Results 41 to 50 of about 90,374 (275)

LLM-Supervised Point Cloud Processing: From Unsupervised 3D Scene-Graph Generation to Interactive Scene Manipulation [PDF]

The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
We demonstrate an end-to-end pipeline for 3D scene understanding which integrates unsupervised graph-based point cloud segmentation with LLM-enabled spatial reasoning and editing.
F. Poux, F. Poux, A. Key
doaj   +1 more source

A novel factor graph-based optimization technique for stereo correspondence estimation

Scientific Reports, 2022
Dense disparities among multiple views are essential for estimating the 3D architecture of a scene based on the geometrical relationship between the scene and the views or cameras.
Hanieh Shabanian, Madhusudhanan Balasubramanian   +1 more
doaj   +1 more source

ROBUST AND ACCURATE PLANE SEGMENTATION FROM POINT CLOUDS OF STRUCTURED SCENES [PDF]

ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2020
Plane segmentation from the point cloud is an important step in various types of geo-information related to human activities. In this paper, we present a new approach to accurate segment planar primitives simultaneously by transforming it into the best ...
P. Hu, Y. Liu, M. Tian, M. Hou
doaj   +1 more source

Statistical Confidence Rescoring for Robust 3D Scene Graph Generation from Multi-View Images [PDF]

IEEE International Conference on Computer Vision
Modern 3D semantic scene graph estimation methods utilize ground truth 3D annotations to accurately predict target objects, predicates, and relationships.
Qi Xun Yeo, Yanyan Li, Gim Hee Lee
semanticscholar   +1 more source

Explainable human‐in‐the‐loop healthcare image information quality assessment and selection

CAAI Transactions on Intelligence Technology, EarlyView., 2023
Abstract Smart healthcare applications cannot be separated from healthcare data analysis and the interactive interpretability between data and model. A human‐in‐the‐loop active learning approach is introduced to reduce the cost of healthcare data labelling by evaluating the information quality of unlabelled medical data and then screening the high ...
Yang Li, Sezai Ercisli
wiley   +1 more source

Integrating Prior Observations for Incremental 3D Scene Graph Prediction [PDF]

International Conference on Machine Learning and Applications
3D semantic scene graphs (3DSSG) provide compact structured representations of environments by explicitly modeling objects, attributes, and relationships.
Marian Renz, F. Igelbrink, Martin Atzmueller   +2 more
semanticscholar   +1 more source

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

Computer Vision and Pattern Recognition
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 ...
Yaxu Xie, A. Pagani, Didier Stricker
semanticscholar   +1 more source

KNA-SG: Keyframe–Node-Associated Open-Vocabulary 3D Scene Graphs from RGB Sequences

Technologies
3D scene graphs organize objects and their relationships in a scene into structured representations, providing an interpretable and queryable foundation for relational reasoning and object grounding.
Yangbin Xu, Wenhui Shi, Jing Xing, Jiangang Yang, Jian Liu   +4 more
doaj   +1 more source

3D Object Detection with Dynamic Weight Graph Convolution [PDF]

Jisuanji kexue
3D object detection is one of the most critical technologies in autonomous driving,and 3D object detection based on LiDAR is usually carried out in the scene of point cloud construction.The current methods cannot fully use the point cloud’s structural ...
LI Zongmin, RONG Guangcai, BAI Yun, XU Chang , XIAN Shiyang
doaj   +1 more source

Dynamic Scene Graph Generation of Point Clouds with Structural Representation Learning

Tsinghua Science and Technology
Scene graphs of point clouds help to understand object-level relationships in the 3D space. Most graph generation methods work on 2D structured data, which cannot be used for the 3D unstructured point cloud data.
Chao Qi, Jianqin Yin, Zhicheng Zhang, Jin Tang   +3 more
doaj   +1 more source