14 31597.90 40599.93 1090.45 39099.18 38497.00 35396.43 36598.67 361
QAPM98.67 21098.30 23099.80 6499.20 32399.67 6899.77 3499.72 1494.74 42698.73 34099.90 3395.78 21799.98 2096.96 35799.88 7699.76 107
SSC-MVS92.73 42993.73 42289.72 45595.02 47281.38 47599.76 3799.23 35394.87 42392.80 46298.93 41394.71 27191.37 47974.49 47893.80 42596.42 465
test_vis3_rt87.04 43785.81 44090.73 45293.99 47681.96 47399.76 3790.23 48792.81 44881.35 47591.56 47540.06 48399.07 40294.27 42288.23 46291.15 475
dcpmvs_299.23 9899.58 998.16 35799.83 4794.68 42899.76 3799.52 13099.07 5899.98 1399.88 5398.56 8099.93 11099.67 3799.98 499.87 40
RRT-MVS98.91 17298.75 18199.39 18299.46 24998.61 24699.76 3799.50 17598.06 20299.81 6999.88 5393.91 31399.94 9299.11 11899.27 19499.61 188
HPM-MVS_fast99.51 2999.40 3899.85 4399.91 199.79 4199.76 3799.56 9097.72 25299.76 9199.75 19099.13 1499.92 12399.07 12599.92 3999.85 46
lecture99.60 1499.50 1999.89 1199.89 899.90 399.75 4299.59 7399.06 6199.88 4399.85 8198.41 9399.96 4199.28 9299.84 10299.83 63
MVSMamba_PlusPlus99.46 4299.41 3799.64 10199.68 13299.50 10899.75 4299.50 17598.27 15299.87 4999.92 1898.09 10899.94 9299.65 4199.95 2399.47 245
v1097.85 29797.52 31298.86 27298.99 37298.67 23799.75 4299.41 26995.70 40798.98 30399.41 33294.75 26899.23 37296.01 39094.63 41098.67 361
APDe-MVScopyleft99.66 699.57 1099.92 199.77 7899.89 699.75 4299.56 9099.02 6299.88 4399.85 8199.18 1299.96 4199.22 10099.92 3999.90 25
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
IS-MVSNet99.05 15498.87 16499.57 12099.73 10799.32 13199.75 4299.20 35998.02 21799.56 16399.86 7496.54 17799.67 29098.09 25999.13 21199.73 123
test_vis1_n97.92 28797.44 32899.34 18799.53 21698.08 28499.74 4799.49 18899.15 38100.00 199.94 679.51 46699.98 2099.88 2699.76 14099.97 4
test_fmvs1_n98.41 22798.14 23999.21 21699.82 5397.71 31099.74 4799.49 18899.32 2999.99 299.95 385.32 44499.97 2999.82 2999.84 10299.96 7
balanced_conf0399.46 4299.39 4099.67 9099.55 20899.58 9399.74 4799.51 15298.42 13499.87 4999.84 9698.05 11199.91 13599.58 4799.94 3199.52 222
tttt051798.42 22598.14 23999.28 20799.66 14898.38 27099.74 4796.85 46697.68 25899.79 7699.74 19591.39 37999.89 16398.83 16899.56 17099.57 209
WB-MVS93.10 42794.10 41890.12 45495.51 46981.88 47499.73 5199.27 34695.05 41893.09 46198.91 41794.70 27291.89 47876.62 47694.02 42396.58 464
test_fmvs297.25 36797.30 34997.09 41699.43 25793.31 45099.73 5198.87 40898.83 8899.28 23699.80 14884.45 44999.66 29397.88 27797.45 33898.30 420
SD_040397.55 34497.53 31197.62 39899.61 18593.64 44799.72 5399.44 25398.03 21498.62 36399.39 34096.06 19899.57 31487.88 46499.01 23499.66 165
MonoMVSNet98.38 23198.47 21998.12 36298.59 42996.19 39099.72 5398.79 41997.89 22799.44 19099.52 29896.13 19598.90 42998.64 19497.54 32899.28 277
baseline99.15 11599.02 12599.53 13399.66 14899.14 16099.72 5399.48 20098.35 14299.42 19699.84 9696.07 19799.79 24199.51 5699.14 20899.67 160
RPSCF98.22 24298.62 20496.99 41899.82 5391.58 45999.72 5399.44 25396.61 35999.66 12699.89 4295.92 20799.82 22397.46 32599.10 22599.57 209
CSCG99.32 7999.32 5499.32 19399.85 3198.29 27299.71 5799.66 3298.11 18999.41 20199.80 14898.37 9699.96 4198.99 13499.96 1799.72 133
dmvs_re98.08 25998.16 23697.85 38399.55 20894.67 42999.70 5898.92 39698.15 17599.06 29099.35 35293.67 32199.25 36997.77 29397.25 34999.64 178
WR-MVS_H98.13 25397.87 27398.90 25899.02 36698.84 21899.70 5899.59 7397.27 30498.40 37799.19 38495.53 22699.23 37298.34 23693.78 42698.61 392
mvsmamba99.06 15098.96 14299.36 18499.47 24798.64 24199.70 5899.05 38097.61 26699.65 13599.83 10296.54 17799.92 12399.19 10499.62 16599.51 231
LTVRE_ROB97.16 1298.02 27197.90 26898.40 33699.23 31696.80 36599.70 5899.60 6797.12 31898.18 39299.70 21291.73 37099.72 26998.39 22997.45 33898.68 353
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
MED-MVS test99.87 2199.88 1399.81 3399.69 6299.87 699.34 2699.90 3499.83 10299.95 7698.83 16899.89 6899.83 63
MED-MVS99.66 699.60 899.87 2199.88 1399.81 3399.69 6299.87 699.18 3499.90 3499.83 10299.30 499.95 7698.83 16899.89 6899.83 63
TestfortrainingZip a99.73 199.67 199.92 199.88 1399.91 299.69 6299.87 699.34 2699.90 3499.83 10299.30 499.95 7699.32 8499.89 6899.90 25
TestfortrainingZip99.69 62
test_f91.90 43191.26 43593.84 44195.52 46885.92 46699.69 6298.53 44295.31 41293.87 45596.37 46855.33 47898.27 44495.70 39690.98 45097.32 460
XVS99.53 2799.42 3299.87 2199.85 3199.83 2299.69 6299.68 2498.98 7299.37 21299.74 19598.81 4999.94 9298.79 17699.86 8799.84 53
X-MVStestdata96.55 38495.45 40399.87 2199.85 3199.83 2299.69 6299.68 2498.98 7299.37 21264.01 48498.81 4999.94 9298.79 17699.86 8799.84 53
V4298.06 26197.79 27898.86 27298.98 37598.84 21899.69 6299.34 31096.53 36699.30 23299.37 34694.67 27499.32 35797.57 31494.66 40998.42 412
mPP-MVS99.44 5099.30 6299.86 3499.88 1399.79 4199.69 6299.48 20098.12 18799.50 17799.75 19098.78 5399.97 2998.57 20999.89 6899.83 63
CP-MVS99.45 4699.32 5499.85 4399.83 4799.75 5199.69 6299.52 13098.07 19899.53 17299.63 25698.93 3899.97 2998.74 18099.91 4699.83 63
FE-MVS98.48 22098.17 23599.40 17799.54 21598.96 18799.68 7298.81 41595.54 40999.62 14799.70 21293.82 31699.93 11097.35 33399.46 17899.32 274
PS-CasMVS97.93 28497.59 30698.95 24698.99 37299.06 17199.68 7299.52 13097.13 31698.31 38299.68 23192.44 35699.05 40498.51 21794.08 42198.75 331
Vis-MVSNetpermissive99.12 13198.97 13899.56 12299.78 7099.10 16499.68 7299.66 3298.49 12599.86 5399.87 6694.77 26699.84 19699.19 10499.41 18299.74 114
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
KinetiMVS99.12 13198.92 15199.70 8799.67 13599.40 12199.67 7599.63 4698.73 10299.94 2899.81 13094.54 28499.96 4198.40 22899.93 3399.74 114
BP-MVS199.12 13198.94 14899.65 9599.51 22599.30 13899.67 7598.92 39698.48 12699.84 5699.69 22394.96 24999.92 12399.62 4499.79 13299.71 144
test_vis1_n_192098.63 21598.40 22399.31 19599.86 2597.94 29799.67 7599.62 5199.43 1799.99 299.91 2687.29 429100.00 199.92 2499.92 3999.98 2
EIA-MVS99.18 10499.09 10499.45 16599.49 23999.18 15299.67 7599.53 12597.66 26199.40 20699.44 32498.10 10799.81 22898.94 14399.62 16599.35 269
MSP-MVS99.42 5599.27 7399.88 1599.89 899.80 3899.67 7599.50 17598.70 10699.77 8599.49 30898.21 10299.95 7698.46 22399.77 13799.88 35
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
MVS_Test99.10 14298.97 13899.48 15699.49 23999.14 16099.67 7599.34 31097.31 30199.58 15999.76 18597.65 12199.82 22398.87 15599.07 22899.46 250
CP-MVSNet98.09 25797.78 28199.01 23798.97 37799.24 14799.67 7599.46 23397.25 30698.48 37499.64 25093.79 31799.06 40398.63 19694.10 42098.74 335
MTAPA99.52 2899.39 4099.89 1199.90 499.86 1899.66 8299.47 22298.79 9599.68 11599.81 13098.43 8999.97 2998.88 15299.90 5799.83 63
HFP-MVS99.49 3399.37 4499.86 3499.87 2099.80 3899.66 8299.67 2798.15 17599.68 11599.69 22399.06 1899.96 4198.69 18899.87 7999.84 53
mvs_tets98.40 23098.23 23398.91 25698.67 42098.51 25899.66 8299.53 12598.19 17098.65 35799.81 13092.75 33899.44 33299.31 8697.48 33798.77 327
EU-MVSNet97.98 27898.03 25497.81 38998.72 41496.65 37299.66 8299.66 3298.09 19398.35 38099.82 11595.25 24098.01 45097.41 32995.30 39798.78 323
ACMMPR99.49 3399.36 4699.86 3499.87 2099.79 4199.66 8299.67 2798.15 17599.67 12199.69 22398.95 3299.96 4198.69 18899.87 7999.84 53
MP-MVScopyleft99.33 7799.15 9399.87 2199.88 1399.82 2899.66 8299.46 23398.09 19399.48 18199.74 19598.29 9999.96 4197.93 27499.87 7999.82 72
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
NormalMVS99.27 8999.19 8899.52 13999.89 898.83 22199.65 8899.52 13099.10 4899.84 5699.76 18595.80 21599.99 499.30 8999.84 10299.74 114
SymmetryMVS99.15 11599.02 12599.52 13999.72 11198.83 22199.65 8899.34 31099.10 4899.84 5699.76 18595.80 21599.99 499.30 8998.72 25899.73 123
Elysia98.88 17498.65 19699.58 11699.58 19599.34 12799.65 8899.52 13098.26 15599.83 6499.87 6693.37 32499.90 14897.81 28799.91 4699.49 236
StellarMVS98.88 17498.65 19699.58 11699.58 19599.34 12799.65 8899.52 13098.26 15599.83 6499.87 6693.37 32499.90 14897.81 28799.91 4699.49 236
test_cas_vis1_n_192099.16 11199.01 13099.61 10999.81 5798.86 21599.65 8899.64 4299.39 2299.97 2599.94 693.20 33099.98 2099.55 5099.91 4699.99 1
