Update in October 2019:

DensePose has been re-implemented with the brand-new object detection framework Detectron2, which is based on PyTorch and much easier to install and use (You don't have to manually compile Caffe2)
I strongly recommend that you check out the new official DensePose code at https://github.com/facebookresearch/detectron2/tree/master/projects/DensePose.



DensePose is a great work in real-time human pose estimation, which is based on Caffe2 and Detectron framework. It extracts dense human body 3D surface based on RGB images. The installation instructions are provided here.

During my installation process, these are the problems that took me some time to tackle. I spent on week to finally figure out solutions to all the issues. So lucky of me not to give up too early...


Greetings from Facebook AI Research

Read More