Simulation-Driven Approach for Occlusion-Based Non-Line-Of-Sight Detection Using a Low-Cost Flash LiDAR
Non-line-of-sight (NLOS) imaging aims to sense objects outside the direct line of sight. While most previous work focuses on the canonical around-the-corner configuration, this work considers a more challenging occlusion-based NLOS setting in which targets are hidden by scene geometry. To avoid the challenge of collecting large real-world datasets, we have developed a photon-based Monte Carlo simulator to generate diverse synthetic training data and validate against experimental data. We trained an AI model to identify multi-bounce photon patterns associated with hidden targets. The model achieves an Average Precision (AP) of 0.91 on synthetic test data and, when transferred directly to 180 real measurements acquired with a TMF8829 SPAD flash LiDAR, achieves 86.67% accuracy and an AP of 0.95. These results show that simulated transient data can support hidden-target detection with a low-cost commercial sensor and provide an initial step toward more general occlusion-based NLOS sensing and, ultimately, hidden-scene reconstruction.