DEEP LEARNING FOR 3D VISION: ALGORITHMS AND APPLICATIONS

3D deep learning is a rapidly evolving field that has the potential to transform various industries. This book provides a comprehensive overview of the current state-of-the-art in 3D deep learning, covering a wide range of research topics and applications. It collates the most recent research advances in 3D deep learning, including algorithms and applications, with a focus on efficient methods to tackle the key technical challenges in current 3D deep learning research and adoption, therefore making 3D deep learning more practical and feasible for real-world applications.

This book is organized into five sections, each of which addresses different aspects of 3D deep learning. Section I: Sample Efficient 3D Deep Learning, focuses on developing efficient algorithms to build accurate 3D models with limited annotated samples. Section II: Representation Efficient 3D Deep Learning, deals with the challenge of developing efficient representations for dynamic 3D scenes and multiple 3D modalities. Section III: Robust 3D Deep Learning, presents methods for improving the robustness and reliability of deep learning models in real-world applications. Section IV: Resource Efficient 3D Deep Learning, explores ways to reduce the computation cost of 3D models and improve their efficiency in resource-limited environments. Section V: Emerging 3D Deep Learning Applications, showcases how 3D deep learning is transforming industries and enabling new applications for healthcare and manufacturing.

This collection is a valuable resource for researchers and practitioners interested in exploring the potential of 3D deep learning.

Contents:

• Introduction to 3D Deep Learning (Xiaoli Li, Xulei Yang, and Hao Su)
• Masked Autoencoders for 3D Point Cloud Self-Supervised Learning (Yatian Pang, Zhenghua Chen, and Li Yuan)
• You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understanding (Zhengzhe Liu, Xiaojuan Qi, and Chi-Wing Fu)
• Representation Learning for Dynamic 3D Scenes (Yunzhu Li and Jiajun Wu)
• eDiGS: Extended Divergence-Guided Shape Implicit Neural Representation for Unoriented Point Clouds (Yizhak Ben-Shabat, Chamin Hewa Koneputugodage, and Stephen Gould)
• Improving Monocular 3D Object Detection by Synthetic Images with Virtual Depth (Chenhang He and Lei Zhang)
• Robust Structured Declarative Classifiers for Point Clouds (Ziming Zhang, Kaidong Li, and Guanghui Wang)
• Towards Inference Stage Robust 3D Point Cloud Recognition (Yongyi Su, Xun Xu, and Kui Jia)
• Algorithm-System-Hardware Co-Design for Efficient 3D Deep Learning (Zhijian Liu, Haotian Tang, Yujun Lin, and Song Han)
• Sampling Strategies for Efficient Segmentation and Object Detection of 3D Point Clouds (Qingyong Hu)
• Efficient 3D Representation Learning for Medical Image Analysis (Yucheng Tang, Jie Liu, Zongwei Zhou, Xin Yu, and Yuankai Huo)
• AI-Based 3D Metrology and Defect Detection of HBMs in XRM Scans (Ramanpreet Singh Pahwa, Richard Chang, and Wang Jie)

Readership: Advanced undergraduate and graduate students, researchers and practitioners in the fields of 3D computer vision, robot perception and autonomous driving.

Key Features:

• 3D deep learning is a rapidly developing field with tremendous research value and potential real-world applications
• This is the first book collating the most recent research advances on 3D deep learning, including algorithms and applications, with a focus on efficient methods to tackle the key technical challenges occurred in current 3D deep learning research and adoption, therefore making 3D deep learning more practical and feasible for real-world applications
• This book provides a comprehensive overview of the current state-of-the-art in 3D deep learning, covering a wide range of research topics and applications
• This book will not only contribute to the advancement of 3D deep learning, but also inspire further research and create more real-world impact in this exciting field