Title:3D Human Pose and Shape Estimation from Single Image: Challenges and Applications
Date: 2023-12-11 14:30-16:00
Location: CSIE R103
Speaker: Prof. Kyoung Mu Lee, Seoul National University
Host: Prof. Wen-Huang Cheng
Abstract:
Recovering accurate 3D human pose and shape from images poses a significant challenge, particularly in in-the-wild scenarios. Despite advancements in deep learning, 3D Human Pose and Shape Estimation (3DHPSE) still faces hurdles, including the scarcity and high cost of labeled data. In this talk, I will discuss recent developments and share the findings of our research group regarding this problem. We will address the issue of limited labeled data by exploring self-supervised representation learning (SSL) techniques for 3DHPSE. Our empirical study will analyze common SSL methods and alternative pre-training approaches to identify the most effective option. Furthermore, I will introduce our integrated framework designed to reconstruct the 3D pose and shape of the whole-body, encompassing the body, hands, and face. Specifically, I will present a novel method that leverages body and hand features to estimate accurate and robust hand shapes. To highlight a practical application, I will showcase the results of applying our whole-body 3DHPSE method to sign language recognition. Additionally, I will discuss the potential of our approach and explore areas that require further investigation for real-world in-the-wild applications.
Biography:
Kyoung Mu Lee (Fellow, IEEE) is currently the Editor-in-Chief of the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI); He is the director of the Interdisciplinary Graduate Program in Artificial Intelligence at Seoul National University (SNU). He is an Advisory Board Member of the Computer Vision Foundation (CVF). He was a Distinguished Lecturer of the Asia-Pacific Signal and Information Processing Association (APSIPA), from 2012 to 2013. He has received several awards, in particular, the Medal of Merit and the Scientist of Engineers of the Month Award from the Korean Government, in 2018 and 2020, respectively; the Most Influential Paper Over the Decade Award by the IAPR Machine Vision Application, in 2009; the ACCV Honorable Mention Award, in 2007; and the SNU Excellence in Research Award in 2020. He has also served as a General Chair for ICCV2019, ACMMM2018, and ACCV2018; a Program Chair for ACCV2012; a Track Chair for ICPR2020 and ICPR2012; and an Area Chair for CVPR, ICCV, and ECCV many times. He has served as an Associate Editor-in-Chief (AEIC) and an Associate Editor for the Machine Vision and Application (MVA) journal, the IPSJ Transactions on Computer Vision and Applications (CVA), and the IEEE SIGNAL PROCESSING LETTERS (SPL); and an Area Editor for the Computer Vision and Image Understanding (CVIU). He is the founding member and served as the President of the Korean Computer Vision Society (KCVS). Prof. Lee is a Fellow of IEEE, a member of the Korean Academy of Science and Technology (KAST) and the National Academy of Engineering of Korea (NAEK).