{"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/a-deep-learning-approach-to-block-based","title":"A Deep Learning Approach to Block-based Compressed Sensing of Images","arxiv_id":"1606.01519","date":"2016-06-05","proceeding":null,"authors":["Amir Adler","David Boublil","Michael Elad","Michael Zibulevsky"],"abstract":"Compressed sensing (CS) is a signal processing framework for efficiently\nreconstructing a signal from a small number of measurements, obtained by linear\nprojections of the signal. Block-based CS is a lightweight CS approach that is\nmostly suitable for processing very high-dimensional images and videos: it\noperates on local patches, employs a low-complexity reconstruction operator and\nrequires significantly less memory to store the sensing matrix. In this paper\nwe present a deep learning approach for block-based CS, in which a\nfully-connected network performs both the block-based linear sensing and\nnon-linear reconstruction stages. During the training phase, the sensing matrix\nand the non-linear reconstruction operator are \\emph{jointly} optimized, and\nthe proposed approach outperforms state-of-the-art both in terms of\nreconstruction quality and computation time. For example, at a 25% sensing rate\nthe average PSNR advantage is 0.77dB and computation time is over 200-times\nfaster.","url_abs":"http://arxiv.org/abs/1606.01519v1","url_pdf":"http://arxiv.org/pdf/1606.01519v1.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":"a-deep-learning-approach-to-block-based","repo_url":"https://github.com/asalp/Block-Based-CS-NNs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"compressed-sensing","task_name":"compressed sensing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1606.01519","atlas_url":"https://app.syntology.ai/?focus=1606.01519","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}