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_ROB86.10 169.45 158.19 176.95 181.50 278.07 355.83 160.55 371.29 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
MVSNet65.82 252.08 274.99 388.07 185.21 141.08 363.08 151.67 6
COLMAP_ROBcopyleft83.01 261.51 350.83 368.63 465.07 466.61 540.64 461.02 274.20 1
Johannes L. Schönberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
PMVScopyleft80.48 357.42 429.11 776.30 279.61 379.41 234.22 524.00 769.88 3
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
OpenMVS_ROBcopyleft70.19 551.98 550.29 453.10 565.07 439.38 742.82 257.77 454.85 4
ACMH76.49 445.64 641.63 548.31 653.97 638.96 834.00 649.25 552.00 5
R-MVSNet37.45 734.59 639.35 741.64 742.85 625.44 743.75 633.57 7
CMPMVSbinary59.41 621.70 80.34 1235.93 838.78 869.01 40.69 120.00 120.00 12
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
hgnet14.22 913.23 914.89 1018.80 1020.68 1010.37 916.09 85.18 9
DPSNet14.22 913.23 914.89 1018.80 1020.68 1010.37 916.09 85.18 9
MVEpermissive40.22 712.38 1114.61 810.89 127.98 1212.62 1213.54 815.69 1012.06 8
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
example11.91 127.31 1114.98 920.88 920.72 98.09 116.53 113.34 11