A cross-border community for researchers with openness, equality and inclusion
Authors: Lan Kun, University of Science and Technology of China Li Haoran, University of Science and Technology of China Shi Haolin, University of Science and Technology of China Wu Wenjun, University of Science and Technology of China Wang Lin, AI Trust, HKUST(GZ)Liao Yong, University of Science and Technology of China
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
Published in: IEEE Transactions on Antennas and Propagation( Volume: 71, Issue: 4, April 2023)
Page(s): 2908 - 2921
Date of Publication: 2908 - 2921
DOI: 10.1109/TAP.2023.3240032
Publisher: UNITED SOCIETIES OF SCIENCE