region2R99.48 3799.35 4899.87 2199.88 1399.80 3899.65 8899.66 3298.13 18399.66 12699.68 23198.96 2799.96 4198.62 19799.87 7999.84 53
TranMVSNet+NR-MVSNet97.93 28497.66 29798.76 28898.78 40398.62 24499.65 8899.49 18897.76 24798.49 37399.60 26894.23 29798.97 42198.00 27092.90 43698.70 344
GDP-MVS99.08 14598.89 16099.64 10199.53 21699.34 12799.64 9599.48 20098.32 14799.77 8599.66 24295.14 24599.93 11098.97 14099.50 17699.64 178
ttmdpeth97.80 31197.63 30298.29 34698.77 40897.38 32199.64 9599.36 29898.78 9896.30 43899.58 27492.34 35999.39 34098.36 23495.58 39098.10 432
mvsany_test393.77 42393.45 42694.74 43895.78 46488.01 46499.64 9598.25 44798.28 15094.31 45297.97 45468.89 47198.51 44197.50 32090.37 45297.71 449
ZNCC-MVS99.47 4099.33 5299.87 2199.87 2099.81 3399.64 9599.67 2798.08 19799.55 16999.64 25098.91 3999.96 4198.72 18399.90 5799.82 72
tfpnnormal97.84 30197.47 32098.98 24199.20 32399.22 14999.64 9599.61 6096.32 38098.27 38699.70 21293.35 32699.44 33295.69 39795.40 39598.27 422
casdiffmvs_mvgpermissive99.15 11599.02 12599.55 12499.66 14899.09 16599.64 9599.56 9098.26 15599.45 18599.87 6696.03 20099.81 22899.54 5199.15 20799.73 123
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SR-MVS-dyc-post99.45 4699.31 6099.85 4399.76 8299.82 2899.63 10199.52 13098.38 13799.76 9199.82 11598.53 8299.95 7698.61 20099.81 12099.77 100
RE-MVS-def99.34 5099.76 8299.82 2899.63 10199.52 13098.38 13799.76 9199.82 11598.75 6098.61 20099.81 12099.77 100
TSAR-MVS + MP.99.58 1699.50 1999.81 6099.91 199.66 7199.63 10199.39 27998.91 8299.78 8199.85 8199.36 299.94 9298.84 16599.88 7699.82 72
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
Anonymous2023120696.22 39096.03 39196.79 42697.31 45494.14 43999.63 10199.08 37496.17 39297.04 42999.06 39793.94 31097.76 45686.96 46895.06 40298.47 406
APD-MVS_3200maxsize99.48 3799.35 4899.85 4399.76 8299.83 2299.63 10199.54 10998.36 14199.79 7699.82 11598.86 4399.95 7698.62 19799.81 12099.78 98
test072699.85 3199.89 699.62 10699.50 17599.10 4899.86 5399.82 11598.94 34
EPNet98.86 18098.71 18799.30 20097.20 45698.18 27799.62 10698.91 40199.28 3198.63 36099.81 13095.96 20399.99 499.24 9999.72 14899.73 123
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
114514_t98.93 17098.67 19199.72 8699.85 3199.53 10199.62 10699.59 7392.65 45099.71 10899.78 17298.06 11099.90 14898.84 16599.91 4699.74 114
HY-MVS97.30 798.85 18998.64 19899.47 16299.42 25999.08 16899.62 10699.36 29897.39 29599.28 23699.68 23196.44 18399.92 12398.37 23298.22 29199.40 262
ACMMPcopyleft99.45 4699.32 5499.82 5799.89 899.67 6899.62 10699.69 2298.12 18799.63 14399.84 9698.73 6699.96 4198.55 21599.83 11399.81 79
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
DeepC-MVS98.35 299.30 8399.19 8899.64 10199.82 5399.23 14899.62 10699.55 10098.94 7899.63 14399.95 395.82 21399.94 9299.37 7599.97 999.73 123
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
EI-MVSNet-Vis-set99.58 1699.56 1299.64 10199.78 7099.15 15999.61 11299.45 24499.01 6499.89 4099.82 11599.01 2099.92 12399.56 4999.95 2399.85 46
reproduce_monomvs97.89 29197.87 27397.96 37499.51 22595.45 40899.60 11399.25 34999.17 3698.85 32799.49 30889.29 40599.64 30299.35 7696.31 36998.78 323
test250696.81 38096.65 37697.29 41199.74 10092.21 45799.60 11385.06 48899.13 4199.77 8599.93 1087.82 42799.85 18799.38 7499.38 18399.80 88
SED-MVS99.61 1099.52 1499.88 1599.84 3899.90 399.60 11399.48 20099.08 5699.91 3199.81 13099.20 999.96 4198.91 14999.85 9499.79 92
OPU-MVS99.64 10199.56 20499.72 5699.60 11399.70 21299.27 799.42 33898.24 24599.80 12599.79 92
GST-MVS99.40 6499.24 7899.85 4399.86 2599.79 4199.60 11399.67 2797.97 22099.63 14399.68 23198.52 8399.95 7698.38 23099.86 8799.81 79
EI-MVSNet-UG-set99.58 1699.57 1099.64 10199.78 7099.14 16099.60 11399.45 24499.01 6499.90 3499.83 10298.98 2699.93 11099.59 4599.95 2399.86 42
ACMH97.28 898.10 25697.99 25898.44 33199.41 26496.96 35399.60 11399.56 9098.09 19398.15 39399.91 2690.87 38799.70 28298.88 15297.45 33898.67 361
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
VortexMVS98.67 21098.66 19498.68 29799.62 17497.96 29299.59 12099.41 26998.13 18399.31 22899.70 21295.48 22999.27 36599.40 7197.32 34798.79 321
guyue99.16 11199.04 11499.52 13999.69 12798.92 20399.59 12098.81 41598.73 10299.90 3499.87 6695.34 23499.88 16899.66 4099.81 12099.74 114
ECVR-MVScopyleft98.04 26798.05 25298.00 37099.74 10094.37 43599.59 12094.98 47699.13 4199.66 12699.93 1090.67 38999.84 19699.40 7199.38 18399.80 88
SR-MVS99.43 5399.29 6699.86 3499.75 9299.83 2299.59 12099.62 5198.21 16899.73 9799.79 16598.68 7099.96 4198.44 22599.77 13799.79 92
thres100view90097.76 31597.45 32398.69 29699.72 11197.86 30199.59 12098.74 42597.93 22399.26 24798.62 42991.75 36899.83 21493.22 43598.18 29698.37 418
thres600view797.86 29697.51 31498.92 25299.72 11197.95 29599.59 12098.74 42597.94 22299.27 24298.62 42991.75 36899.86 18193.73 42998.19 29598.96 313
LCM-MVSNet-Re97.83 30498.15 23896.87 42499.30 29692.25 45699.59 12098.26 44697.43 29096.20 43999.13 39096.27 19198.73 43698.17 25198.99 23599.64 178
baseline198.31 23697.95 26399.38 18399.50 23798.74 23199.59 12098.93 39398.41 13599.14 27199.60 26894.59 27999.79 24198.48 21993.29 43199.61 188
SteuartSystems-ACMMP99.54 2499.42 3299.87 2199.82 5399.81 3399.59 12099.51 15298.62 11299.79 7699.83 10299.28 699.97 2998.48 21999.90 5799.84 53
Skip Steuart: Steuart Systems R&D Blog.
CPTT-MVS99.11 13798.90 15699.74 8099.80 6399.46 11499.59 12099.49 18897.03 33099.63 14399.69 22397.27 13399.96 4197.82 28599.84 10299.81 79
IMVS_040398.86 18098.89 16098.78 28699.55 20896.93 35499.58 13099.44 25398.05 20599.68 11599.80 14896.81 16199.80 23598.15 25498.92 24099.60 191
test_fmvsmvis_n_192099.65 899.61 799.77 7499.38 27499.37 12399.58 13099.62 5199.41 2199.87 4999.92 1898.81 49100.00 199.97 299.93 3399.94 17
dmvs_testset95.02 41196.12 38891.72 44999.10 35080.43 47799.58 13097.87 45697.47 28295.22 44698.82 42093.99 30895.18 47488.09 46294.91 40799.56 212
test_fmvsm_n_192099.69 599.66 499.78 7199.84 3899.44 11699.58 13099.69 2299.43 1799.98 1399.91 2698.62 76100.00 199.97 299.95 2399.90 25
test111198.04 26798.11 24397.83 38699.74 10093.82 44199.58 13095.40 47599.12 4699.65 13599.93 1090.73 38899.84 19699.43 6999.38 18399.82 72
PGM-MVS99.45 4699.31 6099.86 3499.87 2099.78 4799.58 13099.65 3997.84 23699.71 10899.80 14899.12 1599.97 2998.33 23799.87 7999.83 63
LPG-MVS_test98.22 24298.13 24198.49 31899.33 28797.05 34099.58 13099.55 10097.46 28399.24 24999.83 10292.58 34899.72 26998.09 25997.51 33198.68 353
PHI-MVS99.30 8399.17 9199.70 8799.56 20499.52 10599.58 13099.80 1197.12 31899.62 14799.73 20198.58 7899.90 14898.61 20099.91 4699.68 156
fmvsm_s_conf0.5_n_1199.32 7999.16 9299.80 6499.83 4799.70 6099.57 13899.56 9099.45 1199.99 299.93 1094.18 30199.99 499.96 1399.98 499.73 123
AstraMVS99.09 14399.03 11799.25 21099.66 14898.13 28199.57 13898.24 44898.82 8999.91 3199.88 5395.81 21499.90 14899.72 3299.67 15899.74 114
SF-MVS99.38 6799.24 7899.79 6899.79 6899.68 6499.57 13899.54 10997.82 24299.71 10899.80 14898.95 3299.93 11098.19 24899.84 10299.74 114
DVP-MVScopyleft99.57 2099.47 2499.88 1599.85 3199.89 699.57 13899.37 29699.10 4899.81 6999.80 14898.94 3499.96 4198.93 14699.86 8799.81 79
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_SECOND99.91 699.84 3899.89 699.57 13899.51 15299.96 4198.93 14699.86 8799.88 35
Effi-MVS+-dtu98.78 19898.89 16098.47 32599.33 28796.91 35999.57 13899.30 33798.47 12799.41 20198.99 40696.78 16399.74 25998.73 18299.38 18398.74 335
v2v48298.06 26197.77 28398.92 25298.90 38598.82 22499.57 13899.36 29896.65 35499.19 26399.35 35294.20 29899.25 36997.72 30094.97 40498.69 348
DSMNet-mixed97.25 36797.35 34096.95 42197.84 44493.61 44899.57 13896.63 47096.13 39798.87 32298.61 43194.59 27997.70 45795.08 41198.86 24899.55 213
FE-MVSNET94.07 42293.36 42796.22 43394.05 47594.71 42799.56 14698.36 44493.15 44493.76 45697.55 45886.47 43596.49 46987.48 46589.83 45797.48 458
reproduce_model99.63 999.54 1399.90 899.78 7099.88 1099.56 14699.55 10099.15 3899.90 3499.90 3399.00 2499.97 2999.11 11899.91 4699.86 42
MVStest196.08 39695.48 40197.89 38098.93 38096.70 36799.56 14699.35 30592.69 44991.81 46699.46 32189.90 39898.96 42395.00 41392.61 44198.00 441
