.png){kind=icon}
.png){kind=icon}
Return
Objects matter: Learning object relation graph for robust absolute pose regression
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2022.11.090.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Visual relocalization aims to estimate the pose of a camera from one or more images. In recent years deep learning-based absolute pose regression (APR) 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 APR models. Extensive experiments on various public indoor and outdoor datasets demonstrate that our ORG module greatly enhances the robustness of image representation to environmental changes and improves the pose regression performance. The code is available at https://github.com/qcyay/ORGMapNet. (c) 2022 Elsevier B.V. All rights reserved.
Keywords:
Absolute pose regression
Object relation graph
Graph neural networks