Graph-based 3D Human Pose Estimation using WiFi Signals
By: Jichao Chen , YangYang Qu , Ruibo Tang and more
Potential Business Impact:
Lets WiFi see your body's shape.
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.
Similar Papers
Towards Robust and Realistic Human Pose Estimation via WiFi Signals
CV and Pattern Recognition
Lets WiFi see your body's shape.
HGFreNet: Hop-hybrid GraphFomer for 3D Human Pose Estimation with Trajectory Consistency in Frequency Domain
CV and Pattern Recognition
Makes 2D videos show people's real 3D movements.
GraphEnet: Event-driven Human Pose Estimation with a Graph Neural Network
CV and Pattern Recognition
Lets robots see people's movements quickly.