fmvsm_l_conf0.5_n_a99.71 299.67 199.85 4399.86 2599.61 8599.56 14699.63 4699.48 399.98 1399.83 10298.75 6099.99 499.97 299.96 1799.94 17
fmvsm_l_conf0.5_n99.71 299.67 199.85 4399.84 3899.63 8299.56 14699.63 4699.47 499.98 1399.82 11598.75 6099.99 499.97 299.97 999.94 17
sd_testset98.75 20398.57 21199.29 20399.81 5798.26 27499.56 14699.62 5198.78 9899.64 14099.88 5392.02 36299.88 16899.54 5198.26 28899.72 133
KD-MVS_self_test95.00 41294.34 41796.96 42097.07 45995.39 41199.56 14699.44 25395.11 41597.13 42797.32 46391.86 36697.27 46390.35 45481.23 47298.23 426
ETV-MVS99.26 9299.21 8499.40 17799.46 24999.30 13899.56 14699.52 13098.52 12299.44 19099.27 37498.41 9399.86 18199.10 12199.59 16899.04 303
SMA-MVScopyleft99.44 5099.30 6299.85 4399.73 10799.83 2299.56 14699.47 22297.45 28699.78 8199.82 11599.18 1299.91 13598.79 17699.89 6899.81 79
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
AllTest98.87 17798.72 18599.31 19599.86 2598.48 26399.56 14699.61 6097.85 23399.36 21899.85 8195.95 20499.85 18796.66 37399.83 11399.59 202
casdiffmvspermissive99.13 12398.98 13799.56 12299.65 15699.16 15599.56 14699.50 17598.33 14599.41 20199.86 7495.92 20799.83 21499.45 6899.16 20499.70 147
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
XXY-MVS98.38 23198.09 24799.24 21399.26 30899.32 13199.56 14699.55 10097.45 28698.71 34299.83 10293.23 32799.63 30898.88 15296.32 36898.76 329
ACMH+97.24 1097.92 28797.78 28198.32 34399.46 24996.68 37199.56 14699.54 10998.41 13597.79 41199.87 6690.18 39699.66 29398.05 26797.18 35398.62 383
ACMM97.58 598.37 23398.34 22698.48 32099.41 26497.10 33499.56 14699.45 24498.53 12199.04 29399.85 8193.00 33299.71 27598.74 18097.45 33898.64 374
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LS3D99.27 8999.12 9799.74 8099.18 32999.75 5199.56 14699.57 8598.45 13099.49 18099.85 8197.77 11899.94 9298.33 23799.84 10299.52 222
testing3-297.84 30197.70 29398.24 35299.53 21695.37 41299.55 16198.67 43598.46 12899.27 24299.34 35686.58 43399.83 21499.32 8498.63 26199.52 222
test_fmvsmconf0.01_n99.22 10099.03 11799.79 6898.42 43699.48 11199.55 16199.51 15299.39 2299.78 8199.93 1094.80 26199.95 7699.93 2399.95 2399.94 17
test_fmvs198.88 17498.79 17899.16 22199.69 12797.61 31499.55 16199.49 18899.32 2999.98 1399.91 2691.41 37899.96 4199.82 2999.92 3999.90 25
v14419297.92 28797.60 30598.87 26998.83 39798.65 23999.55 16199.34 31096.20 38999.32 22799.40 33694.36 29199.26 36896.37 38495.03 40398.70 344
API-MVS99.04 15599.03 11799.06 23199.40 26999.31 13599.55 16199.56 9098.54 12099.33 22699.39 34098.76 5799.78 24796.98 35599.78 13498.07 434
fmvsm_l_conf0.5_n_399.61 1099.51 1899.92 199.84 3899.82 2899.54 16699.66 3299.46 799.98 1399.89 4297.27 13399.99 499.97 299.95 2399.95 11
fmvsm_s_conf0.1_n_a99.26 9299.06 11099.85 4399.52 22299.62 8399.54 16699.62 5198.69 10799.99 299.96 194.47 28899.94 9299.88 2699.92 3999.98 2
APD_test195.87 39896.49 38094.00 44099.53 21684.01 46999.54 16699.32 32895.91 40597.99 40099.85 8185.49 44299.88 16891.96 44798.84 25098.12 431
thisisatest053098.35 23498.03 25499.31 19599.63 16598.56 24999.54 16696.75 46897.53 27799.73 9799.65 24491.25 38399.89 16398.62 19799.56 17099.48 239
MTMP99.54 16698.88 406
v114497.98 27897.69 29498.85 27598.87 39098.66 23899.54 16699.35 30596.27 38499.23 25399.35 35294.67 27499.23 37296.73 36895.16 40098.68 353
v14897.79 31397.55 30798.50 31798.74 41197.72 30799.54 16699.33 31896.26 38598.90 31699.51 30294.68 27399.14 38997.83 28493.15 43598.63 381
CostFormer97.72 32597.73 29097.71 39499.15 34394.02 44099.54 16699.02 38494.67 42799.04 29399.35 35292.35 35899.77 24998.50 21897.94 30699.34 272
MVSTER98.49 21998.32 22899.00 23999.35 28199.02 17599.54 16699.38 28797.41 29399.20 26099.73 20193.86 31599.36 34998.87 15597.56 32698.62 383
fmvsm_s_conf0.5_n_1099.41 5999.24 7899.92 199.83 4799.84 2099.53 17599.56 9099.45 1199.99 299.92 1894.92 25499.99 499.97 299.97 999.95 11
fmvsm_s_conf0.1_n99.29 8599.10 9999.86 3499.70 12299.65 7599.53 17599.62 5198.74 10199.99 299.95 394.53 28699.94 9299.89 2599.96 1799.97 4
E499.13 12399.01 13099.49 15299.68 13298.90 20799.52 17799.52 13098.13 18399.71 10899.90 3396.32 18899.84 19699.21 10299.11 21899.75 109
reproduce-ours99.61 1099.52 1499.90 899.76 8299.88 1099.52 17799.54 10999.13 4199.89 4099.89 4298.96 2799.96 4199.04 12899.90 5799.85 46
our_new_method99.61 1099.52 1499.90 899.76 8299.88 1099.52 17799.54 10999.13 4199.89 4099.89 4298.96 2799.96 4199.04 12899.90 5799.85 46
fmvsm_s_conf0.5_n_a99.56 2199.47 2499.85 4399.83 4799.64 8199.52 17799.65 3999.10 4899.98 1399.92 1897.35 12999.96 4199.94 2199.92 3999.95 11
MM99.40 6499.28 6999.74 8099.67 13599.31 13599.52 17798.87 40899.55 199.74 9599.80 14896.47 18099.98 2099.97 299.97 999.94 17
patch_mono-299.26 9299.62 698.16 35799.81 5794.59 43199.52 17799.64 4299.33 2899.73 9799.90 3399.00 2499.99 499.69 3599.98 499.89 29
Fast-Effi-MVS+-dtu98.77 20298.83 17498.60 30299.41 26496.99 34999.52 17799.49 18898.11 18999.24 24999.34 35696.96 15299.79 24197.95 27399.45 17999.02 306
Fast-Effi-MVS+98.70 20798.43 22099.51 14499.51 22599.28 14199.52 17799.47 22296.11 39899.01 29699.34 35696.20 19399.84 19697.88 27798.82 25299.39 263
v192192097.80 31197.45 32398.84 27698.80 39998.53 25299.52 17799.34 31096.15 39599.24 24999.47 31793.98 30999.29 36195.40 40595.13 40198.69 348
MIMVSNet195.51 40495.04 40996.92 42397.38 45195.60 40199.52 17799.50 17593.65 43796.97 43199.17 38585.28 44596.56 46888.36 46195.55 39298.60 395
FE-MVSNET295.10 41094.44 41697.08 41795.08 47095.97 39499.51 18799.37 29695.02 41994.10 45397.57 45786.18 43797.66 45993.28 43489.86 45697.61 452
viewmacassd2359aftdt99.08 14598.94 14899.50 14999.66 14898.96 18799.51 18799.54 10998.27 15299.42 19699.89 4295.88 21199.80 23599.20 10399.11 21899.76 107
SSM_040799.13 12399.03 11799.43 17399.62 17498.88 20899.51 18799.50 17598.14 18099.37 21299.85 8196.85 15599.83 21499.19 10499.25 19799.60 191
fmvsm_s_conf0.5_n_899.54 2499.42 3299.89 1199.83 4799.74 5499.51 18799.62 5199.46 799.99 299.90 3396.60 17299.98 2099.95 1699.95 2399.96 7
fmvsm_s_conf0.5_n99.51 2999.40 3899.85 4399.84 3899.65 7599.51 18799.67 2799.13 4199.98 1399.92 1896.60 17299.96 4199.95 1699.96 1799.95 11
UniMVSNet_ETH3D97.32 36496.81 37298.87 26999.40 26997.46 31899.51 18799.53 12595.86 40698.54 37099.77 18182.44 45899.66 29398.68 19097.52 33099.50 235
alignmvs98.81 19398.56 21399.58 11699.43 25799.42 11899.51 18798.96 39198.61 11399.35 22198.92 41694.78 26399.77 24999.35 7698.11 30199.54 215
v119297.81 30997.44 32898.91 25698.88 38798.68 23699.51 18799.34 31096.18 39199.20 26099.34 35694.03 30799.36 34995.32 40795.18 39998.69 348
test20.0396.12 39495.96 39396.63 42797.44 45095.45 40899.51 18799.38 28796.55 36596.16 44099.25 37793.76 31996.17 47087.35 46794.22 41798.27 422
mvs_anonymous99.03 15798.99 13499.16 22199.38 27498.52 25699.51 18799.38 28797.79 24399.38 21099.81 13097.30 13199.45 32799.35 7698.99 23599.51 231
TAMVS99.12 13199.08 10599.24 21399.46 24998.55 25099.51 18799.46 23398.09 19399.45 18599.82 11598.34 9799.51 32198.70 18598.93 23899.67 160
viewdifsd2359ckpt1399.06 15098.93 15099.45 16599.63 16598.96 18799.50 19899.51 15297.83 23799.28 23699.80 14896.68 16999.71 27599.05 12799.12 21699.68 156
viewdifsd2359ckpt1198.78 19898.74 18398.89 26299.67 13597.04 34399.50 19899.58 7898.26 15599.56 16399.90 3394.36 29199.87 17599.49 6198.32 28499.77 100
viewmsd2359difaftdt98.78 19898.74 18398.90 25899.67 13597.04 34399.50 19899.58 7898.26 15599.56 16399.90 3394.36 29199.87 17599.49 6198.32 28499.77 100
IMVS_040798.86 18098.91 15498.72 29199.55 20896.93 35499.50 19899.44 25398.05 20599.66 12699.80 14897.13 13999.65 29898.15 25498.92 24099.60 191
viewmanbaseed2359cas99.18 10499.07 10999.50 14999.62 17499.01 17799.50 19899.52 13098.25 16099.68 11599.82 11596.93 15399.80 23599.15 11499.11 21899.70 147
fmvsm_s_conf0.5_n_699.54 2499.44 3199.85 4399.51 22599.67 6899.50 19899.64 4299.43 1799.98 1399.78 17297.26 13699.95 7699.95 1699.93 3399.92 23
test_fmvsmconf0.1_n99.55 2399.45 3099.86 3499.44 25699.65 7599.50 19899.61 6099.45 1199.87 4999.92 1897.31 13099.97 2999.95 1699.99 199.97 4
test_yl98.86 18098.63 19999.54 12599.49 23999.18 15299.50 19899.07 37798.22 16699.61 15299.51 30295.37 23299.84 19698.60 20398.33 28099.59 202
