{"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/bringing-alive-blurred-moments","title":"Bringing Alive Blurred Moments","arxiv_id":"1804.02913","date":"2018-04-09","proceeding":"CVPR 2019 6","authors":["Kuldeep Purohit","Anshul Shah","A. N. Rajagopalan"],"abstract":"We present a solution for the goal of extracting a video from a single motion\nblurred image to sequentially reconstruct the clear views of a scene as beheld\nby the camera during the time of exposure. We first learn motion representation\nfrom sharp videos in an unsupervised manner through training of a convolutional\nrecurrent video autoencoder network that performs a surrogate task of video\nreconstruction. Once trained, it is employed for guided training of a motion\nencoder for blurred images. This network extracts embedded motion information\nfrom the blurred image to generate a sharp video in conjunction with the\ntrained recurrent video decoder. As an intermediate step, we also design an\nefficient architecture that enables real-time single image deblurring and\noutperforms competing methods across all factors: accuracy, speed, and\ncompactness. Experiments on real scenes and standard datasets demonstrate the\nsuperiority of our framework over the state-of-the-art and its ability to\ngenerate a plausible sequence of temporally consistent sharp frames.","url_abs":"http://arxiv.org/abs/1804.02913v2","url_pdf":"http://arxiv.org/pdf/1804.02913v2.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":"bringing-alive-blurred-moments","repo_url":"https://github.com/anshulbshah/Blurred-Image-to-Video","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-deblurring","task_name":"Image Deblurring"},{"task_slug":"single-image-deblurring","task_name":"Single Image Deblurring"},{"task_slug":"video-reconstruction","task_name":"Video Reconstruction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/deblurring-on-gopro","task":"Deblurring","dataset":"GoPro","model":"Blurred-Image-to-Video","rank_in_archive_order":49,"of":56,"metrics":{"PSNR":"30.58","SSIM":"0.941"},"uses_additional_data":true},{"leaderboard":"/sota/image-deblurring-on-gopro","task":"Image Deblurring","dataset":"GoPro","model":"Blurred-Image-to-Video","rank_in_archive_order":47,"of":55,"metrics":{"PSNR":"30.58","SSIM":"0.941"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.02913","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}