MotionDiffuse: Text-Driven Human Motion Generation With Diffusion Model
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-06 · 46 (6) · 4115-4128
DOI: 10.1109/tpami.2024.3355414 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-06. Verfasst von Mingyuan Zhang und 6 weiteren Autor:innen. Hauptthemen laut MEDLINE: Movement. Die Arbeit wurde bisher 381-mal zitiert (Crossref) und nennt 85 Literaturangaben.
Abstract (Originalsprache)
Human motion modeling is important for many modern graphics applications, which typically require professional skills. In order to remove the skill barriers for laymen, recent motion generation methods can directly generate human motions conditioned on natural languages. However, it remains challenging to achieve diverse and fine-grained motion generation with various text inputs. To address this problem, we propose MotionDiffuse, one of the first diffusion model-based text-driven motion generation frameworks, which demonstrates several desired properties over existing methods. 1) Probabilistic Mapping. Instead of a deterministic language-motion mapping, MotionDiffuse generates motions through a series of denoising steps in which variations are injected. 2) Realistic Synthesis. MotionDiffuse excels at modeling complicated data distribution and generating vivid motion sequences. 3) Multi-Level Manipulation. MotionDiffuse responds to fine-grained instructions on body parts, and arbitrary-length motion synthesis with time-varied text prompts. Our experiments show MotionDiffuse outperforms existing SoTA methods by convincing margins on text-driven motion generation and action-conditioned motion generation. A qualitative analysis further demonstrates MotionDiffuse's controllability for comprehensive motion generation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Zitieren
APA
Zhang, M., Cai, Z., Pan, L., Hong, F., Guo, X., Yang, L., & Liu, Z. (2024). MotionDiffuse: Text-Driven Human Motion Generation With Diffusion Model. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(6), 4115-4128. https://doi.org/10.1109/tpami.2024.3355414
Vancouver
Zhang M, Cai Z, Pan L, Hong F, Guo X, Yang L, et al. MotionDiffuse: Text-Driven Human Motion Generation With Diffusion Model. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(6):4115-4128. doi:10.1109/tpami.2024.3355414
BibTeX
@article{Zhang2024,
author = {Zhang, Mingyuan and Cai, Zhongang and Pan, Liang and Hong, Fangzhou and Guo, Xinying and Yang, Lei and Liu, Ziwei},
title = {MotionDiffuse: Text-Driven Human Motion Generation With Diffusion Model},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2024},
volume = {46},
number = {6},
pages = {4115--4128},
doi = {10.1109/tpami.2024.3355414}
}
EUVIMED