Large Motion Model for Unified Multi-modal Motion Generation DOI
Mingyuan Zhang,

Daisheng Jin,

Chenyang Gu

et al.

Lecture notes in computer science, Journal Year: 2024, Volume and Issue: unknown, P. 397 - 421

Published: Oct. 25, 2024

Language: Английский

MotionLCM: Real-Time Controllable Motion Generation via Latent Consistency Model DOI

Wenxun Dai,

Ling-Hao Chen, Jingbo Wang

et al.

Lecture notes in computer science, Journal Year: 2024, Volume and Issue: unknown, P. 390 - 408

Published: Oct. 28, 2024

Language: Английский

Citations

5
LEAD: Latent Realignment for Human Motion Diffusion DOI Creative Commons
N. Andreou, Xi Wang, Victoria Abrevaya

et al.

Computer Graphics Forum, Journal Year: 2025, Volume and Issue: unknown

Published: April 9, 2025

Abstract Our goal is to generate realistic human motion from natural language. Modern methods often face a trade‐off between model expressiveness and text‐to‐motion (T2M) alignment. Some align text latent spaces but sacrifice expressiveness; others rely on diffusion models producing impressive motions lacking semantic meaning in their space. This may compromise realism, diversity applicability. Here, we address this by combining with realignment mechanism, novel, semantically structured space that encodes the semantics of Leveraging capability, introduce task textual inversion capture novel concepts few examples. For synthesis, evaluate LEAD HumanML3D KIT‐ML show comparable performance state‐of‐the‐art terms text‐motion consistency. qualitative analysis user study reveal our synthesised are sharper, more human‐like comply better compared modern methods. (MTI), method demonstrates improvements capturing out‐of‐distribution characteristics comparison traditional VAEs.

Language: Английский

Citations

0
Plan, Posture and Go: Towards Open-Vocabulary Text-to-Motion Generation DOI
Jinpeng Liu,

Wenxun Dai,

Chunyu Wang

et al.

Lecture notes in computer science, Journal Year: 2024, Volume and Issue: unknown, P. 445 - 463

Published: Nov. 2, 2024

Language: Английский

Citations

3
CoMo: Controllable Motion Generation Through Language Guided Pose Code Editing DOI
Yiming Huang, Weilin Wan, Yue Yang

et al.

Lecture notes in computer science, Journal Year: 2024, Volume and Issue: unknown, P. 180 - 196

Published: Nov. 2, 2024

Language: Английский

Citations

2
Disentangled Clothed Avatar Generation from Text Descriptions DOI
Jionghao Wang, Yuan Liu, Zhiyang Dou

et al.

Lecture notes in computer science, Journal Year: 2024, Volume and Issue: unknown, P. 381 - 401

Published: Nov. 28, 2024

Language: Английский

Citations

2
Large Motion Model for Unified Multi-modal Motion Generation DOI
Mingyuan Zhang,

Daisheng Jin,

Chenyang Gu

et al.

Lecture notes in computer science, Journal Year: 2024, Volume and Issue: unknown, P. 397 - 421

Published: Oct. 25, 2024

Language: Английский

Citations

1