LOST-3DSG: Lightweight Open-Vocabulary 3D Scene Graphs with Semantic Tracking in Dynamic Environments

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ferraina, Sara Micol, Brienza, Michele, Argenziano, Francesco, Musumeci, Emanuele, Suriani, Vincenzo, Bloisi, Domenico D., Nardi, Daniele
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911367987986432
author Ferraina, Sara Micol
Brienza, Michele
Argenziano, Francesco
Musumeci, Emanuele
Suriani, Vincenzo
Bloisi, Domenico D.
Nardi, Daniele
author_facet Ferraina, Sara Micol
Brienza, Michele
Argenziano, Francesco
Musumeci, Emanuele
Suriani, Vincenzo
Bloisi, Domenico D.
Nardi, Daniele
contents Tracking objects that move within dynamic environments is a core challenge in robotics. Recent research has advanced this topic significantly; however, many existing approaches remain inefficient due to their reliance on heavy foundation models. To address this limitation, we propose LOST-3DSG, a lightweight open-vocabulary 3D scene graph designed to track dynamic objects in real-world environments. Our method adopts a semantic approach to entity tracking based on word2vec and sentence embeddings, enabling an open-vocabulary representation while avoiding the necessity of storing dense CLIP visual features. As a result, LOST-3DSG achieves superior performance compared to approaches that rely on high-dimensional visual embeddings. We evaluate our method through qualitative and quantitative experiments conducted in a real 3D environment using a TIAGo robot. The results demonstrate the effectiveness and efficiency of LOST-3DSG in dynamic object tracking. Code and supplementary material are publicly available on the project website at https://lab-rococo-sapienza.github.io/lost-3dsg/.
format Preprint
id arxiv_https___arxiv_org_abs_2601_02905
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LOST-3DSG: Lightweight Open-Vocabulary 3D Scene Graphs with Semantic Tracking in Dynamic Environments
Ferraina, Sara Micol
Brienza, Michele
Argenziano, Francesco
Musumeci, Emanuele
Suriani, Vincenzo
Bloisi, Domenico D.
Nardi, Daniele
Robotics
Artificial Intelligence
Tracking objects that move within dynamic environments is a core challenge in robotics. Recent research has advanced this topic significantly; however, many existing approaches remain inefficient due to their reliance on heavy foundation models. To address this limitation, we propose LOST-3DSG, a lightweight open-vocabulary 3D scene graph designed to track dynamic objects in real-world environments. Our method adopts a semantic approach to entity tracking based on word2vec and sentence embeddings, enabling an open-vocabulary representation while avoiding the necessity of storing dense CLIP visual features. As a result, LOST-3DSG achieves superior performance compared to approaches that rely on high-dimensional visual embeddings. We evaluate our method through qualitative and quantitative experiments conducted in a real 3D environment using a TIAGo robot. The results demonstrate the effectiveness and efficiency of LOST-3DSG in dynamic object tracking. Code and supplementary material are publicly available on the project website at https://lab-rococo-sapienza.github.io/lost-3dsg/.
title LOST-3DSG: Lightweight Open-Vocabulary 3D Scene Graphs with Semantic Tracking in Dynamic Environments
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2601.02905