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.
翻译:清除阴影是一项计算机任务,目的是恢复影子地区的图像内容。 虽然几乎所有最近的清除影子方法都需要无影子图像的培训,但在ECCV 2020 Le和Samaras 中,几乎所有最近的清除影子方法都需要无影子图像的培训,但在ECCV 2020 Le 和 Samaras 中,引入了一种创新方法,通过将影子图像的粉状补底补底补底补底补底补底,作为培训样本,而无需这样做。然而,建造大量此类未涂底补底补底补底补底的工作仍然费时费力。在本文中,我们提议建立一个新的G2R-Shadow Net, 将影子生成的阴影生成用于弱色素解底补底补底补底, 仅使用一套影子图像及其相应的影子遮掩面罩进行培训。 拟议的G2R-Shadow Net 由三个子网络组成,分别用于产生影子生成、消除和完善的影子图层补底补底补底补底补底补底补底补底。 特别是, 影子生成的子网的非阴影网区, 将匹配数据配对培训。