This table lists the benchmark results for the low-res many-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 Infoalllow-res
many-view
indooroutdoorlakesidesand boxstorage roomstorage room 2tunnel
sort bysorted bysort bysort bysort bysort bysort bysort bysort by
DeepPCF-MVS96.37 292.61 189.11 194.94 195.58 195.07 185.62 192.60 194.17 1
DeepC-MVS_fast96.70 192.27 288.75 294.63 295.15 394.80 285.14 392.35 293.92 2
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DeepC-MVS95.98 391.43 387.48 494.06 494.52 594.15 583.69 691.26 393.50 3
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TAPA-MVS93.98 790.68 488.05 392.44 792.42 1093.52 885.24 290.85 691.36 14
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
TAPA-MVS(SR)90.57 587.48 492.63 692.64 893.17 1183.91 591.04 492.10 12
PCF-MVS93.45 1090.50 685.08 1394.11 395.54 293.44 1082.27 1187.88 1593.34 4
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
COLMAP(SR)90.17 785.79 1193.08 592.63 993.87 682.51 1089.07 1392.74 6
PLCcopyleft95.07 489.96 887.00 691.94 1290.65 1892.68 1583.01 890.98 592.48 7
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
COLMAP(base)89.91 986.37 892.28 991.56 1492.95 1382.53 990.21 792.33 8
ACMH+92.99 1389.84 1085.96 1092.43 892.28 1192.84 1481.89 1290.03 892.17 10
GSE89.80 1186.71 791.87 1390.87 1792.62 1683.49 789.92 992.11 11
ACMM93.85 889.42 1285.42 1292.10 1191.09 1692.98 1281.16 1489.68 1092.23 9
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMP93.49 989.04 1384.30 1692.21 1090.34 1993.47 979.54 1889.07 1392.81 5
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB92.95 1489.00 1486.32 990.78 1991.67 1389.54 2284.87 487.77 1691.13 16
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
ACMH92.88 1588.89 1584.55 1491.78 1491.37 1592.41 1779.88 1689.21 1191.56 13
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
COLMAP_ROBcopyleft93.27 1188.32 1684.41 1590.93 1889.38 2092.11 1879.72 1789.10 1291.28 15
Johannes L. Schönberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
3Dnovator94.51 587.43 1780.90 2191.78 1494.76 494.22 378.96 1982.85 2186.35 20
3Dnovator+94.38 687.07 1880.26 2291.61 1694.34 694.17 478.01 2082.52 2286.34 21
A-TVSNet + Gipumacopyleft86.96 1982.91 1889.65 2188.10 2291.71 1980.23 1585.60 2089.15 18
BP-MVSNet86.71 2081.68 1990.06 2091.85 1287.55 2775.75 2387.61 1790.77 17
Christian Sormann, Patrick Knöbelreiter, Andreas Kuhn, Mattia Rossi, Thomas Pock, Friedrich Fraundorfer: BP-MVSNet: Belief-Propagation-Layers for Multi-View-Stereo. 3DV 2020
OpenMVScopyleft93.04 1286.34 2179.08 2391.18 1793.50 793.77 776.56 2181.60 2586.26 22
LPCS85.52 2283.61 1786.79 2384.99 2788.49 2481.34 1385.87 1986.89 19
PVSNet_088.72 1782.59 2375.14 2687.55 2288.79 2188.38 2573.35 2676.93 2885.48 23
PVSNet91.96 1681.42 2474.82 2785.83 2587.90 2386.77 2874.82 2474.81 3282.83 24
R-MVSNet81.26 2577.44 2483.81 2782.82 2886.25 2974.52 2580.36 2682.37 25
CIDER80.48 2672.14 2986.05 2487.66 2489.77 2071.75 2772.53 3580.72 27
Qingshan Xu and Wenbing Tao: Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume. AAAI 2020
