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 bysort bysort bysort bysort bysort bysorted bysort bysort by
LTVRE_ROB69.57 153.52 145.46 158.89 158.76 260.60 243.91 147.01 157.32 2
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_ROBcopyleft66.92 352.32 242.45 258.89 156.18 461.09 138.61 246.28 259.41 1
Johannes L. Schönberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
OpenMVS_ROBcopyleft64.09 448.56 338.68 355.15 361.90 149.65 536.02 341.33 453.89 4
ACMH67.68 247.97 438.24 454.45 456.88 350.08 434.49 441.99 356.40 3
R-MVSNet36.87 629.78 541.61 642.00 546.99 624.73 534.83 535.83 6
MVSNet38.33 526.99 645.89 540.49 657.57 320.52 633.47 639.63 5
PMVScopyleft37.38 621.09 711.49 1027.48 724.09 744.44 715.98 77.01 1113.92 8
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVEpermissive26.22 716.26 1016.97 715.79 1111.75 1119.40 1214.45 819.48 716.21 7
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
hgnet16.45 812.31 819.21 921.51 930.31 1012.80 911.82 85.81 9
DPSNet16.45 812.31 819.21 921.51 930.31 1012.80 911.82 85.81 9
example15.69 1110.14 1119.39 823.73 830.32 911.10 119.17 104.13 11
CMPMVSbinary51.72 57.38 120.03 1212.27 122.37 1234.46 80.06 120.00 120.00 12
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011