Title: Learning-based Sampling over 3D Point Clouds
Tencent Meeting ID：458 657 083
Sampling (i.e., up-sampling and down-sampling) is a commonly-used technique in 3D point cloud processing for improving reconstruction quality and saving acquisition cost/storage space/transmission bandwidth/computational complexity. In this talk, I will show our recent works on learning-based sampling frameworks for 3D point cloud data. Specifically, I will introduce a geometry-centric network for 3D point cloud up-sampling, which incorporates discrete differential geometry into deep learning elegantly, followed by a novel network for task-oriented 3D point cloud down-sampling, which is designed from the perspective of matrix optimization. Extensive experiments are provided to demonstrate the advantages of our framework over the existing approaches.
Dr. Junhui Hou received the B.Eng. degree in information engineering (Talented Students Program) from the South China University of Technology, Guangzhou, China, in 2009, the M.Eng. degree in signal and information processing from Northwestern Polytechnical University, Xian, China, in 2012, and the Ph.D. degree in electrical and electronic engineering from the School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, in 2016. He has been an Assistant Professor with the Department of Computer Science, City University of Hong Kong, since 2017. His research interests fall into the general areas of visual computing, such as image/video/3D geometry data representation, processing and analysis, semi/un-supervised data modeling, and data compression and adaptive transmission
Dr. Hou was the recipient of several prestigious awards, including the Chinese Government Award for Outstanding Students Study Abroad from China Scholarship Council in 2015, and the Early Career Award (3/381) from the Hong Kong Research Grants Council in 2018. He is a member of Multimedia Systems & Applications Technical Committee (MSA-TC), IEEE CAS. He is currently serving as an Associate Editor for IEEE Transactions on Circuits and Systems for Video Technology, The Visual Computer, and Signal Processing: Image Communication, and the Guest Editor for the IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. He also served an Area Chair of ACM MM 2019 and 2020, IEEE ICME 2020, and WACV 2021. He is a senior member of IEEE.