{"ID":2830241,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.10581","arxiv_id":"2512.10581","title":"Unleashing Degradation-Carrying Features in Symmetric U-Net: Simpler and Stronger Baselines for All-in-One Image Restoration","abstract":"All-in-one image restoration aims to handle diverse degradations (e.g., noise, blur, adverse weather) within a unified framework, yet existing methods increasingly rely on complex architectures (e.g., Mixture-of-Experts, diffusion models) and elaborate degradation prompt strategies. In this work, we reveal a critical insight: well-crafted feature extraction inherently encodes degradation-carrying information, and a symmetric U-Net architecture is sufficient to unleash these cues effectively. By aligning feature scales across encoder-decoder and enabling streamlined cross-scale propagation, our symmetric design preserves intrinsic degradation signals robustly, rendering simple additive fusion in skip connections sufficient for state-of-the-art performance. Our primary baseline, SymUNet, is built on this symmetric U-Net and achieves better results across benchmark datasets than existing approaches while reducing computational cost. We further propose a semantic enhanced variant, SE-SymUNet, which integrates direct semantic injection from frozen CLIP features via simple cross-attention to explicitly amplify degradation priors. Extensive experiments on several benchmarks validate the superiority of our methods. Both baselines SymUNet and SE-SymUNet establish simpler and stronger foundations for future advancements in all-in-one image restoration. The source code is available at https://github.com/WenlongJiao/SymUNet.","short_abstract":"All-in-one image restoration aims to handle diverse degradations (e.g., noise, blur, adverse weather) within a unified framework, yet existing methods increasingly rely on complex architectures (e.g., Mixture-of-Experts, diffusion models) and elaborate degradation prompt strategies. In this work, we reveal a critical i...","url_abs":"https://arxiv.org/abs/2512.10581","url_pdf":"https://arxiv.org/pdf/2512.10581v1","authors":"[\"Wenlong Jiao\",\"Heyang Lee\",\"Ping Wang\",\"Pengfei Zhu\",\"Qinghua Hu\",\"Dongwei Ren\"]","published":"2025-12-11T12:20:31Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":606013,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2830241,"paper_url":"https://arxiv.org/abs/2512.10581","paper_title":"Unleashing Degradation-Carrying Features in Symmetric U-Net: Simpler and Stronger Baselines for All-in-One Image Restoration","repo_url":"https://github.com/WenlongJiao/SymUNet","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}