Abstract
Occlusion removal is an interesting application of image enhancement, for which, existing work suggests manually-annotated or domain-specific occlusion removal. No work tries to address automatic occlusion detection and removal as a context-aware generic problem. In this paper, we present a novel methodology to identify objects that do not relate to the image context as occlusions and remove them, reconstructing the space occupied coherently. The proposed system detects occlusions by considering the relation between foreground and background object classes represented as vector embeddings, and removes them through inpainting. We test our system on COCO-Stuff dataset and conduct a user study to establish a baseline in context-aware automatic occlusion removal.
Abstract (translated)
遮挡移除是图像增强的一个有趣的应用,对于它,现有的工作建议手动注释或特定于域的遮挡移除。没有工作试图解决自动闭塞检测和删除作为上下文感知的一般问题。在本文中,我们提出了一种新的方法来识别与图像背景无关的物体作为遮挡物,并将其移除,从而重建连贯占用的空间。该系统通过考虑前景对象类和背景对象类之间的关系来检测遮挡,并通过内画消除遮挡。我们在coco-stuff数据集上测试我们的系统,并进行用户研究,以在上下文感知的自动闭塞消除中建立基线。
URL
https://arxiv.org/abs/1905.02710