msLPCC: A Multimodal-Driven Scalable Framework for Deep LiDAR Point Cloud Compression

LiDAR sensors are widely used in autonomous driving, and the growing storage and transmission demands have made LiDAR point cloud compression (LPCC) a hot research topic. To address the challenges posed by the large-scale and uneven-distribution (spatial and categorical) of LiDAR point data, this paper presents a new multimodal-driven scalable LPCC framework. For the large-scale challenge, we decouple the original LiDAR data into multi-layer point subsets, compress and transmit each layer separately, so as to ensure the reconstruction quality requirement under different scenarios. For the uneven-distribution challenge, we extract, align, and fuse heterologous feature representations, including point modality with position information, depth modality with spatial distance information, and segmentation modality with category information. Extensive experimental results on the benchmark SemanticKITTI database validate that our method outperforms 14 recent representative LPCC methods.

Authors

• Miaohui Wang College of Computer Science and Software Engineering, Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen University
• Runnan Huang Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen 518060
• Hengjin Dong Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen 518060
• Di Lin College of Intelligence and Computing, Tianjin University
• Yun Song School of Computer & Communication Engineering, Changsha University of Science & Technology, Changsha 410004
• Wuyuan Xie College of Computer Science and Software Engineering, Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen University

Keywords

• CV: Other Foundations of Computer Vision
• DMKM: Data Compression