English

Unsupervised Shadow Removal Using Target Consistency Generative Adversarial Network

Computer Vision and Pattern Recognition 2021-06-01 v2 Image and Video Processing

Abstract

Unsupervised shadow removal aims to learn a non-linear function to map the original image from shadow domain to non-shadow domain in the absence of paired shadow and non-shadow data. In this paper, we develop a simple yet efficient target-consistency generative adversarial network (TC-GAN) for the shadow removal task in the unsupervised manner. Compared with the bidirectional mapping in cycle-consistency GAN based methods for shadow removal, TC-GAN tries to learn a one-sided mapping to cast shadow images into shadow-free ones. With the proposed target-consistency constraint, the correlations between shadow images and the output shadow-free image are strictly confined. Extensive comparison experiments results show that TC-GAN outperforms the state-of-the-art unsupervised shadow removal methods by 14.9% in terms of FID and 31.5% in terms of KID. It is rather remarkable that TC-GAN achieves comparable performance with supervised shadow removal methods.

Keywords

Cite

@article{arxiv.2010.01291,
  title  = {Unsupervised Shadow Removal Using Target Consistency Generative Adversarial Network},
  author = {Chao Tan and Xin Feng},
  journal= {arXiv preprint arXiv:2010.01291},
  year   = {2021}
}
R2 v1 2026-06-23T18:59:38.728Z