Abstract
The current paradigm in privacy protection in street-view images is to detect and blur sensitive information. In this paper, we propose a framework that is an alternative to blurring, which automatically removes and inpaints moving objects (e.g. pedestrians, vehicles) in street-view imagery. We propose a novel moving object segmentation algorithm exploiting consistencies in depth across multiple street-view images that are later combined with the results of a segmentation network. The detected moving objects are removed and inpainted with information from other views, to obtain a realistic output image such that the moving object is not visible anymore. We evaluate our results on a dataset of 1000 images to obtain a peak noise-to-signal ratio (PSNR) and L1 loss of 27.2 dB and 2.5%, respectively. To ensure the subjective quality, To assess overall quality, we also report the results of a survey conducted on 35 professionals, asked to visually inspect the images whether object removal and inpainting had taken place. The inpainting dataset will be made publicly available for scientific benchmarking purposes at https://research.cyclomedia.com
Abstract (translated)
当前街景图像隐私保护的模式是检测和模糊敏感信息。在本文中，我们提出了一种替代模糊的框架，该框架可以自动删除和修复街景图像中的移动对象（如行人、车辆）。我们提出了一种新的移动物体分割算法，该算法利用多个街景图像的深度一致性，然后结合分割网络的结果进行分割。将检测到的运动对象移除并用其他视图中的信息进行绘制，以获得真实的输出图像，从而使运动对象不再可见。我们在1000张图像的数据集上评估我们的结果，以获得分别为27.2db和2.5%的峰值信噪比（psnr）和l1损失。为了确保主观质量，为了评估整体质量，我们还报告了对35名专业人员进行的调查结果，要求对图像进行目视检查，看是否有物体移除和修复发生。Inpainting数据集将在https://research.cyclomedia.com上公开用于科学基准测试。
URL
https://arxiv.org/abs/1903.11532
