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
indooroutdoordelivery areaelectroforestplaygroundterrains
sort bysorted bysort bysort bysort bysort bysort bysort bysort by
LTVRE_ROB59.44 353.25 156.08 151.36 139.82 153.93 162.24 137.92 272.34 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
ACMH65.37 151.50 253.46 250.20 238.46 252.73 257.24 340.63 168.46 2
COLMAP_ROBcopyleft62.73 249.91 351.76 348.68 337.30 352.31 361.83 231.91 366.23 3
Johannes L. Schönberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
PMVScopyleft39.38 522.01 432.82 414.80 45.84 711.38 526.05 46.98 659.80 4
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
example18.45 528.74 511.60 56.01 65.21 822.21 57.37 551.47 5
MVEpermissive19.12 615.60 622.59 910.94 65.22 814.12 48.87 89.84 439.95 9
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
hgnet15.22 724.38 69.11 76.26 45.91 617.93 63.49 742.51 7
DPSNet15.22 724.38 69.11 76.26 45.91 617.93 63.49 742.51 7
CMPMVSbinary47.78 49.53 923.73 80.07 90.00 90.00 90.20 90.00 947.47 6
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011