/ Machine Learning

Video Inference for Human Body Pose and Shape Estimation

Video Inference for Human Body Pose and Shape Estimation

VIBE

Official implementation of "VIBE: Video Inference for Human Body Pose and Shape Estimation"

VIBEz

VIBE

Features

Video Inference for Body Pose and Shape Estimation (VIBE) is a video pose and shape estimation method.
It predicts the parameters of SMPL body model for each frame of an input video. Pleaser refer to our arXiv report for further details.

This implementation:

  • is the demo code for VIBE implemented purely in PyTorch,
  • can work on arbitrary videos with multi person,
  • supports both CPU and GPU inference (though GPU is way faster),
  • is fast, up-to 30 FPS on a RTX2080Ti (see this table),
  • achieves SOTA results on 3DPW and MPI-INF-3DHP datasets,
  • includes Temporal SMPLify implementation.

Getting Started

VIBE has been implemented and tested on Ubuntu 18.04 with python >= 3.7. It supports both GPU and CPU inference.
If you don't have a suitable device, try running our Colab demo.

Clone the repo:

git clone https://github.com/mkocabas/VIBE.git

Install the requirements using pip or conda:

# pip
bash install_pip.sh

# conda
bash install_conda.sh

Running the Demo

We have prepared a nice demo code to run VIBE on arbitrary videos.
First, you need download the required data(i.e our trained model and SMPL model parameters). To do this you can just run:

bash prepare_data.sh

Then, running the demo is as simple as this:

# Run on a local video
python demo.py --vid_file sample_video.mp4 --output_folder output/ --display

# Run on a YouTube video
python demo.py --vid_file https://www.youtube.com/watch?v=wPZP8Bwxplo --output_folder output/ --display

Refer to doc/demo.md for more details about the demo code.

Google Colab

If you do not have a suitable environment to run this projects then you could give Google Colab a try.
It allows you to run the project in the cloud, free of charge. You may try our Colab demo using the notebook we prepare:
Open In Colab

Evaluation

Here we compare VIBE with recent state-of-the-art methods on 3D pose estimation datasets. Evaluation metric is
Procrustes Aligned Mean Per Joint Position Error (PA-MPJPE) in mm.

Models 3DPW ↓ MPI-INF-3DHP ↓ H36M ↓
SPIN 59.2 67.5 41.1
Temporal HMR 76.7 89.8 56.8
VIBE 56.5 63.4 41.5
VIBE + 3DPW 51.9 64.6 41.4

Citation

@inproceedings{kocabas2019vibe,
  title={VIBE: Video Inference for Human Body Pose and Shape Estimation},
  author={Kocabas, Muhammed and Athanasiou, Nikos and Black, Michael J.},
  journal={arXiv preprint arXiv:1912.05656},
  year={2019}
}

GitHub