指令驱动的虚拟角色风格化动作生成

Wei Liang, Yifan Huang, Yuxin Shen, Qiyuan Cheng*

*此作品的通讯作者

科研成果: 期刊稿件文章同行评审

摘要

To solve the problems existed in instruction-driven motion generation tasks, such as inaccurate instruction comprehension and unrelated motion generation between the given task and the results, under complex scenes, a novel method was proposed based on the combination of instructions and scene information to generate the styled motions for virtual characters. Two main components were arranged in the new method, including instruction parsing and motion generation. Firstly, using a large language model, a set of limited atomic actions were predefined to parse textual instructions into subtasks with the atomic actions in the instruction parsing stage. And then, in the motion generation stage, based on a conditional variational autoencoder (cVAE) to design a frame-by-frame motion generation network, the instruction-driven styled motion generation tasks were carried out, considering various style features such as age (e.g., young, old) and style features described in the textual instructions (e.g., happy, sad). Finally, consumer investigation and four determine tests were carried out for bedroom, park, living room and cookroom scenes, validating the method efficacy, the motion authenticity and style diversity.

投稿的翻译标题Instruction-Driven Styled Motion Generation for Virtual Characters
源语言繁体中文
页(从-至)1199-1207
页数9
期刊Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology
44
11
DOI
出版状态已出版 - 11月 2024

关键词

  • animation
  • instruction-driven
  • motion generation
  • style

指纹

探究 '指令驱动的虚拟角色风格化动作生成' 的科研主题。它们共同构成独一无二的指纹。

引用此