Repository navigation
mocap
- Website
- Wikipedia
A real-time motion capture system for 3D virtual character animating.
We present MocapNET, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance
A SteamVR powered mocap solution for Unreal Engine
A library for machine learning research on motion capture data
Markerless kinematics with any cameras — From 2D Pose estimation to 3D OpenSim motion
A Multi-Task Dataset for Simulated Humanoid Control
The Machinima Studio mod
Phiz is a tool that allows you to perform facial motion capture from any device and location.
Information of public available data sets for biomechanics.
(Eyebeam #13 of 13) Output OSC, MIDI, and After Effects/Maya animation scripts from the Leap Motion controller.
Library to explore, process, and analyze movement acquisition data
(Eyebeam #1 of 13) Developed with @FakeGreenDress. Record, stream, and export Kinect mocap data to After Effects puppet pins. Record directly from the Kinect or over OSC. Compiling or running from source requires SimpleOpenNI.
A free and open-sourced solution to build digital twins