Results 111 to 120 of about 2,792,973 (280)

SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks [PDF]

Scene graphs have been recently introduced into 3D spatial understanding as a comprehensive representation of the scene. The alignment between 3D scene graphs is the first step of many downstream tasks such as scene graph aided point cloud registration ...
Pagani, Alain, Xie, Yaxu, Stricker, Didier   +2 more
core   +1 more source

Open-Vocabulary Octree-Graph for 3D Scene Understanding

2025 IEEE/CVF International Conference on Computer Vision (ICCV)
Open-vocabulary 3D scene understanding is indispensable for embodied agents. Recent works leverage pretrained vision-language models (VLMs) for object segmentation and project them to point clouds to build 3D maps. Despite progress, a point cloud is a set of unordered coordinates that requires substantial storage space and does not directly convey ...
Zhigang Wang 0002, Yifei Su, Chenhui Li, Dong Wang 0028, Yan Huang, Bin Zhao 0001, Xuelong Li 0001   +6 more
openaire   +2 more sources

Application of Photogrammetry and Mesh Comparison in the Study of Human Cranial Morphology

International Journal of Osteoarchaeology, EarlyView.
ABSTRACT Photogrammetric methods for generating three‐dimensional (3D) models are becoming increasingly widespread in the fields of archaeology and biological anthropology. In particular, the study of the variability of skull morphology (generated by the ancestry of the individual or by the application of certain cultural practices) using 3D models is ...
Carlos Cancio Moreno, Javier Lescure, Antonio González‐Martín   +2 more
wiley   +1 more source

LEGS: Visual Localization Enhanced by 3D Gaussian Splatting

Journal of Imaging
Accurate six-degree-of-freedom (6-DoF) visual localization is a fundamental component for modern mapping and navigation. While recent data-centric approaches have leveraged Novel View Synthesis (NVS) to augment training datasets, these methods typically ...
Daewoon Kim, I-gil Kim
doaj   +1 more source

Graph-GSReg: Leveraging 3D Scene Graphs for Gaussian Splatting Registration

Merging multiple 3D Gaussian Splatting (3DGS) scenes into a single unified Gaussian representation is essential for large-scale 3D mapping and long-term map management. Despite its importance, this area remains underexplored, and existing solutions exhibit several limitations.
Jaewon Lee, Mangyu Kong, Euntai Kim
openaire   +2 more sources

Collaborative Dynamic 3D Scene Graphs for Automated Driving

2024 IEEE International Conference on Robotics and Automation (ICRA)
Accepted for "IEEE International Conference on Robotics and Automation (ICRA) 2024"
Greve, Elias, Büchner, Martin Alexander, Vodisch, Niclas, Burgard, Wolfram, Valada, Abhinav   +4 more
openaire   +4 more sources

SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstruction

In the field of 3D scene understanding, 3D scene graphs have emerged as a new scene representation that combines geometric and semantic information about objects and their relationships.
Vaskevicius, Narunas; orcid:, Hermosilla, Pedro, Ropinski, Timo; orcid:, Colosi, Mirco; orcid:, Koch, Sebastian; orcid:   +4 more
core   +1 more source

ADAPT: An Autonomous Forklift for Construction Site Operation

Journal of Field Robotics, EarlyView.
ABSTRACT Efficient material logistics are critical in controlling costs and schedules in the construction industry. However, manual material handling remains prone to inefficiencies, delays, and safety risks. Autonomous forklifts offer a solution to streamline on‐site logistics, reducing reliance on human operators and mitigating labor shortages.
Johannes Huemer, Markus Murschitz, Matthias Schörghuber, Lukas Reisinger, Thomas Kadiofsky, Christoph Weidinger, Mario Niedermeyer, Benedikt Widy, Marcel Zeilinger, Csaba Beleznai, Tobias Glück, Andreas Kugi, Patrik Zips   +12 more
wiley   +1 more source

Integrating multimodal data and machine learning for entrepreneurship research

Strategic Entrepreneurship Journal, EarlyView.
Abstract Research Summary Extant research in neuroscience suggests that human perception is multimodal in nature—we model the world integrating diverse data sources such as sound, images, taste, and smell. Working in a dynamic environment, entrepreneurs are expected to draw on multimodal inputs in their decision making.
Yash Raj Shrestha, Vivianna Fang He
wiley   +1 more source

Enhancing 3D Scene Graph Generation with Multimodal Embeddings

3D Scene Graphs are expressive map representations for scene understanding in robotics and computer vision. Current approaches for automated zero-shot 3D Scene Graph generation rely on spatial ontologies that relate objects with the semantic locations ...
Morales, Joseph
core