{"ID":2830966,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.08161","arxiv_id":"2512.08161","title":"Fourier-RWKV: A Multi-State Perception Network for Efficient Image Dehazing","abstract":"Image dehazing is crucial for reliable visual perception, yet it remains highly challenging under real-world non-uniform haze conditions. Although Transformer-based methods excel at capturing global context, their quadratic computational complexity hinders real-time deployment. To address this, we propose Fourier Receptance Weighted Key Value (Fourier-RWKV), a novel dehazing framework based on a Multi-State Perception paradigm. The model achieves comprehensive haze degradation modeling with linear complexity by synergistically integrating three distinct perceptual states: (1) Spatial-form Perception, realized through the Deformable Quad-directional Token Shift (DQ-Shift) operation, which dynamically adjusts receptive fields to accommodate local haze variations; (2) Frequency-domain Perception, implemented within the Fourier Mix block, which extends the core WKV attention mechanism of RWKV from the spatial domain to the Fourier domain, preserving the long-range dependencies essential for global haze estimation while mitigating spatial attenuation; (3) Semantic-relation Perception, facilitated by the Semantic Bridge Module (SBM), which utilizes Dynamic Semantic Kernel Fusion (DSK-Fusion) to precisely align encoder-decoder features and suppress artifacts. Extensive experiments on multiple benchmarks demonstrate that Fourier-RWKV delivers state-of-the-art performance across diverse haze scenarios while significantly reducing computational overhead, establishing a favorable trade-off between restoration quality and practical efficiency. Code is available at: https://github.com/Dilizlr/Fourier-RWKV.","short_abstract":"Image dehazing is crucial for reliable visual perception, yet it remains highly challenging under real-world non-uniform haze conditions. Although Transformer-based methods excel at capturing global context, their quadratic computational complexity hinders real-time deployment. To address this, we propose Fourier Recep...","url_abs":"https://arxiv.org/abs/2512.08161","url_pdf":"https://arxiv.org/pdf/2512.08161v2","authors":"[\"Lirong Zheng\",\"Yanshan Li\",\"Rui Yu\",\"Kaihao Zhang\"]","published":"2025-12-09T01:35:56Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false,"code_links":[{"ID":606087,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2830966,"paper_url":"https://arxiv.org/abs/2512.08161","paper_title":"Fourier-RWKV: A Multi-State Perception Network for Efficient Image Dehazing","repo_url":"https://github.com/Dilizlr/Fourier-RWKV","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}