OpenMVS_ROBcopyleft86.42 1880.25 2771.88 3185.82 2687.52 2589.56 2170.53 2873.24 3480.39 28
ANet-0.7577.73 2874.78 2879.70 3077.01 3484.71 3267.34 3282.21 2477.39 31
P-MVSNet77.69 2981.61 2075.07 3671.91 4077.33 3776.51 2286.71 1875.98 34
CPR_FA74.23 3072.06 3075.68 3474.30 3870.69 4368.60 3075.52 3082.05 26
ANet74.07 3168.26 3377.94 3377.01 3484.71 3264.75 3371.76 3672.09 37
AttMVS72.35 3268.13 3475.16 3570.98 4480.63 3468.09 3168.16 3773.87 36
Pnet-new-70.55 3353.66 4581.81 2981.27 3085.23 3151.15 4256.17 5178.92 30
CasMVSNet(SR_A)69.66 3455.07 4179.38 3180.08 3187.62 2646.56 4763.58 4470.44 38
Pnet_fast68.89 3547.01 5483.47 2881.84 2989.30 2338.61 5555.42 5279.28 29
CasMVSNet(base)68.63 3653.70 4478.58 3279.92 3285.96 3044.83 4962.57 4669.87 39
A1Net68.49 3775.64 2563.72 4563.53 5151.39 5868.88 2982.41 2376.23 33
MVSNet_plusplus64.09 3848.06 5274.77 3785.29 2662.00 4831.11 5865.01 3877.03 32
Pnet-blend64.02 3952.13 4971.95 3875.81 3678.00 3540.66 5263.61 4262.05 43
Pnet-blend++64.02 3952.13 4971.95 3875.81 3678.00 3540.66 5263.61 4262.05 43
unMVSv163.91 4162.59 3764.80 4466.39 4768.00 4661.62 3463.55 4560.01 46
MVSNet63.58 4256.25 3968.47 4366.00 4871.12 4048.36 4464.13 3968.29 41
MVSCRF63.13 4352.16 4870.45 4070.18 4575.83 3951.17 4153.16 5565.33 42
RMVSNet62.69 4469.01 3258.48 5369.15 4658.56 5259.72 3578.30 2747.75 56
metmvs_fine60.95 4566.50 3557.25 5564.00 4951.92 5659.04 3673.97 3355.84 51
Snet60.77 4647.18 5369.82 4177.90 3361.73 4939.61 5454.76 5369.82 40
Pnet-eth60.43 4765.87 3656.80 5663.59 5045.39 6155.58 3876.16 2961.43 45
MVSNet_++59.91 4845.04 5569.82 4174.28 3960.08 5014.97 6175.11 3175.10 35
hgnet59.89 4954.16 4263.70 4671.39 4170.87 4152.09 3956.24 4948.85 53
DPSNet59.89 4954.16 4263.70 4671.39 4170.87 4152.09 3956.24 4948.85 53
MVEpermissive62.14 2059.41 5160.38 3858.77 5250.39 5969.00 4556.98 3763.78 4156.91 50
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
MVSNet + Gipuma57.07 5253.08 4659.73 5162.91 5457.42 5448.41 4357.74 4758.88 47
CasMVSNet(SR_B)56.87 5355.95 4057.48 5456.06 5667.85 4747.86 4664.05 4048.53 55
F/T MVSNet+Gipuma55.78 5449.83 5159.76 5063.10 5257.51 5346.34 4853.31 5458.66 48
example55.06 5544.75 5661.93 4871.21 4369.85 4442.82 5146.68 5644.73 58
firsttry54.62 5652.74 4755.88 5754.90 5755.69 5548.02 4557.46 4857.06 49
PMVScopyleft61.03 2149.24 5732.69 6160.27 4962.70 5576.26 3842.99 5022.38 6141.86 59
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
unMVSmet48.01 5840.73 5852.86 5853.90 5858.72 5136.72 5744.74 5845.96 57
confMetMVS44.56 5941.82 5746.39 5946.63 6051.78 5737.38 5646.25 5740.77 60
test_1120copyleft40.25 6035.81 6043.21 6030.29 6250.38 5929.89 6041.72 6048.95 52
Cas-MVS_preliminary38.91 6136.73 5940.37 6137.57 6148.76 6030.59 5942.87 5934.76 61
CMPMVSbinary66.06 199.32 620.44 6315.23 626.17 6339.51 620.89 630.00 630.00 63
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FADENet4.02 634.30 623.83 636.03 643.71 635.02 623.58 621.74 62
dnet0.00 640.00 640.00 640.00 650.00 640.00 640.00 630.00 63
UnsupFinetunedMVSNet63.10 52