π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
Convert your videos to densepose and use it on MagicAnimate
This is a pix2pix demo that learns from pose and translates this into a human. A webcam-enabled application is also provided that translates your pose to the trained pose. Everybody dance now !
To convert atlas texuture (defined in Densepose) to normal texture (defined in SMPL), and vice versa.
Pytorch implementation of the paper, Neural re-rendering of humans from a single image.
ESP32 Wi‑Fi CSI radar for human presence & movement detection. Privacy‑first — no cameras, no sensors, just Wi-Fi signal jitter. Real‑time WEB UI dashboard with live RSSI/jitter charts, auto‑calibration, GPIO/LED outputs.
Wi-Fi Vision: Device-free human pose estimation and activity recognition using ESP32 CSI and machine learning.
Person of Interest. A flexible computer vision library on human analysis, such as person re-identification, human attribute, pose estimation and dense pose estimation.
TryItOut is a versatile project that brings a variety of innovative features to the forefront, aimed at enhancing the online shopping experience. With a range of capabilities, the project empowers users to explore, visualize, and tailor their digital shopping journeys
Implementation of detectron2 denspose estimation with acknowledgement of body parts gazed.
Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.
preprocessing for VITON models
Fork of DensePose from WiFi — modified for dummy data testing on Apple Silicon
Hack The North 2018
WiFi CSI is a tool that lets you track people through walls by analyzing how WiFi signals bounce off their bodies (yes, it’s real). This repo brings together some of the best methods for working with WiFi CSI, along with additional mathematical modeling techniques. It explores how standard WiFi signals can be used to detect human presence.
👁 Cameras that watch. Eyes that act. AttackNet spots attacks on CCTV, a WebRTC mesh carries the alert across Atlanta even offline, and AI agents dispatch help and warn people nearby over iMessage (Photon). Hacklanta 2026.