Improving Key Human Features for Pose Transfer

Victor-Andrei Ivan, Ionut Mistreanu, Andrei Leica, Sung-Jun Yoon, Manri Cheon, Junwoo Lee, Jinsoo Oh

ICCVW 2021 pp. 1963-1972

doi:10.1109/ICCVW54120.2021.00223 /iccvw/2021/ivan2021iccvw-improving/

Abstract

It is still a great challenge in the Pose Transfer task to generate visually coherent images, to preserve the texture of clothes, to maintain the source identity and to realistically generate key human features such as the face or the hands. To tackle these challenges, we first conduct a study to obtain the most robust conditioning labels for this task and the baseline method [44] that we choose. We then improve upon the baseline by including deep source features from an Auto-encoder through an Attention mechanism. Finally we add region discriminators that are focused on key human features, thus obtaining results competitive with the state-of-the-art.

ICCVW Semantic Scholar

Cite

Text

Ivan et al. "Improving Key Human Features for Pose Transfer." IEEE/CVF International Conference on Computer Vision Workshops, 2021. doi:10.1109/ICCVW54120.2021.00223

Markdown

[Ivan et al. "Improving Key Human Features for Pose Transfer." IEEE/CVF International Conference on Computer Vision Workshops, 2021.](https://mlanthology.org/iccvw/2021/ivan2021iccvw-improving/) doi:10.1109/ICCVW54120.2021.00223

BibTeX

@inproceedings{ivan2021iccvw-improving,
  title     = {{Improving Key Human Features for Pose Transfer}},
  author    = {Ivan, Victor-Andrei and Mistreanu, Ionut and Leica, Andrei and Yoon, Sung-Jun and Cheon, Manri and Lee, Junwoo and Oh, Jinsoo},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2021},
  pages     = {1963-1972},
  doi       = {10.1109/ICCVW54120.2021.00223},
  url       = {https://mlanthology.org/iccvw/2021/ivan2021iccvw-improving/}
}