Dynamic Low-light Imaging with Quanta Image Sensors

TL;DR

This paper introduces a novel approach for dynamic low-light imaging using Quanta Image Sensors and a student-teacher training protocol, enabling effective reconstruction of moving scenes at extremely low photon levels.

Contribution

It presents a new image reconstruction algorithm for dynamic scenes in low light using QIS and a student-teacher training method, addressing a key open problem.

Findings

Reconstructed dynamic scenes from burst frames at 1 photon per pixel.

Proposed method outperforms existing low-light imaging techniques.

Effective in capturing moving scenes in extremely low-light conditions.

Abstract

Imaging in low light is difficult because the number of photons arriving at the sensor is low. Imaging dynamic scenes in low-light environments is even more difficult because as the scene moves, pixels in adjacent frames need to be aligned before they can be denoised. Conventional CMOS image sensors (CIS) are at a particular disadvantage in dynamic low-light settings because the exposure cannot be too short lest the read noise overwhelms the signal. We propose a solution using Quanta Image Sensors (QIS) and present a new image reconstruction algorithm. QIS are single-photon image sensors with photon counting capabilities. Studies over the past decade have confirmed the effectiveness of QIS for low-light imaging but reconstruction algorithms for dynamic scenes in low light remain an open problem. We fill the gap by proposing a student-teacher training protocol that transfers knowledge from a motion teacher and a denoising teacher to a student network. We show that dynamic scenes can be reconstructed from a burst of frames at a photon level of 1 photon per pixel per frame. Experimental results confirm the advantages of the proposed method compared to existing methods.