English

PINA: Learning a Personalized Implicit Neural Avatar from a Single RGB-D Video Sequence

Computer Vision and Pattern Recognition 2022-04-11 v2

Abstract

We present a novel method to learn Personalized Implicit Neural Avatars (PINA) from a short RGB-D sequence. This allows non-expert users to create a detailed and personalized virtual copy of themselves, which can be animated with realistic clothing deformations. PINA does not require complete scans, nor does it require a prior learned from large datasets of clothed humans. Learning a complete avatar in this setting is challenging, since only few depth observations are available, which are noisy and incomplete (i.e. only partial visibility of the body per frame). We propose a method to learn the shape and non-rigid deformations via a pose-conditioned implicit surface and a deformation field, defined in canonical space. This allows us to fuse all partial observations into a single consistent canonical representation. Fusion is formulated as a global optimization problem over the pose, shape and skinning parameters. The method can learn neural avatars from real noisy RGB-D sequences for a diverse set of people and clothing styles and these avatars can be animated given unseen motion sequences.

Keywords

Cite

@article{arxiv.2203.01754,
  title  = {PINA: Learning a Personalized Implicit Neural Avatar from a Single RGB-D Video Sequence},
  author = {Zijian Dong and Chen Guo and Jie Song and Xu Chen and Andreas Geiger and Otmar Hilliges},
  journal= {arXiv preprint arXiv:2203.01754},
  year   = {2022}
}

Comments

CVPR'2022; Video: https://youtu.be/oGpKUuD54Qk | Project page: https://zj-dong.github.io/pina/ | Supplementary Material: https://ait.ethz.ch/projects/2022/pina/downloads/supp.pdf

R2 v1 2026-06-24T10:00:56.410Z