{"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/towards-efficient-and-scale-robust-ultra-high","title":"Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing","arxiv_id":"2207.09935","date":"2022-07-20","proceeding":null,"authors":["Xin Yu","Peng Dai","Wenbo Li","Lan Ma","Jiajun Shen","Jia Li","Xiaojuan Qi"],"abstract":"With the rapid development of mobile devices, modern widely-used mobile phones typically allow users to capture 4K resolution (i.e., ultra-high-definition) images. However, for image demoireing, a challenging task in low-level vision, existing works are generally carried out on low-resolution or synthetic images. Hence, the effectiveness of these methods on 4K resolution images is still unknown. In this paper, we explore moire pattern removal for ultra-high-definition images. To this end, we propose the first ultra-high-definition demoireing dataset (UHDM), which contains 5,000 real-world 4K resolution image pairs, and conduct a benchmark study on current state-of-the-art methods. Further, we present an efficient baseline model ESDNet for tackling 4K moire images, wherein we build a semantic-aligned scale-aware module to address the scale variation of moire patterns. Extensive experiments manifest the effectiveness of our approach, which outperforms state-of-the-art methods by a large margin while being much more lightweight. Code and dataset are available at https://xinyu-andy.github.io/uhdm-page.","url_abs":"https://arxiv.org/abs/2207.09935v1","url_pdf":"https://arxiv.org/pdf/2207.09935v1.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":"towards-efficient-and-scale-robust-ultra-high","repo_url":"https://github.com/CVMI-Lab/UHDM","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"4k","task_name":"4k"},{"task_slug":"image-enhancement","task_name":"Image Enhancement"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[],"datasets_introduced":[{"slug":"uhdm","name":"UHDM","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-enhancement-on-tip-2018","task":"Image Enhancement","dataset":"TIP 2018","model":"ESDNet-L","rank_in_archive_order":1,"of":6,"metrics":{"PSNR":"30.11","SSIM":"0.920"},"uses_additional_data":false},{"leaderboard":"/sota/image-enhancement-on-tip-2018","task":"Image Enhancement","dataset":"TIP 2018","model":"ESDNet","rank_in_archive_order":3,"of":6,"metrics":{"PSNR":"29.81","SSIM":"0.916"},"uses_additional_data":false},{"leaderboard":"/sota/image-restoration-on-uhdm","task":"Image Restoration","dataset":"UHDM","model":"ESDNet-L","rank_in_archive_order":1,"of":2,"metrics":{"PSNR":"22.422"},"uses_additional_data":false},{"leaderboard":"/sota/image-restoration-on-uhdm","task":"Image Restoration","dataset":"UHDM","model":"ESDNet","rank_in_archive_order":2,"of":2,"metrics":{"PSNR":"22.119"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.09935","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}