This website is still being actively developed. The version you are using at the moment is probably not even properly tested. It comes absolutely without any warranty regarding the data that you are submitting. Use it at your own risk.
Here, we provide data and information on the Sintel Depth Benchmark, a companion benchmark to the MPI-Sintel Optical Flow Benchmark.
To train your algorithm, we provide training images (with and without effects such as motion and focus blur) and ground truth depth data.
To test your algorithm, please run it on the provided test set.
You can then submit your algorithm (for details on the file format, please see the FAQ, and, after successful evaluation, compare your algorithm to others in the leaderboard.
These example show the final pass (top) and the corresponding depth data (bottom).
@inproceedings{Butler:ECCV:2012,
title = {A naturalistic open source movie for optical flow evaluation},
author = {Butler, D. J. and Wulff, J. and Stanley, G. B. and Black, M. J.},
booktitle = {European Conf. on Computer Vision (ECCV)},
editor = {{A. Fitzgibbon et al. (Eds.)}},
publisher = {Springer-Verlag},
series = {Part IV, LNCS 7577},
month = oct,
pages = {611--625},
year = {2012}
}
If you have any questions or problems regarding this dataset, please do not hesitate to contact us.
This website was built by Ivan Oreshnikov and Jean-Claude Passy from Software Workshop at Max-Planck Institute for Intelligent Systems, and by Jonas Wulff from Computer Science and Artificial Intelligence Lab at MIT.