Technical Focus Session

    Friday, 22 November

    09:00 - 13:00

    Convention Hall C

     

    Time Title & Lab Website Speaker
    09:00 - 09:10 Opening  
    09:10 - 09:30 Design Everything by Yourself -
    User interfaces for graphics, CAD modeling, and robots
    http://www-ui.is.s.u-tokyo.ac.jp/
    Takeo Igarashi
    09:30 - 09:50 Intelligent processing of internet Visual media
    http://cg.cs.tsinghua.edu.cn/research.htm
    Shi-Min Hu
    09:50 - 10:10 Graphics and Image Researches at POSTECH
    http://cg.postech.ac.kr/introduction/
    Seungyong Lee
    10:10 - 10:30 Modeling the World through Laser Scanning
    http://vcc.siat.ac.cn
    Baoquan Chen
    10:30 - 10:50 A Global Linear Structure-from-Motion Algorithm Ping Tan
    10:50 - 11:10 Coffee break  
    11:10 - 11:30 Computer Graphics Research at Zhejiang University
    http://www.cad.zju.edu.cn/english.html
    Kun Zhou
    11:30 - 11:50 Recent Activities in the HKU Graphics Group
    http://www.csis.hku.hk/GraphicsGroup
    Yizhou Yu
    11:50 - 12:10 Graphics Researches at National Taiwan University
    http://graphics.csie.ntu.edu.tw/
    Yung-Yu Chuang
    12:10 - 12:30 Computational Manga and Perception @ CUHK
    http://appsrv.cse.cuhk.edu.hk/~vrcentre/index.html
    Tien-Tsin Wong
    12:30 - 12:50 Graphics Researches at USTC
    http://gcl.ustc.edu.cn
    Ligang Liu
    12:50 - 13:00 Closing  

     

     


     

     

     

    Takeo Igarashi, University of Tokyo

     

    Title: Design Everything by Yourself -- User interfaces for graphics, CAD modeling, and robots

     

    Abstract: We live in a mass-production society today and everyone buys and uses the same things all over the world. This is cheap, but not necessarily ideal for individual persons. We envision that computer tools that help people to design things by themselves can enrich their lives. To that end, we develop innovative interaction techniques for end users to (1) create rich graphics such as three-dimensional models and animations by simple sketching (2) design their own real-world, everyday objects such as clothing and furniture with realtime physical simulation integrated in a simple geometry editor, and (3) design the behavior of their personal robots and give instructions to them to satisfy their particular needs.

     

    Bio: Takeo Igarashi is a professor at CS department, the University of Tokyo. He received PhD from Dept of Information Engineering, the University of Tokyo in 2000. His research interest is in user interface in general and current focus is on interaction techniques for 3D graphics. He is known as the inventor of sketch-based modeling system called Teddy, and received The Significant New Researcher Award at SIGGRAPH 2006. He is currently leading a JST ERATO Igarashi Design Interface Project as a director.

     

     


     

     

    Shi-Min Hu, Tsinghua University

     

    Title: Intelligent processing of internet Visual media

     

    Abstract: With the rapid progress of internet technology, massive visual media data has been emerging on the internet, which brings a big opportunity to the new evolution of information technology, as well as the industry development. Given the massive visual media data, how to find the inherent patterns, systematical management, efficient processing and utilization is a great challenge. Visual media itself has the properties of large file size, no inherent structures, high dimension and rich semantics. In this talk, I will introduce some research of Graphics Group in Tsinghua on intelligent processing of internet visual media, include visual media analysis, search, systhesis and composition.

     

    Bio: Shi-Min Hu received the PhD degree from Zhejiang University in 1996. He is currently a chair professor of computer science in the Department of Computer Science and Technology, Tsinghua University, Beijing. His research interests include digital geometry processing, video processing, rendering, computer animation, and computer-aided geometric design. He is associate editor-in-chief of The Visual Computer and on the editorial boards of Computer Aided Design, Computer & Graphics, and IEEE TVCG. He is a member of the IEEE, ACM and CCF.

     

     


     

     

    Seungyong Lee, Pohang University of Science and Technology (POSTECH)

     

    Title: Graphics and Image Researches at POSTECH

     

    Abstract: POSTECH Computer Graphics Group has been investigating on various topics in graphics and related areas, including image and video processing, non-photorealistic rendering, and 3D surface reconstruction. In image and video processing, we worked on image/video deblurring and photo upright adjustment. In non-photorealistic rendering, we developed stylistic rendering methods for 2D images and 3D models. In surface reconstruction, we work on simple geometry reconstruction from 3D points captured by MS Kinect. In this talk, I will briefly introduce recent research results of the group as well as on-going research projects. Recent papers of the group can be found at http://cg.postech.ac.kr/publications/

     

    Bio: Seungyong Lee is a professor of computer science and engineering at Pohang University of Science and Technology (POSTECH), Korea. He received a PhD degree in computer science from Korea Advanced Institute of Science and Technology (KAIST) in 1995. From 1995 to 1996, he worked at City College of New York as a postdoctoral research associate. Since 1996, he has been a faculty member of POSTECH, where he leads the Computer Graphics Group. He spent sabbatical years at MPI Informatik in Germany (2003-2004) and Adobe Research in Seattle (2010 ~ 2011). His current research interests include image and video processing, non-photorealistic rendering, 3D surface reconstruction, and graphics applications.

