Blind Super Resolution with Reference Images and Implicit Degradation Representation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Do, Huu-Phu, Hu, Po-Chih, Hsueh, Hao-Chien, Liu, Che-Kai, Tran, Vu-Hoang, Huang, Ching-Chun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916849911857152
author Do, Huu-Phu
Hu, Po-Chih
Hsueh, Hao-Chien
Liu, Che-Kai
Tran, Vu-Hoang
Huang, Ching-Chun
author_facet Do, Huu-Phu
Hu, Po-Chih
Hsueh, Hao-Chien
Liu, Che-Kai
Tran, Vu-Hoang
Huang, Ching-Chun
contents Previous studies in blind super-resolution (BSR) have primarily concentrated on estimating degradation kernels directly from low-resolution (LR) inputs to enhance super-resolution. However, these degradation kernels, which model the transition from a high-resolution (HR) image to its LR version, should account for not only the degradation process but also the downscaling factor. Applying the same degradation kernel across varying super-resolution scales may be impractical. Our research acknowledges degradation kernels and scaling factors as pivotal elements for the BSR task and introduces a novel strategy that utilizes HR images as references to establish scale-aware degradation kernels. By employing content-irrelevant HR reference images alongside the target LR image, our model adaptively discerns the degradation process. It is then applied to generate additional LR-HR pairs through down-sampling the HR reference images, which are keys to improving the SR performance. Our reference-based training procedure is applicable to proficiently trained blind SR models and zero-shot blind SR methods, consistently outperforming previous methods in both scenarios. This dual consideration of blur kernels and scaling factors, coupled with the use of a reference image, contributes to the effectiveness of our approach in blind super-resolution tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2507_13915
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Blind Super Resolution with Reference Images and Implicit Degradation Representation
Do, Huu-Phu
Hu, Po-Chih
Hsueh, Hao-Chien
Liu, Che-Kai
Tran, Vu-Hoang
Huang, Ching-Chun
Image and Video Processing
Computer Vision and Pattern Recognition
Previous studies in blind super-resolution (BSR) have primarily concentrated on estimating degradation kernels directly from low-resolution (LR) inputs to enhance super-resolution. However, these degradation kernels, which model the transition from a high-resolution (HR) image to its LR version, should account for not only the degradation process but also the downscaling factor. Applying the same degradation kernel across varying super-resolution scales may be impractical. Our research acknowledges degradation kernels and scaling factors as pivotal elements for the BSR task and introduces a novel strategy that utilizes HR images as references to establish scale-aware degradation kernels. By employing content-irrelevant HR reference images alongside the target LR image, our model adaptively discerns the degradation process. It is then applied to generate additional LR-HR pairs through down-sampling the HR reference images, which are keys to improving the SR performance. Our reference-based training procedure is applicable to proficiently trained blind SR models and zero-shot blind SR methods, consistently outperforming previous methods in both scenarios. This dual consideration of blur kernels and scaling factors, coupled with the use of a reference image, contributes to the effectiveness of our approach in blind super-resolution tasks.
title Blind Super Resolution with Reference Images and Implicit Degradation Representation
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.13915