Rotation invariant convolutions for 3D point clouds deep learning

• المؤلفون الرئيسيون: ZHANG, Zhiyuan, HUA, Binh-Son, ROSEN, David W., YEUNG, Sai-Kit
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2019
• الموضوعات: Three-dimensional displays; Feature extraction; Deep learning; Task analysis; Neural networks; Training; Semantics; Graphics and Human Computer Interfaces; OS and Networks
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/7942; https://ink.library.smu.edu.sg/context/sis_research/article/8945/viewcontent/313100a204.pdf
• المؤسسة: 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...