     

     


     

     

    Baoquan Chen, Shandong University

     

    Title: Modeling the World through Laser Scanning

     

    Abstract: 3D has been becoming an integral part of digital media. Especially, Digital Earth platforms such as Google Earth and Apple 3D Maps have seen explosive growth in applications by governments, industry, and end users. This has thus provided impetus for more efficient and capable tools to push representation and simulation of urban environments to a finer level than it is today. In this talk we introduce our effort on acquiring, modeling, and analyzing large and detailed urban environments, facilitating generation of a "live" digital city. Specifically we introduce a set of methods and tools for reconstructing both exterior and interior structures based on laser-scanned 3D point clouds and color photos.

     

    Bio: Baoquan Chen is a Professor of Shandong University, where he is also the Dean of School of Computer Science and Technology. Prior to the current post, he was the founding director of the Visual Computer Research Center, Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Sciences (2008-2013), and a faculty member at Computer Science and Engineering at the University of Minnesota at Twin Cities (2000-2008). His research interests generally lie in computer graphics, visualization, and human-computer interaction, focusing specifically on large-scale city modeling, simulation and visualization. He has published more than 80 papers in international journals and conferences, including more than a dozen papers in SIGGRAPH and SIGGRAPH Asia. Chen received an MS in Electronic Engineering from Tsinghua University, Beijing (1994), and a second MS (1997) and then PhD (1999) in Computer Science from the State University of New York at Stony Brook. Chen is the recipient of the Microsoft Innovation Excellence Program 2002, the NSF CAREER award 2003, McKnight Land-Grant Professorship at University of Minnesota for 2004-2006, IEEE Visualization Best Paper Award 2005, and mostly recently, the NSFC "Outstanding Young Researcher" program in 2010.

     

     


     

     

    Ping Tan, National University of Singapore

     

    Title: A Global Linear Structure-from-Motion Algorithm

     

    Abstract: I will present a linear and global optimization method for structure-from-motion from pairwise relative poses encoded in essential matrices. This method minimizes an approximate geometric error to enforce the triangular relationship in camera triplets. This formulation does not suffer from the typical ‘unbalanced scale’ problem in previous linear methods; nor the system degeneracy from collinear motion. In the case of three cameras, this method provides a good linear approximation of the trifocal tensor. It can be directly scaled up to register multiple cameras. The results obtained are accurate for point triangulation and can serve as a good initialization for final bundle adjustment. This system produces good accuracy, robustness, and outperforms some well-known systems on efficiency.

     

    Bio: Ping Tan is an assistant professor at the Department of Electrical and Computer Engineering at the National University of Singapore. He received the Ph.D. degree in Computer Science & Engineering from the Hong Kong University of Science and Technology in 2007. Before that, he received the B.S. degree in Applied Mathematics and M.S. degree in Pattern Recognition and Intelligent System from Shanghai Jiao Tong University, China, in 2000 and 2003 respectively. Dr. Tan's research interests include computer vision and computer graphics. He has served as an editorial member of the International Journal of Computer Vision (IJCV), an associate editor of the Machine Vision and Applications (MVA). He has served in the program committees of SIGGRAPH, SIGGRAPH Asia. He received the inaugural MIT TR35@Singapore award in 2012 (among 12 top innovators under 35 from Southeast Asia, Australia, and New Zealand), the Image and Vision Computing Outstanding Young Researcher Award Honorable Mention Award in 2012.

     

     


     

     

    Kun Zhou, Zheijiang Univeristy

     

    Title: Computer Graphics Research at Zhejiang University

     

    Abstract: In this talk I will briefly introduce recent graphics projects conducted at the State Key Lab of CAD&CG, Zhejiang University, including surface/volume remeshing, GPU-based film rendering, and human-centric graphics.

     

    Bio: Kun Zhou is a Cheung Kong Professor and vice dean of the computer science department of Zhejiang University. Prior to joining Zhejiang University in 2008, he was a Lead Researcher of the Internet Graphics Group at Microsoft Research Asia. He received his BS degree and PhD degree from Zhejiang University in 1997 and 2002, respectively. His research interests include computer graphics and parallel computing, in the areas of geometry processing, real-time rendering and GPU parallel computing. He is currently on the editorial board of ACM Transactions on Graphics, The Visual Computer, and the Frontiers of Computer Science.

