Rotation invariant convolutions for 3D point clouds deep learning

• Main Authors: ZHANG, Zhiyuan, HUA, Binh-Son, ROSEN, David W., YEUNG, Sai-Kit
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2019
• Subjects: Three-dimensional displays; Feature extraction; Deep learning; Task analysis; Neural networks; Training; Semantics; Graphics and Human Computer Interfaces; OS and Networks
• Online Access: https://ink.library.smu.edu.sg/sis_research/7942; https://ink.library.smu.edu.sg/context/sis_research/article/8945/viewcontent/313100a204.pdf
• Institution: Singapore Management University

Recent progresses in 3D deep learning has shown that it is possible to design special convolution operators to consume point cloud data. However, a typical drawback is that rotation invariance is often not guaranteed, resulting in networks that generalizes poorly to arbitrary rotations. In this pape...