# Shape Your Ground: Refining Road Surfaces Beyond Planar Representations

arXiv: https://arxiv.org/abs/2504.16103 · HTML: https://mlsanity.com/paper/2504.16103/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 28 references that are in the map.
- First posted on arXiv 15 Apr 2025.

## Builds on (most cited first, 10 of 10)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [MonoGround: Detecting Monocular 3D Objects from the Ground](https://mlsanity.com/paper/2206.07372/) (2022)
- [RoMe: Towards Large Scale Road Surface Reconstruction via Mesh Representation](https://mlsanity.com/paper/2306.11368/) (2023)
- [EMIE-MAP: Large-Scale Road Surface Reconstruction Based on Explicit Mesh and Implicit Encoding](https://mlsanity.com/paper/2403.11789/) (2024)
- [NURBS-Diff: A Differentiable Programming Module for NURBS](https://mlsanity.com/paper/2104.14547/) (2021)
- [RSRD: A Road Surface Reconstruction Dataset and Benchmark for Safe and Comfortable Autonomous Driving](https://mlsanity.com/paper/2310.02262/) (2023)
- [Ground Plane Matters: Picking Up Ground Plane Prior in Monocular 3D Object Detection](https://mlsanity.com/paper/2211.01556/) (2022)
- [Learning Digital Terrain Models from Point Clouds: ALS2DTM Dataset and Rasterization-based GAN](https://mlsanity.com/paper/2206.03778/) (2022)
- [Sparsity-driven Digital Terrain Model Extraction](https://mlsanity.com/paper/2012.08639/) (2020)

## Built on by (most cited first, 2 of 2)

- [Highly Accurate and Diverse Traffic Data: The DeepScenario Open 3D Dataset](https://mlsanity.com/paper/2504.17371/) (2025)
- [GrounDiff: Diffusion-Based Ground Surface Generation from Digital Surface Models](https://mlsanity.com/paper/2511.10391/) (2025)

## Abstract (arXiv)

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.