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

Autor:	Perron, Yohann, Bezzam, Eric, Vetterli, Martin
Rok vydání:	2024
Předmět:	Electrical Engineering and Systems Science - Image and Video Processing
Druh dokumentu:	Working Paper
Popis:	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. The pre- and post-processors address noise and artifacts unique to lensless imaging before and after camera inversion respectively. By training the three components end-to-end, we obtain a 1.9 dB increase in PSNR and a 14% relative improvement in a perceptual image metric (LPIPS) with respect to previously proposed physics-based methods. We also demonstrate how the proposed pre-processor provides more robustness to input noise, and how an auxiliary loss can improve interpretability. Comment: 6 pages, 2024 IEEE International Conference on Image Processing (ICIP), demo notebook: https://go.epfl.ch/lensless-modular
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2403.00537 Zobrazit plný text záznamu View this record from Arxiv