TinySense: Effective CSI Compression for Scalable and Accurate Wi-Fi Sensing

2026-01-22

AI Summary

This work addresses the scalability limitations of Wi-Fi sensing caused by the large volume of raw channel state information (CSI) data. The authors propose TinySense, an efficient CSI compression framework based on a vector-quantized generative adversarial network (VQGAN). TinySense uniquely integrates VQGAN with K-means-based dynamic codebook pruning and incorporates a lightweight Transformer module to compensate for compression-induced fidelity loss, thereby significantly enhancing robustness under weak network conditions. Experimental deployment on edge devices such as the Jetson Nano and Raspberry Pi demonstrates that, at the same compression ratio, TinySense improves the PCK20 accuracy of human pose estimation by 1.5× while reducing latency and network overhead to one-fifth and two-fifths of the original, respectively, achieving an optimal balance between high accuracy and low resource consumption.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Humans and AI: Brain-Sensing and Analysis

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Large-scale security measurements

Abstract

With the growing demand for device-free and privacy-preserving sensing solutions, Wi-Fi sensing has emerged as a promising approach for human pose estimation (HPE). However, existing methods often process vast amounts of channel state information (CSI) data directly, ultimately straining networking resources. This paper introduces TinySense, an efficient compression framework that enhances the scalability of Wi-Fi-based human sensing. Our approach is based on a new vector quantization-based generative adversarial network (VQGAN). Specifically, by leveraging a VQGAN-learned codebook, TinySense significantly reduces CSI data while maintaining the accuracy required for reliable HPE. To optimize compression, we employ the K-means algorithm to dynamically adjust compression bitrates to cluster a large-scale pre-trained codebook into smaller subsets. Furthermore, a Transformer model is incorporated to mitigate bitrate loss, enhancing robustness in unreliable networking conditions. We prototype TinySense on an experimental testbed using Jetson Nano and Raspberry Pi to measure latency and network resource use. Extensive results demonstrate that TinySense significantly outperforms state-of-the-art compression schemes, achieving up to 1.5x higher HPE accuracy score (PCK20) under the same compression rate. It also reduces latency and networking overhead, respectively, by up to 5x and 2.5x. The code repository is available online at here.

Problem

• Wi-Fi sensing
• channel state information (CSI)
• data compression
• human pose estimation
• network resource overhead

Innovation

• VQGAN
• CSI compression
• Wi-Fi sensing
• Transformer
• human pose estimation