AI Paper Atlas

Research map / 3D vision / Depth and stereo

Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching

Yujiao Shi, Xin Yu, Liu Liu, Dylan Campbell, Piotr Koniusz, Hongdong Li

TPAMI 2022 · 3D vision › Depth and stereo · approach: Scene coordinate regression for localization · 60 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the projective transform branch to the polar-only pipeline (ablation)coarse localization · CVUSA FoV=180 orientation unknownr@1: 48.53 -> 54.27Improved
add the projective transform branch (ablation)coarse localization · CVACT_val FoV=180 orientation unknownr@1: 49.12 -> 52.98Improved
add the projective transform branch (ablation)coarse localization · CVUSA FoV=90 orientation unknownr@1: 16.19 -> 11.30Hurt
add the projective transform branch (ablation)coarse localization · CVACT_val FoV=70 orientation unknownr@1: 8.29 -> 4.60Hurt
add the polar transform branch (ablation)coarse localization · CVUSA FoV=360 orientation unknownr@1: 65.33 -> 78.94Improved
add the polar transform branch (ablation)coarse localization · CVACT_val FoV=180 orientation unknownr@1: 27.95 -> 52.98Improved
use both polar and projective transforms for orientation estimation instead of projective only (ablation)orientation estimation · CVUSA FoV=180r@1: 52.00 -> 54.27Improved
use both transforms for orientation estimation instead of polar only (ablation)orientation estimation · CVUSA FoV=180r@1: 53.88 -> 54.27Improved
align orientation only to the matching satellite image instead of the whole database (ablation)DSM orientation alignment · CVUSA FoV=180r@1: 54.27 -> 79.44Improved
remove orientation augmentation knowledge: unknown orientation versus alignedOurs · CVUSA FoV=180r@1: 75.65 -> 54.27Hurt
replace SAFA spatial-aware modules with new projective geometry (this work vs SAFA)Ours · CVACT_testtop-1 recall: 55.50% -> 60.46%Improved
random orientation augmentation in trainingCVFT and SAFA · CVUSA FoV=360r@1: 61.43 -> 23.13 (CVFT); 89.84 -> 53.33 (SAFA)Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy