@inproceedings{GuoCVPR23,
  title = {{Vid2Avatar}: {3D} Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition},
  booktitle = {EEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  abstract = {We present Vid2Avatar, a method to learn human avatars from monocular in-the-wild videos. Reconstructing humans that move naturally from monocular in-the-wild videos is difficult. Solving it requires accurately separating humans from arbitrary backgrounds. Moreover, it requires reconstructing detailed 3D surface from short video sequences, making it even more challenging. Despite these challenges, our method does not require any groundtruth supervision or priors extracted from large datasets of clothed human scans, nor do we rely on any external segmentation modules. Instead, it solves the tasks of scene decomposition and surface reconstruction directly in 3D by modeling both the human and the background in the scene jointly, parameterized via two separate neural fields. Specifically, we define a temporally consistent human representation in canonical space and formulate a global optimization over the background model, the canonical human shape and texture, and per-frame human pose parameters. A coarse-to-fine sampling strategy for volume rendering and novel objectives are introduced for a clean separation of dynamic human and static background, yielding detailed and robust 3D human reconstructions. The evaluation of our method shows improvements over prior art on publicly available datasets.},
  pages = {12858-12868},
  year = {2023},
  slug = {guocvpr23},
  author = {Guo, Chen and Jiang, Tianjian and Chen, Xu and Song, Jie and Hilliges, Otmar},
  url = {https://ieeexplore.ieee.org/document/10203910}
}