Energy-relaxed Wassertein GANs(EnergyWGAN): Towards More Stable and High Resolution Image Generation

12/04/2017
by   Jiqing Wu, et al.
0

Recently, generative adversarial networks (GANs) have achieved great impacts on a broad number of applications, including low resolution(LR) image synthesis. However, they suffer from unstable training especially when image resolution increases. To overcome this bottleneck, this paper generalizes the state-of-the-art Wasserstein GANs (WGANs) to an energy-relaxed objective which enables more stable and higher-resolution image generation. The benefits of this generalization can be summarized in three main points. Firstly, the proposed EnergyWGAN objective guarantees a valid symmetric divergence serving as a more rigorous and meaningful quantitative measure. Secondly, EnergyWGAN is capable of searching a more faithful solution space than the original WGANs without fixing a specific k-Lipschitz constraint. Finally, the proposed EnergyWGAN offers a natural way of stacking GANs for high resolution image generation. In our experiments we not only demonstrate the stable training ability of the proposed EnergyWGAN and its better image generation results on standard benchmark datasets, but also show the advantages over the state-of-the-art GANs on a real-world high resolution image dataset.

READ FULL TEXT

page 6

page 7

page 8

page 9

research
12/05/2017

Manifold-valued Image Generation with Wasserstein Adversarial Networks

Unsupervised image generation has recently received an increasing amount...
research
05/28/2017

Conditional CycleGAN for Attribute Guided Face Image Generation

State-of-the-art techniques in Generative Adversarial Networks (GANs) su...
research
08/30/2019

Systematic Analysis of Image Generation using GANs

Generative Adversarial Networks have been crucial in the developments ma...
research
03/21/2017

GP-GAN: Towards Realistic High-Resolution Image Blending

Recent advances in generative adversarial networks (GANs) have shown pro...
research
07/04/2020

BézierSketch: A generative model for scalable vector sketches

The study of neural generative models of human sketches is a fascinating...
research
07/08/2021

Grid Partitioned Attention: Efficient TransformerApproximation with Inductive Bias for High Resolution Detail Generation

Attention is a general reasoning mechanism than can flexibly deal with i...
research
12/24/2021

Cluster-guided Image Synthesis with Unconditional Models

Generative Adversarial Networks (GANs) are the driving force behind the ...

Please sign up or login with your details

Forgot password? Click here to reset