PB-MLD: Part-Based Motion Latent Diffusion Model

J. B. Liu

doi:10.1016/j.imavis.2026.106118

2026-07-11

PRE

DOI：10.1016/j.imavis.2026.106118

原文链接

原文求助

摘要

En 中文

• 基于部件的框架：PB-MLD将人体分解为上、下部分进行文本到动作生成。 • 结构化建模：部件特定的VAEs和InLineAttention模型处理局部和全局运动。 • 高质量合成：生成全局一致、物理合理的与文本对齐的动作。

期刊

Image and Vision Computing

IF:

4.2

论文数:

4.1K

被引数:

6.7K

机构

riken

学者数:

2.2W

论文数: 1.9W

被引数: 24

guangdong university of technology

学者数:

3.0W

论文数: 2.0W

被引数: 36

引用论文

MoMask: Generative Masked Modeling of 3D Human Motions MoMask: 3D人体运动的生成蒙面建模

IF0

2024-06-16

PREAI

Chuan Guo; Yuxuan Mu; Muhammad Gohar Javed; Sen Wang; Li Cheng

TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration TM2D: 通过音乐文本集成实现双模驱动的3D舞蹈生成

2023 IEEE/CVF International Conference on Computer Vision (ICCV)

IF0

2023-10-01

OAAI

Kehong Gong; Dongze Lian; Heng Chang; Chuan Guo; Zihang Jiang; Xinxin Zuo; Michael Bi Mi; Xinchao Wang

A novel framework for diverse video generation from a single video using frame-conditioned denoising diffusion probabilistic model and ConvNeXt-V2

IMAGE AND VISION COMPUTING

IF4.2

2025-02-01

PREAI

Verma, Ayushi; Badal, Tapas; Bansal, Abhay

High-Resolution Image Synthesis with Latent Diffusion Models 具有潜在扩散模型的高分辨率图像合成

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

IF0

2022-06-01

OAAI

Robin Rombach; Andreas Blattmann; Dominik Lorenz; Patrick Esser; Bjorn Ommer

Generating Diverse and Natural 3D Human Motions from Text 从文本生成多样化和自然的3D人体运动

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

IF0

2022-06-01

PREAI

Chuan Guo; Shihao Zou; Xinxin Zuo; Sen Wang; Wei Ji; Xingyu Li; Li Cheng

Language-guided Human Motion Synthesis with Atomic Actions 语言引导的基于原子动作的人类运动合成

Proceedings of the 31st ACM International Conference on Multimedia

IF0

2023-10-26

PREAI

Zhai,Yuanhao; Huang,Mingzhen; Luan,Tianyu; Dong,Lu; Nwogu,Ifeoma; Lyu,Siwei; Doermann,David; Yuan,Junsong

The KIT Motion-Language Dataset KIT运动语言数据集

Big Data

IF0

2016-12-01

OAAI

Matthias Plappert; Christian Mandery; Tamim Asfour

GUESS: GradUally Enriching SyntheSis for Text-Driven Human Motion Generation

IEEE Transactions on Visualization and Computer Graphics

IF0

2024-12-01

OAAI

Xuehao Gao; Yang Yang; Zhenyu Xie; Shaoyi Du; Zhongqian Sun; Yang Wu

On the Continuity of Rotation Representations in Neural Networks 关于神经网络中旋转表示的连续性

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

IF0

2019-06-01

PREAI

Yi Zhou; Connelly Barnes; Jingwan Lu; Jimei Yang; Hao Li

MotionDiffuse: Text-Driven Human Motion Generation With Diffusion Model

IEEE Transactions on Pattern Analysis and Machine Intelligence

IF0

2024-06-01

OAAI

Mingyuan Zhang; Zhongang Cai; Liang Pan; Fangzhou Hong; Xinying Guo; Lei Yang; Ziwei Liu

查看更多内容