We present MocapNET, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the ... ... <看更多>

In this work, we demonstrate that 3D poses in video can be effectively estimated with a fully convolutional model based on dilated temporal convolutions over 2D ... ... <看更多>

In this work, we demonstrate that 3D poses in video can be effectively estimated with a fully convolutional model based on dilated temporal convolutions ... ... <看更多>

2D -->2D, 2D-->3D both are not for your application. ICP -> Yes. It's overkill if your data is noiseless. Your problem is called rigid body ... ... <看更多>