BriefGPT.xyz
Aug, 2016
使用三维卷积神经网络实现时空人体姿态估计
Human Pose Estimation in Space and Time using 3D CNN
HTML
PDF
Agne Grinciunaite, Amogh Gudi, Emrah Tasli, Marten den Uyl
TL;DR
本研究探讨了卷积神经网络在处理单目视觉下3D人体姿态感知任务方面的能力，通过将时间维度编码在卷积空间中的第三个维度，直接回归到3D坐标空间中的人体关节位置，从而在选定的Human3.6M数据集上展示了该网络达到了最先进的性能。
Abstract
This paper explores the capabilities of
convolutional neural networks
to deal with a task that is easily manageable for humans: perceiving
3d pose
of a human body from varying angles. However, in our approach, we
→