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, paired with computational ground truth registration. Our dataset acquisition system consists of a hardware system for data acquisition and software framework for hardware control and computational processing. 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.
Our paper, ConvRML: high-quality lensless imaging with random multi-focal lenslets, uses our new, updated lensless imaging dataset with 100,000 images.
The paper is available on [arXiv], and the code and dataset are available on the ConvRML Project Page.
We provide an open-source, 25,000 image dataset with two lensless imagers—the Diffuser and the Random Multi-focal Lenslet (RML) imager—and paired ground truth images. We used the first 25,000 images of the MIRFLICKR-1M dataset. Our dataset consists of:
The dataset includes a calibration PSF for each imager at an exposure that produced the best results during our tests. We also include a folder of PSFs for both imagers at varying exposures for further experimentation.
If you use our dataset in our research, we kindly ask that you cite our publication.
Access our datasetOur hardware system captures measurements from multiple lensless imaging systems and a ground truth lensed camera in parallel. We provide a step-by-step tutorial for building our system on our Hardware Setup page and encourage other researchers to build off of our setup.
We are excited to collaborate with researchers broadly in computational imaging and machine learning. If you are interested in using our dataset, have questions about our work, or would like to collaborate, please reach out to clarahung@berkeley.edu.
This work was presented at SPIE Photonics West 2025. The paper and poster can be found in the proceedings here.
@inproceedings{hung2025scalable,
title={Scalable dataset acquisition for data-driven lensless imaging},
author={Hung, Clara S and Kabuli, Leyla A and Ponomarenko, Vasilisa and Waller, Laura},
booktitle={Computational Optical Imaging and Artificial Intelligence in Biomedical Sciences II},
volume={13333},
pages={54--58},
year={2025},
organization={SPIE}
}