Shaohua Pan Claim this profile

A Generalizable Codebase for World-Action Models

StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

Code for our SIGGRAPH ASIA 2023 paper "Fusing Monocular Images and Sparse IMU Signals for Real-time Human Motion Capture".

Code for our TVCG paper "DiffCap: Diffusion-based Real-time Human Motion Capture using Sparse IMUs and a Monocular Camera".

A real-time system that simultaneously captures human pose, reconstructs the scene in sparse 3D points, and localizes the human in the scene with 6 IMUs and a body-worn phone camera

3D-space human motion capture from 6 IMUs built upon TransPose, PIP, and PNP

Enjoy the magic of Diffusion models!

Shaohua Pan's homepage

Website of RobustCap.