A Fast Multi-Scale Generative Adversarial Network for Image Compressed Sensing

Abstract

Recently, deep neural network-based image compressed sensing methods have achieved impressive success in reconstruction quality. However, these methods (1) have limitations in sampling pattern and (2) usually have the disadvantage of high computational complexity. To this end, a fast multi-scale generative adversarial network (FMSGAN) is implemented in this paper. Specifically, (1) an effective multi-scale sampling structure is proposed. It contains four different kernels with varying sizes so that decompose, and sample images effectively, which is capable of capturing different levels of spatial features at multiple scales. (2) An efficient lightweight multi-scale residual structure for deep image reconstruction is proposed to balance receptive field size and computational complexity. The key idea is to apply smaller convolution kernel sizes in the multi-scale residual structure to reduce the number of operations while maintaining the receptive field. Meanwhile, the channel attention structure is employed for enriching useful information. Moreover, perceptual loss is combined with MSE loss and adversarial loss as the optimization function to recover a finer image. Numerous experiments show that our FMSGAN achieves state-of-the-art image reconstruction quality with low computational complexity.

A coherence parameter characterizing generative compressed sensing with Fourier measurements

“…Several recent works have developed sophisticated generative adversarial networks (GANs) (which are effectively a type of GNN) for compressed sensing in medical imaging (Deora et al, 2020;Mardani et al, 2018). Other work has empirically explored multi-scale (non-Gaussian) sampling strategies for image compressed sensing using GANs (Li et al, 2022). Separately, see Wentz and Doostan (2022) for the use of GCS in uncertainty quantification of high-dimensional partial differential equations with random inputs.…”