Scalable dataset acquisition for data-driven lensless imaging

TL;DR

This paper presents a scalable data acquisition pipeline and an open-access dataset for lensless imaging, facilitating data-driven research and machine learning advancements in the field.

Contribution

It introduces a novel parallel data collection system with ground truth registration and provides a large, open dataset for lensless imaging research.

Findings

Captured 25,000 images with two lensless imagers

Reproducible hardware setup and synchronization code provided

Dataset enables development of machine learning-based reconstruction algorithms

Abstract

Data-driven developments in lensless imaging, such as machine learning-based reconstruction algorithms, require large datasets. In this work, we introduce a data acquisition pipeline that can capture from multiple lensless imaging systems in parallel, under the same imaging conditions, and paired with computational ground truth registration. We provide an open-access 25,000 image dataset with two lensless imagers, a reproducible hardware setup, and open-source camera synchronization code. Experimental datasets from our system can enable data-driven developments in lensless imaging, such as machine learning-based reconstruction algorithms and end-to-end system design.