报告题目：3D Reconstruction, Decomposition and Manipulation

主讲人： Bo YANG, The Hong Kong Polytechnic University

报告时间：2022年06月22日（星期三）14:00-15:30

报告地点：腾讯会议：727-587-424

报告摘要：

A long-standing goal in machine intelligence is to build systems that are able to infer the underlying 3D scene structure as well as understand its object composition. This is a fundamental necessity for autonomous driving, augmented reality, and robotics. This talk will firstly present reporter's recent work RangeUDF on 3D semantic surface reconstruction from sparse point clouds. After that, this talk will present repoter's recent work on 3D object decomposition and manipulation only from 2D images. At last, the key challenges and possible research directions will be discussed.

报告人简介：

Dr. Bo YANG is an Assistant Professor and leads the Visual Learning and Reasoning Group in the Department of Computing at The Hong Kong Polytechnic University. He completed his DPhil(PhD) degree in computer science at the University of Oxford. He is generally interested in machine learning, computer vision, and robotics. The overarching goal of his research is to build intelligent systems which endow machines to recover, understand, and eventually interact with the real 3D world.

Homepage: https://yang7879.github.io/

Group page: https://vlar-group.github.io/

邀请人：人工智能系 温程璐副教授