{"ID":2864603,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.23150","arxiv_id":"2509.23150","title":"WeatherCycle: Unpaired Multi-Weather Restoration via Color Space Decoupled Cycle Learning","abstract":"Unsupervised image restoration under multi-weather conditions remains a fundamental yet underexplored challenge. While existing methods often rely on task-specific physical priors, their narrow focus limits scalability and generalization to diverse real-world weather scenarios. In this work, we propose \\textbf{WeatherCycle}, a unified unpaired framework that reformulates weather restoration as a bidirectional degradation-content translation cycle, guided by degradation-aware curriculum regularization. At its core, WeatherCycle employs a \\textit{lumina-chroma decomposition} strategy to decouple degradation from content without modeling complex weather, enabling domain conversion between degraded and clean images. To model diverse and complex degradations, we propose a \\textit{Lumina Degradation Guidance Module} (LDGM), which learns luminance degradation priors from a degraded image pool and injects them into clean images via frequency-domain amplitude modulation, enabling controllable and realistic degradation modeling. Additionally, we incorporate a \\textit{Difficulty-Aware Contrastive Regularization (DACR)} module that identifies hard samples via a CLIP-based classifier and enforces contrastive alignment between hard samples and restored features to enhance semantic consistency and robustness. Extensive experiments across serve multi-weather datasets, demonstrate that our method achieves state-of-the-art performance among unsupervised approaches, with strong generalization to complex weather degradations.","short_abstract":"Unsupervised image restoration under multi-weather conditions remains a fundamental yet underexplored challenge. While existing methods often rely on task-specific physical priors, their narrow focus limits scalability and generalization to diverse real-world weather scenarios. In this work, we propose \\textbf{WeatherC...","url_abs":"https://arxiv.org/abs/2509.23150","url_pdf":"https://arxiv.org/pdf/2509.23150v1","authors":"[\"Wenxuan Fang\",\"Jiangwei Weng\",\"Jianjun Qian\",\"Jian Yang\",\"Jun Li\"]","published":"2025-09-27T06:44:27Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}