Learning Structral coherence Via Generative Adversarial Network for Single Image Super-Resolution

01/25/2021
by   Yuanzhuo Li, et al.
3

Among the major remaining challenges for single image super resolution (SISR) is the capacity to recover coherent images with global shapes and local details conforming to human vision system. Recent generative adversarial network (GAN) based SISR methods have yielded overall realistic SR images, however, there are always unpleasant textures accompanied with structural distortions in local regions. To target these issues, we introduce the gradient branch into the generator to preserve structural information by restoring high-resolution gradient maps in SR process. In addition, we utilize a U-net based discriminator to consider both the whole image and the detailed per-pixel authenticity, which could encourage the generator to maintain overall coherence of the reconstructed images. Moreover, we have studied objective functions and LPIPS perceptual loss is added to generate more realistic and natural details. Experimental results show that our proposed method outperforms state-of-the-art perceptual-driven SR methods in perception index (PI), and obtains more geometrically consistent and visually pleasing textures in natural image restoration.

READ FULL TEXT

page 2

page 4

research
03/29/2020

Structure-Preserving Super Resolution with Gradient Guidance

Structures matter in single image super resolution (SISR). Recent studie...
research
06/19/2021

One-to-many Approach for Improving Super-Resolution

Super-resolution (SR) is a one-to-many task with multiple possible solut...
research
09/26/2021

Structure-Preserving Image Super-Resolution

Structures matter in single image super-resolution (SISR). Benefiting fr...
research
07/24/2019

Progressive Perception-Oriented Network for Single Image Super-Resolution

Recently, it has been shown that deep neural networks can significantly ...
research
11/24/2022

Perception-Oriented Single Image Super-Resolution using Optimal Objective Estimation

Single-image super-resolution (SISR) networks trained with perceptual an...
research
09/19/2019

Deeply Matting-based Dual Generative Adversarial Network for Image and Document Label Supervision

Although many methods have been proposed to deal with nature image super...
research
12/25/2021

DSRGAN: Detail Prior-Assisted Perceptual Single Image Super-Resolution via Generative Adversarial Networks

The generative adversarial network (GAN) is successfully applied to stud...

Please sign up or login with your details

Forgot password? Click here to reset