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
ACMH63.93 152.68 135.79 363.93 160.12 170.07 134.99 336.59 361.61 1
OpenMVS_ROBcopyleft61.12 248.48 231.63 459.71 259.03 267.15 231.08 432.18 452.95 2
COLMAP_ROBcopyleft57.96 445.89 337.03 251.79 349.43 356.42 636.78 137.28 249.53 3
Johannes L. Schönberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
LTVRE_ROB59.60 343.60 437.31 147.80 445.94 449.52 836.19 238.43 147.93 4
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
R-MVSNet37.16 526.49 544.27 542.37 552.02 724.06 528.93 538.41 5
MVSNet27.67 618.22 733.96 626.28 743.46 913.67 1022.78 732.14 6
MVEpermissive24.84 726.04 720.59 629.66 822.29 1042.00 1015.49 925.70 624.70 7
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
example24.50 816.56 829.80 727.47 656.53 517.69 615.43 85.40 11
hgnet22.90 913.03 929.49 925.13 856.72 316.70 79.35 96.62 9
DPSNet22.90 913.03 929.49 925.13 856.72 316.70 79.35 96.62 9
PMVScopyleft26.43 613.46 117.26 1117.59 1114.19 1130.85 1110.42 114.11 117.73 8
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
CMPMVSbinary48.56 54.84 120.02 128.06 121.22 1222.96 120.03 120.00 120.00 12
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011