Compressive Image Recovery Using Recurrent Generative Model

TL;DR

This paper introduces a novel method for compressive image reconstruction using a recurrent generative model called RIDE, which effectively captures global image dependencies and outperforms existing techniques.

Contribution

The paper proposes using RIDE as an image prior for compressive sensing, employing MAP inference with entropy thresholding to enhance texture preservation.

Findings

Outperforms D-AMP and TVAL3 in reconstruction quality

Effective modeling of long-range dependencies in images

Demonstrated on both simulated and real data

Abstract

Reconstruction of signals from compressively sensed measurements is an ill-posed problem. In this paper, we leverage the recurrent generative model, RIDE, as an image prior for compressive image reconstruction. Recurrent networks can model long-range dependencies in images and hence are suitable to handle global multiplexing in reconstruction from compressive imaging. We perform MAP inference with RIDE using back-propagation to the inputs and projected gradient method. We propose an entropy thresholding based approach for preserving texture in images well. Our approach shows superior reconstructions compared to recent global reconstruction approaches like D-AMP and TVAL3 on both simulated and real data.