{"ID":2868120,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.17024","arxiv_id":"2509.17024","title":"When Color-Space Decoupling Meets Diffusion for Adverse-Weather Image Restoration","abstract":"Adverse Weather Image Restoration (AWIR) is a highly challenging task due to the unpredictable and dynamic nature of weather-related degradations. Traditional task-specific methods often fail to generalize to unseen or complex degradation types, while recent prompt-learning approaches depend heavily on the degradation estimation capabilities of vision-language models, resulting in inconsistent restorations. In this paper, we propose \\textbf{LCDiff}, a novel framework comprising two key components: \\textit{Lumina-Chroma Decomposition Network} (LCDN) and \\textit{Lumina-Guided Diffusion Model} (LGDM). LCDN processes degraded images in the YCbCr color space, separately handling degradation-related luminance and degradation-invariant chrominance components. This decomposition effectively mitigates weather-induced degradation while preserving color fidelity. To further enhance restoration quality, LGDM leverages degradation-related luminance information as a guiding condition, eliminating the need for explicit degradation prompts. Additionally, LGDM incorporates a \\textit{Dynamic Time Step Loss} to optimize the denoising network, ensuring a balanced recovery of both low- and high-frequency features in the image. Finally, we present DriveWeather, a comprehensive all-weather driving dataset designed to enable robust evaluation. Extensive experiments demonstrate that our approach surpasses state-of-the-art methods, setting a new benchmark in AWIR. The dataset and code are available at: https://github.com/fiwy0527/LCDiff.","short_abstract":"Adverse Weather Image Restoration (AWIR) is a highly challenging task due to the unpredictable and dynamic nature of weather-related degradations. Traditional task-specific methods often fail to generalize to unseen or complex degradation types, while recent prompt-learning approaches depend heavily on the degradation...","url_abs":"https://arxiv.org/abs/2509.17024","url_pdf":"https://arxiv.org/pdf/2509.17024v1","authors":"[\"Wenxuan Fang\",\"Jili Fan\",\"Chao Wang\",\"Xiantao Hu\",\"Jiangwei Weng\",\"Ying Tai\",\"Jian Yang\",\"Jun Li\"]","published":"2025-09-21T10:39:06Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Diffusion Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":609547,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2868120,"paper_url":"https://arxiv.org/abs/2509.17024","paper_title":"When Color-Space Decoupling Meets Diffusion for Adverse-Weather Image Restoration","repo_url":"https://github.com/fiwy0527/LCDiff","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}