{"ID":2888450,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.23685","arxiv_id":"2507.23685","title":"UniLDiff: Unlocking the Power of Diffusion Priors for All-in-One Image Restoration","abstract":"All-in-One Image Restoration (AiOIR) has emerged as a promising yet challenging research direction. To address the core challenges of diverse degradation modeling and detail preservation, we propose UniLDiff, a unified framework enhanced with degradation- and detail-aware mechanisms, unlocking the power of diffusion priors for robust image restoration. Specifically, we introduce a Degradation-Aware Feature Fusion (DAFF) to dynamically inject low-quality features into each denoising step via decoupled fusion and adaptive modulation, enabling implicit modeling of diverse and compound degradations. Furthermore, we design a Detail-Aware Expert Module (DAEM) in the decoder to enhance texture and fine-structure recovery through expert routing. Extensive experiments across multi-task and mixed degradation settings demonstrate that our method consistently achieves state-of-the-art performance, highlighting the practical potential of diffusion priors for unified image restoration. Our code will be released.","short_abstract":"All-in-One Image Restoration (AiOIR) has emerged as a promising yet challenging research direction. To address the core challenges of diverse degradation modeling and detail preservation, we propose UniLDiff, a unified framework enhanced with degradation- and detail-aware mechanisms, unlocking the power of diffusion pr...","url_abs":"https://arxiv.org/abs/2507.23685","url_pdf":"https://arxiv.org/pdf/2507.23685v2","authors":"[\"Zihan Cheng\",\"Liangtai Zhou\",\"Dian Chen\",\"Ni Tang\",\"Xiaotong Luo\",\"Yanyun Qu\"]","published":"2025-07-31T16:02:00Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}