A Bayesian Based Deep Unrolling Algorithm for Single-Photon Lidar Systems
This work addresses challenges in deploying single-photon Lidar for critical applications like autonomous vehicles or remote sensing by combining statistical and learning-based approaches for more reliable imaging.
The paper tackles the problem of robust 3D image reconstruction from single-photon Lidar data in high-noise environments by unrolling a Bayesian statistical algorithm into a deep learning architecture, resulting in competitive performance with reduced parameters and improved interpretability.
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.