Abstract

Human performance capture is a highly important computer vision problem with many applications in movie production and virtual/augmented reality. Many previous performance capture approaches either required expensive multi-view setups or did not recover dense space-time coherent geometry with frame-to-frame correspondences. We propose a novel deep learning approach for monocular dense human performance capture. Our method is trained in a weakly supervised manner based on multi-view supervision completely removing the need for training data with 3D ground truth annotations. The network architecture is based on two separate networks that disentangle the task into a pose estimation and a non-rigid surface deformation step. Extensive qualitative and quantitative evaluations show that our approach outperforms the state of the art in terms of quality and robustness. This work is an extended version of DeepCap where we provide more detailed explanations, comparisons and results as well as applications.

Downloads


Dataset


Citation

BibTeX, 1 KB

@inproceedings{habermann21a,
author={Habermann, Marc and Xu, Weipeng and Zollhoefer, Michael and Pons-Moll, Gerard and Theobalt, Christian},
booktitle={IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)}, 
title={A Deeper Look into DeepCap}, 
year={2021},
volume={},
number={},
pages={1-1},
doi={10.1109/TPAMI.2021.3093553},
publisher={IEEE}
}
				

Acknowledgments

This work was funded by the ERC Consolidator Grant 4DRepLy (770784).

Contact

For questions, clarifications, please get in touch with:
Marc Habermann
mhaberma@mpi-inf.mpg.de

This page is Zotero translator friendly. Page last updated Imprint. Data Protection.