Perceptual Compressive Sensing

TL;DR

This paper introduces perceptual compressive sensing, which emphasizes high-level visual quality and structure in recovered images over pixel-perfect accuracy, using perceptual loss to improve visual effects at low measurement rates.

Contribution

It proposes a novel perceptual CS method that enhances structural information in recovered images by employing feature-level perceptual loss, moving beyond pixel-level recovery.

Findings

Achieves better visual quality than existing CS methods at the same measurement rate.

Enhances structural information in reconstructed images.

Produces visually more appealing images with stronger structure details.

Abstract

Compressive sensing (CS) works to acquire measurements at sub-Nyquist rate and recover the scene images. Existing CS methods always recover the scene images in pixel level. This causes the smoothness of recovered images and lack of structure information, especially at a low measurement rate. To overcome this drawback, in this paper, we propose perceptual CS to obtain high-level structured recovery. Our task no longer focuses on pixel level. Instead, we work to make a better visual effect. In detail, we employ perceptual loss, defined on feature level, to enhance the structure information of the recovered images. Experiments show that our method achieves better visual results with stronger structure information than existing CS methods at the same measurement rate.