PLIN: A Network for Pseudo-LiDAR Point Cloud Interpolation
This addresses a bottleneck in autonomous driving and UAV navigation systems by enabling better sensor fusion between LiDAR and cameras, though it is an incremental improvement in deep learning for point cloud processing.
The paper tackles the problem of low-frequency LiDAR data in multi-sensor systems by proposing PLIN, a network for pseudo-LiDAR point cloud interpolation, which generates high-quality intermediate point clouds to match camera frequencies, achieving promising performance on the KITTI dataset and outperforming traditional and state-of-the-art methods.
LiDAR sensors can provide dependable 3D spatial information at a low frequency (around 10Hz) and have been widely applied in the field of autonomous driving and UAV. However, the camera with a higher frequency (around 20Hz) has to be decreased so as to match with LiDAR in a multi-sensor system. In this paper, we propose a novel Pseudo-LiDAR interpolation network (PLIN) to increase the frequency of LiDAR sensors. PLIN can generate temporally and spatially high-quality point cloud sequences to match the high frequency of cameras. To achieve this goal, we design a coarse interpolation stage guided by consecutive sparse depth maps and motion relationship. We also propose a refined interpolation stage guided by the realistic scene. Using this coarse-to-fine cascade structure, our method can progressively perceive multi-modal information and generate accurate intermediate point clouds. To the best of our knowledge, this is the first deep framework for Pseudo-LiDAR point cloud interpolation, which shows appealing applications in navigation systems equipped with LiDAR and cameras. Experimental results demonstrate that PLIN achieves promising performance on the KITTI dataset, significantly outperforming the traditional interpolation method and the state-of-the-art video interpolation technique.