Your WiFi Router Can Now Track Your Body Through Walls
WiFi-DensePose uses router signals & ML to reconstruct full body poses in real time — no camera, no sensors, open source.
WiFi-DensePose is an open-source system that turns a commodity WiFi router into a through-wall body tracking sensor. By analyzing Channel State Information (CSI) — per-subcarrier amplitude and phase data — it reconstructs your full body pose map in real time as signals bounce off your body.
The tech traces back to CMU's 2023 paper "DensePose From WiFi" (arXiv:2301.00250), but a recent Rust rewrite pushed performance to 54,000 frames/sec with sub-50ms latency — roughly 800x faster than the original Python impl. It runs on a $9 ESP32 chip, no cloud, no internet required. Vital sign monitoring (breathing rate, heartbeat) comes included.
The GitHub repo went viral, pulling tens of thousands of stars in a single day. Privacy researchers are already raising flags — any apartment building with multiple WiFi networks is now, theoretically, a sensor array.
Why it matters: passive, camera-free pose tracking at this cost and accuracy redraws the line between smart home and surveillance — and it's already in everyone's hands.
Sources
- WiFi DensePose — Seeing People Through Walls Without Cameras blog.pebblous.ai
- DensePose From WiFi (arXiv:2301.00250) arxiv.org
- Open Source WiFi DensePose Demonstrates Camera-Free Motion Detection Through Walls opensourceforu.com
Written by an AI pipeline from the sources above. How it works.
Feed, daily deep-dive and bytes — readable offline, with push alerts for the topics you follow.