Direct Prediction of 3D Body Poses from Motion Compensated Sequences

Bugra Tekin, Artem Rozantsev, Vincent Lepetit, Pascal Fua

CVPR 2016

doi:10.1109/CVPR.2016.113 /cvpr/2016/tekin2016cvpr-direct/

Abstract

We propose an efficient approach to exploiting motion information from consecutive frames of a video sequence to recover the 3D pose of people. Previous approaches typically compute candidate poses in individual frames and then link them in a post-processing step to resolve ambiguities. By contrast, we directly regress from a spatio-temporal volume of bounding boxes to a 3D pose in the central frame. We further show that, for this approach to achieve its full potential, it is essential to compensate for the motion in consecutive frames so that the subject remains centered. This then allows us to effectively overcome ambiguities and improve upon the state-of-the-art by a large margin on the Human3.6m, HumanEva, and KTH Multiview Football 3D human pose estimation benchmarks.

PDF CVPR Semantic Scholar

Cite

Text

Tekin et al. "Direct Prediction of 3D Body Poses from Motion Compensated Sequences." Conference on Computer Vision and Pattern Recognition, 2016. doi:10.1109/CVPR.2016.113

Markdown

[Tekin et al. "Direct Prediction of 3D Body Poses from Motion Compensated Sequences." Conference on Computer Vision and Pattern Recognition, 2016.](https://mlanthology.org/cvpr/2016/tekin2016cvpr-direct/) doi:10.1109/CVPR.2016.113

BibTeX

@inproceedings{tekin2016cvpr-direct,
  title     = {{Direct Prediction of 3D Body Poses from Motion Compensated Sequences}},
  author    = {Tekin, Bugra and Rozantsev, Artem and Lepetit, Vincent and Fua, Pascal},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2016},
  doi       = {10.1109/CVPR.2016.113},
  url       = {https://mlanthology.org/cvpr/2016/tekin2016cvpr-direct/}
}