SyncAI.news, a Varaisys broadcasting
Improving Zero-shot 3D Semantic Mapping in Offroad with Geometric Priors
EA

Eerik Alamikkotervo, Risto Ojala

· 1 min read

ResearcharXiv cs.CV

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

arXiv:2611.24696v1 Announce Type: new 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.

Original source

This story was published by arXiv cs.CV and written by Eerik Alamikkotervo, Risto Ojala. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News