SGAligner++: Cross-Modal Language-Aided 3D Scene Graph Alignment

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Singh, Binod, Sarkar, Sayan Deb, Armeni, Iro
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915558343049216
author Singh, Binod
Sarkar, Sayan Deb
Armeni, Iro
author_facet Singh, Binod
Sarkar, Sayan Deb
Armeni, Iro
contents Aligning 3D scene graphs is a crucial initial step for several applications in robot navigation and embodied perception. Current methods in 3D scene graph alignment often rely on single-modality point cloud data and struggle with incomplete or noisy input. We introduce SGAligner++, a cross-modal, language-aided framework for 3D scene graph alignment. Our method addresses the challenge of aligning partially overlapping scene observations across heterogeneous modalities by learning a unified joint embedding space, enabling accurate alignment even under low-overlap conditions and sensor noise. By employing lightweight unimodal encoders and attention-based fusion, SGAligner++ enhances scene understanding for tasks such as visual localization, 3D reconstruction, and navigation, while ensuring scalability and minimal computational overhead. Extensive evaluations on real-world datasets demonstrate that SGAligner++ outperforms state-of-the-art methods by up to 40% on noisy real-world reconstructions, while enabling cross-modal generalization.
format Preprint
id arxiv_https___arxiv_org_abs_2509_20401
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SGAligner++: Cross-Modal Language-Aided 3D Scene Graph Alignment
Singh, Binod
Sarkar, Sayan Deb
Armeni, Iro
Computer Vision and Pattern Recognition
Robotics
Aligning 3D scene graphs is a crucial initial step for several applications in robot navigation and embodied perception. Current methods in 3D scene graph alignment often rely on single-modality point cloud data and struggle with incomplete or noisy input. We introduce SGAligner++, a cross-modal, language-aided framework for 3D scene graph alignment. Our method addresses the challenge of aligning partially overlapping scene observations across heterogeneous modalities by learning a unified joint embedding space, enabling accurate alignment even under low-overlap conditions and sensor noise. By employing lightweight unimodal encoders and attention-based fusion, SGAligner++ enhances scene understanding for tasks such as visual localization, 3D reconstruction, and navigation, while ensuring scalability and minimal computational overhead. Extensive evaluations on real-world datasets demonstrate that SGAligner++ outperforms state-of-the-art methods by up to 40% on noisy real-world reconstructions, while enabling cross-modal generalization.
title SGAligner++: Cross-Modal Language-Aided 3D Scene Graph Alignment
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2509.20401