@inproceedings{15299ed47a5045819f16307ff820ad52,
title = "Cross Attention Based Style Distribution for Controllable Person Image Synthesis",
abstract = "Controllable person image synthesis task enables a wide range of applications through explicit control over body pose and appearance. In this paper, we propose a cross attention based style distribution module that computes between the source semantic styles and target pose for pose transfer. The module intentionally selects the style represented by each semantic and distributes them according to the target pose. The attention matrix in cross attention expresses the dynamic similarities between the target pose and the source styles for all semantics. Therefore, it can be utilized to route the color and texture from the source image, and is further constrained by the target parsing map to achieve a clearer objective. At the same time, to encode the source appearance accurately, the self attention among different semantic styles is also added. The effectiveness of our model is validated quantitatively and qualitatively on pose transfer and virtual try-on tasks. Codes are available at https://github.com/xyzhouo/CASD.",
keywords = "Person image synthesis, Pose transfer, Virtual try-on",
author = "Xinyue Zhou and Mingyu Yin and Xinyuan Chen and Li Sun and Changxin Gao and Qingli Li",
note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 17th European Conference on Computer Vision, ECCV 2022 ; Conference date: 23-10-2022 Through 27-10-2022",
year = "2022",
doi = "10.1007/978-3-031-19784-0\_10",
language = "英语",
isbn = "9783031197833",
series = "Lecture Notes in Computer Science",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "161--178",
editor = "Shai Avidan and Gabriel Brostow and Moustapha Ciss{\'e} and Farinella, \{Giovanni Maria\} and Tal Hassner",
booktitle = "Computer Vision {\textendash} ECCV 2022 - 17th European Conference, Proceedings",
address = "德国",
}