Adaptive Measurement Network for CS Image Reconstruction

TL;DR

This paper introduces an adaptive measurement network that learns optimal measurements for compressive sensing image reconstruction, resulting in faster processing and improved image quality compared to traditional methods.

Contribution

It proposes a novel adaptive measurement network combining a fully-connected layer with ReconNet, enabling learned measurements that enhance reconstruction performance.

Findings

Outperforms traditional Gaussian measurement in reconstruction quality.

Achieves faster processing with learned adaptive measurements.

Demonstrates improved scene information extraction at the same measurement rate.

Abstract

Conventional compressive sensing (CS) reconstruction is very slow for its characteristic of solving an optimization problem. Convolu- tional neural network can realize fast processing while achieving compa- rable results. While CS image recovery with high quality not only de- pends on good reconstruction algorithms, but also good measurements. In this paper, we propose an adaptive measurement network in which measurement is obtained by learning. The new network consists of a fully-connected layer and ReconNet. The fully-connected layer which has low-dimension output acts as measurement. We train the fully-connected layer and ReconNet simultaneously and obtain adaptive measurement. Because the adaptive measurement fits dataset better, in contrast with random Gaussian measurement matrix, under the same measuremen- t rate, it can extract the information of scene more efficiently and get better reconstruction results. Experiments show that the new network outperforms the original one.