Real-World Adverse Weather Image Restoration via Dual-Level Reinforcement Learning with High-Quality Cold Start
This work addresses the challenge of real-world image restoration for applications like autonomous driving or surveillance, though it is incremental as it builds on existing reinforcement learning and dataset methods.
The paper tackles the problem of restoring images degraded by adverse weather conditions, which impairs visual perception, by introducing a dual-level reinforcement learning framework that achieves state-of-the-art performance across diverse weather scenarios.
Adverse weather severely impairs real-world visual perception, while existing vision models trained on synthetic data with fixed parameters struggle to generalize to complex degradations. To address this, we first construct HFLS-Weather, a physics-driven, high-fidelity dataset that simulates diverse weather phenomena, and then design a dual-level reinforcement learning framework initialized with HFLS-Weather for cold-start training. Within this framework, at the local level, weather-specific restoration models are refined through perturbation-driven image quality optimization, enabling reward-based learning without paired supervision; at the global level, a meta-controller dynamically orchestrates model selection and execution order according to scene degradation. This framework enables continuous adaptation to real-world conditions and achieves state-of-the-art performance across a wide range of adverse weather scenarios. Code is available at https://github.com/xxclfy/AgentRL-Real-Weather