DCV-MVSNet98.86 18098.63 19999.54 12599.49 23999.18 15299.50 19899.07 37798.22 16699.61 15299.51 30295.37 23299.84 19698.60 20398.33 28099.59 202
tfpn200view997.72 32597.38 33698.72 29199.69 12797.96 29299.50 19898.73 43197.83 23799.17 26898.45 43691.67 37299.83 21493.22 43598.18 29698.37 418
UA-Net99.42 5599.29 6699.80 6499.62 17499.55 9699.50 19899.70 1898.79 9599.77 8599.96 197.45 12499.96 4198.92 14899.90 5799.89 29
pm-mvs197.68 33397.28 35298.88 26599.06 35998.62 24499.50 19899.45 24496.32 38097.87 40799.79 16592.47 35299.35 35297.54 31793.54 42898.67 361
EI-MVSNet98.67 21098.67 19198.68 29799.35 28197.97 29099.50 19899.38 28796.93 33999.20 26099.83 10297.87 11499.36 34998.38 23097.56 32698.71 339
CVMVSNet98.57 21798.67 19198.30 34599.35 28195.59 40299.50 19899.55 10098.60 11599.39 20899.83 10294.48 28799.45 32798.75 17998.56 26899.85 46
VPA-MVSNet98.29 23997.95 26399.30 20099.16 33999.54 9899.50 19899.58 7898.27 15299.35 22199.37 34692.53 35099.65 29899.35 7694.46 41298.72 337
thres40097.77 31497.38 33698.92 25299.69 12797.96 29299.50 19898.73 43197.83 23799.17 26898.45 43691.67 37299.83 21493.22 43598.18 29698.96 313
APD-MVScopyleft99.27 8999.08 10599.84 5599.75 9299.79 4199.50 19899.50 17597.16 31499.77 8599.82 11598.78 5399.94 9297.56 31599.86 8799.80 88
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
E299.15 11599.03 11799.49 15299.65 15698.93 20299.49 21599.52 13098.14 18099.72 10299.88 5396.57 17699.84 19699.17 11099.13 21199.72 133
E399.15 11599.03 11799.49 15299.62 17498.91 20499.49 21599.52 13098.13 18399.72 10299.88 5396.61 17199.84 19699.17 11099.13 21199.72 133
SSM_040499.16 11199.06 11099.44 17099.65 15698.96 18799.49 21599.50 17598.14 18099.62 14799.85 8196.85 15599.85 18799.19 10499.26 19699.52 222
fmvsm_s_conf0.5_n_499.36 7299.24 7899.73 8399.78 7099.53 10199.49 21599.60 6799.42 2099.99 299.86 7495.15 24499.95 7699.95 1699.89 6899.73 123
test_vis1_rt95.81 40095.65 39996.32 43299.67 13591.35 46099.49 21596.74 46998.25 16095.24 44598.10 45174.96 46799.90 14899.53 5398.85 24997.70 451
TransMVSNet (Re)97.15 37196.58 37798.86 27299.12 34598.85 21699.49 21598.91 40195.48 41097.16 42699.80 14893.38 32399.11 39894.16 42591.73 44598.62 383
UniMVSNet (Re)98.29 23998.00 25799.13 22699.00 36999.36 12699.49 21599.51 15297.95 22198.97 30599.13 39096.30 19099.38 34298.36 23493.34 43098.66 370
EPMVS97.82 30797.65 29898.35 34098.88 38795.98 39399.49 21594.71 47897.57 27099.26 24799.48 31492.46 35599.71 27597.87 27999.08 22799.35 269
viewcassd2359sk1199.18 10499.08 10599.49 15299.65 15698.95 19399.48 22399.51 15298.10 19299.72 10299.87 6697.13 13999.84 19699.13 11599.14 20899.69 150
fmvsm_s_conf0.5_n_999.41 5999.28 6999.81 6099.84 3899.52 10599.48 22399.62 5199.46 799.99 299.92 1895.24 24199.96 4199.97 299.97 999.96 7
SSC-MVS3.297.34 36297.15 35997.93 37699.02 36695.76 39999.48 22399.58 7897.62 26599.09 28299.53 29487.95 42399.27 36596.42 38095.66 38898.75 331
fmvsm_s_conf0.5_n_399.37 6899.20 8699.87 2199.75 9299.70 6099.48 22399.66 3299.45 1199.99 299.93 1094.64 27899.97 2999.94 2199.97 999.95 11
test_fmvsmconf_n99.70 499.64 599.87 2199.80 6399.66 7199.48 22399.64 4299.45 1199.92 3099.92 1898.62 7699.99 499.96 1399.99 199.96 7
Anonymous2023121197.88 29297.54 31098.90 25899.71 11798.53 25299.48 22399.57 8594.16 43298.81 33199.68 23193.23 32799.42 33898.84 16594.42 41498.76 329
v124097.69 33097.32 34798.79 28498.85 39498.43 26799.48 22399.36 29896.11 39899.27 24299.36 34993.76 31999.24 37194.46 41995.23 39898.70 344
VPNet97.84 30197.44 32899.01 23799.21 32198.94 19799.48 22399.57 8598.38 13799.28 23699.73 20188.89 40899.39 34099.19 10493.27 43298.71 339
UniMVSNet_NR-MVSNet98.22 24297.97 26098.96 24498.92 38298.98 18099.48 22399.53 12597.76 24798.71 34299.46 32196.43 18499.22 37698.57 20992.87 43898.69 348
TDRefinement95.42 40694.57 41497.97 37289.83 48196.11 39299.48 22398.75 42296.74 34796.68 43499.88 5388.65 41499.71 27598.37 23282.74 47098.09 433
fmvsm_l_conf0.5_n_999.58 1699.47 2499.92 199.85 3199.82 2899.47 23399.63 4699.45 1199.98 1399.89 4297.02 14899.99 499.98 199.96 1799.95 11
ACMMP_NAP99.47 4099.34 5099.88 1599.87 2099.86 1899.47 23399.48 20098.05 20599.76 9199.86 7498.82 4899.93 11098.82 17599.91 4699.84 53
NR-MVSNet97.97 28197.61 30499.02 23698.87 39099.26 14499.47 23399.42 26697.63 26397.08 42899.50 30595.07 24799.13 39297.86 28093.59 42798.68 353
PVSNet_Blended_VisFu99.36 7299.28 6999.61 10999.86 2599.07 17099.47 23399.93 297.66 26199.71 10899.86 7497.73 11999.96 4199.47 6699.82 11799.79 92
E3new99.18 10499.08 10599.48 15699.63 16598.94 19799.46 23799.50 17598.06 20299.72 10299.84 9697.27 13399.84 19699.10 12199.13 21199.67 160
LuminaMVS99.23 9899.10 9999.61 10999.35 28199.31 13599.46 23799.13 36898.61 11399.86 5399.89 4296.41 18699.91 13599.67 3799.51 17499.63 183
fmvsm_s_conf0.1_n_299.37 6899.22 8399.81 6099.77 7899.75 5199.46 23799.60 6799.47 499.98 1399.94 694.98 24899.95 7699.97 299.79 13299.73 123
SD-MVS99.41 5999.52 1499.05 23399.74 10099.68 6499.46 23799.52 13099.11 4799.88 4399.91 2699.43 197.70 45798.72 18399.93 3399.77 100
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
viewdifsd2359ckpt0799.11 13799.00 13399.43 17399.63 16598.73 23299.45 24199.54 10998.33 14599.62 14799.81 13096.17 19499.87 17599.27 9599.14 20899.69 150
testing397.28 36596.76 37498.82 27899.37 27798.07 28599.45 24199.36 29897.56 27297.89 40698.95 41183.70 45298.82 43196.03 38898.56 26899.58 206
tt080597.97 28197.77 28398.57 30799.59 19396.61 37499.45 24199.08 37498.21 16898.88 31999.80 14888.66 41399.70 28298.58 20697.72 31699.39 263
tpm297.44 35797.34 34397.74 39399.15 34394.36 43699.45 24198.94 39293.45 44198.90 31699.44 32491.35 38099.59 31297.31 33498.07 30299.29 276
FMVSNet297.72 32597.36 33898.80 28399.51 22598.84 21899.45 24199.42 26696.49 36898.86 32699.29 36990.26 39298.98 41496.44 37996.56 36298.58 397
CDS-MVSNet99.09 14399.03 11799.25 21099.42 25998.73 23299.45 24199.46 23398.11 18999.46 18499.77 18198.01 11299.37 34598.70 18598.92 24099.66 165
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MAR-MVS98.86 18098.63 19999.54 12599.37 27799.66 7199.45 24199.54 10996.61 35999.01 29699.40 33697.09 14399.86 18197.68 30599.53 17399.10 291
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
viewdifsd2359ckpt0999.01 16298.87 16499.40 17799.62 17498.79 22799.44 24899.51 15297.76 24799.35 22199.69 22396.42 18599.75 25698.97 14099.11 21899.66 165
fmvsm_s_conf0.5_n_299.32 7999.13 9599.89 1199.80 6399.77 4899.44 24899.58 7899.47 499.99 299.93 1094.04 30699.96 4199.96 1399.93 3399.93 22
UGNet98.87 17798.69 18999.40 17799.22 32098.72 23499.44 24899.68 2499.24 3299.18 26799.42 32892.74 34099.96 4199.34 8199.94 3199.53 221
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
ab-mvs98.86 18098.63 19999.54 12599.64 16199.19 15099.44 24899.54 10997.77 24699.30 23299.81 13094.20 29899.93 11099.17 11098.82 25299.49 236
test_040296.64 38396.24 38597.85 38398.85 39496.43 38099.44 24899.26 34793.52 43896.98 43099.52 29888.52 41799.20 38392.58 44597.50 33397.93 446
ACMP97.20 1198.06 26197.94 26598.45 32899.37 27797.01 34799.44 24899.49 18897.54 27698.45 37599.79 16591.95 36499.72 26997.91 27597.49 33698.62 383
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
GG-mvs-BLEND98.45 32898.55 43198.16 27899.43 25493.68 48097.23 42298.46 43589.30 40499.22 37695.43 40498.22 29197.98 443
HPM-MVS++copyleft99.39 6699.23 8299.87 2199.75 9299.84 2099.43 25499.51 15298.68 10999.27 24299.53 29498.64 7599.96 4198.44 22599.80 12599.79 92
tpm cat197.39 35997.36 33897.50 40599.17 33793.73 44399.43 25499.31 33291.27 45498.71 34299.08 39494.31 29699.77 24996.41 38298.50 27299.00 307
tpm97.67 33697.55 30798.03 36599.02 36695.01 42099.43 25498.54 44196.44 37499.12 27499.34 35691.83 36799.60 31197.75 29696.46 36499.48 239
GBi-Net97.68 33397.48 31798.29 34699.51 22597.26 32799.43 25499.48 20096.49 36899.07 28599.32 36490.26 39298.98 41497.10 34796.65 35998.62 383
test197.68 33397.48 31798.29 34699.51 22597.26 32799.43 25499.48 20096.49 36899.07 28599.32 36490.26 39298.98 41497.10 34796.65 35998.62 383
FMVSNet196.84 37996.36 38398.29 34699.32 29497.26 32799.43 25499.48 20095.11 41598.55 36999.32 36483.95 45198.98 41495.81 39396.26 37098.62 383
