Detailed Human Avatars from Monocular Video
We present a novel method for high detail-preserving human avatar creation from monocular video. A parameterized body model is refined and optimized to maximally resemble subjects from a video showing them from all sides. Our avatars feature a natural face, hairstyle, clothes with garment wrinkles, and high-resolution texture. Our paper contributes facial landmark and shading-based human body shape refinement, a semantic texture prior, and a novel texture stitching strategy, resulting in the most sophisticated-looking human avatars obtained from a single video to date. Numerous results show the robustness and versatility of our method. A user study illustrates its superiority over the state-of-the-art in terms of identity preservation, level of detail, realism, and overall user preference.
| Author(s): | Thiemo Alldieck, Marcus Magnor, Weipeng Xu, Christian Theobalt, Gerard Pons-Moll |
|---|---|
| Published: | September 2018 |
| Type: | Article in conference proceedings |
| Book: | International Conference on 3D Vision (IEEE) |
| DOI: | 10.1109/3DV.2018.00022 |
| Presented at: | International Conference on 3D Vision (3DV) 2018 |
| Project(s): | Comprehensive Human Performance Capture from Monocular Video Footage Immersive Digital Reality |
BibTex PDF Link Code Video arXiv
@inproceedings{alldieck2018detailed,
title = {Detailed Human Avatars from Monocular Video},
author = {Alldieck, Thiemo and Magnor, Marcus and Xu, Weipeng and Theobalt, Christian and Pons-Moll, Gerard},
booktitle = {International Conference on 3D Vision},
doi = {10.1109/3{DV}.2018.00022},
pages = {98--109},
month = {Sep},
year = {2018}
}
Authors
-
Thiemo Alldieck
Fmr. Researcher -
Marcus Magnor
Director, Chair -
Weipeng Xu
External -
Christian Theobalt
External -
Gerard Pons-Moll
External