{"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/adversarial-spatio-temporal-learning-for","title":"Adversarial Spatio-Temporal Learning for Video Deblurring","arxiv_id":"1804.00533","date":"2018-03-28","proceeding":null,"authors":["Kaihao Zhang","Wenhan Luo","Yiran Zhong","Lin Ma","Wei Liu","Hongdong Li"],"abstract":"Camera shake or target movement often leads to undesired blur effects in\nvideos captured by a hand-held camera. Despite significant efforts having been\ndevoted to video-deblur research, two major challenges remain: 1) how to model\nthe spatio-temporal characteristics across both the spatial domain (i.e., image\nplane) and temporal domain (i.e., neighboring frames), and 2) how to restore\nsharp image details w.r.t. the conventionally adopted metric of pixel-wise\nerrors. In this paper, to address the first challenge, we propose a DeBLuRring\nNetwork (DBLRNet) for spatial-temporal learning by applying a modified 3D\nconvolution to both spatial and temporal domains. Our DBLRNet is able to\ncapture jointly spatial and temporal information encoded in neighboring frames,\nwhich directly contributes to improved video deblur performance. To tackle the\nsecond challenge, we leverage the developed DBLRNet as a generator in the GAN\n(generative adversarial network) architecture, and employ a content loss in\naddition to an adversarial loss for efficient adversarial training. The\ndeveloped network, which we name as DeBLuRring Generative Adversarial Network\n(DBLRGAN), is tested on two standard benchmarks and achieves the\nstate-of-the-art performance.","url_abs":"http://arxiv.org/abs/1804.00533v2","url_pdf":"http://arxiv.org/pdf/1804.00533v2.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":"adversarial-spatio-temporal-learning-for","repo_url":"https://github.com/themathgeek13/STdeblur","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"video-deblurring","task_name":"Video Deblurring"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.00533","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}