{"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/multi-scale-separable-network-for-ultra-high","title":"Multi-Scale Separable Network for Ultra-High-Definition Video Deblurring","arxiv_id":null,"date":"2021-01-01","proceeding":"ICCV 2021 10","authors":["Senyou Deng","Wenqi Ren","Yanyang Yan","Tao Wang","Fenglong Song","Xiaochun Cao"],"abstract":"    Although recent research has witnessed a significant progress on the video deblurring task, these methods struggle to reconcile inference efficiency and visual quality simultaneously, especially on ultra-high-definition (UHD) videos (e.g., 4K resolution). To address the problem, we propose a novel deep model for fast and accurate UHD Video Deblurring (UHDVD). The proposed UHDVD is achieved by a separable-patch architecture, which collaborates with a multi-scale integration scheme to achieve a large receptive field without adding the number of generic convolutional layers and kernels. Additionally, we design a residual channel-spatial attention (RCSA) module to improve accuracy and reduce the depth of the network appropriately. The proposed UHDVD is the first real-time deblurring model for 4K videos at 35 fps. To train the proposed model, we build a new dataset comprised of 4K blurry videos and corresponding sharp frames using three different smartphones. Comprehensive experimental results show that our network performs favorably against the state-ofthe-art methods on both the 4K dataset and public benchmarks in terms of accuracy, speed, and model size.    ","url_abs":"http://openaccess.thecvf.com//content/ICCV2021/html/Deng_Multi-Scale_Separable_Network_for_Ultra-High-Definition_Video_Deblurring_ICCV_2021_paper.html","url_pdf":"http://openaccess.thecvf.com//content/ICCV2021/papers/Deng_Multi-Scale_Separable_Network_for_Ultra-High-Definition_Video_Deblurring_ICCV_2021_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":"multi-scale-separable-network-for-ultra-high","repo_url":"https://github.com/dseny/UHDVD","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"4k","task_name":"4k"},{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"video-deblurring","task_name":"Video Deblurring"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}