{"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/docunet-document-image-unwarping-via-a","title":"DocUNet: Document Image Unwarping via a Stacked U-Net","arxiv_id":null,"date":"2018-06-01","proceeding":"CVPR 2018 6","authors":["Ke Ma","Zhixin Shu","Xue Bai","Jue Wang","Dimitris Samaras"],"abstract":"Capturing document images is a common way for digitizing and recording physical documents due to the ubiquitousness of mobile cameras. To make text recognition easier, it is often desirable to digitally flatten a document image when the physical document sheet is folded or curved. In this paper, we develop the first learning-based method to achieve this goal. We propose a stacked U-Net with intermediate supervision to directly predict the forward mapping from a distorted image to its rectified version. Because large-scale real-world data with ground truth deformation is difficult to obtain, we create a synthetic dataset with approximately 100 thousand images by warping non-distorted document images. The network is trained on this dataset with various data augmentations to improve its generalization ability. We further create a comprehensive benchmark that covers various real-world conditions. We evaluate the proposed model quantitatively and qualitatively on the proposed benchmark, and compare it with previous non-learning-based methods.","url_abs":"http://openaccess.thecvf.com/content_cvpr_2018/html/Ma_DocUNet_Document_Image_CVPR_2018_paper.html","url_pdf":"http://openaccess.thecvf.com/content_cvpr_2018/papers/Ma_DocUNet_Document_Image_CVPR_2018_paper.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":"docunet-document-image-unwarping-via-a","repo_url":"https://github.com/teresasun/docUnet.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"local-distortion","task_name":"Local Distortion"},{"task_slug":"ms-ssim","task_name":"MS-SSIM"},{"task_slug":"ssim","task_name":"SSIM"}],"methods":[{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[{"slug":"docunet","name":"DocUNet","full_name":"Document Image Unwarping via a Stacked U-Net"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/local-distortion-on-docunet","task":"Local Distortion","dataset":"DocUNet","model":"DocUNet","rank_in_archive_order":5,"of":5,"metrics":{"LD":"14.08"},"uses_additional_data":true},{"leaderboard":"/sota/ms-ssim-on-docunet","task":"MS-SSIM","dataset":"DocUNet","model":"DocUNet","rank_in_archive_order":4,"of":4,"metrics":{"MS-SSIM":"0.41"},"uses_additional_data":true},{"leaderboard":"/sota/ssim-on-docunet","task":"SSIM","dataset":"DocUNet","model":"DocUNet","rank_in_archive_order":4,"of":4,"metrics":{"SSIM":"0.4083"},"uses_additional_data":true}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}