Two Heads Better than One: Dual Degradation Representation for Blind Super-Resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yuan, Hsuan, Weng, Shao-Yu, Lo, I-Hsuan, Chiu, Wei-Chen, Xu, Yu-Syuan, Hsueh, Hao-Chien, Chuang, Jen-Hui, Huang, Ching-Chun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908680582070272
author Yuan, Hsuan
Weng, Shao-Yu
Lo, I-Hsuan
Chiu, Wei-Chen
Xu, Yu-Syuan
Hsueh, Hao-Chien
Chuang, Jen-Hui
Huang, Ching-Chun
author_facet Yuan, Hsuan
Weng, Shao-Yu
Lo, I-Hsuan
Chiu, Wei-Chen
Xu, Yu-Syuan
Hsueh, Hao-Chien
Chuang, Jen-Hui
Huang, Ching-Chun
contents Previous methods have demonstrated remarkable performance in single image super-resolution (SISR) tasks with known and fixed degradation (e.g., bicubic downsampling). However, when the actual degradation deviates from these assumptions, these methods may experience significant declines in performance. In this paper, we propose a Dual Branch Degradation Extractor Network to address the blind SR problem. While some blind SR methods assume noise-free degradation and others do not explicitly consider the presence of noise in the degradation model, our approach predicts two unsupervised degradation embeddings that represent blurry and noisy information. The SR network can then be adapted to blur embedding and noise embedding in distinct ways. Furthermore, we treat the degradation extractor as a regularizer to capitalize on differences between SR and HR images. Extensive experiments on several benchmarks demonstrate our method achieves SOTA performance in the blind SR problem.
format Preprint
id arxiv_https___arxiv_org_abs_2511_16963
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Two Heads Better than One: Dual Degradation Representation for Blind Super-Resolution
Yuan, Hsuan
Weng, Shao-Yu
Lo, I-Hsuan
Chiu, Wei-Chen
Xu, Yu-Syuan
Hsueh, Hao-Chien
Chuang, Jen-Hui
Huang, Ching-Chun
Computer Vision and Pattern Recognition
Previous methods have demonstrated remarkable performance in single image super-resolution (SISR) tasks with known and fixed degradation (e.g., bicubic downsampling). However, when the actual degradation deviates from these assumptions, these methods may experience significant declines in performance. In this paper, we propose a Dual Branch Degradation Extractor Network to address the blind SR problem. While some blind SR methods assume noise-free degradation and others do not explicitly consider the presence of noise in the degradation model, our approach predicts two unsupervised degradation embeddings that represent blurry and noisy information. The SR network can then be adapted to blur embedding and noise embedding in distinct ways. Furthermore, we treat the degradation extractor as a regularizer to capitalize on differences between SR and HR images. Extensive experiments on several benchmarks demonstrate our method achieves SOTA performance in the blind SR problem.
title Two Heads Better than One: Dual Degradation Representation for Blind Super-Resolution
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.16963