RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributes

Abstract

Multi-domain image-to-image translation has gained increasing attention recently. Previous methods take an image and some target attributes as inputs and generate an output image with the desired attributes. However, such methods have two limitations. First, these methods assume binary-valued attributes and thus cannot yield satisfactory results for fine-grained control. Second, these methods require specifying the entire set of target attributes, even if most of the attributes would not be changed. To address these limitations, we propose RelGAN, a new method for multi-domain image-to-image translation. The key idea is to use relative attributes, which describes the desired change on selected attributes. Our method is capable of modifying images by changing particular attributes of interest in a continuous manner while preserving the other attributes. Experimental results demonstrate both the quantitative and qualitative effectiveness of our method on the tasks of facial attribute transfer and interpolation.

arXiv commentAccepted to ICCV 2019

References in corpus (9)

• Conditional Generative Adversarial Nets
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Generative Adversarial Text to Image Synthesis
• Invertible Conditional GANs for image editing
• Differentiable Learning-to-Normalize via Switchable Normalization
• Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer
• Mask-aware Photorealistic Face Attribute Manipulation
• KG-GAN: Knowledge-Guided Generative Adversarial Networks

Cited by in corpus (18)

• Media Forensics and DeepFakes: an overview
• Bipartite Graph Reasoning GANs for Person Image Generation
• Image-to-Image Translation: Methods and Applications
• PA-GAN: Progressive Attention Generative Adversarial Network for Facial Attribute Editing
• Latent Space Factorisation and Manipulation via Matrix Subspace Projection
• EDIT: Exemplar-Domain Aware Image-to-Image Translation
• Attribute2Font: Creating Fonts You Want From Attributes
• Dual Attention GANs for Semantic Image Synthesis
• Automated Deepfake Detection
• Unsupervised Multimodal Video-to-Video Translation via Self-Supervised Learning
• Perceptual Indistinguishability-Net (PI-Net): Facial Image Obfuscation with Manipulable Semantics
• Dual In-painting Model for Unsupervised Gaze Correction and Animation in the Wild
• Informative Sample Mining Network for Multi-Domain Image-to-Image Translation
• Unsupervised Many-to-Many Image-to-Image Translation Across Multiple Domains
• Coarse-to-Fine Gaze Redirection with Numerical and Pictorial Guidance
• Bridging the Gap between Label- and Reference-based Synthesis in Multi-attribute Image-to-Image Translation
• ClsGAN: Selective Attribute Editing Model Based On Classification Adversarial Network
• Transferring Knowledge with Attention Distillation for Multi-Domain Image-to-Image Translation