When Color-Space Decoupling Meets Diffusion for Adverse-Weather Image Restoration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fang, Wenxuan, Fan, Jili, Wang, Chao, Hu, Xiantao, Weng, Jiangwei, Tai, Ying, Yang, Jian, Li, Jun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916959165087744
author Fang, Wenxuan
Fan, Jili
Wang, Chao
Hu, Xiantao
Weng, Jiangwei
Tai, Ying
Yang, Jian
Li, Jun
author_facet Fang, Wenxuan
Fan, Jili
Wang, Chao
Hu, Xiantao
Weng, Jiangwei
Tai, Ying
Yang, Jian
Li, Jun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_17024
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle When Color-Space Decoupling Meets Diffusion for Adverse-Weather Image Restoration
Fang, Wenxuan
Fan, Jili
Wang, Chao
Hu, Xiantao
Weng, Jiangwei
Tai, Ying
Yang, Jian
Li, Jun
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title When Color-Space Decoupling Meets Diffusion for Adverse-Weather Image Restoration
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2509.17024