Gaussian Semantic Field for One-shot LiDAR Global Localization

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yin, Pengyu, Yuan, Shenghai, Cao, Haozhi, Ji, Xingyu, Bai, Ruofei, Chen, Siyu, Xie, Lihua
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911208926347264
author Yin, Pengyu
Yuan, Shenghai
Cao, Haozhi
Ji, Xingyu
Bai, Ruofei
Chen, Siyu
Xie, Lihua
author_facet Yin, Pengyu
Yuan, Shenghai
Cao, Haozhi
Ji, Xingyu
Bai, Ruofei
Chen, Siyu
Xie, Lihua
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_12101
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Gaussian Semantic Field for One-shot LiDAR Global Localization
Yin, Pengyu
Yuan, Shenghai
Cao, Haozhi
Ji, Xingyu
Bai, Ruofei
Chen, Siyu
Xie, Lihua
Robotics
Computer Vision and Pattern Recognition
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.
title Gaussian Semantic Field for One-shot LiDAR Global Localization
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.12101