BriefGPT.xyz
Aug, 2018
MT-VAE: 学习运动变换以生成多模式人体动力学
MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics
HTML
PDF
Xinchen Yan, Akash Rastogi, Ruben Villegas, Kalyan Sunkavalli, Eli Shechtman...
TL;DR
本文提出了一种新颖的动作序列生成方法MT-VAE,它可以利用动作序列之间的转换关系,学习运动方式的特征嵌入和运动方式之间的特征变换,从而生成多样性且逼真的面部和全身运动,并展示了与类比运动传递和视频合成相关的应用。
Abstract
Long-term human motion can be represented as a series of
motion modes
---motion sequences that capture short-term temporal dynamics---with transitions between them. We leverage this structure and present a novel
motion t
→