Perceiving Systems, Computer Vision

HMR: End-to-end Recovery of Human Shape and Pose

2018-03-30


Trained model to estimate 3D human shape and pose directly from an image. The input is pixels, and the output is a 3D body in SMPL format (shape parameters and pose parameters). Also provided is the code and data needed to train the model.

Author(s): Angjoo Kanazawa and Michael J Black and David W. Jacobs and Jitendra Malik
Department(s): Perceiving Systems
Publication(s): End-to-end Recovery of Human Shape and Pose
Authors: Angjoo Kanazawa and Michael J Black and David W. Jacobs and Jitendra Malik
Release Date: 2018-03-30
Repository: https://github.com/akanazawa/hmr
External Link: https://akanazawa.github.io/hmr/