Two Minute Papers has a look at the paper “3D Human Pose Machines with Self-supervised Learning” in his latest video. This topic actually came up in a meeting on Friday. 
Two Minute Papers has posted a video exploring the paper “A Variational U-Net for Conditional Appearance and Shape Generation”
In this video, Siraj Raval talks about the technology behind Human Pose Estimation. This technology can, among other things, convert humans depicted in video to 3D models.
Think of what this means for motion capture.
Comments
Top 5 Programming Languages and their Libraries for Machine Learning in 2020
Why You Should be Using Jupyter Notebooks
TensorFlow 2.0 Tutorial – Part 1
A Complete Roadmap to Web Development in 2020
A Dark Matter Hunter Is Built With Quantum Computer Parts