StarGAN v2 閱讀筆記

StarGAN v2 閱讀筆記

@article{RN12,
author = {Choi, Yunjey and Uh, Youngjung and Yoo, Jaejun and Ha, Jung-Woo},
title = {StarGAN v2: Diverse Image Synthesis for Multiple Domains},
journal = {arXiv preprint arXiv:1912.01865},
year = {2019},
type = {Journal Article}
}

Contribution

StarGAN v2 在 StarGAN 的基礎上進行了改進，解決了由一個域圖像轉換到目標域的多種圖像，並支持多個目標域的問題。

Important Points

1. 設計了Mapping Network用於生成風格編碼，擺脫了標籤的束縛；
2. 用風格編碼器指導Mapping Network進行目標風格學習，可以實現目標域下多風格圖像的轉換；
3. 公開了動物面部數據集AFQH，實現了圖像翻譯下較好的結果。

Motivation

Existing methods have limited diversity or multiple models for all domains, which are the issues that StarGAN v2 trys to address.