Removing Hair from Portraits Using GANs

CVPR 2022
1State Key Lab of CAD&CG, Zhejiang University, 2ZJU-Tencent Game and Intelligent Graphics InnovationTechnology Joint Lab, 3University of Bath

Given portrait images with their faces partially occluded by hair, our method is able to generate portraits without hair while preserving facial identity. After removing the effects of hair, the resulting portrait images can be well employed in hair design by simply blending the clean face with some hairstyle templates without the interference from existing hair. Our results can also benefit 3D face reconstruction by using the clean face textures generated by our method (rows 2 and 4) in contrast to the results of the original images (rows 1 and 3).


Removing hair from portrait images is challenging due to the complex occlusions between hair and face, as well as the lack of paired portrait data with/without hair.

To this end, we present a dataset and a baseline method for removing hair from portrait images using generative adversarial networks (GANs). Our core idea is to train a fully connected network $HairMapper$ to find the direction of hair removal in the latent space of StyleGAN for the training stage. We develop a new separation boundary and diffuse method to generate paired training data for males, and a novel ''female-male-bald'' pipeline for paired data of females.

Experiments show that our method can naturally deal with portrait images with variations on gender, age, etc. We validate the superior performance of our method by comparing it to state-of-the-art methods through extensive experiments and user studies. We also demonstrate its applications in hair design and 3D face reconstruction.



The pipeline of our HairMapper.



    author    = {Wu, Yiqian and Yang, Yong-Liang and Jin, Xiaogang},
    title     = {HairMapper: Removing Hair From Portraits Using GANs},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2022},
    pages     = {4227-4236}