Salvato in:
Dettagli Bibliografici
Autori principali: Li, Honggui, Zhang, Zhengyang, Li, Dingtai, Chen, Sinan, Hossain, Nahid Md Lokman, Xu, Xinfeng, Qin, Yinlu, Wang, Ruobing, Lu, Hantao, Feng, Yuting, Trocan, Maria, Galayko, Dimitri, Amara, Amara, Sawan, Mohamad
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2605.08173
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914545740546048
author Li, Honggui
Zhang, Zhengyang
Li, Dingtai
Chen, Sinan
Hossain, Nahid Md Lokman
Xu, Xinfeng
Qin, Yinlu
Wang, Ruobing
Lu, Hantao
Feng, Yuting
Trocan, Maria
Galayko, Dimitri
Amara, Amara
Sawan, Mohamad
author_facet Li, Honggui
Zhang, Zhengyang
Li, Dingtai
Chen, Sinan
Hossain, Nahid Md Lokman
Xu, Xinfeng
Qin, Yinlu
Wang, Ruobing
Lu, Hantao
Feng, Yuting
Trocan, Maria
Galayko, Dimitri
Amara, Amara
Sawan, Mohamad
contents The generalization performance (GP) of deep learning-based arbitrary-scale image super-resolution (ASISR) methods is subject to limited training datasets and unlimited testing datasets. It is vitally significant to enhance the GP of the pretrained ASISR models by making full use of the testing samples. The ASISR models usually employ an open-loop architecture from low-resolution (LR) images to super-resolution (SR) images. The degradation model from SR samples to LR samples is known bicubic down-sampling for the classical ASISR, is supposed down-sampling with additive random noise for the blind ASISR, and is learnable for the real-world ASISR. Combining the ASISR and degradation models, it is potentially possible to adopt a closed-loop architecture based on the automatic control theory for strengthening the GP of the ASISR methods. Therefore, this paper proposes a closed-loop architecture, circular ASISR (CASISR), to lift the capability of image reconstruction. A mathematical nonlinear loop equation is established to describe the CASISR, the reasonability of the CASISR is proven by conditional probability theory, and the stability of the CASISR is proven by Taylor series approximation. The first-order and second-order absolute difference images are defined to compare the image reconstruction performance of the ASISR and the CASISR methods. Comprehensive simulation experiments show that the proposed CASISR approach outperforms the eight state-of-the-art ASISR approaches in the quality of image reconstruction. Especially, the proposed CASISR is extraordinarily suitable for fractional SR scale factors and is extremely effective for text and stripe images with drastically changed edges.
format Preprint
id arxiv_https___arxiv_org_abs_2605_08173
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CASISR: Circular Arbitrary-Scale Image Super-Resolution
Li, Honggui
Zhang, Zhengyang
Li, Dingtai
Chen, Sinan
Hossain, Nahid Md Lokman
Xu, Xinfeng
Qin, Yinlu
Wang, Ruobing
Lu, Hantao
Feng, Yuting
Trocan, Maria
Galayko, Dimitri
Amara, Amara
Sawan, Mohamad
Computer Vision and Pattern Recognition
Machine Learning
The generalization performance (GP) of deep learning-based arbitrary-scale image super-resolution (ASISR) methods is subject to limited training datasets and unlimited testing datasets. It is vitally significant to enhance the GP of the pretrained ASISR models by making full use of the testing samples. The ASISR models usually employ an open-loop architecture from low-resolution (LR) images to super-resolution (SR) images. The degradation model from SR samples to LR samples is known bicubic down-sampling for the classical ASISR, is supposed down-sampling with additive random noise for the blind ASISR, and is learnable for the real-world ASISR. Combining the ASISR and degradation models, it is potentially possible to adopt a closed-loop architecture based on the automatic control theory for strengthening the GP of the ASISR methods. Therefore, this paper proposes a closed-loop architecture, circular ASISR (CASISR), to lift the capability of image reconstruction. A mathematical nonlinear loop equation is established to describe the CASISR, the reasonability of the CASISR is proven by conditional probability theory, and the stability of the CASISR is proven by Taylor series approximation. The first-order and second-order absolute difference images are defined to compare the image reconstruction performance of the ASISR and the CASISR methods. Comprehensive simulation experiments show that the proposed CASISR approach outperforms the eight state-of-the-art ASISR approaches in the quality of image reconstruction. Especially, the proposed CASISR is extraordinarily suitable for fractional SR scale factors and is extremely effective for text and stripe images with drastically changed edges.
title CASISR: Circular Arbitrary-Scale Image Super-Resolution
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2605.08173