A large-scale face dataset for face parsing, recognition, generation and editing.
CelebAMask-HQ is a large-scale face image dataset that has 30,000 high-resolution face images selected from the CelebA dataset by following CelebA-HQ. Each image has segmentation mask of facial attributes corresponding to CelebA.
The masks of CelebAMask-HQ were manually-annotated with the size of 512 x 512 and 19 classes including all facial components and accessories such as skin, nose, eyes, eyebrows, ears, mouth, lip, hair, hat, eyeglass, earring, necklace, neck, and cloth.
CelebAMask-HQ can be used to train and evaluate algorithms of face parsing, face recognition, and GANs for face generation and editing.
If you need the identity labels and the attribute labels of the images, please send request to the CelebA team.
Demo of interactive facial image manipulation
CelebAMask-HQ can be used on several research fields including: facial image manipulation, face parsing, face recognition, and face hallucination. We showcase an application on interactive facial image manipulation as bellow:
The use of this software is RESTRICTED to non-commercial research and educational purposes.
@inproceedings{CelebAMask-HQ,
title={MaskGAN: Towards Diverse and Interactive Facial Image Manipulation},
author={Lee, Cheng-Han and Liu, Ziwei and Wu, Lingyun and Luo, Ping},
booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2020}
}