{"ID":6596602,"CreatedAt":"2026-07-14T18:34:44.309704555Z","UpdatedAt":"2026-07-14T18:34:44.309704555Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2605.08627","arxiv_id":"2605.08627","title":"DRNet: All-in-One Image Restoration via Prior-Guided Dynamic Reparameterization","abstract":"All-in-one image restoration aims to handle diverse degradations within a single model. However, existing methods often suffer from three key limitations: 1) per-input computational overhead from dynamic degradation estimation; 2) optimization challenges due to task heterogeneity; and 3) inefficient, frequency-agnostic encoder designs. To overcome these, we introduce the Dynamic Reparameterization Network (DRNet), a novel framework operating on an initialization-stage reconfiguration paradigm that fundamentally eliminates per-input overhead. At its core, a Dynamic Reparameterization MLP (DRMLP) guided by a Task-Specific Modulator (TSM), which effectively mitigates task heterogeneity by orchestrating both specific restoration goals and a versatile general-purpose mode within a unified architecture. Furthermore, we incorporate a Continuous Wavelet Transform Encoder (CWTE) that explicitly leverages frequency characteristics via wavelet decomposition for a lightweight yet powerful design. Extensive experiments demonstrate that DRNet achieves state-of-the-art performance across five restoration tasks with superior parameter efficiency. Crucially, it showcases unique flexibility, excelling as both a highly competitive foundation model for blind restoration and a top-performing user-guided specialist.","url_abs":"https://arxiv.org/abs/2605.08627v1","url_pdf":"https://arxiv.org/pdf/2605.08627v1","authors":"Ao Li, Xiaoning Liu, Sheng Li, Yapeng Du, Zhen Long, Lei Luo, Le Zhang, Ce Zhu","published":"2026-05-09T02:43:00Z","has_code":false}