{"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/moire-photo-restoration-using-multiresolution","title":"Moiré Photo Restoration Using Multiresolution Convolutional Neural Networks","arxiv_id":"1805.02996","date":"2018-05-08","proceeding":null,"authors":["Yujing Sun","Yizhou Yu","Wenping Wang"],"abstract":"Digital cameras and mobile phones enable us to conveniently record precious\nmoments. While digital image quality is constantly being improved, taking\nhigh-quality photos of digital screens still remains challenging because the\nphotos are often contaminated with moir\\'{e} patterns, a result of the\ninterference between the pixel grids of the camera sensor and the device\nscreen. Moir\\'{e} patterns can severely damage the visual quality of photos.\nHowever, few studies have aimed to solve this problem. In this paper, we\nintroduce a novel multiresolution fully convolutional network for automatically\nremoving moir\\'{e} patterns from photos. Since a moir\\'{e} pattern spans over a\nwide range of frequencies, our proposed network performs a nonlinear\nmultiresolution analysis of the input image before computing how to cancel\nmoir\\'{e} artefacts within every frequency band. We also create a large-scale\nbenchmark dataset with $100,000^+$ image pairs for investigating and evaluating\nmoir\\'{e} pattern removal algorithms. Our network achieves state-of-the-art\nperformance on this dataset in comparison to existing learning architectures\nfor image restoration problems.","url_abs":"http://arxiv.org/abs/1805.02996v1","url_pdf":"http://arxiv.org/pdf/1805.02996v1.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":"moire-photo-restoration-using-multiresolution","repo_url":"https://github.com/ZhengJun-AI/MoirePhotoRestoration-MCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-enhancement","task_name":"Image Enhancement"},{"task_slug":"image-restoration","task_name":"Image Restoration"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fcn","method_name":"FCN"},{"method_slug":"max-pooling","method_name":"Max Pooling"}],"datasets_introduced":[{"slug":"tip-2018","name":"TIP 2018","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-enhancement-on-tip-2018","task":"Image Enhancement","dataset":"TIP 2018","model":"DMCNN","rank_in_archive_order":6,"of":6,"metrics":{"FSIM":"0.914","PSNR":"26.77","SSIM":"0.871"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.02996","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}