We propose a novel DNN for 3D point set segmentation called Rotation-invariant and Multi-scale feature Graph convolutional neural network, or RMGnet. Our RMGnet is more flexible than the previous ...

In the field of 3D face alignment, most researchers have focused on improving the prediction accuracy of algorithms and ignored the portability for practical applications. To this end, this study ...

scikit-kinematics primarily contains functions for working with 3D kinematics, e.g quaternions and rotation matrices. This includes utilities to read in data from the following IMU-sensors: - polulu - ...