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

by   Yuanzhuo Li, et al.

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.



There are no comments yet.


page 2

page 4


Structure-Preserving Super Resolution with Gradient Guidance

Structures matter in single image super resolution (SISR). Recent studie...

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...

One-to-many Approach for Improving Super-Resolution

Super-resolution (SR) is a one-to-many task with multiple possible solut...

Structure-Preserving Image Super-Resolution

Structures matter in single image super-resolution (SISR). Benefiting fr...

Progressive Perception-Oriented Network for Single Image Super-Resolution

Recently, it has been shown that deep neural networks can significantly ...

Natural and Realistic Single Image Super-Resolution with Explicit Natural Manifold Discrimination

Recently, many convolutional neural networks for single image super-reso...

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

The generative adversarial network (GAN) is successfully applied to stud...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.