SliceMatch: Geometry-Guided Aggregation for Cross-View Pose Estimation

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

1 Downloads (Pure)

Abstract

This work addresses cross-view camera pose estimation, i.e., determining the 3-Degrees-of-Freedom camera pose of a given ground-level image w.r.t. an aerial image of the local area. We propose SliceMatch, which consists of ground and aerial feature extractors, feature aggregators, and a pose predictor. The feature extractors extract dense features from the ground and aerial images. Given a set of candidate camera poses, the feature aggregators construct a single ground descriptor and a set of pose-dependent aerial descriptors. Notably, our novel aerial feature aggregator has a cross-view attention module for ground-view guided aerial feature selection and utilizes the geometric projection of the ground camera's viewing frustum on the aerial image to pool features. The efficient construction of aerial descriptors is achieved using precomputed masks. SliceMatch is trained using contrastive learning and pose estimation is formulated as a similarity comparison between the ground descriptor and the aerial descriptors. Compared to the state-of-the-art, SliceMatch achieves a 19% lower median localization error on the VIGOR benchmark using the same VGG16 backbone at 150 frames per second, and a 50% lower error when using a ResNet50 backbone.
Original languageEnglish
Title of host publicationProceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
EditorsLisa O'Conner
Place of PublicationPiscataway
PublisherIEEE
Pages17225-17234
ISBN (Electronic)979-8-3503-0129-8
ISBN (Print)979-8-3503-0130-4
DOIs
Publication statusPublished - 2023
Event2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) - Vancouver, Canada
Duration: 17 Jun 202324 Jun 2023

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2023-June
ISSN (Print)1063-6919

Conference

Conference2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Country/TerritoryCanada
CityVancouver
Period17/06/2324/06/23

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Fingerprint

Dive into the research topics of 'SliceMatch: Geometry-Guided Aggregation for Cross-View Pose Estimation'. Together they form a unique fingerprint.

Cite this