# Gaussian Semantic Field for One-shot LiDAR Global Localization

arXiv: https://arxiv.org/abs/2510.12101 · HTML: https://mlsanity.com/paper/2510.12101/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 14 Oct 2025.

## Builds on (most cited first, 22 of 22)

- [In-Place Scene Labelling and Understanding with Implicit Scene Representation](https://mlsanity.com/paper/2103.15875/) (2021)
- [3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera](https://mlsanity.com/paper/1910.02527/) (2019)
- [NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes](https://mlsanity.com/paper/2111.13260/) (2021)
- [SuMa++: Efficient LiDAR-based Semantic SLAM](https://mlsanity.com/paper/2105.11320/) (2021)
- [SegMatch: Segment based loop-closure for 3D point clouds](https://mlsanity.com/paper/1609.07720/) (2016)
- [SegMap: Segment-based mapping and localization using data-driven descriptors](https://mlsanity.com/paper/1909.12837/) (2019)
- [Bayesian Spatial Kernel Smoothing for Scalable Dense Semantic Mapping](https://mlsanity.com/paper/1909.04631/) (2019)
- [RING++: Roto-translation Invariant Gram for Global Localization on a Sparse Scan Map](https://mlsanity.com/paper/2210.05984/) (2022)
- [SFD2: Semantic-guided Feature Detection and Description](https://mlsanity.com/paper/2304.14845/) (2023)
- [Indoor and Outdoor 3D Scene Graph Generation via Language-Enabled Spatial Ontologies](https://mlsanity.com/paper/2312.11713/) (2023)
- [STD: Stable Triangle Descriptor for 3D place recognition](https://mlsanity.com/paper/2209.12435/) (2022)
- [Hydra-Multi: Collaborative Online Construction of 3D Scene Graphs with Multi-Robot Teams](https://mlsanity.com/paper/2304.13487/) (2023)
- [Multi-Modal Continual Test-Time Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/2303.10457/) (2023)
- [BEVPlace++: Fast, Robust, and Lightweight LiDAR Global Localization for Unmanned Ground Vehicles](https://mlsanity.com/paper/2408.01841/) (2024)
- [MoPA: Multi-Modal Prior Aided Domain Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/2309.11839/) (2023)
- [MCD: Diverse Large-Scale Multi-Campus Dataset for Robot Perception](https://mlsanity.com/paper/2403.11496/) (2024)
- [Parallel Maximum Clique Algorithms with Applications to Network Analysis and Storage](https://mlsanity.com/paper/1302.6256/) (2013)
- [Outram: One-shot Global Localization via Triangulated Scene Graph and Global Outlier Pruning](https://mlsanity.com/paper/2309.08914/) (2023)
- [Gaussian Process Autonomous Mapping and Exploration for Range Sensing Mobile Robots](https://mlsanity.com/paper/1605.00335/) (2016)
- [Global Localization in Unstructured Environments using Semantic Object Maps Built from Various Viewpoints](https://mlsanity.com/paper/2303.04658/) (2023)
- [SGLC: Semantic Graph-Guided Coarse-Fine-Refine Full Loop Closing for LiDAR SLAM](https://mlsanity.com/paper/2407.08106/) (2024)
- [REGRACE: A Robust and Efficient Graph-based Re-localization Algorithm using Consistency Evaluation](https://mlsanity.com/paper/2503.03599/) (2025)

## Abstract (arXiv)

We present a one-shot LiDAR global localization algorithm featuring semantic disambiguation ability based on a lightweight tri-layered scene graph. While landmark semantic registration-based methods have shown promising performance improvements in global localization compared with geometric-only methods, landmarks can be repetitive and misleading for correspondence establishment. We propose to mitigate this problem by modeling semantic distributions with continuous functions learned from a population of Gaussian processes. Compared with discrete semantic labels, the continuous functions capture finer-grained geo-semantic information and also provide more detailed metric information for correspondence establishment. We insert this continuous function as the middle layer between the object layer and the metric-semantic layer, forming a tri-layered 3D scene graph, serving as a light-weight yet performant backend for one-shot localization. We term our global localization pipeline Outram-GSF (Gaussian semantic field) and conduct a wide range of experiments on publicly available data sets, validating the superior performance against the current state-of-the-art.