AI Paper Atlas

Research map / 3D vision / Depth and stereo

Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View Transformer

Yujiao Shi, Fei Wu, Akhil Perincherry, Ankit Vora, Hongdong Li

ICCV 2023 · 3D vision › Depth and stereo · approach: Scene coordinate regression for localization · 51 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
replace joint LM optimization with ground-to-satellite synthesis plus neural pose optimizer and dense searchcross-view camera localization · KITTI Test1 with aligned orientationLateral rate d=1 (%): 64.27 -> 93.85Improved
use neural pose optimizer for rotation instead of deep LMdecoupled localization pipeline · KITTI Test1, 20 deg noiseAzimuth rate theta=1 (%): 19.64 -> 99.10Improved
estimate translation with neural optimizer instead of LM (ablation)neural pose optimizer (R & t) · KITTI Test1, 20 deg noiseLateral rate d=1 (%): 27.72 -> 4.90Hurt
replace LM translation with dense search spatial correlation (ablation)Neural Opt. (R) + translation estimator · KITTI Test1, 20 deg noiseLateral rate d=1 (%): 41.82 -> 64.83Improved
add geometry-guided cross-view transformer over geometry projection (ablation)Neural Opt. (R) + DS (t) without uncertainty · KITTI Test1, 20 deg noiseLateral rate d=1 (%): 64.83 -> 70.29Improved
add uncertainty map to spatial correlation (ablation)full method · KITTI Test1, 20 deg noiseLateral rate d=1 (%): 70.29 -> 76.44Improved
geometry-guided transformer instead of Persformer for G2S synthesis (ablation)full method · KITTI Test1, 20 deg noiseLongitudinal rate d=1 (%): 5.51 -> 23.54Improved
add translation supervision on neural optimizer output (ablation)neural pose optimizer · KITTI Test1, 20 deg noiseAzimuth rate theta=1 (%): 10.52 -> 99.10Improved
use ground-to-satellite synthesis instead of satellite-to-ground (ablation)full method · KITTI Test1, 80 deg noiseAzimuth rate theta=1 (%): 19.56 -> 53.27Improved
increase neural optimizer iterations from 2 to 3 (ablation)neural pose optimizer · KITTI Test1Azimuth rate theta=1 (%): 99.10 -> 80.52No clear effect
compare dense-search method with CVML regression on mean errorfull method · Oxford RobotCar overallMean error (m): 2.07 -> 2.79Hurt
dense-search similarity matching versus CVML regression on median errorfull method · Oxford RobotCar overallMedian error (m): 1.44 -> 1.02Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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