ISF-GAN: An Implicit Style Function for High-Resolution Image-to-Image Translation
This work addresses the problem of preserving domain-invariant features and enabling multi-modal translations for high-resolution image editing, which is incremental as it builds on existing GAN-based methods.
The paper tackles the challenge of multi-modal and multi-domain image-to-image translation using pre-trained unconditional generators like StyleGAN, achieving significantly improved results in human face and animal manipulations compared to baselines.
Recently, there has been an increasing interest in image editing methods that employ pre-trained unconditional image generators (e.g., StyleGAN). However, applying these methods to translate images to multiple visual domains remains challenging. Existing works do not often preserve the domain-invariant part of the image (e.g., the identity in human face translations), they do not usually handle multiple domains, or do not allow for multi-modal translations. This work proposes an implicit style function (ISF) to straightforwardly achieve multi-modal and multi-domain image-to-image translation from pre-trained unconditional generators. The ISF manipulates the semantics of an input latent code to make the image generated from it lying in the desired visual domain. Our results in human face and animal manipulations show significantly improved results over the baselines. Our model enables cost-effective multi-modal unsupervised image-to-image translations at high resolution using pre-trained unconditional GANs. The code and data are available at: \url{https://github.com/yhlleo/stylegan-mmuit}.