GaussianMap: Learning Gaussian Representation for Multi-Sensor Online HD Map Construction

• URL: http://arxiv.org/abs/2606.31177v1
• Date: Tue, 30 Jun 2026 06:08:42 GMT
• Title: GaussianMap: Learning Gaussian Representation for Multi-Sensor Online HD Map Construction
• Abstract summary: 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.
• Score: 6.54359101227443
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autonomous driving systems benefit from high-definition (HD) maps that provide critical information about road infrastructure. The online construction of HD maps offers a scalable approach to generate local vectorized maps from onboard sensor observations. Existing methods commonly adopt bird's-eye-view (BEV) features as the intermediate scene representation, encoding the surrounding space with fixed-resolution dense grids. However, map elements are spatially sparse yet require fine-grained geometric localization, making uniformly allocated BEV representations redundant and less effective for vectorized map prediction. In this work, we propose GaussianMap, an online HD map construction framework that learns an adaptive Gaussian representation of the surrounding scene. This representation consists of a set of Gaussian primitives on the BEV plane, each encoding a flexible local region with geometric properties and a feature vector, allowing the model to allocate representational capacity to map-relevant regions. To generate such a representation from sensor observations, we introduce a feed-forward Gaussian encoder that progressively refines these primitives through Gaussian interaction modeling and multi-sensor feature aggregation. The refined Gaussian representation is then splatted into a BEV feature map and decoded into vectorized map predictions. Extensive experiments on nuScenes and Argoverse 2 datasets demonstrate that GaussianMap achieves state-of-the-art performance in both camera-only and camera-LiDAR fusion settings. Our code will be made publicly available.

Related papers

• Gaussian-JEPA: Joint-Embedding Predictive Learning for 3D Gaussian Splats [91.55220894541151]
  3D Gaussian Splatting (3DGS) represents 3D content with anisotropic primitives that jointly encode geometry and appearance.<n>We introduce Gaussian-JEPA, which predicts representations of held-out Gaussian token blocks from visible context.
  arXiv  Detail & Related papers  (2026-08-16T09:43:50Z)
• 3D Gaussian Map with Open-Set Semantic Grouping for Vision-Language Navigation [48.641376758484505]
  Vision-language navigation (VLN) requires an agent to traverse complex 3D environments based on natural language instructions.<n>This work proposes a 3D Gaussian Map that represents the environment as a set of differentiable 3D Gaussians.<n>Egocentric Scene Map is constructed online by initializing 3D Gaussians from sparse pseudo-lidar point clouds.
  arXiv  Detail & Related papers  (2026-05-26T03:25:49Z)
• GSMap: 2D Gaussians for Online HD Mapping [8.653416286011359]
  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.
  arXiv  Detail & Related papers  (2026-05-10T15:57:07Z)
• Multi-Scale Gaussian-Language Map for Zero-shot Embodied Navigation and Reasoning [33.03611808441931]
  We propose the multi-scale Gaussian-Language Map (GLMap), which introduces three key designs.<n>The 3D Gaussians enable compact storage and fast rendering of task-relevant images.<n> Experiments on ObjectNav, InstNav, and SQA tasks show that GLMap effectively enhances target navigation and contextual reasoning.
  arXiv  Detail & Related papers  (2026-05-03T06:22:14Z)
• MapDiffusion: Generative Diffusion for Vectorized Online HD Map Construction and Uncertainty Estimation in Autonomous Driving [24.962900390344235]
  Autonomous driving requires an understanding of the static environment from sensor data.<n>Traditional map construction models provide deterministic point estimates.<n>We propose MapDiffusion, a novel generative approach that learns the full distribution of possible vectorized maps.
  arXiv  Detail & Related papers  (2025-07-29T01:16:40Z)
• GS-LIVO: Real-Time LiDAR, Inertial, and Visual Multi-sensor Fused Odometry with Gaussian Mapping [22.432252084121274]
  LiDAR-Inertial-Visual (LIV) sensor configuration has demonstrated superior performance in localization and dense mapping.<n>We propose a novel real-time Gaussian-based simultaneous localization and mapping (SLAM) system.<n>The framework achieves real-time performance while maintaining robust multi-sensor fusion capabilities.
  arXiv  Detail & Related papers  (2025-01-15T09:04:56Z)
• GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction [55.60972844777044]
  3D semantic occupancy prediction is an important task for robust vision-centric autonomous driving.<n>Most existing methods leverage dense grid-based scene representations, overlooking the spatial sparsity of the driving scenes.<n>We propose a probabilistic Gaussian superposition model which interprets each Gaussian as a probability distribution of its neighborhood being occupied.
  arXiv  Detail & Related papers  (2024-12-05T17:59:58Z)
• PixelGaussian: Generalizable 3D Gaussian Reconstruction from Arbitrary Views [116.10577967146762]
  PixelGaussian is an efficient framework for learning generalizable 3D Gaussian reconstruction from arbitrary views. Our method achieves state-of-the-art performance with good generalization to various numbers of views.
  arXiv  Detail & Related papers  (2024-10-24T17:59:58Z)
• SemVecNet: Generalizable Vector Map Generation for Arbitrary Sensor Configurations [3.8472678261304587]
  We propose a modular pipeline for vector map generation with improved generalization to sensor configurations. By adopting a BEV semantic map robust to different sensor configurations, our proposed approach significantly improves the generalization performance.
  arXiv  Detail & Related papers  (2024-04-30T23:45:16Z)
• Online Map Vectorization for Autonomous Driving: A Rasterization Perspective [58.71769343511168]
  We introduce a newization-based evaluation metric, which has superior sensitivity and is better suited to real-world autonomous driving scenarios. We also propose MapVR (Map Vectorization via Rasterization), a novel framework that applies differentiableization to preciseized outputs and then performs geometry-aware supervision on HD maps.
  arXiv  Detail & Related papers  (2023-06-18T08:51:14Z)
• Learning Implicit Feature Alignment Function for Semantic Segmentation [51.36809814890326]
  Implicit Feature Alignment function (IFA) is inspired by the rapidly expanding topic of implicit neural representations. We show that IFA implicitly aligns the feature maps at different levels and is capable of producing segmentation maps in arbitrary resolutions. Our method can be combined with improvement on various architectures, and it achieves state-of-the-art accuracy trade-off on common benchmarks.
  arXiv  Detail & Related papers  (2022-06-17T09:40:14Z)

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.