GitHub - ruvnet/RuView: π RuView: WiFi DensePose turns commodity WiFi signals into real-time human pose estimation, vital sign monitoring, and presence detection — all without a single pixel of video.

RuView is an open-source system that uses WiFi Channel State Information (CSI) to perform real-time human pose estimation, vital sign monitoring (breathing 6-30 BPM, heart rate 40-120 BPM), and presence detection — all without cameras. Built primarily in Rust (54,000 frames/sec), it runs on commodity ESP32-S3 hardware (~$8) or research NICs. The system uses physics-based signal processing (SpotFi, Hampel, Fresnel zone modeling) combined with graph transformer neural networks to reconstruct 17-keypoint body poses from WiFi scattering patterns. It supports self-supervised learning with no labeled data, cross-environment generalization, and 65 edge WASM modules deployable on-device. Use cases span healthcare monitoring, retail analytics, disaster search-and-rescue, industrial safety, and robotics. Deployable via Docker in 30 seconds, with 15 published Rust crates on crates.io.