Skip to main content

SANet: Scene agnostic network for camera localization

Resource type
Thesis type
(Thesis) M.Sc.
Date created
2021-03-04
Authors/Contributors
Author: Bai, Ziqian
Abstract
This thesis 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 with scene coordinate regression, 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 6 DoF 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 among methods working for arbitrary scenes without retraining or adaptation.
Document
Identifier
etd21281
Copyright statement
Copyright is held by the author(s).
Permissions
This thesis may be printed or downloaded for non-commercial research and scholarly purposes.
Supervisor or Senior Supervisor
Thesis advisor: Tan, Ping
Language
English
Member of collection
Download file Size
input_data\21197\etd21281.pdf 10.1 MB

Views & downloads - as of June 2023

Views: 18
Downloads: 0