cs.CVNov 18, 2026

Improving Zero-shot 3D Semantic Mapping in Offroad with Geometric Priors

Authors: Eerik Alamikkotervo, Risto Ojala

Organizations: Energy and Mechanical Engineering, Aalto University, Espoo, Finland

Abstract

Semantic 3D mapping is a powerful representation that enables platform agnostic mobile robot navigation in challenging offroad conditions. Current vision foundation models can accurately predict semantics zero-shot on structured scenes but performance is compromised in natural environments. On the other hand, 3D point clouds encode valuable information for discriminating semantics in scenarios where vision foundation models fail. In this work, we propose fitting a sphericity-elevation distribution for each semantic class to act as geometric anchor. Only the points with the most confident vision foundation model predictions are considered when fitting to produce high quality geometric prior distributions. The geometric prior is fused with the vision foundation model prediction to produce the final semantic mapping. The proposed prior improves SAM3 baseline by +6.3 in mIoU and +8.9 in accuracy on the RELLIS-3D dataset, and by +1.7 in mIoU and +2.1 in accuracy on the WildScenes dataset. The source code will be made public upon paper acceptance.

Figures & tables

Explore similar work

CardsList
  1. Geometry Matters: 3D Foundation Priors for Learning Semantic Correspondence

    May 28, 2026Artur Jesslen, Olaf Dünkel, Adam KortylewskiSemantic Correspondence

  2. Multiple Consistent 2D-3D Mappings for Robust Zero-Shot 3D Visual Grounding

    Apr 29, 2026Yufei Yin, Jie Zheng, Qianke Meng +73D VLMs3D Visual Grounding

  3. AOV-GS: Active Open-Vocabulary Semantic Mapping with 3D Gaussian Splatting

    Oct 21, 2026Rodion Shkokov, Tatiana Zemskova, Dmitry YudinSemantic MappingOpen-Vocabulary Semantic Mapping