A multistage progressive image restoration network for single image deraining
TL;DR
Experimental results show that MPINet effectively removes rain streaks of varying densities while preserving fine textures, and across all evaluated datasets, MPINet outperforms MPRNet by about 6.5% in PSNR and 1.3% in SSIM on average.
Abstract
Image deraining remains a fundamental challenge in computer vision, as rain streaks severely degrade visual quality, obscure scene content, and hinder downstream applications such as autonomous driving and video surveillance. Existing methods often struggle to balance global scene understanding with precise rain removal, resulting in either residual artifacts or over-smoothed textures. To address this issue, we propose MPINet, a Multi-Stage Progressive Image Restoration Network for image deraining. MPINet integrates illumination-aware modeling with global context learning to improve deraining performance under diverse lighting conditions. Specifically, the illumination-aware module generates illumination maps to enhance robustness in scenes with varying brightness, while the UniMetaFormer-based core captures global semantic information through dynamic transformations and attention mechanisms, enabling more effective discrimination between rain streaks and underlying image structures. Built upon the multi-stage restoration paradigm of MPRNet, MPINet adopts a hierarchical progressive framework with patch-based processing and deep supervision across three stages, allowing efficient feature refinement with reasonable model complexity. Experimental results show that MPINet effectively removes rain streaks of varying densities while preserving fine textures. Across all evaluated datasets, MPINet outperforms MPRNet by about 6.5% in PSNR and 1.3% in SSIM on average.