Octree-Based Temporal-Spatial Context Entropy Model for LiDAR Point Cloud Compression

It’s difficult to effectively remove redundancy in Li-DAR point clouds due to their extremely sparse and nonuniform distribution. Taking advantage of both octree-based methods and voxel-based schemes, we propose to design an effective temporal-spatial context to compress the sequence octree-structured point cloud data into a more compact bitstream. In this paper, we first build a temporal-spatial multiscale context for the deep learning entropy model. It further utilize the correlation of sequential point cloud data from both the spatial domain and temporal domain. In terms of spatial context, we design a hierarchical dependency in an octree to encode the occupancy information of each non-leaf octree node into a bitstream. We propose to further group the nodes according to their octant which effectively expands the context receptive field. In terms of temporal context, the KNN algorithm is applied to explore the most relative context with the strongest dependency in the temporal domain. Finally, we design a voxel re-localization network to convert the discrete voxels into refined 3D points, which makes up for the coordinate loss in the process of generating an octree. The quantitative evaluation shows that our method outperforms state-of-the-art baselines with saving most bitrate on KITTI Odometry dataset, and achieving the best reconstreuction benefit by the designed refinement module.

I. Introduction

The LiDAR sensor is one of the most important 3D sensors for machines to perceive the world. With the rapid development of hardware devices, these sensors produce a significant amount of data. For example, a single Velodyne HDL-64 LiDAR sensor generates over 100,000 points per sweep, resulting in over 84 billion points per day [1]. This enormous quantity of raw sensor data brings challenges to storage as well as the application of real-time communication. Hence, it is necessary to develop an efficient compression method for continuous sweeps of 3D point clouds.