Your Super Resolution Model is not Enough
for Tackling Real-World Scenarios

Abstract

Despite remarkable progress in Single Image SuperResolution (SISR), traditional models often struggle to generalize across varying scale factors, limiting their realworld applicability.

To address this, we propose a plugin Scale-Aware Attention Module (SAAM) designed to retrofit modern fixed-scale SR models with the ability to perform arbitrary-scale SR. SAAM employs lightweight, scaleadaptive 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.