AI Paper Atlas

Research map / 3D vision / Depth and stereo

PAUL: Uncertainty-Guided Partition and Augmentation for Robust Cross-View Geo-Localization under Noisy Correspondence

Zheng Li, Xueyi Zhang, Yanming Guo, Yuxiang Xie, Zhaoyun Ding, Siqi Cai, Haizhou Li, Mingrui Lao

CVPR 2026 · 3D vision › Depth and stereo · approach: Scene coordinate regression for localization

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 L_match (InfoNCE on clean and augmented pairs) without L_EDL (ablation)PAUL · GTA-UAV cross-area, 30% noiseR@1: 46.27 -> 55.72Improved
add L_EDL on noisy pairs without L_match (ablation)PAUL · GTA-UAV cross-area, 30% noiseR@1: 46.27 -> 54.36Improved
add L_EDL on top of L_match (ablation)PAUL · GTA-UAV cross-area, 30% noiseR@1: 55.72 -> 58.70Improved
add L_match on top of L_EDL (ablation)PAUL · GTA-UAV cross-area, 30% noiseR@1: 54.36 -> 58.70Improved
increase lambda (EDL loss KL coefficient) from 0.001 to 0.005 (ablation)PAUL · GTA-UAV cross-area, 30% noiseretrieval performanceImproved
increase lambda_EDL beyond 1 (ablation)PAUL · GTA-UAV cross-area, 30% noiseretrieval performanceHurt
use GMM loss-based partition instead of other partition strategies (ablation)PAUL co-partition · GTA-UAV cross-area, 30% noisenoisy-set purityImproved
guide mask generation with EDL loss instead of InfoNCE or uncertainty (ablation)PAUL co-augment · GTA-UAV cross-area, 30% noiseretrieval performanceImproved
use direct (zero) masking instead of magnification, Gaussian noise or mean masking (ablation)PAUL co-augment · GTA-UAV cross-area, 30% noiseretrieval performanceImproved
use generic noisy-correspondence methods (NCR, BiCro, ESC) instead of plain InfoNCESample4Geo · GTA-UAV cross-area, 30% noiseR@1: 46.27 -> 44.40 (NCR)Hurt
PAUL vs InfoNCE at 0% noise on same-area splitSample4Geo · GTA-UAV same-area, 0% noiseR@1: 72.29 -> 73.55Improved
PAUL vs InfoNCE as noise rises from 0% to 60%Sample4Geo · GTA-UAV cross-areaR@1: 42.15 -> 52.61 at 60% noiseImproved

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