Single Photon Challenge

Sacha Jungerman1, Atul Ingle2, Sotiris Nousias3, Mian Wei4, Mel White5, Mohit Gupta1

1University of Wisconsin - Madison, 2Portland State University, 3Purdue University,
4Carnegie Mellon University, 5US Naval Research Lab

Not logged in | Login | Create Account

Welcome to the Single Photon Challenge website! Here you'll find large synthetic single photon datasets that consist of bursts of single photon camera images and their corresponding ground truth reconstructions. There is also a public leaderboard showcasing various user-submitted reconstructions for this benchmark. You can directly compare submissions as well!


Teaser image
Single-photon cameras are capable of detecting individual photons, making them extremely sensitive, high-speed cameras. However, each image they capture is extremely noisy and binary valued, being dominated by photon shot noise. Given a burst of such binary frames, how can we recover a clean, high-fidelity image?

Announcing: Single Photon Challenge 2026 Special Mentions 🏆

Thank you to all of the teams who submitted entries to the Single Photon Challenge 2026. We received much interest in the competition and were impressed by the quality and diversity of the submissions, garnering 62 user accounts and 342 submissions (some of which are private)! We would like to give special recognition to the following teams who submitted exceptional work, but could not directly compete for prizes due to e.g. conflict of interest or company policy (in no particular order): QRBIT, UnSPAD, ShotInTheDark, Attention U-Net, and FluxISP.

News

Citation

If you make use of our dataset or benchmark results, please cite:

@software{visionsim,
    author = {Jungerman, Sacha and Gupta, Shantanu and Sadekar, Kaustubh and Leblang, Max and Gupta, Mohit},
    license = {MIT},
    month = may,
    title = {{visionsim}},
    url = {https://github.com/WISION-Lab/visionsim},
    year = {2025}
}