Iterative Motion Editing with Natural Language
This work addresses a common task in computer animation workflows, enabling animators to make precise edits using natural language, though it is incremental as it builds on existing text-to-motion diffusion models.
The paper tackles the problem of fine-grained motion editing in character animations by introducing a method that uses natural language to iteratively specify local edits, leveraging kinematic motion editing operators and diffusion models to generate realistic outputs that respect user intent and original animation fidelity.
Text-to-motion diffusion models can generate realistic animations from text prompts, but do not support fine-grained motion editing controls. In this paper, we present a method for using natural language to iteratively specify local edits to existing character animations, a task that is common in most computer animation workflows. Our key idea is to represent a space of motion edits using a set of kinematic motion editing operators (MEOs) whose effects on the source motion is well-aligned with user expectations. We provide an algorithm that leverages pre-existing language models to translate textual descriptions of motion edits into source code for programs that define and execute sequences of MEOs on a source animation. We execute MEOs by first translating them into keyframe constraints, and then use diffusion-based motion models to generate output motions that respect these constraints. Through a user study and quantitative evaluation, we demonstrate that our system can perform motion edits that respect the animator's editing intent, remain faithful to the original animation (it edits the original animation, but does not dramatically change it), and yield realistic character animation results.