{"ID":2870987,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.12039","arxiv_id":"2509.12039","title":"RAM++: Robust Representation Learning via Adaptive Mask for All-in-One Image Restoration","abstract":"This work presents Robust Representation Learning via Adaptive Mask (RAM++), a two-stage framework for all-in-one image restoration. RAM++ integrates high-level semantic understanding with low-level texture generation to achieve content-oriented robust restoration. It addresses the limitations of existing degradation-oriented methods in extreme scenarios (e.g., degradations strongly coupled with image structures). RAM++ also mitigates common challenges such as unbalanced performance across tasks, overfitting to seen degradations, and weak generalization to unseen ones through three key designs: 1) Adaptive Semantic-Aware Mask (AdaSAM): a pretraining strategy that applies pixel-level masks to semantically rich and textured regions. This design enables the network to learn both generative priors and image content priors from various degradations. 2) Mask Attribute Conductance (MAC): a selective fine-tuning strategy that adjusts the layers with higher contributions to bridge the integrity gap between masked pretraining and full-image fine-tuning while retaining learned priors. 3) Robust Feature Regularization (RFR): a strategy that leverages DINOv2's semantically consistent and degradation-invariant representations, together with efficient feature fusion, to achieve faithful and semantically coherent restoration. With these designs, RAM++ achieves robust, well-balanced, and state-of-the-art performance across seen, unseen, extreme, and mixed degradations. Our code and model will be released at https://github.com/DragonisCV/RAM","short_abstract":"This work presents Robust Representation Learning via Adaptive Mask (RAM++), a two-stage framework for all-in-one image restoration. RAM++ integrates high-level semantic understanding with low-level texture generation to achieve content-oriented robust restoration. It addresses the limitations of existing degradation-o...","url_abs":"https://arxiv.org/abs/2509.12039","url_pdf":"https://arxiv.org/pdf/2509.12039v1","authors":"[\"Zilong Zhang\",\"Chujie Qin\",\"Chunle Guo\",\"Yong Zhang\",\"Chao Xue\",\"Ming-Ming Cheng\",\"Chongyi Li\"]","published":"2025-09-15T15:24:15Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":609816,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2870987,"paper_url":"https://arxiv.org/abs/2509.12039","paper_title":"RAM++: Robust Representation Learning via Adaptive Mask for All-in-One Image Restoration","repo_url":"https://github.com/DragonisCV/RAM","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}