A Bayesian Based Unrolling Approach to Single-Photon Lidar Imaging through Obscurants

In this paper, we propose a deep learning model for 3D single-photon Lidar imaging through obscurants, i.e., in the presence of a high and non-uniform background. The proposed method unrolls the iterative steps of a Bayesian based-algorithm into the layers of a deep neural network. To deal with imaging through obscurants, the method first unmix signal and background photons in a pre-processing step. Following this, the method builds on multiscale information to improve robustness to noise and uses the attention framework for scale selection within the network. Experimental results on simulated and real underwater data demonstrate that our method can estimate accurate depth maps in challenging situations with a high non-uniform background. Compared to state-of-the-art deep learning methods, the proposed method enables an estimation of parameters uncertainties, suitable for decision making.