For questions about the code, please make sure to check the FAQs before contacting us.
Code, data and results for "Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image"
We provide a Python demo code including the neutral SMPL and other models required to run them.
For all the dataset we used (LSP, HumanEva-I, Human3.6M) we provide the detected joints and our results as the SMPL parameters and the mesh parameters (vertices and faces). Our code package includes an example script showing how to load results. Please see the README in the code package.
OS X, Linux
Please login or sign up to be able to access SMPLify downloads.