Home

Awesome

FFHQ-UV

FFHQ-UV: Normalized Facial UV-Texture Dataset for 3D Face Reconstruction

By Haoran Bai, Di Kang, Haoxian Zhang, Jinshan Pan, and Linchao Bao
In CVPR 2023 [Paper: https://arxiv.org/abs/2211.13874]
Rendering demos [YouTube video]

teaser

FFHQ-UV is a large-scale facial UV-texture dataset that contains over 50,000 high-quality texture UV-maps with even illuminations, neutral expressions, and cleaned facial regions, which are desired characteristics for rendering realistic 3D face models under different lighting conditions.

The dataset is derived from a large-scale face image dataset namely FFHQ, with the help of our fully automatic and robust UV-texture production pipeline. Our pipeline utilizes the recent advances in StyleGAN-based facial image editing approaches to generate multi-view normalized face images from single-image inputs. An elaborated UV-texture extraction, correction, and completion procedure is then applied to produce high-quality UV-maps from the normalized face images. Compared with existing UV-texture datasets, our dataset has more diverse and higher-quality texture maps.

Updates

[2023-07-11] A solution for using our UV-texture maps on a FLAME mesh is available [here].
[2023-07-10] A more detailed description and a new version of the RGB fitting process is available [here].
[2023-07-10] A more detailed description of the facial UV-texture dataset creation pipeline is available [here].
[2023-03-17] The source codes for adding eyeballs into head mesh are available [here].
[2023-03-16] The project details of the FFHQ-UV dataset creation pipeline are released [here].
[2023-03-16] The OneDrive download link was updated and the file structures have been reorganized.
[2023-02-28] This paper will appear in CVPR 2023.
[2023-01-19] The source codes are available, refer to [here] for quickly running.
[2022-12-16] The OneDrive download link is available.
[2022-12-16] The AWS CloudFront download link is offline.
[2022-12-06] The script for generating face images from latent codes is available.
[2022-12-02] The latent codes of the multi-view normalized face images are available.
[2022-12-02] The FFHQ-UV-Interpolate dataset is available.
[2022-12-01] The FFHQ-UV dataset is available [here].
[2022-11-28] The paper is available [here].

Dependencies

mkdir thirdparty
cd thirdparty
git clone https://github.com/facebookresearch/iopath
git clone https://github.com/facebookresearch/fvcore
git clone https://github.com/facebookresearch/pytorch3d
git clone https://github.com/NVlabs/nvdiffrast
conda install -c bottler nvidiacub
pip install -e iopath
pip install -e fvcore
pip install -e pytorch3d
pip install -e nvdiffrast

Get dataset

Run source codes

Download checkpoints and topology assets

Create FFHQ-UV dataset

RGB fitting

Add eyeballs into head mesh

sh run_mesh_add_eyeball.sh  # Please refer to this script for detailed configuration

Generate a UV-texture map from a single facial image

There are two ways to generate a UV-texture map from a given facial image:

  1. Facial editing + texture unwrapping (Section 3.1 of the paper)
  2. RGB fitting (Section 4.2 of the paper)

1. UV-texture map from: facial editing + texture unwrapping

2. UV-texture map from: RGB fitting

Using our UV-texture maps on a FLAME mesh

Citation

@InProceedings{Bai_2023_CVPR,
  title={FFHQ-UV: Normalized Facial UV-Texture Dataset for 3D Face Reconstruction},
  author={Bai, Haoran and Kang, Di and Zhang, Haoxian and Pan, Jinshan and Bao, Linchao},
  booktitle={IEEE Conference on Computer Vision and Pattern Recognition},
  month={June},
  year={2023}
}

Acknowledgments

This implementation builds upon the awesome works done by Tov et al. (e4e), Zhou et al. (DPR), Abdal et al. (StyleFlow), and Karras et al. (StyleGAN2, StyleGAN2-ADA-PyTorch, FFHQ).

This work is based on HiFi3D++ topology, and was supported by Tencent AI Lab.