Separating Content and Style for Unsupervised Image-to-Image Translation

Abstract

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.

arXiv commentAccepted by BMVC2021

References in corpus (20)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Axiomatic Attribution for Deep Networks
• ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
• The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
• CyCADA: Cycle-Consistent Adversarial Domain Adaptation
• Deep High-Resolution Representation Learning for Visual Recognition
• Unsupervised Attention-guided Image to Image Translation
• On the importance of single directions for generalization
• GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
• Image Super-Resolution Using Deep Convolutional Networks
• Learning Linear Transformations for Fast Arbitrary Style Transfer
• How convolutional neural network see the world - A survey of convolutional neural network visualization methods
• Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency
• MISO: Mutual Information Loss with Stochastic Style Representations for Multimodal Image-to-Image Translation
• TransGaGa: Geometry-Aware Unsupervised Image-to-Image Translation
• Semantics-Aware Image to Image Translation and Domain Transfer
• Generative Adversarial Network with Multi-Branch Discriminator for Cross-Species Image-to-Image Translation
• Controlling biases and diversity in diverse image-to-image translation
• Improving Style-Content Disentanglement in Image-to-Image Translation