Perceiving Systems, Computer Vision

VIBE: Video Inference for Human Body Pose and Shape Estimation

2020-02-27


VIBE is a neural network method that takes video of a human in motion as input and outputs the 3D pose and shape of the body in every frame. The output is in SMPL body format and represents the state of the art at time of release. The method runs quickly and can process arbitrary sequence lengths. The trained model is available now and training code will be provided later.

VIBE is a neural network method that takes video of a human in motion as input and outputs the 3D pose and shape of the body in every frame. The output is in SMPL body format and represents the state of the art at time of release. The method runs quickly and can process arbitrary sequence lengths. The trained model is available now and training code will be provided later.

Author(s): Muhammed Kocabas and Nikos Athanasiou and Michael J. Black
Department(s): Perceiving Systems
Publication(s): {VIBE}: Video Inference for Human Body Pose and Shape Estimation
Authors: Muhammed Kocabas and Nikos Athanasiou and Michael J. Black
Release Date: 2020-02-27
Repository: https://github.com/mkocabas/VIBE