Unsupervised Image-to-Image Translation with Generative Adversarial Networks

Abstract

It's useful to automatically transform an image from its original form to some synthetic form (style, partial contents, etc.), while keeping the original structure or semantics. We define this requirement as the "image-to-image translation" problem, and propose a general approach to achieve it, based on deep convolutional and conditional generative adversarial networks (GANs), which has gained a phenomenal success to learn mapping images from noise input since 2014. In this work, we develop a two step (unsupervised) learning method to translate images between different domains by using unlabeled images without specifying any correspondence between them, so that to avoid the cost of acquiring labeled data. Compared with prior works, we demonstrated the capacity of generality in our model, by which variance of translations can be conduct by a single type of model. Such capability is desirable in applications like bidirectional translation

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Generative Adversarial Text to Image Synthesis
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Semi-Supervised Learning with Generative Adversarial Networks
• Deep Learning Face Attributes in the Wild
• Fast Face-swap Using Convolutional Neural Networks

Cited by in corpus (15)

• Auto-painter: Cartoon Image Generation from Sketch by Using Conditional Generative Adversarial Networks
• TensorLayer: A Versatile Library for Efficient Deep Learning Development
• Unsupervised Diverse Colorization via Generative Adversarial Networks
• Characterizing Bias in Classifiers using Generative Models
• CorGAN: Correlation-Capturing Convolutional Generative Adversarial Networks for Generating Synthetic Healthcare Records
• AlignGAN: Learning to Align Cross-Domain Images with Conditional Generative Adversarial Networks
• Collision Detection: An Improved Deep Learning Approach Using SENet and ResNext
• Learning Inverse Mapping by Autoencoder based Generative Adversarial Nets
• Disentanglement for Discriminative Visual Recognition
• MIXGAN: Learning Concepts from Different Domains for Mixture Generation
• Sparsely Grouped Multi-task Generative Adversarial Networks for Facial Attribute Manipulation
• MU-GAN: Facial Attribute Editing based on Multi-attention Mechanism
• Towards Real-Time Advancement of Underwater Visual Quality with GAN
• Quality-Aware Multimodal Saliency Detection via Deep Reinforcement Learning
• High Diversity Attribute Guided Face Generation with GANs