Unpaired Multi-Domain Image Generation via Regularized Conditional GANs

by   Xudong Mao, et al.

In this paper, we study the problem of multi-domain image generation, the goal of which is to generate pairs of corresponding images from different domains. With the recent development in generative models, image generation has achieved great progress and has been applied to various computer vision tasks. However, multi-domain image generation may not achieve the desired performance due to the difficulty of learning the correspondence of different domain images, especially when the information of paired samples is not given. To tackle this problem, we propose Regularized Conditional GAN (RegCGAN) which is capable of learning to generate corresponding images in the absence of paired training data. RegCGAN is based on the conditional GAN, and we introduce two regularizers to guide the model to learn the corresponding semantics of different domains. We evaluate the proposed model on several tasks for which paired training data is not given, including the generation of edges and photos, the generation of faces with different attributes, etc. The experimental results show that our model can successfully generate corresponding images for all these tasks, while outperforms the baseline methods. We also introduce an approach of applying RegCGAN to unsupervised domain adaptation.


page 3

page 4

page 5

page 6


MPG: A Multi-ingredient Pizza Image Generator with Conditional StyleGANs

Multilabel conditional image generation is a challenging problem in comp...

Paired 3D Model Generation with Conditional Generative Adversarial Networks

Generative Adversarial Networks (GANs) are shown to be successful at gen...

Shape-conditioned Image Generation by Learning Latent Appearance Representation from Unpaired Data

Conditional image generation is effective for diverse tasks including tr...

Learning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image Synthesis

Existing text-to-image generation approaches have set high standards for...

MetalGAN: Multi-Domain Label-Less Image Synthesis Using cGANs and Meta-Learning

Image synthesis is currently one of the most addressed image processing ...

Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field

This work explores the use of 3D generative models to synthesize trainin...

Unsupervised Open-domain Keyphrase Generation

In this work, we study the problem of unsupervised open-domain keyphrase...

Please sign up or login with your details

Forgot password? Click here to reset