HUGS-Net: A Lightweight and Unified Network for Adverse Weather Image Denoising

Image denoising under adverse weather conditions aims to eliminate multiple weather-related noises and restore bright and clear images. Until now, most methods are task-specific while all-in-one algorithms often require a large number of parameters, limiting their model efficiency. Our theoretical analysis and statistical experiments reveal that adverse weather images in Hue channel contain rich contextual information for further processing. With this observation, we propose a novel lightweight HUe-Guided Synergistic Network (HUGS-Net) with multi-scale detail refinement. First, we design a Fourier interaction and evolution module to capture global information from Hue channel without introducing excessive network parameters. Second, we develop a lightweight residue group convolution block to model local texture features, incorporating them with global information to guide noises removal. Third, we introduce a multi-scale fusion module to enhance high-frequency details at a small feature resolution in RGB color space. With the above design, HUGS-Net further supervises and supplements refined background information. Comprehensive experiments showcase the superiority of HUGS-Net across various adverse weather datasets (e.g., image deraining, desnowing, dehazing) with the least parameter size and fast running speed.The source code will be made public after peer review process.