SD-PSFNet: Sequential and Dynamic Point Spread Function Network for Image Deraining

TL;DR

SD-PSFNet introduces a physics-aware, multi-stage neural network that dynamically models rain streaks using Point Spread Function mechanisms, significantly improving image deraining performance in complex scenes.

Contribution

It proposes a novel sequential, multi-stage architecture with learned PSF components for dynamic rain modeling and adaptive feature fusion, advancing the state-of-the-art in image deraining.

Findings

Achieves state-of-the-art PSNR/SSIM on multiple datasets.

Effectively separates rain streaks from complex backgrounds.

Demonstrates robustness in dense rainfall conditions.

Abstract

Image deraining is crucial for vision applications but is challenged by the complex multi-scale physics of rain and its coupling with scenes. To address this challenge, a novel approach inspired by multi-stage image restoration is proposed, incorporating Point Spread Function (PSF) mechanisms to reveal the image degradation process while combining dynamic physical modeling with sequential feature fusion transfer, named SD-PSFNet. Specifically, SD-PSFNet employs a sequential restoration architecture with three cascaded stages, allowing multiple dynamic evaluations and refinements of the degradation process estimation. The network utilizes components with learned PSF mechanisms to dynamically simulate rain streak optics, enabling effective rain-background separation while progressively enhancing outputs through novel PSF components at each stage. Additionally, SD-PSFNet incorporates adaptive gated fusion for optimal cross-stage feature integration, enabling sequential refinement from coarse rain removal to fine detail restoration. Our model achieves state-of-the-art PSNR/SSIM metrics on Rain100H (33.12dB/0.9371), RealRain-1k-L (42.28dB/0.9872), and RealRain-1k-H (41.08dB/0.9838). In summary, SD-PSFNet demonstrates excellent capability in complex scenes and dense rainfall conditions, providing a new physics-aware approach to image deraining.