cs.CVMay 5, 2026

CASISR: Circular Arbitrary-Scale Image Super-Resolution

Authors: Honggui LiZhengyang ZhangDingtai LiSinan ChenNahid Md Lokman HossainXinfeng XuYinlu QinRuobing Wang+6 more

Organizations: School of Information and Artificial Intelligence, Yangzhou University, Yangzhou 225127, China · Shanghai Qigong Research Institute, Shanghai University of Traditional Chinese Medicine, Shanghai 201203, China · LISITE Research Laboratory, Institut Supérieur d'Électronique de Paris, Paris 75006, France · Laboratoire d'Informatique de Paris 6, Sorbonne University, Paris 75020, France · International Campus (Hangzhou), Beijing University of Aeronautics and Astronautics, Hangzhou 310000, China · School of Engineering, Westlake University, Hangzhou 310024, China · Polystim Neurotech Laboratory, Polytechnique Montreal, Montreal H3T1J4, Canada

Abstract

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.

Explore similar work

CardsList