Real-time Animation Generation and Control on Rigged Models via Large Language Models
This addresses animation generation for game developers or animators, but it appears incremental as it applies existing LLMs to a new domain.
The paper tackles real-time animation control for rigged models using natural language input, achieving robust qualitative results by embedding a large language model in Unity to generate structured animations and enable flexible state transitions.
We introduce a novel method for real-time animation control and generation on rigged models using natural language input. First, we embed a large language model (LLM) in Unity to output structured texts that can be parsed into diverse and realistic animations. Second, we illustrate LLM's potential to enable flexible state transition between existing animations. We showcase the robustness of our approach through qualitative results on various rigged models and motions.