Sparsity-regularized coded ptychography for robust and efficient lensless microscopy on a chip
Ninghe Liu, Qianhao Zhao, Guoan Zheng

TL;DR
This paper presents a sparsity-regularized ptychography method called PPTV that significantly reduces measurement requirements for high-quality lensless microscopy, enabling faster and more efficient imaging on a chip.
Contribution
Introduction of the PPTV algorithm that integrates total variation regularization into coded ptychography, reducing measurements needed without hardware changes.
Findings
Accurate reconstructions with as few as eight measurements.
Robustness and stability confirmed through convergence analysis.
Experimental validation with an optical prototype.
Abstract
Coded ptychography has emerged as a powerful technique for high-throughput, high-resolution lensless imaging. However, the trade-off between acquisition speed and image quality remains a significant challenge. To address this, we introduce a novel sparsity-regularized approach to coded ptychography that dramatically reduces the number of required measurements while maintaining high reconstruction quality. The reported approach, termed the ptychographic proximal total-variation (PPTV) solver, formulates the reconstruction task as a total variation regularized optimization problem. Unlike previous implementations that rely on specialized hardware or illumination schemes, PPTV integrates seamlessly into existing coded ptychography setups. Through comprehensive numerical simulations, we demonstrate that PPTV-driven coded ptychography can produce accurate reconstructions with as few as eight…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced X-ray Imaging Techniques · Astrophysical Phenomena and Observations · Medical Imaging Techniques and Applications
MethodsSPEED: Separable Pyramidal Pooling EncodEr-Decoder for Real-Time Monocular Depth Estimation on Low-Resource Settings
