SCC-Loc: A Unified Semantic Cascade Consensus Framework for UAV Thermal Geo-Localization
Xiaoran Zhang, Yu Liu, Jinyu Liang, Kangqiushi Li, Zhiwei Huang, Huaxin Xiao

TL;DR
SCC-Loc is a novel UAV thermal geo-localization framework that integrates semantic guidance, spatial filtering, and consensus strategies to achieve highly accurate, all-weather positioning in GNSS-denied environments.
Contribution
It introduces a unified semantic cascade framework with a shared backbone, new modules for spatial alignment and outlier removal, and a large thermal UAV dataset, advancing state-of-the-art accuracy.
Findings
Achieves a mean localization error of 9.37 meters.
Provides a 7.6-fold improvement over previous methods within 5 meters.
Demonstrates robustness in all-weather, GNSS-denied scenarios.
Abstract
Cross-modal Thermal Geo-localization (TG) provides a robust, all-weather solution for Unmanned Aerial Vehicles (UAVs) in Global Navigation Satellite System (GNSS)-denied environments. However, profound thermal-visible modality gaps introduce severe feature ambiguity, systematically corrupting conventional coarse-to-fine registration. To dismantle this bottleneck, we propose SCC-Loc, a unified Semantic-Cascade-Consensus localization framework. By sharing a single DINOv2 backbone across global retrieval and MINIMA matching, it minimizes memory footprint and achieves zero-shot, highly accurate absolute position estimation. Specifically, we tackle modality ambiguity by introducing three cohesive components. First, we design the Semantic-Guided Viewport Alignment (SGVA) module to adaptively optimize satellite crop regions, effectively correcting initial spatial deviations.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
