Invertible Conditional GAN Revisited: Photo-to-Manga Face Translation with Modern Architectures (Student Abstract)

Taro Hatakeyama, Ryusuke Saito, Komei Hiruta, Atsushi Hashimoto, Satoshi Kurihara

AAAI 2023 pp. 16224-16225

doi:10.1609/AAAI.V37I13.26972 /aaai/2023/hatakeyama2023aaai-invertible/

Abstract

Recent style translation methods have extended their transferability from texture to geometry. However, performing translation while preserving image content when there is a significant style difference is still an open problem. To overcome this problem, we propose Invertible Conditional Fast GAN (IcFGAN) based on GAN inversion and cFGAN. It allows for unpaired photo-to-manga face translation. Experimental results show that our method could translate styles under significant style gaps, while the state-of-the-art methods could hardly preserve image content.

PDF AAAI Semantic Scholar

Cite

Text

Hatakeyama et al. "Invertible Conditional GAN Revisited: Photo-to-Manga Face Translation with Modern Architectures (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I13.26972

Markdown

[Hatakeyama et al. "Invertible Conditional GAN Revisited: Photo-to-Manga Face Translation with Modern Architectures (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/hatakeyama2023aaai-invertible/) doi:10.1609/AAAI.V37I13.26972

BibTeX

@inproceedings{hatakeyama2023aaai-invertible,
  title     = {{Invertible Conditional GAN Revisited: Photo-to-Manga Face Translation with Modern Architectures (Student Abstract)}},
  author    = {Hatakeyama, Taro and Saito, Ryusuke and Hiruta, Komei and Hashimoto, Atsushi and Kurihara, Satoshi},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {16224-16225},
  doi       = {10.1609/AAAI.V37I13.26972},
  url       = {https://mlanthology.org/aaai/2023/hatakeyama2023aaai-invertible/}
}