aiqbench analysis
This research introduces HGeo-TopoMap, a novel architecture that enhances autonomous driving perception by integrating hierarchical geometric priors to improve topological map generation. By leveraging explicit prior maps and implicit spatial relations, the method addresses critical challenges in detecting road centerlines where markings are absent or degraded. The approach demonstrates superior accuracy and robustness on standard benchmarks like OpenLane-V2, offering a practical advancement for real-world path planning systems.
HGeo-TopoMap: Boosting Topological Mapping with Hierarchical Geometric Priors
arXiv:2607.21281v1 Announce Type: cross Abstract: Topological maps are key outputs of autonomous driving perception systems, delivering essential road information for path planning. They identify instances such as centerlines and traffic signs, along with their connectivity relationships. Due to the lack of explicit markings for centerlines in real-world environments, the detection of centerline instances remains a significant challenge. To tackle this problem, we propose HGeo-TopoMap, which leverages an explicit prior map and implicit spatial relations to hierarchically boost topological mapping. First, a geometric adaptive learning module is designed for the road structure map obtained via inverse perspective mapping. This module discretely encodes semantic and spatial features from the map, followed by a prior-mask attention mechanism that selectively focuses on informative regions. Then, a geometric consistency learning module is devised, which leverages the geometric properties and spatial relationships of centerlines. Built on the geometry-aware decoder, it enforces spatial consistency by aligning features of centerline instances with identical geometric orientations. The proposed method is evaluated on the OpenLane-V2 dataset across the centerline, lane segment, and robustness benchmarks. Beyond substantial improvements in topological mapping accuracy, the proposed method offers the benefit of enhanced robustness, consistently outperforming baselines under both standard and challenging conditions. The source code and model weights will be made publicly available at https://github.com/lynn-yu/HGeo-TopoMap.
Abstract:Topological maps are key outputs of autonomous driving perception systems, delivering essential road information for path planning. They identify instances such as centerlines and traffic signs, along with their connectivity relationships. Due to the lack of explicit markings for centerlines in real-world environments, the detection of centerline instances remains a significant challenge. To tackle this problem, we propose HGeo-TopoMap, which leverages an explicit prior map and implicit spatial relations to hierarchically boost topological mapping. First, a geometric adaptive learning module is designed for the road structure map obtained via inverse perspective mapping. This module discretely encodes semantic and spatial features from the map, followed by a prior-mask attention mechanism that selectively focuses on informative regions. Then, a geometric consistency learning module is devised, which leverages the geometric properties and spatial relationships of centerlines. Built on the geometry-aware decoder, it enforces spatial consistency by aligning features of centerline instances with identical geometric orientations. The proposed method is evaluated on the OpenLane-V2 dataset across the centerline, lane segment, and robustness benchmarks. Beyond substantial improvements in topological mapping accuracy, the proposed method offers the benefit of enhanced robustness, consistently outperforming baselines under both standard and challenging conditions. The source code and model weights will be made publicly available at this https URL.
Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO); Image and Video Processing (eess.IV)
arXiv:2607.21281 [cs.CV]
(or arXiv:2607.21281v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2607.21281 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 313 words
Related coverage
L2G-Map: Local-to-Global Mapping via Hierarchical Diffusion Refinement and Elliptical Bayesian Fusion
arXiv · Sep 9, 2026
Topology-Adaptive Hyperbolic Graph Attention Networks Guided by the Hyperbolic Sombor Index
arXiv · Sep 30, 2026
Explore From Sketch: Accelerating UAV Exploration in Large-scale Environments with Prior Maps
arXiv · Jun 11, 2026
EgoNav: Bridging Learned Waypoints and Geometry-Aware Local Control for Robust Indoor Navigation
arXiv · Aug 27, 2026