GSMap: 2D Gaussians for Online HD Mapping

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zeng, Zhenxuan, Wang, Lingxuan, Yang, Sheng, He, Yanan, Chen, Mingxia, Suo, Wei, Wang, Peng
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918505232728064
author Zeng, Zhenxuan
Wang, Lingxuan
Yang, Sheng
He, Yanan
Chen, Mingxia
Suo, Wei
Wang, Peng
author_facet Zeng, Zhenxuan
Wang, Lingxuan
Yang, Sheng
He, Yanan
Chen, Mingxia
Suo, Wei
Wang, Peng
contents Accurate High-Definition (HD) map construction is critical for autonomous driving, yet existing methods face a fundamental trade-off: vectorization-based approaches preserve topology but struggle with geometric fidelity, while rasterization-based approaches enable precise geometric supervision but produce unstructured outputs. To bridge this gap, we propose GSMap, a novel framework that unifies both paradigms via a learnable 2D Gaussian representation. Each map element is modeled as an ordered sequence of 2D Gaussians, whose centers correspond to the vertices of the vectorized polyline/polygon. This formulation enables simultaneous optimization through: (1) Differentiable rasterization that enforces pixel-level geometric constraints, and (2) Topology-aware vectorization that maintains structural regularity. Experiments on both nuScenes and Argoverse2 demonstrate that our Gaussian-based representation effectively unifies geometric and topological learning, achieving significant performance improvements and demonstrating strong compatibility with existing HD mapping architectures. Code will be available at https://github.com/peakpang/GSMap
format Preprint
id arxiv_https___arxiv_org_abs_2605_09619
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GSMap: 2D Gaussians for Online HD Mapping
Zeng, Zhenxuan
Wang, Lingxuan
Yang, Sheng
He, Yanan
Chen, Mingxia
Suo, Wei
Wang, Peng
Computer Vision and Pattern Recognition
Accurate High-Definition (HD) map construction is critical for autonomous driving, yet existing methods face a fundamental trade-off: vectorization-based approaches preserve topology but struggle with geometric fidelity, while rasterization-based approaches enable precise geometric supervision but produce unstructured outputs. To bridge this gap, we propose GSMap, a novel framework that unifies both paradigms via a learnable 2D Gaussian representation. Each map element is modeled as an ordered sequence of 2D Gaussians, whose centers correspond to the vertices of the vectorized polyline/polygon. This formulation enables simultaneous optimization through: (1) Differentiable rasterization that enforces pixel-level geometric constraints, and (2) Topology-aware vectorization that maintains structural regularity. Experiments on both nuScenes and Argoverse2 demonstrate that our Gaussian-based representation effectively unifies geometric and topological learning, achieving significant performance improvements and demonstrating strong compatibility with existing HD mapping architectures. Code will be available at https://github.com/peakpang/GSMap
title GSMap: 2D Gaussians for Online HD Mapping
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.09619