WeatherCycle: Unpaired Multi-Weather Restoration via Color Space Decoupled Cycle Learning

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 $\mathbf{\text{WeatherCycle}}$, 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 $\mathit{\text{lumina-chroma}}\mathit{\text{decomposition}}$ 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 $\mathit{\text{Lumina}}\mathit{\text{Degradation}}\mathit{\text{Guidance}}\mathit{\text{Module}}$ (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 $\mathit{\text{Difficulty-Aware}}\mathit{\text{Contrastive}}\mathit{\text{Regularization}}\mathit{\text{(DACR)}}$ 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.