嘉宾简介：Qingyong Hu is currently a DPhil candidate in the Department of Computer Science at the University of Oxford. He received his M.Eng. degree in information and communication engineering from the National University of Defense Technology (NUDT) in 2018. His research interests lie in 3D computer vision, particularly in the semantic understanding of large-scale 3D point clouds, instance segmentation, and registration. He has published several papers in major journals and conferences including IEEE TPAMI/IJCV/CVPR/NeurIPS. His papers have been cited by 2000+ times (Google Scholar), and the RandLA-Net paper has also been listed as the most influential paper in CVPR 2020 (PaperDigest). Additionally, he also chaired 2 International Workshops (Urban3D) at ICCV’21 and ECCV’22. He was fortunately awarded the Huawei UK AI Fellowship during 2021-2023, and received the World Artificial Intelligence Conference Youth Outstanding Paper Award, and the outstanding student reviewer of ICCV 2021 (top 5%).
报告题目：Learning to Understand Large-Scale 3D Point Clouds
报告摘要：Giving machines the ability to precisely perceive and understand the 3D visual world is the fundamental step to allow them to interact competently within our physical world. However, the research on large-scale 3D scene understanding and perception is still in its infancy, due to the complex geometrical structure of 3D shapes and limited high-quality data resources. Among various 3D representations, point clouds have attracted increasing attention due to its flexibility, compactness, and the nature of closing to raw sensory data. Nevertheless, the semantic understanding of large-scale 3D point clouds remains challenging due to its orderless, unstructured, and non-uniform properties. The main goal of my DPhil project is to semantically understand large-scale 3D point clouds by learning general and robust representations using deep neural networks. In particular, several research questions including large-scale point cloud reconstruction, semantic segmentation and registration will be introduced in this presentation.