Auto-Embedding Generative Adversarial Networks for High Resolution Image Synthesis

Abstract

Generating images via the generative adversarial network (GAN) has attracted much attention recently. However, most of the existing GAN-based methods can only produce low-resolution images of limited quality. Directly generating high-resolution images using GANs is nontrivial, and often produces problematic images with incomplete objects. To address this issue, we develop a novel GAN called Auto-Embedding Generative Adversarial Network (AEGAN), which simultaneously encodes the global structure features and captures the fine-grained details. In our network, we use an autoencoder to learn the intrinsic high-level structure of real images and design a novel denoiser network to provide photo-realistic details for the generated images. In the experiments, we are able to produce 512x512 images of promising quality directly from the input noise. The resultant images exhibit better perceptual photo-realism, i.e., with sharper structure and richer details, than other baselines on several datasets, including Oxford-102 Flowers, Caltech-UCSD Birds (CUB), High-Quality Large-scale CelebFaces Attributes (CelebA-HQ), Large-scale Scene Understanding (LSUN) and ImageNet.

Accepted by IEEE Transactions on Multimedia

References in corpus (15)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• 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
• Conditional Image Synthesis With Auxiliary Classifier GANs
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
• Energy-based Generative Adversarial Network
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
• Video (language) modeling: a baseline for generative models of natural videos
• Variational Approaches for Auto-Encoding Generative Adversarial Networks
• Generative Image Inpainting with Contextual Attention
• Texture Synthesis with Spatial Generative Adversarial Networks
• On Self Modulation for Generative Adversarial Networks

Cited by in corpus (2)

• Graph Convolutional Networks for Temporal Action Localization
• Sparsely Grouped Multi-task Generative Adversarial Networks for Facial Attribute Manipulation