Separating Content and Style for Unsupervised Image-to-Image Translation
This work addresses the problem of generating diverse and interpretable translated images for computer vision applications, representing an incremental improvement over prior disentanglement approaches.
The paper tackles unsupervised image-to-image translation by proposing a unified framework that simultaneously separates content and style codes, resulting in superior performance in multimodal translation, interpretability, and manipulation compared to existing methods.
Unsupervised image-to-image translation aims to learn the mapping between two visual domains with unpaired samples. Existing works focus on disentangling domain-invariant content code and domain-specific style code individually for multimodal purposes. However, less attention has been paid to interpreting and manipulating the translated image. In this paper, we propose to separate the content code and style code simultaneously in a unified framework. Based on the correlation between the latent features and the high-level domain-invariant tasks, the proposed framework demonstrates superior performance in multimodal translation, interpretability and manipulation of the translated image. Experimental results show that the proposed approach outperforms the existing unsupervised image translation methods in terms of visual quality and diversity.