简介：KYOUNG MU LEE (Fellow, IEEE) is currently the Editor in Chief of the IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (TPAMI); He received the B.S. and M.S. degrees in control and instrumentation engineering from Seoul National University (SNU), Seoul, South Korea, in 1984 and 1986, respectively, and the Ph.D. degree in electrical engineering from the University of Southern California, in 1993. He is the director of the Interdisciplinary Graduate Program in Artificial Intelligence at 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; the Okawa Foundation Research Grant Award, in 2006; the Distinguished Professor Award from the College of Engineering of SNU, in 2009; 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).
报告题目：Toward Real-World Image Super-Resolution: Challenges and Approaches
报告摘要：Image Super Resolution (SR) which aims to reconstruct a high-resolution (HR) image from a low-resolution (LR) input, plays an essential role in computer vision, digital photography, and many real applications. Recently, a plethora of SR methods have been developed based on deep CNNs and large-scale datasets. However, most of the state-of-the-art methods still do not generalize well to real-world scenarios even though they perform relatively well on public benchmarks. In this talk, we will address some of the technical issues and challenges in the real-world SR problem including the domain gap, arbitrary scale transformation, and real-time processing issues. And then we introduce new approaches to tackle these challenges by learning unknown real down-sampling process via GAN with new effective losses, allowing generalized Image SR under arbitrary transformation, and optimizing the network structures via adaptive quantization and pruning. We empirically demonstrate that our new strategie