Robust Vision Challenge 2022 Banner

Benchmarks

SLAM benchmark

Stereo benchmark

Open Source Code

See the ETH3D project on GitHub.

News

More details are available in the changelog.

  • 2019-06-16: Added the SLAM Benchmark.
  • 2018-04-16: Added pre-rendered depth maps for training datasets for convenience.
  • 2018-02-05: Open source release of the dataset pipeline.
  • 2017-10-04: Extension with more data.
  • 2017-07-19: Initial release of the dataset.

Publications

If you use our data in your research, please cite the appropriate publication. The SLAM benchmark was introduced in:

T. Schöps, T. Sattler, M. Pollefeys, "BAD SLAM: Bundle Adjusted Direct RGB-D SLAM", Conference on Computer Vision and Pattern Recognition (CVPR), 2019. [Bibtex][PDF][Supplementary][Talk][Code][Poster]

The stereo benchmark was introduced in:

T. Schöps, J. L. Schönberger, S. Galliani, T. Sattler, K. Schindler, M. Pollefeys, A. Geiger, "A Multi-View Stereo Benchmark with High-Resolution Images and Multi-Camera Videos", Conference on Computer Vision and Pattern Recognition (CVPR), 2017. [Bibtex][PDF][Supplementary][Poster]

License

The data provided here is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.