ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Measurements

CVPR 2016

Kuldeep Kulkarni     Suhas Lohit     Pavan Turaga     Ronan Kerviche     Amit Ashok

Arizona State University   and   University of Arizona

Paper     Supplementary     Code     ICCP 2016 poster     Featured on Nuit Blanche    


The goal of this paper is to present a non-iterative and more importantly an extremely fast algorithm to reconstruct images from compressively sensed (CS) random measurements. To this end, we propose a novel convolutional neural network (CNN) architecture which takes in CS measurements of an image as input and outputs an intermediate reconstruction. We call this network, ReconNet . The intermediate reconstruction is fed into an off-the-shelf denoiser to obtain the final reconstructed image. On a standard dataset of images we show significant improvements in reconstruction results (both in terms of PSNR and time complexity) over state-of-the-art iterative CS reconstruction algorithms at various measurement rates. Further, through qualitative experiments on real data collected using our block single pixel camera (SPC), we show that our network is highly robust to sensor noise and can recover visually better quality images than competitive algorithms at extremely low sensing rates of 0.1 and 0.04. To demonstrate that our algorithm can recover semantically informative images even at a low measurement rate of 0.01, we present a very robust proof of concept real-time visual tracking application.

Citation (BibTex):

author = {Kulkarni, Kuldeep and Lohit, Suhas and Turaga, Pavan and Kerviche, Ronan and Ashok, Amit},
title = {ReconNet: Non-Iterative Reconstruction of Images From Compressively Sensed Measurements},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2016}


Kuldeep Kulkarni, kkulkar1 “at” asu “dot” edu


The work of KK, SL, and PT was supported by ONR Grant N00014-12-1-0124 sub-award Z868302. We thank Charles Collins for installing Caffe, and the anonymous reviewers, Rushil Anirudh, Suren Jayasuriya and Arjun Jauhari for their valuable suggestions.