Lightweight Image Super-Resolution Via Superpixel Prior and Feature Reinforcement

Authors

  • Rui Xu Chongqing University of Technology, Chongqing 400054, China
  • Wei Fan Chongqing University of Technology, Chongqing 400054, China

DOI:

https://doi.org/10.53469/jrse.2025.07(06).03

Keywords:

Image Super-Resolution, Superpixel Awareness, Lightweight, Structural Modeling

Abstract

Single Image Super-Resolution (SISR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs, serving as a core task in computer vision. Despite recent advances, existing methods often struggle to balance structural fidelity and computational efficiency. To address this, we propose PFRNet, a lightweight superpixel-aware model integrating superpixel segmentation, local attention aggregation, and global structure modeling. The framework comprises four key modules: GASS, SPDF, SPFA, and LAP, jointly enabling multi-scale and structure-consistent feature learning. Experiments on benchmark datasets (e.g., Set5, Urban100) show that PFRNet achieves superior performance with fewer parameters. Ablation studies further verify the effectiveness of each module.

Downloads

Published

2025-06-30

How to Cite

Xu, R., & Fan, W. (2025). Lightweight Image Super-Resolution Via Superpixel Prior and Feature Reinforcement. Journal of Research in Science and Engineering, 7(6), 11–16. https://doi.org/10.53469/jrse.2025.07(06).03

Issue

Section

Articles