BriefGPT.xyz
Apr, 2017
Hand3D：使用3D神经网络进行手部姿态估计
Hand3D: Hand Pose Estimation using 3D Neural Network
HTML
PDF
Xiaoming Deng, Shuo Yang, Yinda Zhang, Ping Tan, Liang Chang...
TL;DR
使用新的3D神经网络架构，通过深度图到三维体积表示的转化，直接对手的三维姿态进行估计，无需进一步处理。同时通过合成深度图来增加训练数据覆盖率，在公开数据上达到了最优性能。
Abstract
We propose a novel
3d neural network
architecture for 3D
hand pose estimation
from a single depth image. Different from previous works that mostly run on 2D depth image domain and require intermediate or post pro
→