Shape Your Ground: Refining Road Surfaces Beyond Planar Representations

2025-04-15

AI Summary

Existing road surface reconstruction methods suffer from artifacts and geometric inconsistencies, while downstream tasks often resort to planar modeling—sacrificing 3D geometric fidelity. This paper introduces the first end-to-end NURBS-based surface reconstruction framework tailored for aerial imagery, breaking the planar assumption to achieve high-accuracy, smooth, and compact 3D road modeling. Key contributions include: (1) a differentiable NURBS surface fitting architecture; (2) an Elevation-Constrained Spatial Road Clustering (ECSRC) algorithm that robustly corrects outliers under elevation constraints; and (3) GeRoD—the first open-source benchmark dataset for road terrain reconstruction. Evaluated on GeRoD and DSC3D, our method reduces surface roughness by 42% and fitting error by 37% versus planar and mesh-based baselines, demonstrating strong generalization across noise, terrain variability, and multi-source inputs.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Computer Vision: 3D Computer Vision

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Road surface reconstruction from aerial images is fundamental for autonomous driving, urban planning, and virtual simulation, where smoothness, compactness, and accuracy are critical quality factors. Existing reconstruction methods often produce artifacts and inconsistencies that limit usability, while downstream tasks have a tendency to represent roads as planes for simplicity but at the cost of accuracy. We introduce FlexRoad, the first framework to directly address road surface smoothing by fitting Non-Uniform Rational B-Splines (NURBS) surfaces to 3D road points obtained from photogrammetric reconstructions or geodata providers. Our method at its core utilizes the Elevation-Constrained Spatial Road Clustering (ECSRC) algorithm for robust anomaly correction, significantly reducing surface roughness and fitting errors. To facilitate quantitative comparison between road surface reconstruction methods, we present GeoRoad Dataset (GeRoD), a diverse collection of road surface and terrain profiles derived from openly accessible geodata. Experiments on GeRoD and the photogrammetry-based DeepScenario Open 3D Dataset (DSC3D) demonstrate that FlexRoad considerably surpasses commonly used road surface representations across various metrics while being insensitive to various input sources, terrains, and noise types. By performing ablation studies, we identify the key role of each component towards high-quality reconstruction performance, making FlexRoad a generic method for realistic road surface modeling.

Problem

• Reconstructing smooth, accurate road surfaces from aerial images
• Addressing artifacts in existing road surface reconstruction methods
• Introducing NURBS-based framework for realistic road modeling

Innovation

• Uses NURBS surfaces for accurate road modeling
• Applies ECSRC algorithm for anomaly correction
• Introduces GeRoD dataset for quantitative comparison