arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.12997cs.CV
收藏

从阴影生成到阴影消除

From Shadow Generation to Shadow Removal

Beijing Jiaotong University(北京交通大学);University of South Carolina(南卡罗来纳大学);China Agriculture University(中国农业大学)

Zhihao Liu, Hui Yin, Xinyi Wu, Zhenyao Wu, Yang Mi, Song Wang

摘要:

阴影去除是一项计算机视觉任务,旨在恢复阴影区域中的图像内容。虽然几乎所有最近的阴影去除方法都需要无阴影图像进行训练,但在ECCV 2020中,Le和Samaras引入了一种创新方法,通过裁剪阴影图像中有阴影和没有阴影的补丁作为训练样本,而没有这种要求。然而,它仍然是费力和耗时的,以构建大量的这种不成对的补丁。在本文中,我们提出了一种新的G2 R-ShadowNet,它利用阴影生成进行弱监督阴影去除,只使用一组阴影图像及其相应的阴影掩模进行训练。建议的G2 R-ShadowNet由三个子网络组成,分别用于阴影生成,阴影消除和细化,它们以端到端的方式联合训练。特别地,阴影生成子网将非阴影区域风格化为阴影区域,从而产生用于训练阴影去除子网的配对数据。在ISTD数据集和Video Shadow Removal数据集上的大量实验表明,所提出的G2 R-ShadowNet实现了与当前技术水平相比具有竞争力的性能,并且优于Le和Samaras的基于补丁的阴影去除方法。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