code for learning trajectory dependencies for human motion prediction
-
Updated
Sep 25, 2023 - Python
code for learning trajectory dependencies for human motion prediction
Partially labelled, interpreted, and analyzed version of the CMU Motion Capture dataset.
GPSM (Generative Pre-trained State Machine) is a neural motion model trained on large-scale mocap data to predict and generate human motion, aiming to replace hand-crafted animation state machines used in traditional motion matching systems.
ZPE-Mocap V0.0: DETERMINISTIC MOTION CAPTURE CODEC: Joint Angles | Positional Fidelity | Search Ranking | Sub-ms Query | Skeletal Transport
Add a description, image, and links to the cmu-mocap topic page so that developers can more easily learn about it.
To associate your repository with the cmu-mocap topic, visit your repo's landing page and select "manage topics."