Deep joint source-channel coding for wireless point cloud transmission

TL;DR

This paper introduces Deep Point Cloud Semantic Transmission (PCST), a novel end-to-end wireless point cloud transmission system that uses deep joint source-channel coding and adaptive entropy-based importance assessment to improve efficiency and quality.

Contribution

The paper presents a new deep JSCC-based system for wireless point cloud transmission that incorporates semantic feature importance and adaptive rate control, outperforming traditional methods.

Findings

Significantly outperforms traditional SSCC schemes.

Achieves over 50% reduction in bandwidth usage.

Provides robust performance across various SNR levels.

Abstract

The growing demand for high-quality point cloud transmission over wireless networks presents significant challenges, primarily due to the large data sizes and the need for efficient encoding techniques. In response to these challenges, we introduce a novel system named Deep Point Cloud Semantic Transmission (PCST), designed for end-to-end wireless point cloud transmission. Our approach employs a progressive resampling framework using sparse convolution to project point cloud data into a semantic latent space. These semantic features are subsequently encoded through a deep joint source-channel (JSCC) encoder, generating the channel-input sequence. To enhance transmission efficiency, we use an adaptive entropy-based approach to assess the importance of each semantic feature, allowing transmission lengths to vary according to their predicted entropy. PCST is robust across diverse Signal-to-Noise Ratio (SNR) levels and supports an adjustable rate-distortion (RD) trade-off, ensuring flexible and efficient transmission. Experimental results indicate that PCST significantly outperforms traditional separate source-channel coding (SSCC) schemes, delivering superior reconstruction quality while achieving over a 50% reduction in bandwidth usage.