Presentation Details
  1. Home
  2. Presentation List
  3. Presentation Details
2D Guided 3D Gaussian Segmentation
ID：50 View Protection：ATTENDEE Updated Time：2024-10-18 08:02:01 Hits：1613 Virtual Presentation

Start Time：2024-10-26 11:20（Asia/Bangkok）

Duration：15min

Session：RS1 Regular Session 1 » RS1-3Emerging Trends of AI/ML

Video No Permission Presentation File

Tips: Only the registered participant can access the file. Please sign in first.

Abstract
We add an attribute to each Gaussian to represent its probability distribution across various categories, and use the 2D segmentation results as supervision. After learning the probability distribution, we use KNN and point cloud filtering algorithms to refine the segmentation results
Keywords
3D Gaussian, 3D Segmentation
Speaker
Kun Lan
University of Science and Technology of China

Submission Author
Kun Lan University of Science and Technology of China
Haoran Li University of Science and Technology of China
Haolin Shi University of Science and Technology of China
Wenjun Wu University of Science and Technology of China
Lin Wang AI Trust, HKUST(GZ)
Yong Liao University of Science and Technology of China
Submit Comment
Verify Code Change Another
All Comments
Important Date

  • Conference Date

    Oct 24

    2024

    to

    Oct 27

    2024

  • Oct 14 2024

    Draft paper submission deadline

  • Oct 29 2024

    Registration deadline

  • Oct 31 2024

    Contribution Submission Deadline

Sponsored By
United Societies of Science
King Mongkut's University of Technology North Bangkok (KMUTNB)
IEEE Thailand Section
IEEE Thailand Section C Chapter
Contact Information
Login to view full contact details
Previous Conferences