Varied datasets

  • 13 / 12 DSLR datasets for training / testing.
  • 5 / 5 multi-cam rig videos for training / testing.
  • 27 / 20 frames for two-view stereo training / testing.

New challenges

  • High-resolution (24 Mpx) DSLR images
  • Multi-camera rig videos (4 cameras, ~13.6 Hz)

Rich visualizations

This webpage presents a multi-view stereo / 3D reconstruction benchmark covering a variety of indoor and outdoor scenes.
Ground truth geometry has been obtained using a high-precision laser scanner.
A DSLR camera as well as a synchronized multi-camera rig with varying field-of-view was used to capture images.
We offer the following challenges:

For a detailed description of the data and the format in which it is provided, see Documentation.
For downloading the datasets, go to Datasets.
Open source code related to the benchmark is available on GitHub.
The ETH3D benchmark is a part of the Robust Vision Challenge.


This list is a summary, more details are available in the changelog.


If you use our data in your research, please cite:

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]


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