Semantic Communication for Efficient Point Cloud Transmission

• DOI: 10.48550/arxiv.2409.03319
• Publication Date: 2024-09-05
• Authors: Shuang Xie; Qianqian Yang; Yuyi Sun; Tianxiao Han; Zhaohui Yang; Zhiguo Shi
• Keywords: FOS: Computer and information sciences; Emerging Technologies (cs.ET); Computer Science - Emerging Technologies

As three-dimensional acquisition technologies like LiDAR cameras advance, the need for efficient transmission of 3D point clouds is becoming increasingly important. In this paper, we present a novel semantic communication (SemCom) approach cloud transmission. Different from existing methods that rely on downsampling and feature extraction compression, our utilizes parallel structure to separately extract both global local information clouds. This system composed five key components: encoder, channel decoder, decoder. Our numerical results indicate surpasses traditional Octree compression methodology alternative deep learning-based strategies in terms reconstruction quality. Moreover, capable achieving high-quality under adverse conditions, specifically maintaining quality over 37dB even with severe noise.