Your Super Resolution Model is not Enough for Tackling Real-World Scenarios
This addresses a real-world applicability issue for image processing and computer vision users, though it is incremental as it retrofits existing models.
The paper tackles the problem of single image super-resolution models struggling with varying scale factors by proposing a plug-in Scale-Aware Attention Module (SAAM) that enables arbitrary-scale SR, achieving competitive or superior performance across multiple scale factors with minimal computational overhead.
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.