{"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/deep-video-deblurring","title":"Deep Video Deblurring","arxiv_id":"1611.08387","date":"2016-11-25","proceeding":null,"authors":["Shuochen Su","Mauricio Delbracio","Jue Wang","Guillermo Sapiro","Wolfgang Heidrich","Oliver Wang"],"abstract":"Motion blur from camera shake is a major problem in videos captured by\nhand-held devices. Unlike single-image deblurring, video-based approaches can\ntake advantage of the abundant information that exists across neighboring\nframes. As a result the best performing methods rely on aligning nearby frames.\nHowever, aligning images is a computationally expensive and fragile procedure,\nand methods that aggregate information must therefore be able to identify which\nregions have been accurately aligned and which have not, a task which requires\nhigh level scene understanding. In this work, we introduce a deep learning\nsolution to video deblurring, where a CNN is trained end-to-end to learn how to\naccumulate information across frames. To train this network, we collected a\ndataset of real videos recorded with a high framerate camera, which we use to\ngenerate synthetic motion blur for supervision. We show that the features\nlearned from this dataset extend to deblurring motion blur that arises due to\ncamera shake in a wide range of videos, and compare the quality of results to a\nnumber of other baselines.","url_abs":"http://arxiv.org/abs/1611.08387v1","url_pdf":"http://arxiv.org/pdf/1611.08387v1.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":"deep-video-deblurring","repo_url":"https://github.com/susomena/DeepSlowMotion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"image-deblurring","task_name":"Image Deblurring"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"single-image-deblurring","task_name":"Single Image Deblurring"},{"task_slug":"video-deblurring","task_name":"Video Deblurring"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}