Photon-Starved Scene Inference using Single Photon Cameras

TL;DR

This paper introduces a novel training approach using a spectrum of high-SNR images at different photon levels to enable reliable scene inference with single-photon cameras in extremely low-light conditions, achieving high accuracy.

Contribution

It proposes photon scale-space and training techniques that improve scene inference robustness in photon-starved conditions using single-photon cameras.

Findings

Effective inference at < 1 PPP demonstrated

High accuracy in classification and depth estimation

Validated with simulations and real SPAD camera data

Abstract

Scene understanding under low-light conditions is a challenging problem. This is due to the small number of photons captured by the camera and the resulting low signal-to-noise ratio (SNR). Single-photon cameras (SPCs) are an emerging sensing modality that are capable of capturing images with high sensitivity. Despite having minimal read-noise, images captured by SPCs in photon-starved conditions still suffer from strong shot noise, preventing reliable scene inference. We propose photon scale-space a collection of high-SNR images spanning a wide range of photons-per-pixel (PPP) levels (but same scene content) as guides to train inference model on low photon flux images. We develop training techniques that push images with different illumination levels closer to each other in feature representation space. The key idea is that having a spectrum of different brightness levels during training enables effective guidance, and increases robustness to shot noise even in extreme noise cases. Based on the proposed approach, we demonstrate, via simulations and real experiments with a SPAD camera, high-performance on various inference tasks such as image classification and monocular depth estimation under ultra low-light, down to < 1 PPP.