PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
This work addresses the challenging problem of removing heterogeneous and unseen weather degradations in real-world images, offering a unified solution that improves both fidelity and perceptual quality over existing methods.
PVRF proposes a unified framework for adverse weather removal that integrates zero-shot soft weather perceptions from VLMs with velocity-constrained rectified flow, achieving state-of-the-art fidelity and perceptual quality across multiple weather types and unseen degradations.
Adverse weather removal (AWR) in real-world images remains challenging due to heterogeneous and unseen degradations, while distortion-driven training often yields overly smooth results. We propose PVRF, a unified framework that integrates zero-shot soft weather perceptions with velocity-constrained rectified-flow refinement. PVRF introduces an AWR-specific question answering module (AWR-QA) that uses frozen vision--language models (VLMs) to estimate soft probabilities of weather types and low-level attribute scores. These perceptions condition restoration networks via attribute-modulated normalization (AMN) and weather-weighted adapters (WWA), producing an anchor estimate for refinement. We then learn a terminal-consistent residual rectified flow with perception-adaptive source perturbation and a terminal-consistent velocity parameterization to stabilize learning near the terminal regime. Extensive experiments show that PVRF improves both fidelity and perceptual quality over state-of-the-art baselines, with strong cross-dataset generalization on single and combined degradations. Code will be released at https://github.com/dongw22/PVRF.