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
Python Just Overtook Java On GitHub
Quantum Supremacy & AI
Quantum Supremacy & AI
How to Switch an Existing Azure SQL Database from Provisioned Compute to Serverless
New Face Swapping AI Creates Amazing DeepFakes