{"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/csvideonet-a-real-time-end-to-end-learning","title":"CSVideoNet: A Real-time End-to-end Learning Framework for High-frame-rate Video Compressive Sensing","arxiv_id":"1612.05203","date":"2016-12-15","proceeding":null,"authors":["Kai Xu","Fengbo Ren"],"abstract":"This paper addresses the real-time encoding-decoding problem for\nhigh-frame-rate video compressive sensing (CS). Unlike prior works that perform\nreconstruction using iterative optimization-based approaches, we propose a\nnon-iterative model, named \"CSVideoNet\". CSVideoNet directly learns the inverse\nmapping of CS and reconstructs the original input in a single forward\npropagation. To overcome the limitations of existing CS cameras, we propose a\nmulti-rate CNN and a synthesizing RNN to improve the trade-off between\ncompression ratio (CR) and spatial-temporal resolution of the reconstructed\nvideos. The experiment results demonstrate that CSVideoNet significantly\noutperforms the state-of-the-art approaches. With no pre/post-processing, we\nachieve 25dB PSNR recovery quality at 100x CR, with a frame rate of 125 fps on\na Titan X GPU. Due to the feedforward and high-data-concurrency natures of\nCSVideoNet, it can take advantage of GPU acceleration to achieve three orders\nof magnitude speed-up over conventional iterative-based approaches. We share\nthe source code at https://github.com/PSCLab-ASU/CSVideoNet.","url_abs":"http://arxiv.org/abs/1612.05203v5","url_pdf":"http://arxiv.org/pdf/1612.05203v5.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":"csvideonet-a-real-time-end-to-end-learning","repo_url":"https://github.com/PSCLab-ASU/CSVideoNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"csvideonet-a-real-time-end-to-end-learning","repo_url":"https://github.com/calmevtime/CSImageNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"compressive-sensing","task_name":"Compressive Sensing"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"video-compressive-sensing","task_name":"Video Compressive Sensing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1612.05203","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}