BriefGPT.xyz
May, 2019
2D动作重定向中的跨字符动作学习
Learning Character-Agnostic Motion for Motion Retargeting in 2D
HTML
PDF
Kfir Aberman, Rundi Wu, Dani Lischinski, Baoquan Chen, Daniel Cohen-Or
TL;DR
本文提出了一种新的方法,通过使用神经网络从视频中提取人体运动的高级潜在表示的方法,实现了不需要显式重建三维姿态和/或相机参数的不同人类表演者之间的视频捕获运动的再定向。
Abstract
Analyzing
human motion
is a challenging task with a wide variety of applications in computer vision and in graphics. One such application, of particular importance in computer animation, is the
retargeting
of mot
→