A Regularized Conditional GAN for Posterior Sampling in Image Recovery Problems

Abstract

In image recovery problems, one seeks to infer an image from distorted, incomplete, and/or noise-corrupted measurements. Such problems arise in magnetic resonance imaging (MRI), computed tomography, deblurring, super-resolution, inpainting, phase retrieval, image-to-image translation, and other applications. Given a training set of signal/measurement pairs, we seek to do more than just produce one good image estimate. Rather, we aim to rapidly and accurately sample from the posterior distribution. To do this, we propose a regularized conditional Wasserstein GAN that generates dozens of high-quality posterior samples per second. Our regularization comprises an ${\ell }_1$ penalty and an adaptively weighted standard-deviation reward. Using quantitative evaluation metrics like conditional Fréchet inception distance, we demonstrate that our method produces state-of-the-art posterior samples in both multicoil MRI and large-scale inpainting applications. The code for our model can be found here: https://github.com/matt-bendel/rcGAN

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Conditional Generative Adversarial Nets
• Score-Based Generative Modeling through Stochastic Differential Equations
• Guided Image Generation with Conditional Invertible Neural Networks
• Solving Inverse Problems in Medical Imaging with Score-Based Generative Models
• Large Scale Image Completion via Co-Modulated Generative Adversarial Networks
• Technical Report (v1.0)--Pseudo-random Cartesian Sampling for Dynamic MRI