A Bayesian Based Deep Unrolling Algorithm for Single-Photon Lidar Systems

TL;DR

This paper introduces a novel deep unrolling Bayesian algorithm for single-photon Lidar systems that combines statistical robustness with deep learning efficiency, enhancing image reconstruction in noisy environments.

Contribution

It unrolls a Bayesian statistical algorithm into a neural network, improving robustness, interpretability, and efficiency over existing methods for single-photon Lidar imaging.

Findings

Outperforms existing methods in noise robustness and accuracy

Requires fewer trainable parameters than comparable deep learning models

Provides uncertainty measures alongside image estimates

Abstract

Deploying 3D single-photon Lidar imaging in real world applications faces multiple challenges including imaging in high noise environments. Several algorithms have been proposed to address these issues based on statistical or learning-based frameworks. Statistical methods provide rich information about the inferred parameters but are limited by the assumed model correlation structures, while deep learning methods show state-of-the-art performance but limited inference guarantees, preventing their extended use in critical applications. This paper unrolls a statistical Bayesian algorithm into a new deep learning architecture for robust image reconstruction from single-photon Lidar data, i.e., the algorithm's iterative steps are converted into neural network layers. The resulting algorithm benefits from the advantages of both statistical and learning based frameworks, providing best estimates with improved network interpretability. Compared to existing learning-based solutions, the proposed architecture requires a reduced number of trainable parameters, is more robust to noise and mismodelling effects, and provides richer information about the estimates including uncertainty measures. Results on synthetic and real data show competitive results regarding the quality of the inference and computational complexity when compared to state-of-the-art algorithms.