Graph-based 3D Human Pose Estimation using WiFi Signals

TL;DR

GraphPose-Fi introduces a graph-based WiFi human pose estimation framework that models skeletal topology explicitly, significantly improving accuracy over existing regression-based WiFi HPE methods.

Contribution

The paper proposes a novel graph-based framework for WiFi-based 3D human pose estimation that captures skeletal topology using GCN and self-attention, outperforming prior regression approaches.

Findings

Outperforms existing WiFi HPE methods on MM-Fi dataset

Effectively models skeletal topology with GCN and self-attention

Achieves significant accuracy improvements in various settings

Abstract

WiFi-based human pose estimation (HPE) has attracted increasing attention due to its resilience to occlusion and privacy-preserving compared to camera-based methods. However, existing WiFi-based HPE approaches often employ regression networks that directly map WiFi channel state information (CSI) to 3D joint coordinates, ignoring the inherent topological relationships among human joints. In this paper, we present GraphPose-Fi, a graph-based framework that explicitly models skeletal topology for WiFi-based 3D HPE. Our framework comprises a CNN encoder shared across antennas for subcarrier-time feature extraction, a lightweight attention module that adaptively reweights features over time and across antennas, and a graph-based regression head that combines GCN layers with self-attention to capture local topology and global dependencies. Our proposed method significantly outperforms existing methods on the MM-Fi dataset in various settings. The source code is available at: https://github.com/Cirrick/GraphPose-Fi.