WiFi-3D-Fusion: Open-Source Project Using WiFi CSI Signals and Deep Learning for 3D Human Pose Estimation
By
aerosol
Hand-rolled, kettle-boiled, baked to perfection. Worth every minute at the bakery.
Summary
WiFi-3D-Fusion is an open-source research project that uses WiFi Channel State Information (CSI) signals combined with deep learning to estimate 3D human pose. The project fuses wireless sensing with computer vision techniques to enable spatial awareness and real-time motion detection. It features robust CSI ingestion from local Wi-Fi devices (ESP32-CSI via UDP or Nexmon via tcpdump + csiread), a real-time movement detector, and a 3D viewer for visualization.
Key quotes
· 5 pulledWiFi-3D-Fusion is an open-source research project that leverages WiFi CSI signals and deep learning to estimate 3D human pose
fusing wireless sensing with computer vision techniques for next-generation spatial awareness
Live local Wi-Fi sensing with CSI: real-time motion detection + visualization
This monorepo is production-oriented: robust CSI ingestion from local Wi-Fi
a realtime movement detector, and a 3D viewer
You might also wanna read
Apple to present 14 AI research papers at CVPR conference in Denver ahead of WWDC
Apple will present 14 AI research papers at the 2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) in Denver next we
appleinsider.com·3d ago
OpenAI's o3 model shows surprising geoguessing capabilities from photos
The article discusses how OpenAI's o3 model unexpectedly demonstrated impressive geoguessing capabilities, able to identify locations from n
seangoedecke.com·11d ago
LoGeR: Hybrid Memory System Enables Dense 3D Reconstruction from Long Videos
LoGeR (Long-Context Geometric Reconstruction with Hybrid Memory) is a novel AI system developed by Google DeepMind and UC Berkeley researche
ShapeR: Robust Conditional 3D Shape Generation from Casual Image Captures
ShapeR is a novel system for generative, object-centric 3D reconstruction from casual image sequences. The research paper presents a method
Apple's SHARP: Photorealistic 3D View Synthesis from a Single Image in Under a Second
Apple researchers present SHARP, a neural network approach for photorealistic view synthesis from a single image. The method regresses param
github.com·5mo ago
ALIGN-Parts: One-Shot 3D Part Segmentation and Naming via Set-Level Alignment
The article discusses ALIGN-Parts, a new approach for 3D part segmentation and naming that addresses the challenge of inconsistent labeling
name-that-part.github.io·5mo ago