Generative Patch Priors for Practical Compressive Image Recovery
This addresses the challenge of high-quality image reconstruction at low sensing rates for practical applications like compressive sensing and phase retrieval, offering a more generally applicable solution compared to existing generative priors.
The paper tackles the problem of compressive image recovery by proposing a generative patch prior (GPP) that uses patch-manifold models to recover a wide variety of natural images, outperforming several unsupervised and supervised techniques on three sensing models and performing favorably on a real-world dataset.
In this paper, we propose the generative patch prior (GPP) that defines a generative prior for compressive image recovery, based on patch-manifold models. Unlike learned, image-level priors that are restricted to the range space of a pre-trained generator, GPP can recover a wide variety of natural images using a pre-trained patch generator. Additionally, GPP retains the benefits of generative priors like high reconstruction quality at extremely low sensing rates, while also being much more generally applicable. We show that GPP outperforms several unsupervised and supervised techniques on three different sensing models -- linear compressive sensing with known, and unknown calibration settings, and the non-linear phase retrieval problem. Finally, we propose an alternating optimization strategy using GPP for joint calibration-and-reconstruction which performs favorably against several baselines on a real world, un-calibrated compressive sensing dataset.