Quanta Diffusion

TL;DR

Quanta Diffusion (QuDi) is a novel generative reconstruction method for single-photon imaging that integrates physics-based modeling with diffusion algorithms, significantly improving image quality under low-light conditions.

Contribution

It introduces a physics-informed diffusion algorithm that effectively handles motion and shot noise in single-photon imaging, supporting advanced sensor technologies.

Findings

2.4 dB PSNR improvement over existing methods

Supports latest QIS and SPAD sensors for low-light imaging

Effectively manages motion and shot noise in reconstructions

Abstract

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.