Optimizing Generative Adversarial Networks for Image Super Resolution via Latent Space Regularization

01/22/2020
by   Sheng Zhong, et al.
57

Natural images can be regarded as residing in a manifold that is embedded in a higher dimensional Euclidean space. Generative Adversarial Networks (GANs) try to learn the distribution of the real images in the manifold to generate samples that look real. But the results of existing methods still exhibit many unpleasant artifacts and distortions even for the cases where the desired ground truth target images are available for supervised learning such as in single image super resolution (SISR). We probe for ways to alleviate these problems for supervised GANs in this paper. We explicitly apply the Lipschitz Continuity Condition (LCC) to regularize the GAN. An encoding network that maps the image space to a new optimal latent space is derived from the LCC, and it is used to augment the GAN as a coupling component. The LCC is also converted to new regularization terms in the generator loss function to enforce local invariance. The GAN is optimized together with the encoding network in an attempt to make the generator converge to a more ideal and disentangled mapping that can generate samples more faithful to the target images. When the proposed models are applied to the single image super resolution problem, the results outperform the state of the art.

READ FULL TEXT

page 2

page 6

page 7

page 10

research
04/28/2022

Generative Adversarial Networks for Image Super-Resolution: A Survey

Single image super-resolution (SISR) has played an important role in the...
research
03/13/2018

Learning to Maintain Natural Image Statistics

Maintaining natural image statistics is a crucial factor in restoration ...
research
09/30/2019

Unsupervised Projection Networks for Generative Adversarial Networks

We propose the use of unsupervised learning to train projection networks...
research
08/04/2022

Latent Multi-Relation Reasoning for GAN-Prior based Image Super-Resolution

Recently, single image super-resolution (SR) under large scaling factors...
research
11/16/2021

A Latent Encoder Coupled Generative Adversarial Network (LE-GAN) for Efficient Hyperspectral Image Super-resolution

Realistic hyperspectral image (HSI) super-resolution (SR) techniques aim...
research
03/24/2023

A Three-Player GAN for Super-Resolution in Magnetic Resonance Imaging

Learning based single image super resolution (SISR) task is well investi...
research
02/27/2019

Generative Collaborative Networks for Single Image Super-Resolution

A common issue of deep neural networks-based methods for the problem of ...

Please sign up or login with your details

Forgot password? Click here to reset