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

Research output: Contribution to journalArticlepeer-review

9 Downloads (Pure)

Abstract

Deploying 3D single-photon Lidar imaging in real world applications presents multiple challenges including imag- ing 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 of the system impulse response function, 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.
Original languageEnglish
JournalIEEE Journal of Selected Topics in Signal Processing
Early online date26 Apr 2022
DOIs
Publication statusE-pub ahead of print - 26 Apr 2022

Keywords

  • 3D reconstruction
  • Bayes methods
  • Bayesian inference
  • Deep learning
  • Histograms
  • Laser radar
  • Lidar
  • Photonics
  • Signal processing algorithms
  • Three-dimensional displays
  • algorithm unrolling
  • attention
  • single-photon imaging

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'A Bayesian Based Deep Unrolling Algorithm for Single-Photon Lidar Systems'. Together they form a unique fingerprint.

Cite this