RISurConv : Rotation invariant surface attention-augmented convolutions for 3D point cloud classification and segmentation

• Main Authors: ZHANG, Zhiyuan, YANG, Licheng, XIANG Zhiyu
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Point cloud; Rotation invariant; Attention; Deep learning; Artificial Intelligence and Robotics; Computer Sciences
• Online Access: https://ink.library.smu.edu.sg/sis_research/9747; https://ink.library.smu.edu.sg/context/sis_research/article/10747/viewcontent/2408.06110v1.pdf
• Institution: Singapore Management University

Despite the progress on 3D point cloud deep learning, most prior works focus on learning features that are invariant to translation and point permutation, and very limited efforts have been devoted for rotation invariant property. Several recent studies achieve rotation invariance at the cost of low...