Shadow removal is a computer-vision task that aims to restore the image
content in shadow regions. While almost all recent shadow-removal methods
require shadow-free images for training, in ECCV 2020 Le and Samaras introduces
an innovative approach without this requirement by cropping patches with and
without shadows from shadow images as training samples. However, it is still
laborious and time-consuming to construct a large amount of such unpaired
patches. In this paper, we propose a new G2R-ShadowNet which leverages shadow
generation for weakly-supervised shadow removal by only using a set of shadow
images and their corresponding shadow masks for training. The proposed
G2R-ShadowNet consists of three sub-networks for shadow generation, shadow
removal and refinement, respectively and they are jointly trained in an
end-to-end fashion. In particular, the shadow generation sub-net stylises
non-shadow regions to be shadow ones, leading to paired data for training the
shadow-removal sub-net. Extensive experiments on the ISTD dataset and the Video
Shadow Removal dataset show that the proposed G2R-ShadowNet achieves
competitive performances against the current state of the arts and outperforms
Le and Samaras' patch-based shadow-removal method.

本文提出了一种新的 G2R-ShadowNet 方法，通过使用一组阴影图像及其相应的阴影掩模进行训练，利用阴影生成进行弱监督阴影去除。此方法包含三个子网络，分别为阴影生成、阴影去除和细化，共同以端到端的方式进行训练，通过广泛的实验表明，这种方法在 ISTD 数据集和 Video Shadow Removal 数据集上取得了竞争性结果，并且优于以往方法。