paper-with-me

홈 › Papers

MagicRoad: Semantic-Aware 3D Road Surface Reconstruction via Obstacle Inpainting

2025-07-31 · Xingyue Peng, Yuandong Lyu, Lang Zhang, Jian Zhu, Songtao Wang, Jiaxin Deng, Songxin Lu, Weiliang Ma, Dangen She, Peng Jia, XianPeng Lang arxiv

Road surface reconstruction is essential for autonomous driving, supporting centimeter-accurate lane perception and high-definition mapping in complex urban environments.While recent methods based on mesh rendering or 3D Gaussian splatting (3DGS) achieve promising results under clean and static conditions, they remain vulnerable to occlusions from dynamic agents, visual clutter from static obstacles, and appearance degradation caused by lighting and weather changes. We present a robust reconstruction framework that integrates occlusion-aware 2D Gaussian surfels with semantic-guided color enhancement to recover clean, consistent road surfaces. Our method leverages a planar-adapted Gaussian representation for efficient large-scale modeling, employs segmentation-guided video inpainting to remove both dynamic and static foreground objects, and enhances color coherence via semantic-aware correction in HSV space. Extensive experiments on urban-scale datasets demonstrate that our framework produces visually coherent and geometrically faithful reconstructions, significantly outperforming prior methods under real-world conditions.

📄 PDF Abstract BibTeX arXiv:2507.23340

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingVideo Inpainting

Similar Papers 제목 키워드 기반

RoGS: Adaptive Meshgrid Gaussian for Large-Scale Road Surface Mapping

2026-07-16 · Tianchen Deng, Zhiheng Feng, Wenhua Wu, Ziming Li 외 arxiv

Road surface mapping plays a crucial role in autonomous driving, supporting high-definition map generation, lane-level perception, and automatic road annotation. Recent mesh-based road surface reconstruction methods have…

Autonomous Driving

RoGs: Large Scale Road Surface Reconstruction with Meshgrid Gaussian

2024-05-23 · Zhiheng Feng, Wenhua Wu, Tianchen Deng, Hesheng Wang

Road surface reconstruction plays a crucial role in autonomous driving, which can be used for road lane perception and autolabeling. Recently, mesh-based road surface reconstruction algorithms have shown promising recons…

Autonomous DrivingSurface Reconstruction

NeRO: Neural Road Surface Reconstruction

2024-05-17 · Ruibo Wang, Song Zhang, Ping Huang, Donghai Zhang 외

Accurately reconstructing road surfaces is pivotal for various applications especially in autonomous driving. This paper introduces a position encoding Multi-Layer Perceptrons (MLPs) framework to reconstruct road surface…

Autonomous DrivingPositionSurface Reconstruction

EMIE-MAP: Large-Scale Road Surface Reconstruction Based on Explicit Mesh and Implicit Encoding

2024-03-18 · Wenhua Wu, Qi Wang, Guangming Wang, JunPing Wang 외

Road surface reconstruction plays a vital role in autonomous driving systems, enabling road lane perception and high-precision mapping. Recently, neural implicit encoding has achieved remarkable results in scene represen…

Autonomous DrivingSurface Reconstruction

RoMe: Towards Large Scale Road Surface Reconstruction via Mesh Representation

2023-06-20 · Ruohong Mei, Wei Sui, Jiaxin Zhang, Xue Qin 외

In autonomous driving applications, accurate and efficient road surface reconstruction is paramount. This paper introduces RoMe, a novel framework designed for the robust reconstruction of large-scale road surfaces. Leve…

Autonomous DrivingComputational EfficiencyGPUSurface Reconstruction