fmvsm_s_conf0.5_n_799.34 7599.29 6699.48 15699.70 12298.63 24299.42 26199.63 4699.46 799.98 1399.88 5395.59 22499.96 4199.97 299.98 499.85 46
fmvsm_s_conf0.5_n_599.37 6899.21 8499.86 3499.80 6399.68 6499.42 26199.61 6099.37 2499.97 2599.86 7494.96 24999.99 499.97 299.93 3399.92 23
mamv499.33 7799.42 3299.07 22999.67 13597.73 30599.42 26199.60 6798.15 17599.94 2899.91 2698.42 9199.94 9299.72 3299.96 1799.54 215
testgi97.65 33897.50 31598.13 36199.36 28096.45 37999.42 26199.48 20097.76 24797.87 40799.45 32391.09 38498.81 43294.53 41898.52 27199.13 290
F-COLMAP99.19 10199.04 11499.64 10199.78 7099.27 14399.42 26199.54 10997.29 30399.41 20199.59 27098.42 9199.93 11098.19 24899.69 15399.73 123
Anonymous20240521198.30 23897.98 25999.26 20999.57 20098.16 27899.41 26698.55 44096.03 40399.19 26399.74 19591.87 36599.92 12399.16 11398.29 28799.70 147
MSLP-MVS++99.46 4299.47 2499.44 17099.60 19199.16 15599.41 26699.71 1698.98 7299.45 18599.78 17299.19 1199.54 31999.28 9299.84 10299.63 183
VNet99.11 13798.90 15699.73 8399.52 22299.56 9499.41 26699.39 27999.01 6499.74 9599.78 17295.56 22599.92 12399.52 5598.18 29699.72 133
baseline297.87 29497.55 30798.82 27899.18 32998.02 28799.41 26696.58 47296.97 33396.51 43599.17 38593.43 32299.57 31497.71 30199.03 23198.86 317
DU-MVS98.08 25997.79 27898.96 24498.87 39098.98 18099.41 26699.45 24497.87 22998.71 34299.50 30594.82 25999.22 37698.57 20992.87 43898.68 353
Baseline_NR-MVSNet97.76 31597.45 32398.68 29799.09 35398.29 27299.41 26698.85 41095.65 40898.63 36099.67 23794.82 25999.10 40098.07 26692.89 43798.64 374
XVG-ACMP-BASELINE97.83 30497.71 29298.20 35499.11 34796.33 38399.41 26699.52 13098.06 20299.05 29299.50 30589.64 40299.73 26597.73 29897.38 34598.53 400
DP-MVS99.16 11198.95 14699.78 7199.77 7899.53 10199.41 26699.50 17597.03 33099.04 29399.88 5397.39 12599.92 12398.66 19299.90 5799.87 40
9.1499.10 9999.72 11199.40 27499.51 15297.53 27799.64 14099.78 17298.84 4699.91 13597.63 30699.82 117
D2MVS98.41 22798.50 21798.15 36099.26 30896.62 37399.40 27499.61 6097.71 25398.98 30399.36 34996.04 19999.67 29098.70 18597.41 34398.15 430
Anonymous2024052998.09 25797.68 29599.34 18799.66 14898.44 26699.40 27499.43 26493.67 43699.22 25499.89 4290.23 39599.93 11099.26 9898.33 28099.66 165
FMVSNet398.03 26997.76 28798.84 27699.39 27298.98 18099.40 27499.38 28796.67 35299.07 28599.28 37192.93 33398.98 41497.10 34796.65 35998.56 399
LFMVS97.90 29097.35 34099.54 12599.52 22299.01 17799.39 27898.24 44897.10 32299.65 13599.79 16584.79 44799.91 13599.28 9298.38 27799.69 150
HQP_MVS98.27 24198.22 23498.44 33199.29 30096.97 35199.39 27899.47 22298.97 7599.11 27699.61 26592.71 34399.69 28797.78 29097.63 31998.67 361
plane_prior299.39 27898.97 75
CHOSEN 1792x268899.19 10199.10 9999.45 16599.89 898.52 25699.39 27899.94 198.73 10299.11 27699.89 4295.50 22799.94 9299.50 5799.97 999.89 29
PAPM_NR99.04 15598.84 17299.66 9199.74 10099.44 11699.39 27899.38 28797.70 25699.28 23699.28 37198.34 9799.85 18796.96 35799.45 17999.69 150
gg-mvs-nofinetune96.17 39395.32 40598.73 28998.79 40098.14 28099.38 28394.09 47991.07 45798.07 39891.04 47789.62 40399.35 35296.75 36799.09 22698.68 353
VDDNet97.55 34497.02 36699.16 22199.49 23998.12 28399.38 28399.30 33795.35 41199.68 11599.90 3382.62 45799.93 11099.31 8698.13 30099.42 257
ME-MVS99.56 2199.46 2899.86 3499.80 6399.81 3399.37 28599.70 1899.18 3499.83 6499.83 10298.74 6599.93 11098.83 16899.89 6899.83 63
MGCNet99.15 11598.96 14299.73 8398.92 38299.37 12399.37 28596.92 46599.51 299.66 12699.78 17296.69 16799.97 2999.84 2899.97 999.84 53
pmmvs696.53 38596.09 39097.82 38898.69 41895.47 40799.37 28599.47 22293.46 44097.41 41699.78 17287.06 43199.33 35596.92 36292.70 44098.65 372
PM-MVS92.96 42892.23 43295.14 43795.61 46589.98 46399.37 28598.21 45094.80 42595.04 45097.69 45565.06 47297.90 45394.30 42089.98 45597.54 457
WTY-MVS99.06 15098.88 16399.61 10999.62 17499.16 15599.37 28599.56 9098.04 21299.53 17299.62 26196.84 15999.94 9298.85 16298.49 27399.72 133
IterMVS-LS98.46 22298.42 22198.58 30699.59 19398.00 28899.37 28599.43 26496.94 33899.07 28599.59 27097.87 11499.03 40798.32 23995.62 38998.71 339
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
h-mvs3397.70 32997.28 35298.97 24399.70 12297.27 32599.36 29199.45 24498.94 7899.66 12699.64 25094.93 25299.99 499.48 6484.36 46799.65 171
DPE-MVScopyleft99.46 4299.32 5499.91 699.78 7099.88 1099.36 29199.51 15298.73 10299.88 4399.84 9698.72 6799.96 4198.16 25299.87 7999.88 35
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
UnsupCasMVSNet_eth96.44 38796.12 38897.40 40898.65 42195.65 40099.36 29199.51 15297.13 31696.04 44298.99 40688.40 41898.17 44696.71 36990.27 45398.40 415
sss99.17 10999.05 11299.53 13399.62 17498.97 18399.36 29199.62 5197.83 23799.67 12199.65 24497.37 12899.95 7699.19 10499.19 20399.68 156
DeepC-MVS_fast98.69 199.49 3399.39 4099.77 7499.63 16599.59 8899.36 29199.46 23399.07 5899.79 7699.82 11598.85 4499.92 12398.68 19099.87 7999.82 72
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CANet99.25 9699.14 9499.59 11399.41 26499.16 15599.35 29699.57 8598.82 8999.51 17699.61 26596.46 18199.95 7699.59 4599.98 499.65 171
pmmvs-eth3d95.34 40894.73 41197.15 41295.53 46795.94 39599.35 29699.10 37195.13 41393.55 45797.54 45988.15 42297.91 45294.58 41789.69 45897.61 452
MDTV_nov1_ep13_2view95.18 41799.35 29696.84 34399.58 15995.19 24397.82 28599.46 250
FE-MVSNET193.64 42492.69 43096.48 43094.12 47494.21 43899.34 29999.38 28793.42 44293.33 45997.58 45674.82 46997.65 46092.56 44689.64 45997.58 455
VDD-MVS97.73 32397.35 34098.88 26599.47 24797.12 33399.34 29998.85 41098.19 17099.67 12199.85 8182.98 45599.92 12399.49 6198.32 28499.60 191
COLMAP_ROBcopyleft97.56 698.86 18098.75 18199.17 22099.88 1398.53 25299.34 29999.59 7397.55 27398.70 34899.89 4295.83 21299.90 14898.10 25899.90 5799.08 296
Johannes L. Schönberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
viewmambaseed2359dif99.01 16298.90 15699.32 19399.58 19598.51 25899.33 30299.54 10997.85 23399.44 19099.85 8196.01 20199.79 24199.41 7099.13 21199.67 160
myMVS_eth3d2897.69 33097.34 34398.73 28999.27 30597.52 31699.33 30298.78 42098.03 21498.82 33098.49 43486.64 43299.46 32598.44 22598.24 29099.23 284
EGC-MVSNET82.80 44177.86 44797.62 39897.91 44296.12 39199.33 30299.28 3438.40 48525.05 48699.27 37484.11 45099.33 35589.20 45798.22 29197.42 459
diffmvs_AUTHOR99.19 10199.10 9999.48 15699.64 16198.85 21699.32 30599.48 20098.50 12499.81 6999.81 13096.82 16099.88 16899.40 7199.12 21699.71 144
ETVMVS97.50 35096.90 37099.29 20399.23 31698.78 23099.32 30598.90 40397.52 27998.56 36898.09 45284.72 44899.69 28797.86 28097.88 30999.39 263
FMVSNet596.43 38896.19 38797.15 41299.11 34795.89 39699.32 30599.52 13094.47 43198.34 38199.07 39587.54 42897.07 46492.61 44495.72 38698.47 406
dp97.75 31997.80 27797.59 40299.10 35093.71 44499.32 30598.88 40696.48 37199.08 28499.55 28592.67 34699.82 22396.52 37798.58 26599.24 283
tpmvs97.98 27898.02 25697.84 38599.04 36494.73 42599.31 30999.20 35996.10 40298.76 33899.42 32894.94 25199.81 22896.97 35698.45 27498.97 311
tpmrst98.33 23598.48 21897.90 37999.16 33994.78 42499.31 30999.11 37097.27 30499.45 18599.59 27095.33 23599.84 19698.48 21998.61 26299.09 295
testing9997.36 36096.94 36998.63 30099.18 32996.70 36799.30 31198.93 39397.71 25398.23 38798.26 44484.92 44699.84 19698.04 26897.85 31299.35 269
MP-MVS-pluss99.37 6899.20 8699.88 1599.90 499.87 1799.30 31199.52 13097.18 31299.60 15599.79 16598.79 5299.95 7698.83 16899.91 4699.83 63
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
NCCC99.34 7599.19 8899.79 6899.61 18599.65 7599.30 31199.48 20098.86 8499.21 25799.63 25698.72 6799.90 14898.25 24499.63 16499.80 88
JIA-IIPM97.50 35097.02 36698.93 25098.73 41297.80 30399.30 31198.97 38991.73 45398.91 31494.86 47195.10 24699.71 27597.58 31097.98 30499.28 277
BH-RMVSNet98.41 22798.08 24899.40 17799.41 26498.83 22199.30 31198.77 42197.70 25698.94 31199.65 24492.91 33699.74 25996.52 37799.55 17299.64 178
testing1197.50 35097.10 36398.71 29499.20 32396.91 35999.29 31698.82 41397.89 22798.21 39098.40 43885.63 44199.83 21498.45 22498.04 30399.37 267
Syy-MVS97.09 37497.14 36096.95 42199.00 36992.73 45499.29 31699.39 27997.06 32697.41 41698.15 44793.92 31298.68 43791.71 44898.34 27899.45 253
