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

Daisheng Jin,

Chenyang Gu

и другие.

Lecture notes in computer science, Год журнала: 2024, Номер unknown, С. 397 - 421

Опубликована: Окт. 25, 2024

Язык: Английский

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

Wenxun Dai,

Ling-Hao Chen, Jingbo Wang

и другие.

Lecture notes in computer science, Год журнала: 2024, Номер unknown, С. 390 - 408

Опубликована: Окт. 28, 2024

Язык: Английский

Процитировано

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

и другие.

Computer Graphics Forum, Год журнала: 2025, Номер unknown

Опубликована: Апрель 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.

Язык: Английский

Процитировано

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

Wenxun Dai,

Chunyu Wang

и другие.

Lecture notes in computer science, Год журнала: 2024, Номер unknown, С. 445 - 463

Опубликована: Ноя. 2, 2024

Язык: Английский

Процитировано

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

и другие.

Lecture notes in computer science, Год журнала: 2024, Номер unknown, С. 180 - 196

Опубликована: Ноя. 2, 2024

Язык: Английский

Процитировано

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

и другие.

Lecture notes in computer science, Год журнала: 2024, Номер unknown, С. 381 - 401

Опубликована: Ноя. 28, 2024

Язык: Английский

Процитировано

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

Daisheng Jin,

Chenyang Gu

и другие.

Lecture notes in computer science, Год журнала: 2024, Номер unknown, С. 397 - 421

Опубликована: Окт. 25, 2024

Язык: Английский

Процитировано

1