Saved in:
Bibliographic Details
Main Authors: Yoon, Dongsik, Kim, Jongeun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.06387
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917197767507968
author Yoon, Dongsik
Kim, Jongeun
author_facet Yoon, Dongsik
Kim, Jongeun
contents Despite remarkable progress in Single Image Super-Resolution (SISR), traditional models often struggle to generalize across varying scale factors, limiting their real-world applicability. To address this, we propose a plug-in Scale-Aware Attention Module (SAAM) designed to retrofit modern fixed-scale SR models with the ability to perform arbitrary-scale SR. SAAM employs lightweight, scale-adaptive feature extraction and upsampling, incorporating the Simple parameter-free Attention Module (SimAM) for efficient guidance and gradient variance loss to enhance sharpness in image details. Our method integrates seamlessly into multiple state-of-the-art SR backbones (e.g., SCNet, HiT-SR, OverNet), delivering competitive or superior performance across a wide range of integer and non-integer scale factors. Extensive experiments on benchmark datasets demonstrate that our approach enables robust multi-scale upscaling with minimal computational overhead, offering a practical solution for real-world scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2509_06387
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Your Super Resolution Model is not Enough for Tackling Real-World Scenarios
Yoon, Dongsik
Kim, Jongeun
Computer Vision and Pattern Recognition
Despite remarkable progress in Single Image Super-Resolution (SISR), traditional models often struggle to generalize across varying scale factors, limiting their real-world applicability. To address this, we propose a plug-in Scale-Aware Attention Module (SAAM) designed to retrofit modern fixed-scale SR models with the ability to perform arbitrary-scale SR. SAAM employs lightweight, scale-adaptive feature extraction and upsampling, incorporating the Simple parameter-free Attention Module (SimAM) for efficient guidance and gradient variance loss to enhance sharpness in image details. Our method integrates seamlessly into multiple state-of-the-art SR backbones (e.g., SCNet, HiT-SR, OverNet), delivering competitive or superior performance across a wide range of integer and non-integer scale factors. Extensive experiments on benchmark datasets demonstrate that our approach enables robust multi-scale upscaling with minimal computational overhead, offering a practical solution for real-world scenarios.
title Your Super Resolution Model is not Enough for Tackling Real-World Scenarios
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.06387