Human Motion Synthesis and Editing Based on Deep Learning

DOI Web Site

Bibliographic Information

Other Title
  • 深層学習に基づく人物モーションの生成と編集
  • シンソウ ガクシュウ ニ モトズク ジンブツ モーション ノ セイセイ ト ヘンシュウ

Search this article

Abstract

<p>This paper proposed a motion synthesis and edit for character animations via latent variable space. An existing method using an auto-encoder is unsuited for efficient explorations and manipulations because the latent space has a large number of dimensions. Moreover, its encoder and decoder are composed of a single-layer, which is not suited to synthesize various types or styles of motions. We propose two types of generative neural networks that can map the latent variables so as to fit to a Gaussian distribution and can embed various motions in a lower dimensional latent space. We evaluate the plausibility of motions synthesized with our method, by demonstrating motion transitions and interpolations without preprocessing of time-alignment.</p>

Journal

Keywords

Details 詳細情報について

Report a problem

Back to top