{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/from-zero-to-detail-deconstructing-ultra-high-1","title":"From Zero to Detail: Deconstructing Ultra-High-Definition Image Restoration from Progressive Spectral Perspective","arxiv_id":"2503.13165","date":"2025-03-17","proceeding":"CVPR 2025 1","authors":["Chen Zhao","Zhizhou Chen","Yunzhe Xu","Enxuan Gu","Jian Li","Zili Yi","Qian Wang","Jian Yang","Ying Tai"],"abstract":"Ultra-high-definition (UHD) image restoration faces significant challenges due to its high resolution, complex content, and intricate details. To cope with these challenges, we analyze the restoration process in depth through a progressive spectral perspective, and deconstruct the complex UHD restoration problem into three progressive stages: zero-frequency enhancement, low-frequency restoration, and high-frequency refinement. Building on this insight, we propose a novel framework, ERR, which comprises three collaborative sub-networks: the zero-frequency enhancer (ZFE), the low-frequency restorer (LFR), and the high-frequency refiner (HFR). Specifically, the ZFE integrates global priors to learn global mapping, while the LFR restores low-frequency information, emphasizing reconstruction of coarse-grained content. Finally, the HFR employs our designed frequency-windowed kolmogorov-arnold networks (FW-KAN) to refine textures and details, producing high-quality image restoration. Our approach significantly outperforms previous UHD methods across various tasks, with extensive ablation studies validating the effectiveness of each component. The code is available at \\href{https://github.com/NJU-PCALab/ERR}{here}.","url_abs":"https://arxiv.org/abs/2503.13165v1","url_pdf":"https://arxiv.org/pdf/2503.13165v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"from-zero-to-detail-deconstructing-ultra-high-1","repo_url":"https://github.com/nju-pcalab/err","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"kolmogorov-arnold-networks","task_name":"Kolmogorov-Arnold Networks"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2503.13165","atlas_url":"https://app.syntology.ai/?focus=2503.13165","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}