myMVS_eth3d96.89 37796.37 38298.43 33399.00 36997.16 33199.29 31699.39 27997.06 32697.41 41698.15 44783.46 45498.68 43795.27 40898.34 27899.45 253
MCST-MVS99.43 5399.30 6299.82 5799.79 6899.74 5499.29 31699.40 27698.79 9599.52 17499.62 26198.91 3999.90 14898.64 19499.75 14299.82 72
LF4IMVS97.52 34797.46 32297.70 39598.98 37595.55 40399.29 31698.82 41398.07 19898.66 35199.64 25089.97 39799.61 31097.01 35296.68 35897.94 445
hse-mvs297.50 35097.14 36098.59 30399.49 23997.05 34099.28 32199.22 35598.94 7899.66 12699.42 32894.93 25299.65 29899.48 6483.80 46999.08 296
OPM-MVS98.19 24698.10 24498.45 32898.88 38797.07 33899.28 32199.38 28798.57 11799.22 25499.81 13092.12 36099.66 29398.08 26397.54 32898.61 392
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
diffmvspermissive99.14 12199.02 12599.51 14499.61 18598.96 18799.28 32199.49 18898.46 12899.72 10299.71 20896.50 17999.88 16899.31 8699.11 21899.67 160
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_BlendedMVS98.86 18098.80 17599.03 23599.76 8298.79 22799.28 32199.91 397.42 29299.67 12199.37 34697.53 12299.88 16898.98 13597.29 34898.42 412
OMC-MVS99.08 14599.04 11499.20 21799.67 13598.22 27699.28 32199.52 13098.07 19899.66 12699.81 13097.79 11799.78 24797.79 28999.81 12099.60 191
testing22297.16 37096.50 37999.16 22199.16 33998.47 26599.27 32698.66 43697.71 25398.23 38798.15 44782.28 46099.84 19697.36 33297.66 31899.18 287
AUN-MVS96.88 37896.31 38498.59 30399.48 24697.04 34399.27 32699.22 35597.44 28998.51 37199.41 33291.97 36399.66 29397.71 30183.83 46899.07 301
pmmvs597.52 34797.30 34998.16 35798.57 43096.73 36699.27 32698.90 40396.14 39698.37 37999.53 29491.54 37799.14 38997.51 31995.87 38198.63 381
131498.68 20998.54 21499.11 22798.89 38698.65 23999.27 32699.49 18896.89 34097.99 40099.56 28297.72 12099.83 21497.74 29799.27 19498.84 319
MVS97.28 36596.55 37899.48 15698.78 40398.95 19399.27 32699.39 27983.53 47198.08 39599.54 29096.97 15199.87 17594.23 42399.16 20499.63 183
BH-untuned98.42 22598.36 22498.59 30399.49 23996.70 36799.27 32699.13 36897.24 30898.80 33399.38 34395.75 21899.74 25997.07 35199.16 20499.33 273
MDTV_nov1_ep1398.32 22899.11 34794.44 43399.27 32698.74 42597.51 28099.40 20699.62 26194.78 26399.76 25397.59 30998.81 254
DP-MVS Recon99.12 13198.95 14699.65 9599.74 10099.70 6099.27 32699.57 8596.40 37899.42 19699.68 23198.75 6099.80 23597.98 27199.72 14899.44 255
PatchmatchNetpermissive98.31 23698.36 22498.19 35599.16 33995.32 41399.27 32698.92 39697.37 29699.37 21299.58 27494.90 25699.70 28297.43 32899.21 20199.54 215
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
thres20097.61 34197.28 35298.62 30199.64 16198.03 28699.26 33598.74 42597.68 25899.09 28298.32 44291.66 37499.81 22892.88 44098.22 29198.03 437
CNVR-MVS99.42 5599.30 6299.78 7199.62 17499.71 5899.26 33599.52 13098.82 8999.39 20899.71 20898.96 2799.85 18798.59 20599.80 12599.77 100
mamba_040899.08 14598.96 14299.44 17099.62 17498.88 20899.25 33799.47 22298.05 20599.37 21299.81 13096.85 15599.85 18798.98 13599.25 19799.60 191
SSM_0407299.06 15098.96 14299.35 18699.62 17498.88 20899.25 33799.47 22298.05 20599.37 21299.81 13096.85 15599.58 31398.98 13599.25 19799.60 191
tt032095.71 40395.07 40797.62 39899.05 36295.02 41999.25 33799.52 13086.81 46697.97 40299.72 20583.58 45399.15 38796.38 38393.35 42998.68 353
1112_ss98.98 16698.77 17999.59 11399.68 13299.02 17599.25 33799.48 20097.23 30999.13 27299.58 27496.93 15399.90 14898.87 15598.78 25599.84 53
TAPA-MVS97.07 1597.74 32197.34 34398.94 24899.70 12297.53 31599.25 33799.51 15291.90 45299.30 23299.63 25698.78 5399.64 30288.09 46299.87 7999.65 171
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
UWE-MVS-2897.36 36097.24 35697.75 39198.84 39694.44 43399.24 34297.58 46197.98 21999.00 30099.00 40491.35 38099.53 32093.75 42898.39 27699.27 281
UBG97.85 29797.48 31798.95 24699.25 31297.64 31299.24 34298.74 42597.90 22698.64 35898.20 44688.65 41499.81 22898.27 24298.40 27599.42 257
PLCcopyleft97.94 499.02 15898.85 17099.53 13399.66 14899.01 17799.24 34299.52 13096.85 34299.27 24299.48 31498.25 10199.91 13597.76 29499.62 16599.65 171
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test_post199.23 34565.14 48394.18 30199.71 27597.58 310
ADS-MVSNet298.02 27198.07 25197.87 38199.33 28795.19 41699.23 34599.08 37496.24 38699.10 27999.67 23794.11 30398.93 42696.81 36599.05 22999.48 239
ADS-MVSNet98.20 24598.08 24898.56 31199.33 28796.48 37899.23 34599.15 36596.24 38699.10 27999.67 23794.11 30399.71 27596.81 36599.05 22999.48 239
EPNet_dtu98.03 26997.96 26198.23 35398.27 43895.54 40599.23 34598.75 42299.02 6297.82 40999.71 20896.11 19699.48 32293.04 43899.65 16199.69 150
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CR-MVSNet98.17 24997.93 26698.87 26999.18 32998.49 26199.22 34999.33 31896.96 33499.56 16399.38 34394.33 29499.00 41294.83 41698.58 26599.14 288
RPMNet96.72 38195.90 39499.19 21899.18 32998.49 26199.22 34999.52 13088.72 46499.56 16397.38 46194.08 30599.95 7686.87 46998.58 26599.14 288
sc_t195.75 40195.05 40897.87 38198.83 39794.61 43099.21 35199.45 24487.45 46597.97 40299.85 8181.19 46399.43 33698.27 24293.20 43399.57 209
WBMVS97.74 32197.50 31598.46 32699.24 31497.43 31999.21 35199.42 26697.45 28698.96 30799.41 33288.83 40999.23 37298.94 14396.02 37498.71 339
plane_prior96.97 35199.21 35198.45 13097.60 322
IMVS_040498.53 21898.52 21698.55 31399.55 20896.93 35499.20 35499.44 25398.05 20598.96 30799.80 14894.66 27699.13 39298.15 25498.92 24099.60 191
tt0320-xc95.31 40994.59 41397.45 40698.92 38294.73 42599.20 35499.31 33286.74 46797.23 42299.72 20581.14 46498.95 42497.08 35091.98 44498.67 361
testing9197.44 35797.02 36698.71 29499.18 32996.89 36199.19 35699.04 38197.78 24598.31 38298.29 44385.41 44399.85 18798.01 26997.95 30599.39 263
WR-MVS98.06 26197.73 29099.06 23198.86 39399.25 14699.19 35699.35 30597.30 30298.66 35199.43 32693.94 31099.21 38198.58 20694.28 41698.71 339
new-patchmatchnet94.48 41894.08 41995.67 43695.08 47092.41 45599.18 35899.28 34394.55 43093.49 45897.37 46287.86 42697.01 46591.57 44988.36 46197.61 452
AdaColmapbinary99.01 16298.80 17599.66 9199.56 20499.54 9899.18 35899.70 1898.18 17399.35 22199.63 25696.32 18899.90 14897.48 32299.77 13799.55 213
EG-PatchMatch MVS95.97 39795.69 39896.81 42597.78 44592.79 45399.16 36098.93 39396.16 39394.08 45499.22 38082.72 45699.47 32395.67 39997.50 33398.17 428
PatchT97.03 37596.44 38198.79 28498.99 37298.34 27199.16 36099.07 37792.13 45199.52 17497.31 46494.54 28498.98 41488.54 46098.73 25799.03 304
CNLPA99.14 12198.99 13499.59 11399.58 19599.41 12099.16 36099.44 25398.45 13099.19 26399.49 30898.08 10999.89 16397.73 29899.75 14299.48 239
MDA-MVSNet-bldmvs94.96 41393.98 42097.92 37798.24 43997.27 32599.15 36399.33 31893.80 43580.09 47899.03 40088.31 41997.86 45493.49 43294.36 41598.62 383
CDPH-MVS99.13 12398.91 15499.80 6499.75 9299.71 5899.15 36399.41 26996.60 36299.60 15599.55 28598.83 4799.90 14897.48 32299.83 11399.78 98
save fliter99.76 8299.59 8899.14 36599.40 27699.00 67
WB-MVSnew97.65 33897.65 29897.63 39798.78 40397.62 31399.13 36698.33 44597.36 29799.07 28598.94 41295.64 22399.15 38792.95 43998.68 26096.12 469
testf190.42 43590.68 43689.65 45697.78 44573.97 48499.13 36698.81 41589.62 45991.80 46798.93 41362.23 47598.80 43386.61 47091.17 44796.19 467
APD_test290.42 43590.68 43689.65 45697.78 44573.97 48499.13 36698.81 41589.62 45991.80 46798.93 41362.23 47598.80 43386.61 47091.17 44796.19 467
xiu_mvs_v1_base_debu99.29 8599.27 7399.34 18799.63 16598.97 18399.12 36999.51 15298.86 8499.84 5699.47 31798.18 10499.99 499.50 5799.31 19199.08 296
xiu_mvs_v1_base99.29 8599.27 7399.34 18799.63 16598.97 18399.12 36999.51 15298.86 8499.84 5699.47 31798.18 10499.99 499.50 5799.31 19199.08 296
xiu_mvs_v1_base_debi99.29 8599.27 7399.34 18799.63 16598.97 18399.12 36999.51 15298.86 8499.84 5699.47 31798.18 10499.99 499.50 5799.31 19199.08 296
XVG-OURS-SEG-HR98.69 20898.62 20498.89 26299.71 11797.74 30499.12 36999.54 10998.44 13399.42 19699.71 20894.20 29899.92 12398.54 21698.90 24699.00 307
jason99.13 12399.03 11799.45 16599.46 24998.87 21299.12 36999.26 34798.03 21499.79 7699.65 24497.02 14899.85 18799.02 13299.90 5799.65 171
jason: jason.
