EnGe-CSNet: A Trainable Image Compressed Sensing Model Based on Variational Encoder and Generative Networks

The present study primarily investigates the topic of image reconstruction at high compression rates. As proven from compressed sensing theory, an appropriate algorithm is capable of reconstructing natural images from a few measurements since they are sparse in several transform domains (e.g., Discrete Cosine Transform and Wavelet Transform). To enhance the quality of reconstructed images in specific applications, this paper builds a trainable deep compressed sensing model, termed as EnGe-CSNet, by combining Convolution Generative Adversarial Networks and a Variational Autoencoder. Given the significant structural similarity between a certain type of natural images collected with image sensors, deep convolutional networks are pre-trained on images that are set to learn the low dimensional manifolds of high dimensional images. The generative network is employed as the prior information, and it is used to reconstruct images from compressed measurements. As revealed from the experimental results, the proposed model exhibits a better performance than competitive algorithms at high compression rates. Furthermore, as indicated by several reconstructed samples of noisy images, the model here is robust to pattern noise. The present study is critical to facilitating the application of image compressed sensing.

Automated summary

The study introduces a trainable deep compressed sensing model, EnGe-CSNet, by combining Convolution Generative Adversarial Networks and a Variational Autoencoder to enhance the quality of image reconstruction at high compression rates. Experimental results demonstrate that the proposed model outperforms competitive algorithms at high compression rates and exhibits robustness to pattern noise in noisy images.