Real-Time LiDAR Point Cloud Densification for Low-Latency Spatial Data Transmission

抄録

To realize low-latency spatial transmission system for immersive telepresence, there are two major problems: capturing dynamic 3D scene densely and processing them in real time. LiDAR sensors capture 3D in real time, but produce sparce point clouds. Therefore, this paper presents a high-speed LiDAR point cloud densification method to generate a dense 3D scene with minimal latency, addressing the need for on-the-fly depth completion while maintaining real-time performance. Our approach combines multiple LiDAR inputs with high-resolution color images and applies a joint bilateral filtering strategy implemented with a CNN-inspired architecture. Experiments demonstrate that the proposed method produces dense depth maps at full HD resolution in real time (30 fps), which is over 15x faster than a recent training-based depth completion approach [1]. The resulting dense point clouds exhibit accurate geometry without multi-view inconsistencies or ghosting artifacts.