FAUST contains 300 real, high-resolution human scans of 10 different subjects in 30 different poses, with automatically computed ground-truth correspondences. Each scan is a high-resolution, triangulated, non-watertight mesh acquired with a 3D multi-stereo system.
FAUST is subdivided into a training and a test set. The training set includes 100 scans (10 per subject) with their corresponding ground-truth alignments. The test set includes 200 scans. The FAUST benchmark defines 100 preselected scan pairs, partitioned into two classes – 60 requiring intra-subject matching, 40 requiring inter-subject matching.
Real human body scans High resolution Different topologies Missing data Self contacts Dense ground-truth correspondences
Please sign up or log in to download the dataset and to submit your predictions for evaluation.
@inproceedings{Bogo:CVPR:2014,
title = {{FAUST}: Dataset and evaluation for {3D} mesh registration},
author = {Bogo, Federica and Romero, Javier and Loper, Matthew and Black, Michael J.},
booktitle = {Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
address = {Piscataway, NJ, USA},
publisher = {IEEE},
month = jun,
year = {2014}
}
If you have any questions or problems regarding this dataset, please do not hesitate to contact us.
This website was built by the Software Workshop at Max-Planck Institute for Intelligent Systems