We present Quanta Diffusion (QuDi), a powerful generative video reconstruction method for single-photon imaging. QuDi is an algorithm supporting the latest Quanta Image Sensors (QIS) and Single Photon Avalanche Diodes (SPADs) for extremely low-light imaging conditions. Compared to existing methods, QuDi overcomes the difficulties of simultaneously managing the motion and the strong shot noise. The core innovation of QuDi is to inject a physics-based forward model into the diffusion algorithm, while keeping the motion estimation in the loop. QuDi demonstrates an average of 2.4 dB PSNR improvement over the best existing methods.
@article{arxiv.2506.06945,
title = {Quanta Diffusion},
author = {Prateek Chennuri and Dongdong Fu and Stanley H. Chan},
journal= {arXiv preprint arXiv:2506.06945},
year = {2025}
}