A causal convolutional neural network for multi-subject motion modeling and generation

Inspired by the success of WaveNet in multi-subject speech synthesis, we propose a novel neural network based on causal convolutions for multi-subject motion modeling and generation. The network can capture the intrinsic characteristics of the motion of different subjects, such as the influence of s...

Full description

Saved in:
Bibliographic Details
Published inComputational visual media (Beijing) Vol. 10; no. 1; pp. 45 - 59
Main Authors Hou, Shuaiying, Wang, Congyi, Zhuang, Wenlin, Chen, Yu, Wang, Yangang, Bao, Hujun, Chai, Jinxiang, Xu, Weiwei
Format Journal Article
LanguageEnglish
Published Beijing Tsinghua University Press 01.02.2024
Springer Nature B.V
SpringerOpen
Subjects
Artificial Intelligence
Artificial neural networks
Computer Graphics
Computer Science
Datasets
Deep learning
Image Processing and Computer Vision
Methods
Modelling
motion control
motion denoising
motion generation
Neural networks
optimization
Research Article
Speech recognition
User Interfaces and Human Computer Interaction
motion denoising
motion generation
deep learning
motion control
optimization
Online AccessGet full text

Cover

More Information
Summary:Inspired by the success of WaveNet in multi-subject speech synthesis, we propose a novel neural network based on causal convolutions for multi-subject motion modeling and generation. The network can capture the intrinsic characteristics of the motion of different subjects, such as the influence of skeleton scale variation on motion style. Moreover, after fine-tuning the network using a small motion dataset for a novel skeleton that is not included in the training dataset, it is able to synthesize high-quality motions with a personalized style for the novel skeleton. The experimental results demonstrate that our network can model the intrinsic characteristics of motions well and can be applied to various motion modeling and synthesis tasks.
ISSN:2096-0433
2096-0662
DOI:10.1007/s41095-022-0307-3