TUHH Open Research
Help
  • Log In
    New user? Click here to register.Have you forgotten your password?
  • English
  • Deutsch
  • Communities & Collections
  • Publications
  • Research Data
  • People
  • Institutions
  • Projects
  • Statistics
  1. Home
  2. TUHH
  3. Publication References
  4. Exploiting large-scale pre-trained vision foundation models in 3D point cloud segmentation
 
Options

Exploiting large-scale pre-trained vision foundation models in 3D point cloud segmentation

Publikationstyp
Journal Article
Date Issued
2025
Sprache
English
Author(s)
Moenck, Keno  orcid-logo
Flugzeug-Produktionstechnik M-23  
Schüppstuhl, Thorsten  orcid-logo
Flugzeug-Produktionstechnik M-23  
TORE-URI
https://hdl.handle.net/11420/61198
Journal
Allgemeine Vermessungs-Nachrichten  
Volume
132
Issue
4
Start Page
158
End Page
167
Citation
Allgemeine Vermessungs Nachrichten 132 (4): 158-167 (2025)
Publisher DOI
10.14627/avn.2025.4.2
Scopus ID
2-s2.0-105027515493
Publisher
VDE
The recent upstream of large-scale pre-trained Vision Foundation Models (VFM) follows the success of Large Language Models (LLM), e. g., the GPT series. Models like the Segment Anything Model (SAM) or Contrastive Language-Image Pre-training (CLIP) demonstrate strong generalization capabilities and open a new area of tasks, including various downstream tasks. The research vision community mainly focuses on the 2D and text modality, resulting in textual or visual promptable models capable of zero-shot object recognition or segmentation, which applications and transfer to the 3D domain are subject to current research. This article overviews approaches in leveraging large-scale pre-trained VFMs in the 3D domain. Moreover, we dive deeper into the application of the SAM and propose an approach for class-agnostic 3D segmentation in large-scale scenes.
Subjects
3D segmentation
SAM
VFM
Vision Foundation Model
DDC Class
600: Technology
006.31: Machine Learning
006.37: Machine Vision
TUHH
Weiterführende Links
  • Contact
  • Send Feedback
  • Cookie settings
  • Privacy policy
  • Impress
DSpace Software

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science
Design by effective webwork GmbH

  • Deutsche NationalbibliothekDeutsche Nationalbibliothek
  • ORCiD Member OrganizationORCiD Member Organization
  • DataCiteDataCite
  • Re3DataRe3Data
  • OpenDOAROpenDOAR
  • OpenAireOpenAire
  • BASE Bielefeld Academic Search EngineBASE Bielefeld Academic Search Engine
Feedback