Iterative Motion Editing with Natural Language

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Goel, Purvi, Wang, Kuan-Chieh, Liu, C. Karen, Fatahalian, Kayvon
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929370740817920
author Goel, Purvi
Wang, Kuan-Chieh
Liu, C. Karen
Fatahalian, Kayvon
author_facet Goel, Purvi
Wang, Kuan-Chieh
Liu, C. Karen
Fatahalian, Kayvon
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2312_11538
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Iterative Motion Editing with Natural Language
Goel, Purvi
Wang, Kuan-Chieh
Liu, C. Karen
Fatahalian, Kayvon
Graphics
Computer Vision and Pattern Recognition
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.
title Iterative Motion Editing with Natural Language
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.11538