Video Based Reconstruction of 3D People Models

CVPR 2018 (spotlight), Salt Lake City, USA

Download Video: HD (MP4, 68 MB)

Abstract

This paper describes how to obtain accurate 3D body models and texture of arbitrary people from a single, monocular video in which a person is moving. Based on a parametric body model, we present a robust processing pipeline achieving 3D model fits with 5mm accuracy also for clothed people. Our main contribution is a method to nonrigidly deform the silhouette cones corresponding to the dynamic human silhouettes, resulting in a visual hull in a common reference frame that enables surface reconstruction. This enables efficient estimation of a consensus 3D shape, texture and implanted animation skeleton based on a large number of frames. We present evaluation results for a number of test subjects and analyze overall performance. Requiring only a smartphone or webcam, our method enables everyone to create their own fully animatable digital double, e.g., for social VR applications or virtual try-on for online fashion shopping.

Downloads

Citation

BibTeX, 1 KB

@inproceedings{alldieck2018video,
  title = {Video Based Reconstruction of 3D People Models},
  author = {Alldieck, Thiemo and Magnor, Marcus and Xu, Weipeng and Theobalt, Christian and Pons-Moll, Gerard},
  booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition},
  note = {{CVPR} Spotlight Paper}
}
	  

Contact

For questions, clarifications, and access to the dataset, please get in touch with:
Thiemo Alldieck
alldieck@cg.cs.tu-bs.de