BriefGPT.xyz
Apr, 2015
从短序列预测人体 3D 姿势
Predicting People's 3D Poses from Short Sequences
HTML
PDF
Bugra Tekin, Xiaolu Sun, Xinchao Wang, Vincent Lepetit, Pascal Fua
TL;DR
本文介绍一种利用视频序列中连续帧的运动信息来恢复人体3D姿态的高效方法，直接从时空块回归到中间帧的3D姿态，克服了模糊和提升了现有方法的性能。
Abstract
We propose an efficient approach to exploiting
motion information
from consecutive frames of a
video sequence
to recover the
3d pose
of pe
→