2D Guided 3D Gaussian Segmentation
Time: 01 Jan 1970, 08:00
Session: [RS1] Regular Session 1 » [RS1-3] Emerging Trends of AI/ML
Type: Virtual Presentation
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: