论文标题
对象很重要：学习对象关系图的可靠摄像头重新定位
Objects Matter: Learning Object Relation Graph for Robust Camera Relocalization
论文作者
论文摘要
视觉重新定位旨在估算一个或多个图像的相机姿势。近年来，基于深度学习的姿势回归方法吸引了许多关注。它们功能可以预测绝对姿势，而无需依赖任何先前的构建地图或存储的图像，从而使重新定位非常有效。但是，在具有复杂外观变化和真实动态的环境下，稳健的重新定位仍然非常具有挑战性。在本文中，我们建议通过提取物体之间的深层关系来增强图像特征的独特性。特别是，我们在图像中提取对象，并构造一个深对象关系图（org），以结合对象的语义连接和相对空间线索。我们将组织模块整合到几个流行的姿势回归模型中。对各种公共室内和室外数据集进行的广泛实验表明，我们的方法可显着提高性能，并优于先前的方法。
Visual relocalization aims to estimate the pose of a camera from one or more images. In recent years deep learning based pose regression methods have attracted many attentions. They feature predicting the absolute poses without relying on any prior built maps or stored images, making the relocalization very efficient. However, robust relocalization under environments with complex appearance changes and real dynamics remains very challenging. In this paper, we propose to enhance the distinctiveness of the image features by extracting the deep relationship among objects. In particular, we extract objects in the image and construct a deep object relation graph (ORG) to incorporate the semantic connections and relative spatial clues of the objects. We integrate our ORG module into several popular pose regression models. Extensive experiments on various public indoor and outdoor datasets demonstrate that our method improves the performance significantly and outperforms the previous approaches.
