RoadVGGT: Road-Structure-Aware Feed-Forward Road Surface Reconstruction

• URL: http://arxiv.org/abs/2607.23758v1
• Date: Sun, 26 Jul 2026 17:09:12 GMT
• Title: RoadVGGT: Road-Structure-Aware Feed-Forward Road Surface Reconstruction
• Abstract summary: RoadVGGT is a feed-forward framework that reconstructs compact Gaussian road surfaces without test-time per-scene optimization.<n>It supports RGB and semantic bird's-eye-view maps, elevation estimation, and novel view synthesis.
• Score: 18.76852385853567
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large-scale road surface reconstruction supports high-definition mapping, autonomous-driving perception, annotation, and simulation. Existing road-specialized optimization methods can produce high-quality road representations, but they typically require per-scene training and scene-dependent coverage design around the driving trajectory, limiting scalable reconstruction over newly collected roads. To address these limitations, we introduce RoadVGGT, a road-structure-aware feed-forward framework that reconstructs compact Gaussian road surfaces without test-time per-scene optimization. RoadVGGT uses a geometric foundation model to exploit multi-view images together with provided pose and depth observations, and predicts dense pixel-aligned Gaussian attributes through a learned Gaussian head. To make these dense predictions usable for large road surfaces, we align them into a consistent metric world coordinate system and fuse redundant Gaussians on the road-aligned XY plane through confidence-weighted grid fusion. Category-aware grouping and road--sidewalk junction protection further control fusion around vulnerable road structures. The resulting representation supports RGB and semantic bird's-eye-view maps, elevation estimation, and novel view synthesis. RoadVGGT eliminates the need for per-scene optimization in prior methods, reconstructs complete road surfaces with a compact Gaussian representation, and improves image quality, semantic mapping, and elevation accuracy. Extensive experiments demonstrate the potential of geometric foundation models for scalable feed-forward road surface reconstruction.

Related papers

• RoGS: Adaptive Meshgrid Gaussian for Large-Scale Road Surface Mapping [20.534227619549487]
  Road surface mapping plays a crucial role in autonomous driving, supporting high-definition map generation and lane-level perception.<n>Recent mesh-based road surface reconstruction methods have shown promising results, but they still suffer from limited reconstruction quality and high optimization cost.<n>We propose a robust and efficient large-scale road surface mapping framework based on adaptive meshgrid Gaussian representation.
  arXiv  Detail & Related papers  (2026-07-16T14:26:52Z)
• Shape Your Ground: Refining Road Surfaces Beyond Planar Representations [35.63881467885378]
  Road surface reconstruction from aerial images is fundamental for autonomous driving, urban planning, and virtual simulation.<n>Existing reconstruction methods often produce artifacts and inconsistencies that limit usability.<n>We introduce FlexRoad, the first framework to address road surface smoothing by fitting Non-Uniform Rational B-Splines (NURBS) surfaces to 3D road points obtained from photogrammetric reconstructions or geodata providers.
  arXiv  Detail & Related papers  (2025-04-15T21:20:44Z)
• FlexDrive: Toward Trajectory Flexibility in Driving Scene Reconstruction and Rendering [79.39246982782717]
  We introduce an Inverse View Warping technique to create compact and high-quality images as supervision for the reconstruction of the out-of-path views.<n>Our method achieves superior in-path and out-of-path reconstruction and rendering performance on the widely used Open dataset.
  arXiv  Detail & Related papers  (2025-02-28T14:32:04Z)
• StreetSurfGS: Scalable Urban Street Surface Reconstruction with Planar-based Gaussian Splatting [85.67616000086232]
  StreetSurfGS is first method to employ Gaussian Splatting specifically tailored for scalable urban street scene surface reconstruction. StreetSurfGS utilizes a planar-based octree representation and segmented training to reduce memory costs, accommodate unique camera characteristics, and ensure scalability. To address sparse views and multi-scale challenges, we use a dual-step matching strategy that leverages adjacent and long-term information.
  arXiv  Detail & Related papers  (2024-10-06T04:21:59Z)
• RoGs: Large Scale Road Surface Reconstruction with Meshgrid Gaussian [10.50103969885774]
  Road surface reconstruction plays a crucial role in autonomous driving. We propose a novel large-scale road surface reconstruction approach with meshgrid Gaussian, named RoGs. We obtain excellent results in reconstruction of road surfaces in a variety of challenging real-world scenes.
  arXiv  Detail & Related papers  (2024-05-23T09:11:47Z)
• NeRO: Neural Road Surface Reconstruction [15.99050337416157]
  This paper introduces a position encoding Multi-Layer Perceptrons (MLPs) framework to reconstruct road surfaces, with input as world coordinates x and y, and output as height, color, and semantic information. The effectiveness of this method is demonstrated through its compatibility with a variety of road height sources like vehicle camera poses, LiDAR point clouds, and SFM point clouds, robust to the semantic noise of images like sparse labels and noise semantic prediction, and fast training speed.
  arXiv  Detail & Related papers  (2024-05-17T05:41:45Z)
• Homography Guided Temporal Fusion for Road Line and Marking Segmentation [73.47092021519245]
  Road lines and markings are frequently occluded in the presence of moving vehicles, shadow, and glare. We propose a Homography Guided Fusion (HomoFusion) module to exploit temporally-adjacent video frames for complementary cues. We show that exploiting available camera intrinsic data and ground plane assumption for cross-frame correspondence can lead to a light-weight network with significantly improved performances in speed and accuracy.
  arXiv  Detail & Related papers  (2024-04-11T10:26:40Z)
• EMIE-MAP: Large-Scale Road Surface Reconstruction Based on Explicit Mesh and Implicit Encoding [21.117919848535422]
  EMIE-MAP is a novel method for large-scale road surface reconstruction based on explicit mesh and implicit encoding. Our method achieves remarkable road surface reconstruction performance in a variety of real-world challenging scenarios.
  arXiv  Detail & Related papers  (2024-03-18T13:46:52Z)
• Indoor Scene Reconstruction with Fine-Grained Details Using Hybrid Representation and Normal Prior Enhancement [50.56517624931987]
  The reconstruction of indoor scenes from multi-view RGB images is challenging due to the coexistence of flat and texture-less regions. Recent methods leverage neural radiance fields aided by predicted surface normal priors to recover the scene geometry. This work aims to reconstruct high-fidelity surfaces with fine-grained details by addressing the above limitations.
  arXiv  Detail & Related papers  (2023-09-14T12:05:29Z)
• Monocular BEV Perception of Road Scenes via Front-to-Top View Projection [57.19891435386843]
  We present a novel framework that reconstructs a local map formed by road layout and vehicle occupancy in the bird's-eye view. Our model runs at 25 FPS on a single GPU, which is efficient and applicable for real-time panorama HD map reconstruction.
  arXiv  Detail & Related papers  (2022-11-15T13:52:41Z)
• Convolutional Recurrent Network for Road Boundary Extraction [99.55522995570063]
  We tackle the problem of drivable road boundary extraction from LiDAR and camera imagery. We design a structured model where a fully convolutional network obtains deep features encoding the location and direction of road boundaries. We showcase the effectiveness of our method on a large North American city where we obtain perfect topology of road boundaries 99.3% of the time.
  arXiv  Detail & Related papers  (2020-12-21T18:59:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.