N_pmnet94.95 41495.83 39692.31 44798.47 43479.33 47999.12 36992.81 48593.87 43497.68 41299.13 39093.87 31499.01 41191.38 45096.19 37198.59 396
MDA-MVSNet_test_wron95.45 40594.60 41298.01 36898.16 44097.21 33099.11 37599.24 35293.49 43980.73 47798.98 40893.02 33198.18 44594.22 42494.45 41398.64 374
Patchmtry97.75 31997.40 33598.81 28199.10 35098.87 21299.11 37599.33 31894.83 42498.81 33199.38 34394.33 29499.02 40996.10 38695.57 39198.53 400
YYNet195.36 40794.51 41597.92 37797.89 44397.10 33499.10 37799.23 35393.26 44380.77 47699.04 39992.81 33798.02 44994.30 42094.18 41898.64 374
CANet_DTU98.97 16898.87 16499.25 21099.33 28798.42 26999.08 37899.30 33799.16 3799.43 19399.75 19095.27 23799.97 2998.56 21299.95 2399.36 268
icg_test_0407_298.79 19798.86 16798.57 30799.55 20896.93 35499.07 37999.44 25398.05 20599.66 12699.80 14897.13 13999.18 38498.15 25498.92 24099.60 191
SCA98.19 24698.16 23698.27 35199.30 29695.55 40399.07 37998.97 38997.57 27099.43 19399.57 27992.72 34199.74 25997.58 31099.20 20299.52 222
TSAR-MVS + GP.99.36 7299.36 4699.36 18499.67 13598.61 24699.07 37999.33 31899.00 6799.82 6899.81 13099.06 1899.84 19699.09 12399.42 18199.65 171
MG-MVS99.13 12399.02 12599.45 16599.57 20098.63 24299.07 37999.34 31098.99 6999.61 15299.82 11597.98 11399.87 17597.00 35399.80 12599.85 46
PatchMatch-RL98.84 19298.62 20499.52 13999.71 11799.28 14199.06 38399.77 1297.74 25199.50 17799.53 29495.41 23099.84 19697.17 34699.64 16299.44 255
OpenMVS_ROBcopyleft92.34 2094.38 41993.70 42596.41 43197.38 45193.17 45199.06 38398.75 42286.58 46894.84 45198.26 44481.53 46199.32 35789.01 45897.87 31096.76 462
TEST999.67 13599.65 7599.05 38599.41 26996.22 38898.95 30999.49 30898.77 5699.91 135
train_agg99.02 15898.77 17999.77 7499.67 13599.65 7599.05 38599.41 26996.28 38298.95 30999.49 30898.76 5799.91 13597.63 30699.72 14899.75 109
lupinMVS99.13 12399.01 13099.46 16499.51 22598.94 19799.05 38599.16 36497.86 23099.80 7499.56 28297.39 12599.86 18198.94 14399.85 9499.58 206
DELS-MVS99.48 3799.42 3299.65 9599.72 11199.40 12199.05 38599.66 3299.14 4099.57 16299.80 14898.46 8799.94 9299.57 4899.84 10299.60 191
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
new_pmnet96.38 38996.03 39197.41 40798.13 44195.16 41899.05 38599.20 35993.94 43397.39 41998.79 42491.61 37699.04 40590.43 45395.77 38398.05 436
Patchmatch-test97.93 28497.65 29898.77 28799.18 32997.07 33899.03 39099.14 36796.16 39398.74 33999.57 27994.56 28199.72 26993.36 43399.11 21899.52 222
test_899.67 13599.61 8599.03 39099.41 26996.28 38298.93 31299.48 31498.76 5799.91 135
Test_1112_low_res98.89 17398.66 19499.57 12099.69 12798.95 19399.03 39099.47 22296.98 33299.15 27099.23 37996.77 16499.89 16398.83 16898.78 25599.86 42
IterMVS-SCA-FT97.82 30797.75 28898.06 36499.57 20096.36 38299.02 39399.49 18897.18 31298.71 34299.72 20592.72 34199.14 38997.44 32795.86 38298.67 361
xiu_mvs_v2_base99.26 9299.25 7799.29 20399.53 21698.91 20499.02 39399.45 24498.80 9499.71 10899.26 37698.94 3499.98 2099.34 8199.23 20098.98 310
MIMVSNet97.73 32397.45 32398.57 30799.45 25597.50 31799.02 39398.98 38896.11 39899.41 20199.14 38990.28 39198.74 43595.74 39598.93 23899.47 245
IterMVS97.83 30497.77 28398.02 36799.58 19596.27 38699.02 39399.48 20097.22 31098.71 34299.70 21292.75 33899.13 39297.46 32596.00 37698.67 361
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
HyFIR lowres test99.11 13798.92 15199.65 9599.90 499.37 12399.02 39399.91 397.67 26099.59 15899.75 19095.90 20999.73 26599.53 5399.02 23399.86 42
UWE-MVS97.58 34397.29 35198.48 32099.09 35396.25 38799.01 39896.61 47197.86 23099.19 26399.01 40388.72 41099.90 14897.38 33198.69 25999.28 277
新几何299.01 398
BH-w/o98.00 27697.89 27298.32 34399.35 28196.20 38999.01 39898.90 40396.42 37698.38 37899.00 40495.26 23999.72 26996.06 38798.61 26299.03 304
test_prior499.56 9498.99 401
无先验98.99 40199.51 15296.89 34099.93 11097.53 31899.72 133
pmmvs498.13 25397.90 26898.81 28198.61 42698.87 21298.99 40199.21 35896.44 37499.06 29099.58 27495.90 20999.11 39897.18 34596.11 37398.46 409
HQP-NCC99.19 32698.98 40498.24 16298.66 351
ACMP_Plane99.19 32698.98 40498.24 16298.66 351
HQP-MVS98.02 27197.90 26898.37 33999.19 32696.83 36298.98 40499.39 27998.24 16298.66 35199.40 33692.47 35299.64 30297.19 34397.58 32498.64 374
PS-MVSNAJ99.32 7999.32 5499.30 20099.57 20098.94 19798.97 40799.46 23398.92 8199.71 10899.24 37899.01 2099.98 2099.35 7699.66 15998.97 311
MVP-Stereo97.81 30997.75 28897.99 37197.53 44996.60 37598.96 40898.85 41097.22 31097.23 42299.36 34995.28 23699.46 32595.51 40199.78 13497.92 447
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
test_prior298.96 40898.34 14399.01 29699.52 29898.68 7097.96 27299.74 145
旧先验298.96 40896.70 35099.47 18299.94 9298.19 248
原ACMM298.95 411
MVS_111021_HR99.41 5999.32 5499.66 9199.72 11199.47 11398.95 41199.85 998.82 8999.54 17099.73 20198.51 8499.74 25998.91 14999.88 7699.77 100
mvsany_test199.50 3199.46 2899.62 10899.61 18599.09 16598.94 41399.48 20099.10 4899.96 2799.91 2698.85 4499.96 4199.72 3299.58 16999.82 72
MVS_111021_LR99.41 5999.33 5299.65 9599.77 7899.51 10798.94 41399.85 998.82 8999.65 13599.74 19598.51 8499.80 23598.83 16899.89 6899.64 178
pmmvs394.09 42193.25 42896.60 42894.76 47394.49 43298.92 41598.18 45289.66 45896.48 43698.06 45386.28 43697.33 46289.68 45687.20 46497.97 444
XVG-OURS98.73 20698.68 19098.88 26599.70 12297.73 30598.92 41599.55 10098.52 12299.45 18599.84 9695.27 23799.91 13598.08 26398.84 25099.00 307
test22299.75 9299.49 10998.91 41799.49 18896.42 37699.34 22599.65 24498.28 10099.69 15399.72 133
PMMVS286.87 43885.37 44291.35 45190.21 48083.80 47098.89 41897.45 46383.13 47291.67 46995.03 46948.49 48194.70 47585.86 47277.62 47495.54 470
miper_lstm_enhance98.00 27697.91 26798.28 35099.34 28697.43 31998.88 41999.36 29896.48 37198.80 33399.55 28595.98 20298.91 42797.27 33695.50 39498.51 402
MVS-HIRNet95.75 40195.16 40697.51 40499.30 29693.69 44598.88 41995.78 47385.09 47098.78 33692.65 47391.29 38299.37 34594.85 41599.85 9499.46 250
TR-MVS97.76 31597.41 33498.82 27899.06 35997.87 29998.87 42198.56 43996.63 35898.68 35099.22 38092.49 35199.65 29895.40 40597.79 31498.95 315
testdata198.85 42298.32 147
ET-MVSNet_ETH3D96.49 38695.64 40099.05 23399.53 21698.82 22498.84 42397.51 46297.63 26384.77 47199.21 38392.09 36198.91 42798.98 13592.21 44399.41 260
our_test_397.65 33897.68 29597.55 40398.62 42494.97 42198.84 42399.30 33796.83 34598.19 39199.34 35697.01 15099.02 40995.00 41396.01 37598.64 374
MS-PatchMatch97.24 36997.32 34796.99 41898.45 43593.51 44998.82 42599.32 32897.41 29398.13 39499.30 36788.99 40799.56 31695.68 39899.80 12597.90 448
c3_l98.12 25598.04 25398.38 33899.30 29697.69 31198.81 42699.33 31896.67 35298.83 32899.34 35697.11 14298.99 41397.58 31095.34 39698.48 404
ppachtmachnet_test97.49 35597.45 32397.61 40198.62 42495.24 41498.80 42799.46 23396.11 39898.22 38999.62 26196.45 18298.97 42193.77 42795.97 38098.61 392
PAPR98.63 21598.34 22699.51 14499.40 26999.03 17498.80 42799.36 29896.33 37999.00 30099.12 39398.46 8799.84 19695.23 40999.37 19099.66 165
test0.0.03 197.71 32897.42 33398.56 31198.41 43797.82 30298.78 42998.63 43797.34 29898.05 39998.98 40894.45 28998.98 41495.04 41297.15 35498.89 316
PVSNet_Blended99.08 14598.97 13899.42 17599.76 8298.79 22798.78 42999.91 396.74 34799.67 12199.49 30897.53 12299.88 16898.98 13599.85 9499.60 191
PMMVS98.80 19698.62 20499.34 18799.27 30598.70 23598.76 43199.31 33297.34 29899.21 25799.07 39597.20 13799.82 22398.56 21298.87 24799.52 222
test12339.01 45042.50 45228.53 46639.17 48920.91 49198.75 43219.17 49119.83 48438.57 48366.67 48133.16 48515.42 48537.50 48529.66 48349.26 480
MSDG98.98 16698.80 17599.53 13399.76 8299.19 15098.75 43299.55 10097.25 30699.47 18299.77 18197.82 11699.87 17596.93 36099.90 5799.54 215
CLD-MVS98.16 25098.10 24498.33 34199.29 30096.82 36498.75 43299.44 25397.83 23799.13 27299.55 28592.92 33499.67 29098.32 23997.69 31798.48 404
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
miper_ehance_all_eth98.18 24898.10 24498.41 33499.23 31697.72 30798.72 43599.31 33296.60 36298.88 31999.29 36997.29 13299.13 39297.60 30895.99 37798.38 417
cl____98.01 27497.84 27698.55 31399.25 31297.97 29098.71 43699.34 31096.47 37398.59 36799.54 29095.65 22299.21 38197.21 33995.77 38398.46 409
DIV-MVS_self_test98.01 27497.85 27598.48 32099.24 31497.95 29598.71 43699.35 30596.50 36798.60 36699.54 29095.72 22099.03 40797.21 33995.77 38398.46 409
test-LLR98.06 26197.90 26898.55 31398.79 40097.10 33498.67 43897.75 45797.34 29898.61 36498.85 41894.45 28999.45 32797.25 33799.38 18399.10 291
TESTMET0.1,197.55 34497.27 35598.40 33698.93 38096.53 37698.67 43897.61 46096.96 33498.64 35899.28 37188.63 41699.45 32797.30 33599.38 18399.21 286
test-mter97.49 35597.13 36298.55 31398.79 40097.10 33498.67 43897.75 45796.65 35498.61 36498.85 41888.23 42099.45 32797.25 33799.38 18399.10 291
mvs5depth96.66 38296.22 38697.97 37297.00 46096.28 38598.66 44199.03 38396.61 35996.93 43299.79 16587.20 43099.47 32396.65 37594.13 41998.16 429
IB-MVS95.67 1896.22 39095.44 40498.57 30799.21 32196.70 36798.65 44297.74 45996.71 34997.27 42198.54 43386.03 43899.92 12398.47 22286.30 46599.10 291
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
DPM-MVS98.95 16998.71 18799.66 9199.63 16599.55 9698.64 44399.10 37197.93 22399.42 19699.55 28598.67 7299.80 23595.80 39499.68 15699.61 188
thisisatest051598.14 25297.79 27899.19 21899.50 23798.50 26098.61 44496.82 46796.95 33699.54 17099.43 32691.66 37499.86 18198.08 26399.51 17499.22 285
DeepPCF-MVS98.18 398.81 19399.37 4497.12 41599.60 19191.75 45898.61 44499.44 25399.35 2599.83 6499.85 8198.70 6999.81 22899.02 13299.91 4699.81 79
cl2297.85 29797.64 30198.48 32099.09 35397.87 29998.60 44699.33 31897.11 32198.87 32299.22 38092.38 35799.17 38698.21 24695.99 37798.42 412
