English

Unsupervised Portrait Shadow Removal via Generative Priors

Computer Vision and Pattern Recognition 2021-08-10 v1

Abstract

Portrait images often suffer from undesirable shadows cast by casual objects or even the face itself. While existing methods for portrait shadow removal require training on a large-scale synthetic dataset, we propose the first unsupervised method for portrait shadow removal without any training data. Our key idea is to leverage the generative facial priors embedded in the off-the-shelf pretrained StyleGAN2. To achieve this, we formulate the shadow removal task as a layer decomposition problem: a shadowed portrait image is constructed by the blending of a shadow image and a shadow-free image. We propose an effective progressive optimization algorithm to learn the decomposition process. Our approach can also be extended to portrait tattoo removal and watermark removal. Qualitative and quantitative experiments on a real-world portrait shadow dataset demonstrate that our approach achieves comparable performance with supervised shadow removal methods. Our source code is available at https://github.com/YingqingHe/Shadow-Removal-via-Generative-Priors.

Keywords

Cite

@article{arxiv.2108.03466,
  title  = {Unsupervised Portrait Shadow Removal via Generative Priors},
  author = {Yingqing He and Yazhou Xing and Tianjia Zhang and Qifeng Chen},
  journal= {arXiv preprint arXiv:2108.03466},
  year   = {2021}
}

Comments

Accepted to ACM MM 2021 (Oral). Code is available at: https://github.com/YingqingHe/Shadow-Removal-via-Generative-Priors

R2 v1 2026-06-24T04:54:45.369Z