Unsupervised Shadow Removal Using Target Consistency Generative Adversarial Network

TL;DR

This paper introduces TC-GAN, an unsupervised generative model that effectively removes shadows from images by learning a one-sided mapping with target consistency, outperforming existing methods and rivaling supervised approaches.

Contribution

The paper proposes a novel target-consistency constraint in a one-sided GAN framework for unsupervised shadow removal, improving performance over prior cycle-consistency methods.

Findings

Outperforms state-of-the-art unsupervised methods by 14.9% in FID

Achieves comparable results to supervised shadow removal methods

Demonstrates effective shadow removal without paired training data

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.