GA-MVS97.85 29797.47 32099.00 23999.38 27497.99 28998.57 44799.15 36597.04 32998.90 31699.30 36789.83 39999.38 34296.70 37098.33 28099.62 186
TinyColmap97.12 37296.89 37197.83 38699.07 35795.52 40698.57 44798.74 42597.58 26997.81 41099.79 16588.16 42199.56 31695.10 41097.21 35198.39 416
eth_miper_zixun_eth98.05 26697.96 26198.33 34199.26 30897.38 32198.56 44999.31 33296.65 35498.88 31999.52 29896.58 17499.12 39797.39 33095.53 39398.47 406
CMPMVSbinary69.68 2394.13 42094.90 41091.84 44897.24 45580.01 47898.52 45099.48 20089.01 46291.99 46599.67 23785.67 44099.13 39295.44 40397.03 35696.39 466
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
USDC97.34 36297.20 35797.75 39199.07 35795.20 41598.51 45199.04 38197.99 21898.31 38299.86 7489.02 40699.55 31895.67 39997.36 34698.49 403
ambc93.06 44692.68 47782.36 47198.47 45298.73 43195.09 44997.41 46055.55 47799.10 40096.42 38091.32 44697.71 449
miper_enhance_ethall98.16 25098.08 24898.41 33498.96 37897.72 30798.45 45399.32 32896.95 33698.97 30599.17 38597.06 14699.22 37697.86 28095.99 37798.29 421
CHOSEN 280x42099.12 13199.13 9599.08 22899.66 14897.89 29898.43 45499.71 1698.88 8399.62 14799.76 18596.63 17099.70 28299.46 6799.99 199.66 165
testmvs39.17 44943.78 45125.37 46736.04 49016.84 49298.36 45526.56 48920.06 48338.51 48467.32 48029.64 48615.30 48637.59 48439.90 48243.98 481
FPMVS84.93 44085.65 44182.75 46286.77 48363.39 48898.35 45698.92 39674.11 47483.39 47398.98 40850.85 48092.40 47784.54 47394.97 40492.46 472
KD-MVS_2432*160094.62 41593.72 42397.31 40997.19 45795.82 39798.34 45799.20 35995.00 42097.57 41398.35 44087.95 42398.10 44792.87 44177.00 47598.01 438
miper_refine_blended94.62 41593.72 42397.31 40997.19 45795.82 39798.34 45799.20 35995.00 42097.57 41398.35 44087.95 42398.10 44792.87 44177.00 47598.01 438
CL-MVSNet_self_test94.49 41793.97 42196.08 43496.16 46293.67 44698.33 45999.38 28795.13 41397.33 42098.15 44792.69 34596.57 46788.67 45979.87 47397.99 442
PVSNet96.02 1798.85 18998.84 17298.89 26299.73 10797.28 32498.32 46099.60 6797.86 23099.50 17799.57 27996.75 16599.86 18198.56 21299.70 15299.54 215
PAPM97.59 34297.09 36499.07 22999.06 35998.26 27498.30 46199.10 37194.88 42298.08 39599.34 35696.27 19199.64 30289.87 45598.92 24099.31 275
Patchmatch-RL test95.84 39995.81 39795.95 43595.61 46590.57 46198.24 46298.39 44395.10 41795.20 44798.67 42894.78 26397.77 45596.28 38590.02 45499.51 231
UnsupCasMVSNet_bld93.53 42592.51 43196.58 42997.38 45193.82 44198.24 46299.48 20091.10 45693.10 46096.66 46674.89 46898.37 44294.03 42687.71 46397.56 456
LCM-MVSNet86.80 43985.22 44391.53 45087.81 48280.96 47698.23 46498.99 38771.05 47590.13 47096.51 46748.45 48296.88 46690.51 45285.30 46696.76 462
cascas97.69 33097.43 33298.48 32098.60 42797.30 32398.18 46599.39 27992.96 44698.41 37698.78 42593.77 31899.27 36598.16 25298.61 26298.86 317
kuosan90.92 43490.11 43993.34 44398.78 40385.59 46898.15 46693.16 48389.37 46192.07 46498.38 43981.48 46295.19 47362.54 48297.04 35599.25 282
Effi-MVS+98.81 19398.59 21099.48 15699.46 24999.12 16398.08 46799.50 17597.50 28199.38 21099.41 33296.37 18799.81 22899.11 11898.54 27099.51 231
PCF-MVS97.08 1497.66 33797.06 36599.47 16299.61 18599.09 16598.04 46899.25 34991.24 45598.51 37199.70 21294.55 28399.91 13592.76 44399.85 9499.42 257
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PVSNet_094.43 1996.09 39595.47 40297.94 37599.31 29594.34 43797.81 46999.70 1897.12 31897.46 41598.75 42689.71 40099.79 24197.69 30481.69 47199.68 156
E-PMN80.61 44379.88 44582.81 46190.75 47976.38 48297.69 47095.76 47466.44 47983.52 47292.25 47462.54 47487.16 48168.53 48061.40 47884.89 479
dongtai93.26 42692.93 42994.25 43999.39 27285.68 46797.68 47193.27 48192.87 44796.85 43399.39 34082.33 45997.48 46176.78 47597.80 31399.58 206
ANet_high77.30 44574.86 44984.62 46075.88 48677.61 48097.63 47293.15 48488.81 46364.27 48189.29 47836.51 48483.93 48375.89 47752.31 48092.33 474
EMVS80.02 44479.22 44682.43 46391.19 47876.40 48197.55 47392.49 48666.36 48083.01 47491.27 47664.63 47385.79 48265.82 48160.65 47985.08 478
MVEpermissive76.82 2176.91 44674.31 45084.70 45985.38 48576.05 48396.88 47493.17 48267.39 47871.28 48089.01 47921.66 48987.69 48071.74 47972.29 47790.35 476
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method91.10 43291.36 43490.31 45395.85 46373.72 48694.89 47599.25 34968.39 47795.82 44399.02 40280.50 46598.95 42493.64 43094.89 40898.25 424
Gipumacopyleft90.99 43390.15 43893.51 44298.73 41290.12 46293.98 47699.45 24479.32 47392.28 46394.91 47069.61 47097.98 45187.42 46695.67 38792.45 473
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVScopyleft70.75 2275.98 44774.97 44879.01 46470.98 48755.18 48993.37 47798.21 45065.08 48161.78 48293.83 47221.74 48892.53 47678.59 47491.12 44989.34 477
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt82.80 44181.52 44486.66 45866.61 48868.44 48792.79 47897.92 45468.96 47680.04 47999.85 8185.77 43996.15 47197.86 28043.89 48195.39 471
wuyk23d40.18 44841.29 45336.84 46586.18 48449.12 49079.73 47922.81 49027.64 48225.46 48528.45 48521.98 48748.89 48455.80 48323.56 48412.51 482
mmdepth0.02 4550.03 4580.00 4680.00 4910.00 4930.00 4800.00 4920.00 4860.00 4870.27 4870.00 4900.00 4870.00 4860.00 4850.00 483
monomultidepth0.02 4550.03 4580.00 4680.00 4910.00 4930.00 4800.00 4920.00 4860.00 4870.27 4870.00 4900.00 4870.00 4860.00 4850.00 483
test_blank0.13 4540.17 4570.00 4680.00 4910.00 4930.00 4800.00 4920.00 4860.00 4871.57 4860.00 4900.00 4870.00 4860.00 4850.00 483
uanet_test0.02 4550.03 4580.00 4680.00 4910.00 4930.00 4800.00 4920.00 4860.00 4870.27 4870.00 4900.00 4870.00 4860.00 4850.00 483
DCPMVS0.02 4550.03 4580.00 4680.00 4910.00 4930.00 4800.00 4920.00 4860.00 4870.27 4870.00 4900.00 4870.00 4860.00 4850.00 483
cdsmvs_eth3d_5k24.64 45132.85 4540.00 4680.00 4910.00 4930.00 48099.51 1520.00 4860.00 48799.56 28296.58 1740.00 4870.00 4860.00 4850.00 483
pcd_1.5k_mvsjas8.27 45311.03 4560.00 4680.00 4910.00 4930.00 4800.00 4920.00 4860.00 4870.27 48799.01 200.00 4870.00 4860.00 4850.00 483
sosnet-low-res0.02 4550.03 4580.00 4680.00 4910.00 4930.00 4800.00 4920.00 4860.00 4870.27 4870.00 4900.00 4870.00 4860.00 4850.00 483
sosnet0.02 4550.03 4580.00 4680.00 4910.00 4930.00 4800.00 4920.00 4860.00 4870.27 4870.00 4900.00 4870.00 4860.00 4850.00 483
uncertanet0.02 4550.03 4580.00 4680.00 4910.00 4930.00 4800.00 4920.00 4860.00 4870.27 4870.00 4900.00 4870.00 4860.00 4850.00 483
Regformer0.02 4550.03 4580.00 4680.00 4910.00 4930.00 4800.00 4920.00 4860.00 4870.27 4870.00 4900.00 4870.00 4860.00 4850.00 483
ab-mvs-re8.30 45211.06 4550.00 4680.00 4910.00 4930.00 4800.00 4920.00 4860.00 48799.58 2740.00 4900.00 4870.00 4860.00 4850.00 483
uanet0.02 4550.03 4580.00 4680.00 4910.00 4930.00 4800.00 4920.00 4860.00 4870.27 4870.00 4900.00 4870.00 4860.00 4850.00 483
WAC-MVS97.16 33195.47 402
MSC_two_6792asdad99.87 2199.51 22599.76 4999.33 31899.96 4198.87 15599.84 10299.89 29
PC_three_145298.18 17399.84 5699.70 21299.31 398.52 44098.30 24199.80 12599.81 79
No_MVS99.87 2199.51 22599.76 4999.33 31899.96 4198.87 15599.84 10299.89 29
test_one_060199.81 5799.88 1099.49 18898.97 7599.65 13599.81 13099.09 16
eth-test20.00 491
eth-test0.00 491
ZD-MVS99.71 11799.79 4199.61 6096.84 34399.56 16399.54 29098.58 7899.96 4196.93 36099.75 142
IU-MVS99.84 3899.88 1099.32 32898.30 14999.84 5698.86 16099.85 9499.89 29
test_241102_TWO99.48 20099.08 5699.88 4399.81 13098.94 3499.96 4198.91 14999.84 10299.88 35
test_241102_ONE99.84 3899.90 399.48 20099.07 5899.91 3199.74 19599.20 999.76 253
test_0728_THIRD98.99 6999.81 6999.80 14899.09 1699.96 4198.85 16299.90 5799.88 35
GSMVS99.52 222
test_part299.81 5799.83 2299.77 85
sam_mvs194.86 25899.52 222
sam_mvs94.72 270
MTGPAbinary99.47 222
test_post65.99 48294.65 27799.73 265
patchmatchnet-post98.70 42794.79 26299.74 259
gm-plane-assit98.54 43292.96 45294.65 42899.15 38899.64 30297.56 315
test9_res97.49 32199.72 14899.75 109
agg_prior297.21 33999.73 14799.75 109
agg_prior99.67 13599.62 8399.40 27698.87 32299.91 135
TestCases99.31 19599.86 2598.48 26399.61 6097.85 23399.36 21899.85 8195.95 20499.85 18796.66 37399.83 11399.59 202
test_prior99.68 8999.67 13599.48 11199.56 9099.83 21499.74 114
新几何199.75 7799.75 9299.59 8899.54 10996.76 34699.29 23599.64 25098.43 8999.94 9296.92 36299.66 15999.72 133
旧先验199.74 10099.59 8899.54 10999.69 22398.47 8699.68 15699.73 123
原ACMM199.65 9599.73 10799.33 13099.47 22297.46 28399.12 27499.66 24298.67 7299.91 13597.70 30399.69 15399.71 144
testdata299.95 7696.67 372
segment_acmp98.96 27
testdata99.54 12599.75 9298.95 19399.51 15297.07 32499.43 19399.70 21298.87 4299.94 9297.76 29499.64 16299.72 133
test1299.75 7799.64 16199.61 8599.29 34199.21 25798.38 9599.89 16399.74 14599.74 114
plane_prior799.29 30097.03 346
plane_prior699.27 30596.98 35092.71 343
plane_prior599.47 22299.69 28797.78 29097.63 31998.67 361
plane_prior499.61 265
plane_prior397.00 34898.69 10799.11 276
plane_prior199.26 308
n20.00 492
nn0.00 492
door-mid98.05 453
lessismore_v097.79 39098.69 41895.44 41094.75 47795.71 44499.87 6688.69 41299.32 35795.89 39194.93 40698.62 383
LGP-MVS_train98.49 31899.33 28797.05 34099.55 10097.46 28399.24 24999.83 10292.58 34899.72 26998.09 25997.51 33198.68 353
test1199.35 305
door97.92 454
HQP5-MVS96.83 362
BP-MVS97.19 343
HQP4-MVS98.66 35199.64 30298.64 374
HQP3-MVS99.39 27997.58 324
HQP2-MVS92.47 352
NP-MVS99.23 31696.92 35899.40 336
ACMMP++_ref97.19 352
ACMMP++97.43 342
Test By Simon98.75 60
ITE_SJBPF98.08 36399.29 30096.37 38198.92 39698.34 14398.83 32899.75 19091.09 38499.62 30995.82 39297.40 34498.25 424
DeepMVS_CXcopyleft93.34 44399.29 30082.27 47299.22 35585.15 46996.33 43799.05 39890.97 38699.73 26593.57 43197.77 31598.01 438