【海韵讲座】2021年第37期- Learning End-to-End 2D-3D Representations for Cross-Modality and Cross-Domain Shape Reconstruction and Processing
报告题目：Learning End-to-End 2D-3D Representations for Cross-Modality and Cross-Domain Shape Reconstruction and Processing
主讲人：钟子春，美国韦恩州立大学 副教授
时间：2021年7月28日（星期三）上午9:00-10:30
地点：腾讯会议(会议 ID：928 604 022)
摘要：
Nowadays, there is a pressing need for better visualizing and understanding 3D and 4D (micro-)structures in the raw and wild datasets. For instance, the acquisition of the in-vivo complicated 3D organ structures from multimodality image data is a grand challenge. In this talk, I will introduce some our recent research work to address the above challenges by data-driven approaches, i.e., introducing some new deep learning-based visualization schemes for high-fidelity 3D/4D geometric shape reconstruction and processing in real time, such as (1) DeepOrganNet for efficiently and effectively reconstructing 3D/4D lung models with a variety of geometric shapes by learning the smooth deformation fields from multiple templates based on a trivariate tensor-product deformation technique, leveraging an informative latent descriptor extracted from input 2D images; and (2) VC-Net for robust extraction of 3D microvascular structure through embedding the image composition, generated by maximum intensity projection, into the 3D volumetric image learning process to enhance the overall performance. Finally, some real-world biomedical applications will be discussed.
报告人简介：
Dr. Zichun Zhong is an Associate Professor of Computer Science and the Director of Computer Modeling and Imaging Visualization Lab at Wayne State University (WSU). He was an Assistant Professor at WSU from August 2015 to July 2020. He received the Ph.D. degree (2014) in Computer Science at The University of Texas at Dallas. He was a Postdoctoral Fellow (2014-2015) in Department of Radiation Oncology at UT Southwestern Medical Center at Dallas. His research interests focus on geometric computing for computer graphics, visualization, 3D computer vision, medical image processing, etc. He has published more than 50 conference and journal papers in his research fields, including SIGGRAPH, SIGGRAPH Asia, TOG, VIS, TVCG, CVPR, ICCV, MM, MICCAI, etc. He received NSF CAREER Award in 2019, NSF CRII Award in 2017, College of Engineering Faculty Research Excellence Award at WSU in 2019, Certificate of Academic Excellence at UTD in 2013, and College of Engineering Award for Excellence in Teaching at WSU in 2020.
邀请人：软件工程系 姚俊峰教授