Skip to yearly menu bar Skip to main content


A Regularized Conditional GAN for Posterior Sampling in Image Recovery Problems

Matthew Bendel · Rizwan Ahmad · Philip Schniter

Great Hall & Hall B1+B2 (level 1) #718
[ ] [ Project Page ]
[ Paper [ Poster [ OpenReview
Thu 14 Dec 3 p.m. PST — 5 p.m. PST

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 Fr├ęchet 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:

Chat is not available.