Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video
TCMR_RELEASE
This repository is the official Pytorch implementation of Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video. The base codes are largely borrowed from VIBE.
Qualtitative result
Paper teaser video
Installation
TCMR is tested on Ubuntu 16.04 with Pytorch 1.4 and Python 3.7.10. You may need sudo privilege for the installation.
source scripts/install_pip.sh
Quick demo
-
Download the pre-trained demo TCMR and required data by below command and download SMPL layers from here (male&female) and here (neutral). Put SMPL layers (pkl files) under
${ROOT}/data/base_data/.source scripts/get_base_data.sh
-
Run demo with options (e.g. render on plain background). See more option details in bottom lines of
demo.py.