{"ID":2844861,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.05095","arxiv_id":"2511.05095","title":"Real-World Adverse Weather Image Restoration via Dual-Level Reinforcement Learning with High-Quality Cold Start","abstract":"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","short_abstract":"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,...","url_abs":"https://arxiv.org/abs/2511.05095","url_pdf":"https://arxiv.org/pdf/2511.05095v1","authors":"[\"Fuyang Liu\",\"Jiaqi Xu\",\"Xiaowei Hu\"]","published":"2025-11-07T09:22:53Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Reinforcement Learning\"]","has_code":false,"code_links":[{"ID":607328,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2844861,"paper_url":"https://arxiv.org/abs/2511.05095","paper_title":"Real-World Adverse Weather Image Restoration via Dual-Level Reinforcement Learning with High-Quality Cold Start","repo_url":"https://github.com/xxclfy/AgentRL-Real-Weather","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}