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
LTVRE_ROB88.41 182.23 178.11 184.97 386.24 182.83 276.93 179.30 285.84 3
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_ROBcopyleft87.81 281.57 274.74 286.13 183.81 387.08 169.46 280.01 187.49 1
Johannes L. Schönberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
ACMH87.59 380.55 373.69 385.11 286.17 282.81 368.19 379.20 386.36 2
OpenMVS_ROBcopyleft81.14 473.28 463.11 580.06 482.70 481.62 461.11 465.12 575.87 4
R-MVSNet70.54 563.98 474.91 573.85 577.87 559.85 568.11 473.01 5
MVSNet56.22 646.49 662.70 657.79 767.16 738.93 754.05 663.16 6
MVEpermissive50.73 744.67 745.57 744.07 1135.90 1152.30 1140.89 650.26 744.00 7
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
hgnet44.61 838.48 848.69 857.33 860.08 837.17 839.80 828.65 9
DPSNet44.61 838.48 848.69 857.33 860.08 837.17 839.80 828.65 9
PMVScopyleft53.92 642.74 1026.50 1153.57 754.03 1068.05 636.35 1016.65 1138.64 8
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
example40.49 1130.54 1047.11 1058.75 658.88 1029.97 1131.12 1023.71 11
CMPMVSbinary62.92 58.44 120.22 1213.92 124.26 1237.50 120.45 120.00 120.00 12
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011