V2V-PoseNet
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand andHuman Pose Estimation from a Single Depth Map2018--CVPR 作者：JY Chang，G Moon，KM LeeFig.1V2V-PoseNet. Each feature map without Z-axis and combined the 3D heatmaps of all keypoints...
