LoD-Loc v2: Aerial Visual Localization over Low Level-of-Detail City Models using Explicit Silhouette Alignment

2025-07-01

AI Summary

Existing UAV aerial visual localization methods heavily rely on high-detail city models (LoD2/LoD3), limiting their applicability to widely available low-detail LoD1 models. To address this, we propose the first coarse-to-fine visual localization framework specifically designed for LoD1 models. Our method introduces an explicit building contour alignment mechanism: first, a segmentation network extracts building contours to construct a pose cost volume for coarse pose initialization; then, particle filtering is integrated with multi-beam tracking to perform robust fine-grained optimization under projection-contour alignment constraints. Experiments on real-world datasets demonstrate that our approach significantly outperforms existing LoD1-based methods—achieving accuracy competitive with some texture-dependent LoD2 approaches—and exhibits strong generalization across both LoD1 and LoD2 models. To foster community advancement, we publicly release two LoD1 city model datasets covering a total area of 10.7 km².

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: Low Level & Physics-based Vision
• Search and Optimization: Local Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

We propose a novel method for aerial visual localization over low Level-of-Detail (LoD) city models. Previous wireframe-alignment-based method LoD-Loc has shown promising localization results leveraging LoD models. However, LoD-Loc mainly relies on high-LoD (LoD3 or LoD2) city models, but the majority of available models and those many countries plan to construct nationwide are low-LoD (LoD1). Consequently, enabling localization on low-LoD city models could unlock drones' potential for global urban localization. To address these issues, we introduce LoD-Loc v2, which employs a coarse-to-fine strategy using explicit silhouette alignment to achieve accurate localization over low-LoD city models in the air. Specifically, given a query image, LoD-Loc v2 first applies a building segmentation network to shape building silhouettes. Then, in the coarse pose selection stage, we construct a pose cost volume by uniformly sampling pose hypotheses around a prior pose to represent the pose probability distribution. Each cost of the volume measures the degree of alignment between the projected and predicted silhouettes. We select the pose with maximum value as the coarse pose. In the fine pose estimation stage, a particle filtering method incorporating a multi-beam tracking approach is used to efficiently explore the hypothesis space and obtain the final pose estimation. To further facilitate research in this field, we release two datasets with LoD1 city models covering 10.7 km , along with real RGB queries and ground-truth pose annotations. Experimental results show that LoD-Loc v2 improves estimation accuracy with high-LoD models and enables localization with low-LoD models for the first time. Moreover, it outperforms state-of-the-art baselines by large margins, even surpassing texture-model-based methods, and broadens the convergence basin to accommodate larger prior errors.

Problem

• Aerial visual localization using low-LoD city models
• Enabling drones for global urban localization with LoD1 models
• Improving pose estimation accuracy with coarse-to-fine silhouette alignment

Innovation

• Explicit silhouette alignment for aerial localization
• Coarse-to-fine strategy with pose cost volume
• Particle filtering for efficient pose estimation