Pose estimation in Wi-Fi CSI sensing refers to the task of inferring the spatial configuration of a human body — typically the positions and orientations of key skeletal joints or body parts — from wireless channel signals without requiring cameras or wearable sensors. It matters to the field because it enables privacy-preserving, device-free human body understanding for applications such as healthcare monitoring, rehabilitation, and human-computer interaction, extending the utility of Wi-Fi sensing beyond coarse activity recognition. Key variants include static pose estimation, which infers body posture from a single snapshot of CSI measurements, and dynamic or continuous pose estimation, which tracks the evolution of body configuration over time, with some approaches targeting 2D skeletal keypoint localization and others attempting full 3D body mesh reconstruction.
Source Papers
- A Survey on Wi-Fi Sensing Generalizability: Taxonomy, Techniques, Datasets, and Future Research Prospects ↗ — A Survey on Wi-Fi Sensing Generalizability: Taxonomy, Techni
- Deep Learning-Enhanced Human Sensing with Channel State Information: A Survey ↗ — Deep Learning-Enhanced Human Sensing with Channel State Info
- SenseFi: A library and benchmark on deep-learning-empowered WiFi human sensing ↗ — SenseFi: A library and benchmark on deep-learning-empowered