ML Anthology

UnconFuse: Avatar Reconstruction from Unconstrained Images

Han Huang, Liliang Chen, Xihao Wang
ECCVW 2022 pp. 376-381
doi:10.1007/978-3-031-25072-9_25 /eccvw/2022/huang2022eccvw-unconfuse/

Abstract

The report proposes an effective solution about 3D human body reconstruction from multiple unconstrained frames for ECCV 2022 WCPA Challenge: From Face, Body and Fashion to 3D Virtual avatars I (track1: Multi-View Based 3D Human Body Reconstruction). We reproduce the reconstruction method presented in MVP-Human [ 19 ] as our baseline, and make some improvements for the particularity of this challenge. We finally achieve the score 0.93 on the official testing set, getting the 1st place on the leaderboard.

PDF ECCVW Semantic Scholar

Cite

Text

Huang et al. "UnconFuse: Avatar Reconstruction from Unconstrained Images." European Conference on Computer Vision Workshops, 2022. doi:10.1007/978-3-031-25072-9_25

Markdown

[Huang et al. "UnconFuse: Avatar Reconstruction from Unconstrained Images." European Conference on Computer Vision Workshops, 2022.](https://mlanthology.org/eccvw/2022/huang2022eccvw-unconfuse/) doi:10.1007/978-3-031-25072-9_25

BibTeX

@inproceedings{huang2022eccvw-unconfuse,
  title     = {{UnconFuse: Avatar Reconstruction from Unconstrained Images}},
  author    = {Huang, Han and Chen, Liliang and Wang, Xihao},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2022},
  pages     = {376-381},
  doi       = {10.1007/978-3-031-25072-9_25},
  url       = {https://mlanthology.org/eccvw/2022/huang2022eccvw-unconfuse/}
}