Results 21 to 30 of about 9,013,010 (294)

OpenScene: 3D Scene Understanding with Open Vocabularies

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
CVPR 2023.
Songyou Peng, Kyle Genova, Chiyu Max Jiang, Andrea Tagliasacchi, Marc Pollefeys, Thomas A. Funkhouser   +5 more
openaire   +4 more sources

TO-Scene: A Large-Scale Dataset for Understanding 3D Tabletop Scenes

, 2022
Many basic indoor activities such as eating or writing are always conducted upon different tabletops (e.g., coffee tables, writing desks). It is indispensable to understanding tabletop scenes in 3D indoor scene parsing applications. Unfortunately, it is hard to meet this demand by directly deploying data-driven algorithms, since 3D tabletop scenes are ...
Mutian Xu, Pei Chen, Haolin Liu 0004, Xiaoguang Han 0001   +3 more
openaire   +3 more sources

Using Articulated Scene Models for Dynamic 3D Scene Analysis in Vista Spaces [PDF]

, 2010
Beuter N, Swadzba A, Kummert F, Wachsmuth S. Using Articulated Scene Models for Dynamic 3D Scene Analysis in Vista Spaces. 3D Research. 2010;1(3): 4.In this paper we describe an efficient but detailed new approach to analyze complex dynamic scenes ...
Beuter, Niklas, Agnes Swadzba, Franz Kummert Sven, Kummert, Franz, Swadzba, Agnes, Wachsmuth, Sven ; https://orcid.org/, Franz Kummert, Niklas Beuter, Sven Wachsmuth   +8 more
core   +1 more source

3D Scene Segmentation for Autonomous Robot Grasping [PDF]

, 2012
Ückermann A, Elbrechter C, Haschke R, Ritter H. 3D Scene Segmentation for Autonomous Robot Grasping. Presented at the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2012), Algarve, Portugal.We present an algorithm to segment an
Ückermann, André, Elbrechter, Christof, Ritter, Helge ; https://orcid.org/, Haschke, Robert ; https://orcid.org/, Robert Haschke, Andre Uckermann, Helge Ritter, Christof Elbrechter   +7 more
core   +1 more source

Functionality understanding and segmentation in 3D scenes

2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Understanding functionalities in 3D scenes involves interpreting natural language descriptions to locate functional interactive objects, such as handles and buttons, in a 3D environment. Functionality understanding is highly challenging, as it requires both world knowledge to interpret language and spatial perception to identify fine-grained objects ...
Jaime Corsetti, Francesco Giuliari, Alice Fasoli, Davide Boscaini, Fabio Poiesi   +4 more
openaire   +6 more sources

3D Scene Annotation for Efficient Rendering on Mobile Devices [PDF]

, 2007
This paper presents a new approach for efficient 3D\ud rendering on mobile devices, where selective rendering\ud can be achieved with the help of 3D scene annotation.\ud By taking advantage of first person environments in\ud most 3D applications, we are ...
Pham, Binh L., Jinglan Zhang, Zhang, Jinglan, Siak Chuan Tan, Wong, On, Tan, Siak Chuan, Binh Pham, On Wong   +7 more
core   +1 more source

Optimization of the Virtual Scene Layout Based on the Optimal 3D Viewpoint

IEEE Access, 2022
At present, visual and parametric designs have been widely used in architectural design, urban planning and landscape design for design inspiration. Highly integrated auxiliary design software has become more prevalent and greatly changed the traditional
Yan Zhang, Gang Yang
doaj   +1 more source

Neural Scene Representations for 3D Reconstruction and Scene Understanding

, 2023
In an era where machines are increasingly integrated into our daily lives, their ability to perceive and understand the three-dimensional world becomes of great importance. Central to this capability is the scene representation, which translates sensory data into compact, detailed, and holistic descriptions of the environment.
openaire   +2 more sources

3D Scene Modeling And Understanding From Image Sequences

ELCVIA Electronic Letters on Computer Vision and Image Analysis, 2014
A new method for 3D modeling is proposed, which generates a content-based 3D mosaic (CB3M) representation for long video sequences of 3D, dynamic urban scenes captured by a camera on a mobile platform.
Hao Tang
doaj   +1 more source

Memory-Efficient 3D Scene Understanding via Quantized Multi-View Features [PDF]

ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Projecting high-dimensional representations derived with 2D foundation models onto 3D point clouds via multi-view aggregation has emerged as a powerful paradigm for 3D scene understanding.
A. Alami, A. Alami, F. Remondino
doaj   +1 more source