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
PMVScopyleft863.65 1639.40 1530.00 4712.33 1798.00 5888.00 5701.00 5359.00 1451.00 1
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
hgnet660.88 2500.81 1767.59 2683.99 1726.46 1489.58 1512.04 2892.32 2
example660.88 2500.81 1767.59 2683.99 1726.46 1489.58 1512.04 2892.32 2
DPSNet660.88 2500.81 1767.59 2683.99 1726.46 1489.58 1512.04 2892.32 2
MVSNet769.20 5609.10 5875.93 5786.50 4836.20 4593.70 4624.50 51005.10 5
ACMH993.80 21055.91 6719.19 61280.39 61101.67 61267.33 6717.78 6720.60 61472.17 6
OpenMVS_ROBcopyleft1936.51 31881.32 71172.27 72354.03 72118.19 72241.51 71205.90 71138.64 72702.38 7
R-MVSNet2412.80 81890.00 82761.33 82391.00 82612.00 81879.00 81901.00 83281.00 8
COLMAP_ROBcopyleft2144.59 43311.60 92554.50 93816.33 93382.00 93555.00 92484.00 92625.00 94512.00 9
Johannes L. Schönberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
CMPMVSbinary2623.62 54160.94 103037.05 104910.20 104057.20 105253.20 103109.40 112964.70 105420.20 10
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MVEpermissive10021.00 68749.80 113439.50 1112290.00 116275.00 1116332.00 112923.00 103956.00 1114263.00 12
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
LTVRE_ROB20565.47 713815.20 127669.50 1217912.33 1222283.00 1221104.00 127445.00 127894.00 1210350.00 11
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