A Modular and Robust Physics-Based Approach for Lensless Image Reconstruction

Abstract

In this paper, we present a modular approach for reconstructing lensless measurements. It consists of three components: a newly-proposed pre-processor, a physics-based camera inverter to undo the multiplexing of lensless imaging, and a post-processor. By training the three components end-to-end, we obtain a 1.9 dB increase in PSNR and a 14% relative improvement in LPIPS with respect to previously proposed physics-based methods.