Overview
Learned Motion Matching is a Unity asset designed to generate realistic and smooth transitions for basic humanoid locomotion. It allows for natural, fluid movement with no foot sliding or abrupt animation changes. This asset is developed by AiKodex.
Key Features
- Natural, Fluid Movement: Achieve smooth, weight-shifted motion. The customizable kNN classifier balances fast, responsive transitions and realistic movements.
- Waypoint Navigation: Follow custom-defined paths with precision using an advanced Distance Matching system powered by a Greedy Algorithm. Loop waypoints and adjust the speed.
- Upper Body Customization: Use Inverse Kinematics (IK) for characters to dynamically hold or manipulate objects with realistic hand poses. Customize hand weights and fine-tune motions.
- Effortless Setup: Designed for all humanoid characters with a one-click setup process and comprehensive documentation.
Dependencies
Learned Motion Matching requires the Animation Rigging and Sentis package from the package manager. Specifically requires Sentis Version 1.3.
Limitations
- Locomotion Only: Focused solely on basic human locomotion; advanced moves like jumping or vaulting are not included.
- No Specialized Motions: Custom movements, such as limping or skipping, require external data and are not included.
Research
This asset implements the SIGGRAPH technical paper <Taming Diffusion Probabilistic Models for Character Control>.
Citation: Chen, R., Shi, M., Huang, S., Tan, P., Komura, T., & Chen, X. (2024, April 23). Taming diffusion probabilistic models for character control. arXiv.org. https://arxiv.org/abs/2404.15121
Click the button below to download.
Download:
Login Required
Please register or log in to your account.
