{"ID":2873553,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.06904","arxiv_id":"2509.06904","title":"BIR-Adapter: A parameter-efficient diffusion adapter for blind image restoration","abstract":"We introduce the BIR-Adapter, a parameter-efficient diffusion adapter for blind image restoration. Diffusion-based restoration methods have demonstrated promising performance in addressing this fundamental problem in computer vision, typically relying on auxiliary feature extractors or extensive fine-tuning of pre-trained models. Building on the observation that large-scale pretrained diffusion models can retain informative representations under image degradations, BIR-Adapter introduces a parameter-efficient, plug-and-play attention mechanism that substantially reduces the number of trained parameters. To further improve reliability, we adapt a sampling guidance mechanism that mitigates hallucinations during restoration. Experiments on synthetic and real-world degradations demonstrate that BIR-Adapter achieves competitive, and in several settings superior, performance compared to state-of-the-art methods while requiring up to 36x fewer trained parameters. Moreover, the adapter-based design enables integration into existing models. We validate this generality by extending a super-resolution-only diffusion model to handle additional unknown degradations, highlighting the adaptability of our approach for broader image restoration tasks.","short_abstract":"We introduce the BIR-Adapter, a parameter-efficient diffusion adapter for blind image restoration. Diffusion-based restoration methods have demonstrated promising performance in addressing this fundamental problem in computer vision, typically relying on auxiliary feature extractors or extensive fine-tuning of pre-trai...","url_abs":"https://arxiv.org/abs/2509.06904","url_pdf":"https://arxiv.org/pdf/2509.06904v3","authors":"[\"Cem Eteke\",\"Alexander Griessel\",\"Wolfgang Kellerer\",\"Eckehard Steinbach\"]","published":"2025-09-08T17:22:18Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}