Paper Info
Title
Is This The Right Place? Geometric-Semantic Pose Verification For Indoor Visual Localization
Abstract
Visual localization in large and complex indoor scenes, dominated by weakly textured rooms and repeating geometric patterns, is a challenging problem with high practical relevance for applications such as Augmented Reality and robotics. To handle the ambiguities arising in this scenario, a common strategy is, first, to generate multiple estimates for the camera pose from which a given query image was taken. The pose with the largest geometric consistency with the query image, e.g., in the form of an inlier count, is then selected in a second stage. While a significant amount of research has concentrated on the first stage, there has been considerably less work on the second stage. In this paper, we thus focus on pose verification. We show that combining different modalities, namely appearance, geometry, and semantics, considerably boosts pose verification and consequently pose accuracy. We develop multiple hand-crafted as well as a trainable approach to join into the geometric-semantic verification and show significant improvements over state-of-the-art on a very challenging indoor dataset.
Year
DOI
Venue
2019
10.1109/ICCV.2019.00447
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)
DocType
Volume
Issue
Conference
2019
1
ISSN
Citations 
PageRank 
1550-5499
2
0.38
References 
Authors
15
8
Name
Order
Citations
PageRank
hajime taira1182.69
Ignacio Rocco2562.51
Jirí Sedlár320.72
M. Okutomi4714120.94
Josef Sivic59653513.44
S PAJDLA631621.89
Torsten Sattler770434.68
Akihiko Torii843626.93