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_ROB55.42 236.88 128.57 142.42 140.72 348.22 126.97 130.17 238.32 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
OpenMVS_ROBcopyleft52.78 435.39 227.98 240.33 246.81 136.10 524.79 231.17 138.08 3
COLMAP_ROBcopyleft52.97 333.06 325.38 338.18 435.81 445.04 322.92 327.84 333.69 4
Johannes L. Schönberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
ACMH55.70 132.91 423.69 439.06 341.22 236.76 421.84 425.54 439.18 1
MVSNet27.45 518.54 533.39 529.32 547.13 213.18 623.89 523.72 5
R-MVSNet23.84 618.30 627.54 627.82 633.79 614.57 522.03 621.00 6
PMVScopyleft28.69 610.60 74.70 1114.53 710.82 1030.05 86.66 112.74 112.71 8
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
example9.54 85.97 1011.92 813.40 720.72 96.89 105.05 101.63 11
hgnet9.31 96.52 811.17 1010.91 820.13 107.15 85.89 82.47 9
DPSNet9.31 96.52 811.17 1010.91 820.13 107.15 85.89 82.47 9
MVEpermissive17.77 79.03 119.66 78.62 126.03 1111.40 128.30 711.02 78.42 7
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
CMPMVSbinary42.80 56.77 120.01 1211.27 91.93 1231.86 70.03 120.00 120.00 12
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011