Improving Limited Angle CT Reconstruction with a Robust GAN Prior

Rushil Anirudh, Hyojin Kim, Jayaraman J. Thiagarajan, K. Aditya Mohan, Kyle Champley

TL;DR: We show that robust GAN priors work better than GAN priors for limited angle CT reconstruction which is a highly under-determined inverse problem.

Keywords: GANs, imaging priors, CT reconstruction, robustness, limited angle CT

Abstract: Limited angle CT reconstruction is an under-determined linear inverse problem that requires appropriate regularization techniques to be solved. In this work we study how pre-trained generative adversarial networks (GANs) can be used to clean noisy, highly artifact laden reconstructions from conventional techniques, by effectively projecting onto the inferred image manifold. In particular, we use a robust version of the popularly used GAN prior for inverse problems, based on a recent technique called corruption mimicking, that significantly improves the reconstruction quality. The proposed approach operates in the image space directly, as a result of which it does not need to be trained or require access to the measurement model, is scanner agnostic, and can work over a wide range of sensing scenarios.