Results 1 to 10 of about 90,374 (275)
3D scene graph prediction from point clouds
Virtual Reality & Intelligent Hardware, 2022 Background: In this study, we propose a novel 3D scene graph prediction approach for scene understanding from point clouds. Methods: It can automatically organize the entities of a scene in a graph, where objects are nodes and their relationships are ...
Zhong Zhou, Feihu Yan, Weimin Shi
exaly +5 more sources
3D Scene Graph Prediction on Point Clouds Using Knowledge Graphs [PDF]
2023 IEEE 19th International Conference on Automation Science and Engineering (CASE), 2023 3D scene graph prediction is a task that aims to concurrently predict object classes and their relationships within a 3D environment. As these environments are primarily designed by and for humans, incorporating commonsense knowledge regarding objects ...
Yiding Qiu, Henrik I. Christensen
semanticscholar +3 more sources
MONO-HYDRA: REAL-TIME 3D SCENE GRAPH CONSTRUCTION FROM MONOCULAR CAMERA INPUT WITH IMU [PDF]
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2023 The ability of robots to autonomously navigate through 3D environments depends on their comprehension of spatial concepts, ranging from low-level geometry to high-level semantics, such as objects, places, and buildings.
U. V. B. L. Udugama +2 more
doaj +3 more sources
Explore Contextual Information for 3D Scene Graph Generation [PDF]
IEEE Transactions on Visualization and Computer Graphics, 2022 3D scene graph generation (SGG) has been of high interest in computer vision. Although the accuracy of 3D SGG on coarse classification and single relation label has been gradually improved, the performance of existing works is still far from being ...
Yu-An Liu +6 more
semanticscholar +4 more sources
3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera [PDF]
2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019 A comprehensive semantic understanding of a scene is important for many applications - but in what space should diverse semantic information (e.g., objects, scene categories, material types, 3D shapes, etc.) be grounded and what should be its structure ...
Iro Armeni +6 more
semanticscholar +4 more sources
Scene Graph Masked Variational Autoencoders for 3D Scene Generation
Proceedings of the 31st ACM International Conference on Multimedia, 2023 Generating realistic 3D indoor scenes requires a deep understanding of objects and their spatial relationships. However, existing methods often fail to generate realistic 3D scenes due to the limited understanding of object relationships.
Rui Xu +4 more
semanticscholar +2 more sources
Long-Tail Aware Cross-Modal Graph Attention Network for Fine-Grained Indoor 3D Semantic Segmentation of Point Clouds [PDF]
SensorsAccurate and efficient semantic segmentation of point cloud data is critical in many application areas involving indoor scene understanding. In particular, fine-grained object categories, high data density, and class imbalance in high-resolution indoor ...
Erdal Özbay, Feyza Altunbey Özbay
doaj +2 more sources
Loop Closure with 3D Gaussian Splatting for Dynamic SLAM [PDF]
SensorsRobust pose estimation and high-fidelity scene reconstruction in dynamic environments represent core challenges in the field of Visual Simultaneous Localization and Mapping (SLAM).
Zhanwu Ma, Wansheng Cheng, Song Fan
doaj +2 more sources
Large language model-driven knowledge graph reasoning for enhanced semantic segmentation [PDF]
Scientific ReportsUrban scene segmentation is essential for 3D city modeling and plays a crucial role in various remote sensing applications, including urban planning and environmental monitoring.
Jinhe Su +6 more
doaj +2 more sources
LEGS: Visual Localization Enhanced by 3D Gaussian Splatting [PDF]
Journal of ImagingAccurate 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 +2 more sources