Image-to-image Translation via Hierarchical Style Disentanglement
arXiv:2103.01456
Abstract
Recently, image-to-image translation has made significant progress in achieving both multi-label (\ie, translation conditioned on different labels) and multi-style (\ie, generation with diverse styles) tasks. However, due to the unexplored independence and exclusiveness in the labels, existing endeavors are defeated by involving uncontrolled manipulations to the translation results. In this paper, we propose Hierarchical Style Disentanglement (HiSD) to address this issue. Specifically, we organize the labels into a hierarchical tree structure, in which independent tags, exclusive attributes, and disentangled styles are allocated from top to bottom. Correspondingly, a new translation process is designed to adapt the above structure, in which the styles are identified for controllable translations. Both qualitative and quantitative results on the CelebA-HQ dataset verify the ability of the proposed HiSD. We hope our method will serve as a solid baseline and provide fresh insights with the hierarchically organized annotations for future research in image-to-image translation. The code has been released at https://github.com/imlixinyang/HiSD.
arXiv commentCVPR 2021. The code will be released at at https://github.com/imlixinyang/HiSD
References in corpus (14)
- Conditional Generative Adversarial Nets
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Instance Normalization: The Missing Ingredient for Fast Stylization
- Generative Adversarial Text to Image Synthesis
- Which Training Methods for GANs do actually Converge?
- Unsupervised Cross-Domain Image Generation
- Unsupervised Attention-guided Image to Image Translation
- Multi-mapping Image-to-Image Translation via Learning Disentanglement
- SRPGAN: Perceptual Generative Adversarial Network for Single Image Super Resolution
- Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content Transfer
- Attribute Guided Unpaired Image-to-Image Translation with Semi-supervised Learning
- MulGAN: Facial Attribute Editing by Exemplar
- Information Competing Process for Learning Diversified Representations
- Mask Based Unsupervised Content Transfer