     

     


     

     

    Yizhou Yu, The University of Hong Kong

     

    Title: Recent Activities in the HKU Graphics Group

     

    Abstract: This talk introduces recent research activities in the computer graphics group at The University of Hong Kong. It gives an overview of recent projects on computational photography, image-based graphics, mesh generation, surface modeling as well as the analysis and synthesis of repetitive phenomena, including textures, noises, structures, motions, and interactions.

     

    Bio: Yizhou Yu is a professor in the Department of Computer Science at the University of Hong Kong and an adjunct professor at University of Illinois, Urbana-Champaign. He is a recipient of National Science Foundation CAREER Award and best paper awards at ACM SIGGRAPH/EG Symposium on Computer Animation. Dr Yu is currently on the editorial board of Computer Graphics Forum and International Journal of Software and Informatics. He was a program co-chair of Computer Animation and Social Agents 2011 and Pacific Graphics 2009. He has served on the program committee of many leading international conferences, including SIGGRAPH, SIGGRAPH Asia, and International Conference on Computer Vision.

     

     


     

     

    Yung-Yu Chuang, National Taiwan University

     

    Title: Graphics Researches at National Taiwan University

     

    Abstract: In this talk, I will give a brief introduction to recent graphics related researches at National Taiwan University. The topics include stereoscopic media processing, variance reduction for Monte Carlo rendering and computational photography.

     

    Bio: Yung-Yu Chuang is a professor of the Department of Computer Science and Information Engineering at National Taiwan University. He received his B.S. and M.S. from National Taiwan University in 1993 and 1995 respectively, Ph.D. from University of Washington at Seattle in 2004, all in Computer Science. He joined National Taiwan University in 2004. His research spans the fields of computer graphics, computer vision and multimedia, with focus on computational photography and rendering. Professor Chuang has served on the editorial board of IEEE CG&A and the program committees of several prestigious conferences including ACM SIGGRAPH Asia, IEEE CVPR, IEEE ICCV and IEEE ICCP.

     

     


     

     

    Tien-Tsin Wong, Chinese University of Hong Kong

     

    Title: Computational Manga and Perception @ CUHK

     

    Abstract: Tien-Tsin Wong is known with his pioneer works in Computational Manga, Image-based Relighting, Ambient Occlusion (Dust Accumulation Simulation), Sphere Maps, and GPGPU for Evolutionary Computing. He is currently a Professor in the Computer Science & Engineering Department of the Chinese University of Hong Kong. He is also the director of Digital Visual Entertainment Laboratory at CUHK Shenzhen Research Institute (CUSZRI). He is an ACM Senior Member and a HKIE Fellow. He received the IEEE Transactions on Multimedia Prize Paper Award 2005 and the Young Researcher Award 2004. He was the Academic Committee of Microsoft Digital Cartoon and Animation Laboratory in Beijing Film Academy, visiting professor in both South China University of China and School of Computer Science and Technology at Tianjin University, and the visiting research professor in Biomedical Engineering Department of Shanghai Jiaotong University. Besides, he is also active in transferring graphics technologies to games industry, including writing articles in books for game developers. His main research interests include computer graphics, computational manga, computational perception, pre-computed lighting, image-based rendering, GPU techniques, medical visualization, multimedia compression, and computer vision. More information about him can be found at http://www.cse.cuhk.edu.hk/~ttwong/.

     

    Bio: Yung-Yu Chuang is a professor of the Department of Computer Science and Information Engineering at National Taiwan University. He received his B.S. and M.S. from National Taiwan University in 1993 and 1995 respectively, Ph.D. from University of Washington at Seattle in 2004, all in Computer Science. He joined National Taiwan University in 2004. His research spans the fields of computer graphics, computer vision and multimedia, with focus on computational photography and rendering. Professor Chuang has served on the editorial board of IEEE CG&A and the program committees of several prestigious conferences including ACM SIGGRAPH Asia, IEEE CVPR, IEEE ICCV and IEEE ICCP.

     

     


     

     

    Ligang Liu, University of Science and Technology of China

     

    Title: Graphics Researches at USTC

     

    Abstract:  The graphics group at the University of Science and Technology of China (USTC) primarily focuses on the mathematical foundations of computer graphics, geometric modeling, image processing, scientific computing, and information visualization. I will introduce recent researches on computer graphics at USTC.

     

    Bio: Ligang Liu is a professor at the School of Mathematical Sciences, University of Science and Technology of China. He received his B.Sc. in applied mathematics (1996) and his Ph.D. in computer aided geometric design and computer graphics (2001) from Zhejiang University, China. Between 2001 and 2004, he worked at Microsoft Research Asia as an associate researcher. Then he worked at Zhejiang University as an associate professor and professor during 2004 and 2012. He paid an academic visit to Harvard University during 2009 and 2011. His research interests include digital geometric processing, computer graphics, and image processing. His research works could be found at his research website: http://staff.ustc.edu.cn/~lgliu