MoRF: Mobile Realistic Fullbody Avatars from a Monocular Video

Abstract

We present a system to create Mobile Realistic Fullbody (MoRF) avatars. MoRF avatars are rendered in real-time on mobile devices, learned from monocular videos, and have high realism. We use SMPL-X as a proxy geometry and render it with DNR (neural texture and image-2-image network). We improve on prior work, by overfitting per-frame warping fields in the neural texture space, allowing to better align the training signal between different frames. We also refine SMPL-X mesh fitting procedure to improve the overall avatar quality. In the comparisons to other monocular video-based avatar systems, MoRF avatars achieve higher image sharpness and temporal consistency. Participants of our user study also preferred avatars generated by MoRF.

Cite

Text

Bashirov et al. "MoRF: Mobile Realistic Fullbody Avatars from a Monocular Video." Winter Conference on Applications of Computer Vision, 2024.

Markdown

[Bashirov et al. "MoRF: Mobile Realistic Fullbody Avatars from a Monocular Video." Winter Conference on Applications of Computer Vision, 2024.](https://mlanthology.org/wacv/2024/bashirov2024wacv-morf/)

BibTeX

@inproceedings{bashirov2024wacv-morf,
  title     = {{MoRF: Mobile Realistic Fullbody Avatars from a Monocular Video}},
  author    = {Bashirov, Renat and Larionov, Alexey and Ustinova, Evgeniya and Sidorenko, Mikhail and Svitov, David and Zakharkin, Ilya and Lempitsky, Victor},
  booktitle = {Winter Conference on Applications of Computer Vision},
  year      = {2024},
  pages     = {3545-3555},
  url       = {https://mlanthology.org/wacv/2024/bashirov2024wacv-morf/}
}