Papers › SliceMatch: Geometry-guided Aggregation for Cross-View Pose Estimation

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

26 Nov 2022CVPR 2023 1arXiv:2211.14651archive 2025-07-28

Ted Lentsch, Zimin Xia, Holger Caesar, Julian F. P. Kooij

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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

tudelft-iv/slicematch officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Camera Pose EstimationContrastive LearningPose EstimationVisual Localizationfeature selection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Contrastive LearningFeature Selection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections