SANet: Scene Agnostic Network for Camera Localization

Luwei Yang, Ziqian Bai, Chengzhou Tang, Honghua Li, Yasutaka Furukawa, Ping Tan; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 42-51

Abstract


This paper presents a scene agnostic neural architecture for camera localization, where model parameters and scenes are independent from each other.Despite recent advancement in learning based methods, most approaches require training for each scene one by one, not applicable for online applications such as SLAM and robotic navigation, where a model must be built on-the-fly.Our approach learns to build a hierarchical scene representation and predicts a dense scene coordinate map of a query RGB image on-the-fly given an arbitrary scene. The 6D camera pose of the query image can be estimated with the predicted scene coordinate map. Additionally, the dense prediction can be used for other online robotic and AR applications such as obstacle avoidance. We demonstrate the effectiveness and efficiency of our method on both indoor and outdoor benchmarks, achieving state-of-the-art performance.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Yang_2019_ICCV,
author = {Yang, Luwei and Bai, Ziqian and Tang, Chengzhou and Li, Honghua and Furukawa, Yasutaka and Tan, Ping},
title = {SANet: Scene Agnostic Network for Camera Localization},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}