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
ACMH97.28 295.29 193.25 296.65 196.32 197.93 189.82 296.68 295.69 2
LTVRE_ROB97.16 395.10 294.13 195.75 295.69 295.73 392.87 195.39 395.83 1
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
COLMAP_ROBcopyleft97.56 194.43 393.09 395.33 394.55 396.37 289.45 396.72 195.07 3
Johannes L. Schönberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
R-MVSNet90.93 489.80 491.68 490.81 594.15 587.67 491.93 490.07 4
OpenMVS_ROBcopyleft92.34 487.46 581.75 591.27 592.55 495.21 481.21 582.29 586.05 5
hgnet78.82 676.20 780.57 684.50 682.32 975.56 776.84 874.88 6
DPSNet78.82 676.20 780.57 684.50 682.32 975.56 776.84 874.88 6
MVEpermissive76.82 576.63 877.52 676.03 1070.40 1185.49 675.68 679.36 672.20 10
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
example74.48 965.59 1080.41 884.10 883.16 862.82 968.36 1073.98 9
MVSNet73.65 1070.01 976.07 976.39 977.59 1161.93 1078.09 774.23 8
PMVScopyleft70.75 658.19 1143.22 1168.18 1173.06 1084.09 754.23 1132.21 1147.37 11
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
CMPMVSbinary69.68 711.01 120.97 1217.70 1210.09 1243.01 121.93 120.00 120.00 12
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011