# Unsupervised Shadow Removal Using Target Consistency Generative Adversarial Network

arXiv: https://arxiv.org/abs/2010.01291 · HTML: https://mlsanity.com/paper/2010.01291/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Oct 2020.

## Built on by (most cited first, 5 of 5)

- [Memory augment is All You Need for image restoration](https://mlsanity.com/paper/2309.01377/) (2023)
- [SpA-Former: Transformer image shadow detection and removal via spatial attention](https://mlsanity.com/paper/2206.10910/) (2022)
- [SAM-helps-Shadow:When Segment Anything Model meet shadow removal](https://mlsanity.com/paper/2306.06113/) (2023)
- [Deshadow-Anything: When Segment Anything Model Meets Zero-shot shadow removal](https://mlsanity.com/paper/2309.11715/) (2023)
- [DocShaDiffusion: Diffusion Model in Latent Space for Document Image Shadow Removal](https://mlsanity.com/paper/2507.01422/) (2025)

## Abstract (arXiv)

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.