3D Human Pose Estimation

This post is linked to my research for my VR Person Project.

What is 3D Human Pose Estimation?

3D Human Pose Estimation is the task of estimating the pose of a human from a picture or set of video frames.

PapersWithCode

Its usually done through three ways:

• Model-based generative methods
  • Pictorial Structure Model (PSM)
  • Deep Learning
• Discriminative methods (regression)

There are 3D models generated directly from RGB images and 3D models generated with the aid of 2D Human Pose Estimation.

Read this article for more info.

Approaches

TODO: Paper summaries

Libraries

There are existing github libraries that already implement the 3D Human Pose Estimation I need: I’m mainly looking at DensePose Github, V-Nect Github and VideoPose3D.

References

• Summary Article – It’s a really clear intro article