{"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-fully-connected-networks-for-video","title":"Deep Fully-Connected Networks for Video Compressive Sensing","arxiv_id":"1603.04930","date":"2016-03-16","proceeding":null,"authors":["Michael Iliadis","Leonidas Spinoulas","Aggelos K. Katsaggelos"],"abstract":"In this work we present a deep learning framework for video compressive\nsensing. The proposed formulation enables recovery of video frames in a few\nseconds at significantly improved reconstruction quality compared to previous\napproaches. Our investigation starts by learning a linear mapping between video\nsequences and corresponding measured frames which turns out to provide\npromising results. We then extend the linear formulation to deep\nfully-connected networks and explore the performance gains using deeper\narchitectures. Our analysis is always driven by the applicability of the\nproposed framework on existing compressive video architectures. Extensive\nsimulations on several video sequences document the superiority of our approach\nboth quantitatively and qualitatively. Finally, our analysis offers insights\ninto understanding how dataset sizes and number of layers affect reconstruction\nperformance while raising a few points for future investigation.\n  Code is available at Github: https://github.com/miliadis/DeepVideoCS","url_abs":"http://arxiv.org/abs/1603.04930v2","url_pdf":"http://arxiv.org/pdf/1603.04930v2.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-fully-connected-networks-for-video","repo_url":"https://github.com/miliadis/DeepVideoCS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"tasks":[{"task_slug":"compressive-sensing","task_name":"Compressive Sensing"},{"task_slug":"video-compressive-sensing","task_name":"Video Compressive Sensing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1603.04930","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}