Fully Convolutional Measurement Network for Compressive Sensing Image Reconstruction

TL;DR

This paper introduces a fully convolutional measurement network for compressive sensing image reconstruction that measures entire scenes at once, effectively removing block effects and improving image quality over existing methods.

Contribution

It presents a novel fully convolutional measurement network that measures scenes holistically and jointly trains measurement and recovery, enhancing reconstruction quality.

Findings

Outperforms existing methods in PSNR and SSIM

Removes block-effect in reconstructed images

Achieves better visual quality

Abstract

Recently, deep learning methods have made a significant improvement in compressive sensing image reconstruction task. In the existing methods, the scene is measured block by block due to the high computational complexity. This results in block-effect of the recovered images. In this paper, we propose a fully convolutional measurement network, where the scene is measured as a whole. The proposed method powerfully removes the block-effect since the structure information of scene images is preserved. To make the measure more flexible, the measurement and the recovery parts are jointly trained. From the experiments, it is shown that the results by the proposed method outperforms those by the existing methods in PSNR, SSIM, and visual effect.