Paper
2 December 2024 Texture-attention discriminator for real-world image super-resolution
Author Affiliations +
Proceedings Volume 13443, Fifth International Conference on Computer Vision and Information Technology (CVIT 2024); 1344302 (2024) https://doi.org/10.1117/12.3055583
Event: 2024 5th International Conference on Computer Vision and Information Technology (CVIT 2024), 2024, Beijing, China
Abstract
Applying single-image super-resolution methods to real-world images with complex and unknown degradation is a challenge. Recent research has made significant progress in solving this problem by employing more complex degradation models to emulate real-world scenes, thereby improving perceptual image quality. However, these methods are often limited by network structure, leading to the generation of over-smoothed results with insufficient detail. In this paper, a texture-attention discriminator architecture based on U-Net is proposed for real-world super-resolution tasks. The architecture effectively directs attention to the high-frequency details of the image by leveraging frequency information extracted through the Laplacian pyramid. As a result, it complements GAN-based super-resolution methods in recapturing complex real textures, resulting in better perceptual image quality when applied to real-world images.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Yukun Hao "Texture-attention discriminator for real-world image super-resolution", Proc. SPIE 13443, Fifth International Conference on Computer Vision and Information Technology (CVIT 2024), 1344302 (2 December 2024); https://doi.org/10.1117/12.3055583
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image quality

Super resolution

Image enhancement

Image restoration

Feature extraction

Deep learning

Back to Top