Low-resolution many-view benchmark
This table lists the benchmark results for the low-res many-view scenario. The following metrics are evaluated:
- Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*).
- Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*).
- F1 score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics.
- Time [s]: The runtime of the method.
(*) 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.
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.
|indoor||outdoor||lakeside||sand box||storage room||storage room 2||tunnel|
|LTVRE||69.57 1||53.52 1||45.46 1||58.89 1||58.76 1||60.60 2||43.91 1||47.01 1||57.32 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|
|COLMAP||66.92 2||52.32 2||42.45 2||58.89 1||56.18 2||61.09 1||38.61 2||46.28 2||59.41 1|
|Johannes L. Schönberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016|
|PMVS||37.38 4||21.09 3||11.49 4||27.48 3||24.09 3||44.44 3||15.98 3||7.01 4||13.92 4|
|Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)|
|MVE||26.22 5||16.26 4||16.97 3||15.79 4||11.75 4||19.40 5||14.45 4||19.48 3||16.21 3|
|Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)|
|CMPMVS||51.72 3||7.38 5||0.03 5||12.27 5||2.37 5||34.46 4||0.06 5||0.00 5||0.00 5|
|M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011|