{"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/reconnet-non-iterative-reconstruction-of","title":"ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Random Measurements","arxiv_id":"1601.06892","date":"2016-01-26","proceeding":"CVPR 2016","authors":["Kuldeep Kulkarni","Suhas Lohit","Pavan Turaga","Ronan Kerviche","Amit Ashok"],"abstract":"The goal of this paper is to present a non-iterative and more importantly an\nextremely fast algorithm to reconstruct images from compressively sensed (CS)\nrandom measurements. To this end, we propose a novel convolutional neural\nnetwork (CNN) architecture which takes in CS measurements of an image as input\nand outputs an intermediate reconstruction. We call this network, ReconNet. The\nintermediate reconstruction is fed into an off-the-shelf denoiser to obtain the\nfinal reconstructed image. On a standard dataset of images we show significant\nimprovements in reconstruction results (both in terms of PSNR and time\ncomplexity) over state-of-the-art iterative CS reconstruction algorithms at\nvarious measurement rates. Further, through qualitative experiments on real\ndata collected using our block single pixel camera (SPC), we show that our\nnetwork is highly robust to sensor noise and can recover visually better\nquality images than competitive algorithms at extremely low sensing rates of\n0.1 and 0.04. To demonstrate that our algorithm can recover semantically\ninformative images even at a low measurement rate of 0.01, we present a very\nrobust proof of concept real-time visual tracking application.","url_abs":"http://arxiv.org/abs/1601.06892v2","url_pdf":"http://arxiv.org/pdf/1601.06892v2.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":"reconnet-non-iterative-reconstruction-of","repo_url":"https://github.com/Chinmayrane16/ReconNet-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"real-time-visual-tracking","task_name":"Real-Time Visual Tracking"},{"task_slug":"visual-tracking","task_name":"Visual Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1601.06892","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}