A cross-border community for researchers with openness, equality and inclusion
2D Guided 3D Gaussian Segmentation
ID:50 View protection:Participant Only Updated time:2024-10-18 08:02:01 Views:452 Virtual Presentation

Start Time:2024-10-26 11:20

Duration:15min

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

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

Post comments
Verification Code Change Another
All comments
Important Dates
  • Conference date

    10-24

    2024

    -

    10-27

    2024

  • 10-14 2024

    Draft paper submission deadline

  • 10-29 2024

    Registration deadline

  • 10-31 2024

    Presentation 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 info