Perceptual Compressive Sensing
This work addresses a domain-specific issue in image processing for applications requiring high-quality visual recovery from compressed measurements, but it is incremental as it builds on existing CS methods.
The paper tackles the problem of smoothness and lack of structure in images recovered by compressive sensing at low measurement rates, proposing perceptual CS that uses perceptual loss to enhance structure, resulting in better visual effects and stronger structure information compared to existing methods.
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.