Graph-based 3D Human Pose Estimation using WiFi Signals

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Jichao, Qu, YangYang, Tang, Ruibo, Slock, Dirk
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911283708690432
author Chen, Jichao
Qu, YangYang
Tang, Ruibo
Slock, Dirk
author_facet Chen, Jichao
Qu, YangYang
Tang, Ruibo
Slock, Dirk
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_19105
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Graph-based 3D Human Pose Estimation using WiFi Signals
Chen, Jichao
Qu, YangYang
Tang, Ruibo
Slock, Dirk
Computer Vision and Pattern Recognition
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.
title Graph-based 3D Human Pose Estimation using WiFi Signals
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.19105