Improving Key Human Features for Pose Transfer

Victor-Andrei Ivan, Ionut Mistreanu, Andrei Leica, Sung-Jun Yoon, Manri Cheon, Junwoo Lee, Jinsoo Oh; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2021, pp. 1963-1972

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 [??] 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.

Related Material

[pdf]
[bibtex]
@InProceedings{Ivan_2021_ICCV, author = {Ivan, Victor-Andrei and Mistreanu, Ionut and Leica, Andrei and Yoon, Sung-Jun and Cheon, Manri and Lee, Junwoo and Oh, Jinsoo}, title = {Improving Key Human Features for Pose Transfer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2021}, pages = {1963-1972} }