GSMap: 2D Gaussians for Online HD Mapping

• URL: http://arxiv.org/abs/2605.09619v2
• Date: Sat, 16 May 2026 15:12:41 GMT
• Title: GSMap: 2D Gaussians for Online HD Mapping
• Abstract summary: We propose GSMap, a novel framework that unifies both paradigms via a learnable 2D representation.<n>Experiments on both nuScenes and Argoverse2 demonstrate that our Gaussian-based representation effectively unifies geometric and topological learning.
• Score: 8.653416286011359
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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

Related papers

• CubicSplat: Differentiable Vector Graphics via Error-Bounded Forward Relaxation [41.42805325196858]
  We introduce CubicSplat, a new type of vector graphics solver that replaces Bézier closest-point solvers with uniform polyline surrogates whose geometric error is bounded at $O(S-2)$.<n>The resulting static computation graph yields well-conditioned gradients by construction, while a PSN-derived visibility mechanism prunes primitives without auxiliary regularization.
  arXiv  Detail & Related papers  (2026-08-21T07:21:08Z)
• GaussianMap: Learning Gaussian Representation for Multi-Sensor Online HD Map Construction [6.54359101227443]
  We propose an online HD map construction framework that learns an adaptive Gaussian representation of the surrounding scene.<n>GustafMap achieves state-of-the-art performance in both camera-only and camera-LiDAR fusion settings.
  arXiv  Detail & Related papers  (2026-06-30T06:08:42Z)
• G2P: Gaussian-to-Point Attribute Alignment for Boundary-Aware 3D Semantic Segmentation [22.750868489199686]
  We propose Gaussian-to-Point (G2P), which transfers appearance-aware attributes from 3D Gaussian Splatting to point clouds for more discriminative and appearance-consistent segmentation.<n>Our approach achieves superior performance on standard benchmarks and shows significant improvements on geometrically challenging classes, all without any 2D or language supervision.
  arXiv  Detail & Related papers  (2026-01-07T01:44:29Z)
• GauSSmart: Enhanced 3D Reconstruction through 2D Foundation Models and Geometric Filtering [50.675710727721786]
  We propose GauSSmart, a hybrid method that bridges 2D foundational models and 3D Gaussian Splatting reconstruction.<n>Our approach integrates established 2D computer vision techniques, including convex filtering and semantic feature supervision.<n>We validate our approach across three datasets, where GauSSmart consistently outperforms existing Gaussian Splatting.
  arXiv  Detail & Related papers  (2025-10-16T03:38:26Z)
• GeoPurify: A Data-Efficient Geometric Distillation Framework for Open-Vocabulary 3D Segmentation [57.8059956428009]
  Recent attempts to transfer features from 2D Vision-Language Models to 3D semantic segmentation expose a persistent trade-off.<n>We propose GeoPurify that applies a small Student Affinity Network to 2D VLM-generated 3D point features using geometric priors distilled from a 3D self-supervised teacher model.<n>Benefiting from latent geometric information and the learned affinity network, GeoPurify effectively mitigates the trade-off and achieves superior data efficiency.
  arXiv  Detail & Related papers  (2025-10-02T16:37:56Z)
• GaussianMorphing: Mesh-Guided 3D Gaussians for Semantic-Aware Object Morphing [31.47036497656664]
  We introduce a novel framework for semantic-aware 3D shape and texture morphing from multi-view images.<n>The core of our framework is a unified deformation strategy that anchors 3DGaussians to reconstructed mesh patches.<n>On our proposed TexMorph benchmark, GaussianMorphing substantially outperforms prior 2D/3D methods.
  arXiv  Detail & Related papers  (2025-10-02T14:07:55Z)
• GraphGSOcc: Semantic-Geometric Graph Transformer with Dynamic-Static Decoupling for 3D Gaussian Splatting-based Occupancy Prediction [2.3239379129613535]
  GraphGSOcc is a novel framework that combines semantic and geometric graph Transformer and decouples dynamic-static objects.<n>It achieves state-ofthe-art performance on the SurroundOcc-nuScenes, Occ3D-nuScenes, OpenOcc and KITTI occupancy benchmarks.
  arXiv  Detail & Related papers  (2025-06-13T06:09:57Z)
• Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting [33.01987451251659]
  3D Gaussian Splatting (3DGS) has emerged as a promising technique capable of real-time rendering with high-quality 3D reconstruction.<n>Despite its potential, 3DGS encounters challenges such as needle-like artifacts, suboptimal geometries, and inaccurate normals.<n>We introduce the effective rank as a regularization, which constrains the structure of the Gaussians.
  arXiv  Detail & Related papers  (2024-06-17T15:51:59Z)
• InstaGraM: Instance-level Graph Modeling for Vectorized HD Map Learning [8.556482588459899]
  Online high-definition (HD) map construction plays a significant role in accurate estimation of the pose.<n>Recent advancements in online HD map construction have predominantly investigated on vectorized representation.<n>We propose a novel HD map learning framework that leverages graph modeling.
  arXiv  Detail & Related papers  (2023-01-10T08:15:35Z)
• Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis [66.49788145564004]
  We present an unsupervised deep neural architecture called Flattening-Net to represent irregular 3D point clouds of arbitrary geometry and topology. Our methods perform favorably against the current state-of-the-art competitors.
  arXiv  Detail & Related papers  (2022-12-17T15:05:25Z)
• Self-supervised Geometric Perception [96.89966337518854]
  Self-supervised geometric perception is a framework to learn a feature descriptor for correspondence matching without any ground-truth geometric model labels. We show that SGP achieves state-of-the-art performance that is on-par or superior to the supervised oracles trained using ground-truth labels.
  arXiv  Detail & Related papers  (2021-03-04T15:34:43Z)
• DSG-Net: Learning Disentangled Structure and Geometry for 3D Shape Generation [98.96086261213578]
  We introduce DSG-Net, a deep neural network that learns a disentangled structured and geometric mesh representation for 3D shapes. This supports a range of novel shape generation applications with disentangled control, such as of structure (geometry) while keeping geometry (structure) unchanged. Our method not only supports controllable generation applications but also produces high-quality synthesized shapes, outperforming state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-08-12T17:06:51Z)
• PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsampling [103.09504572409449]
  We propose a novel deep neural network based method, called PUGeo-Net, to generate uniform dense point clouds. Thanks to its geometry-centric nature, PUGeo-Net works well for both CAD models with sharp features and scanned models with rich geometric details.
  arXiv  Detail & Related papers  (2020-02-24T14:13:29Z)

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.