KupynOrest / head_detector

Official repo for VGGHeads: A Large-Scale Synthetic Dataset for 3D Human Heads.

VGGHeads: A Large-Scale Synthetic Dataset for 3D Human Heads

Orest Kupyn¹³ · Eugene Khvedchenia² · Christian Rupprecht¹ ·

¹University of Oxford · ²Ukrainian Catholic University · ³PiñataFarms AI

VGGHeads is a large-scale fully synthetic dataset for human head detection and 3D mesh estimation with over 1 million images generated with diffusion models. A model trained only on synthetic data generalizes well to real-world and is capable of simultaneous heads detection and head meshes reconstruction from a single image in a single step.

Installation

Create a Conda virtual environment:

conda create --name vgg_heads python=3.10
conda activate vgg_heads

Clone the project and install the package:

git clone https://github.com/KupynOrest/head_detector.git
cd head_detector

pip install -e ./

Or simply install

pip install git+https://github.com/KupynOrest/head_detector.git

Usage

To test VGGHeads model on your own images simply use this code:

  from head_detector import HeadDetector

  detector = HeadDetector()
  image_path = "your_image.jpg"
  predictions = detector(image_path)
  # predictions.heads contain a list of heads with .bbox, .vertices_3d, .head_pose params
  predictions.draw() # draw heads on the image

Training

Coming soon

Release

• [2024/07/26] 🔥 We release the initial version of the codebase, the paper, project webpage and an image demo!!

Cite

If you find VGGHeads useful for your research and applications, please cite us using this BibTeX:

@article{vggheads,
      title={VGGHeads: A Large-Scale Synthetic Dataset for 3D Human Heads},
      author={Orest Kupyn and Eugene Khvedchenia and Christian Rupprecht},
      year={2024},
      eprint={2407.18245},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2407.18245},
}

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.