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

TL;DR

ReconNet is a fast, non-iterative CNN-based algorithm for reconstructing images from compressively sensed measurements, outperforming traditional methods in speed and quality, especially at very low sensing rates.

Contribution

This paper introduces ReconNet, a novel CNN architecture that enables rapid, non-iterative image reconstruction from compressive measurements, with demonstrated robustness and superior performance.

Findings

Significant PSNR improvements over iterative algorithms.

High robustness to sensor noise at low sensing rates.

Effective real-time visual tracking at 0.01 measurement rate.

Abstract

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.