OpenLex3D: A New Evaluation Benchmark for Open-Vocabulary 3D Scene Representations

no code implementations • 25 Mar 2025 • Christina Kassab, Sacha Morin, Martin Büchner, Matías Mattamala, Kumaraditya Gupta, Abhinav Valada, Liam Paull, Maurice Fallon

3D scene understanding has been transformed by open-vocabulary language models that enable interaction via natural language.

3D Semantic Segmentation Scene Understanding

The Bare Necessities: Designing Simple, Effective Open-Vocabulary Scene Graphs

no code implementations • 2 Dec 2024 • Christina Kassab, Matías Mattamala, Sacha Morin, Martin Büchner, Abhinav Valada, Liam Paull, Maurice Fallon

3D open-vocabulary scene graph methods are a promising map representation for embodied agents, however many current approaches are computationally expensive.

feature selection Point Cloud Segmentation

Exosense: A Vision-Based Scene Understanding System For Exoskeletons

no code implementations • 21 Mar 2024 • Jianeng Wang, Matias Mattamala, Christina Kassab, Guillaume Burger, Fabio Elnecave, Lintong Zhang, Marine Petriaux, Maurice Fallon

In this work, we present Exosense, a vision-centric scene understanding system for self-balancing exoskeletons.

Language Modelling Motion Planning +2

Language-EXtended Indoor SLAM (LEXIS): A Versatile System for Real-time Visual Scene Understanding

no code implementations • 26 Sep 2023 • Christina Kassab, Matias Mattamala, Lintong Zhang, Maurice Fallon

We use this representation for flexible room classification and segmentation, serving as a basis for room-centric place recognition.

Scene Understanding Simultaneous Localization and Mapping