T3DNet: compressing point cloud models for lightweight 3-D recognition

• Main Authors: Yang, Zhiyuan, Zhou, Yunjiao, Xie, Lihua, Yang, Jianfei
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2025
• Subjects: Engineering; 3-D model compression; Knowledge distillation
• Online Access: https://hdl.handle.net/10356/182680
• Institution: Nanyang Technological University

The 3-D point cloud has been widely used in many mobile application scenarios, including autonomous driving and 3-D sensing on mobile devices. However, existing 3-D point cloud models tend to be large and cumbersome, making them hard to deploy on edged devices due to their high memory requirements a...