Unrolled Optimization with Deep Priors
This addresses a core problem in computational imaging and low-level computer vision, offering a principled approach that improves performance over traditional methods.
The paper tackles the inverse problem of extracting latent images from measurements in computational imaging by introducing a framework that integrates deep priors with unrolled optimization, outperforming state-of-the-art methods in tasks like denoising, deblurring, and compressed sensing MRI.
A broad class of problems at the core of computational imaging, sensing, and low-level computer vision reduces to the inverse problem of extracting latent images that follow a prior distribution, from measurements taken under a known physical image formation model. Traditionally, hand-crafted priors along with iterative optimization methods have been used to solve such problems. In this paper we present unrolled optimization with deep priors, a principled framework for infusing knowledge of the image formation into deep networks that solve inverse problems in imaging, inspired by classical iterative methods. We show that instances of the framework outperform the state-of-the-art by a substantial margin for a wide variety of imaging problems, such as denoising, deblurring, and compressed sensing magnetic resonance imaging (MRI). Moreover, we conduct experiments that explain how the framework is best used and why it outperforms previous methods.