论文标题
自我监督的阴影去除
Self-Supervised Shadow Removal
论文作者
论文摘要
阴影去除是一项重要的计算机视觉任务，旨在检测和成功删除由遮挡的光源和图像内容的光真实恢复所产生的阴影。数十年的重新搜索产生了多种手工制作的修复技术，最近，从Shad-outed and Tovel的训练图对中学习了解决方案。在这项工作中，我们通过使用条件性掩码提出了一种无监督的单图像去除解决方案，通过自我监督的学习解决方案。与现有文献相反，我们不需要成对的阴影和无阴影图像，而是依靠自upervision，并共同学习深层模型以删除和添加阴影。我们在最近引入的ISTD和USR数据集上验证了我们的方法。在比较的方法上，我们在很大程度上进行了定量和质量上的改进，并在单像阴影去除中设定了新的最新性能。
Shadow removal is an important computer vision task aiming at the detection and successful removal of the shadow produced by an occluded light source and a photo-realistic restoration of the image contents. Decades of re-search produced a multitude of hand-crafted restoration techniques and, more recently, learned solutions from shad-owed and shadow-free training image pairs. In this work,we propose an unsupervised single image shadow removal solution via self-supervised learning by using a conditioned mask. In contrast to existing literature, we do not require paired shadowed and shadow-free images, instead we rely on self-supervision and jointly learn deep models to remove and add shadows to images. We validate our approach on the recently introduced ISTD and USR datasets. We largely improve quantitatively and qualitatively over the compared methods and set a new state-of-the-art performance in single image shadow removal.
