LGTM: Local-to-Global Text-Driven Human Motion Diffusion Model
Open Access
- 13 July 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Abstract
In this paper, we introduce LGTM, a novel Local-to-Global pipeline for Text-to-Motion generation. LGTM utilizes a diffusion-based architecture and aims to address the challenge of accurately translating textual descriptions into semantically coherent human motion in computer animation. Specifically, traditional methods often struggle with semantic discrepancies, particularly in aligning specific motions to the correct body parts. To address this issue, we propose a two-stage pipeline to overcome this challenge: it first employs large language models (LLMs) to decompose global motion descriptions into part-specific narratives, which are then processed by independent body-part motion encoders to ensure precise local semantic alignment. Finally, an attention-based full-body optimizer refines the motion generation results and guarantees the overall coherence. Our experiments demonstrate that LGTM gains significant improvements in generating locally accurate, semantically-aligned human motion, marking a notable advancement in text-to-motion applications. Code and data for this paper are available at https://github.com/L-Sun/LGTMKeywords
All Related Versions
Funding Information
- Shenzhen Science and Technology Program (RCYX20210609103121030)
- Guangdong Natural Science Foundation (2021B1515020085)
- National Natural Science Foundation of China (62322207)
This publication has 33 references indexed in Scilit:
- ChatGPT for digital forensic investigation: The good, the bad, and the unknownForensic Science International: Digital Investigation, 2023
- TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts2022
- MotionCLIP: Exposing Human Motion Generation to CLIP Space2022
- TEMOS: Generating Diverse Human Motions from Textual Descriptions2022
- TEACH: Temporal Action Composition for 3D Humans2022
- Generating Diverse and Natural 3D Human Motions from Text2022
- Metaverse: Perspectives from graphics, interactions and visualizationVisual Informatics, 2022
- Towards efficient and photorealistic 3D human reconstruction: A brief surveyVisual Informatics, 2021
- Language2Pose: Natural Language Grounded Pose Forecasting2019
- Enriching a motion database by analogous combination of partial human motionsThe Visual Computer, 2007