This is published under the terms of CC BY-NC.

Downloaded: 95 times

Abstract

Point cloud compression can effectively save the amount of data required for transmission and storage of point clouds. However, the commonly used methods of point cloud compression have serious impacts on the performance of downstream visual tasks due to the ignorance of the semantic information represented by point cloud. Towards this end, this paper proposes an object semantic-aware compression network for 3D point cloud, namely OSC-Net. Firstly, a ground points removal module based on the elevation difference is designed, enabling the network to pay more attention to the semantic information of objects. Secondly, a 3D voxel attention module is proposed to extract multiple priors in deep entropy model that can predict the probability distribution of occupied symbols in voxel space. Finally, experimental results show that our proposed network gains a notable bitrate saving of 16.71% compared to the baseline on the KITTI 3D object detection dataset, while maintaining a comparable detection accuracy.