Speakers

Computational Media: from Processing to Creation of Media Contents

dgif_2017_program_book_내지_171123_최종_확인용
Jean-Charles Bazin
KAIST
Nov. 30 14:25~14:55

Abstract

Computational media refers to the analysis and creation of media contents with computer algorithms, such as photos, videos, VR/AR experiences and music. It encompasses several disciplines such as computer vision, machine learning and multimedia. Exploring the complementarity of these disciplines provides exciting research opportunities and opens a wide range of novel and unconventional applications. In this talk, I will present some of our representative computational media projects on gaze correction in Skype calls, editing of facial performance videos and automatic camera control.

 

Biography

Jean-Charles Bazin received the MS degree in computer science from the Universite de Technologie de Compiegne, France, in 2006, and the PhD degree in electrical engineering from KAIST, South Korea, in 2011. He is an assistant professor at KAIST, where he holds a joint appointment at the Graduate School of Culture Technology (CT) and the School of Electrical Engineering (EE). Before joining KAIST, he was an associate research scientist at Disney Research Zurich, Switzerland, and a postdoc at the Computer Graphics Laboratory of Prof. Markus Gross and at the Computer Vision and Geometry Group of Prof. Marc Pollefeys at ETH Zurich, Switzerland. He was also a postdoctoral fellow at Computer Vision Lab of Prof. Katsushi Ikeuchi, Tokyo, Japan. He is a member of the IEEE.

 

Education

  • 2006.09-2010.08, PhD in Electrical Engineering at Robotics and Computer Vision Lab, KAIST, South Korea
    – Thesis title: Catadioptric Vision for Robotic Applications
    – Advisor: Professor Inso Kweon
    – Graduation: February 2011 (PhD defense in July 2010)
    – Committee: Peter Sturm (INRIA, France), Pascal Vasseur (UPJV, France), Jong Beom Ra (KAIST, South Korea), Hyun Wook Park (KAIST, South Korea)
  • 2001.09-2006.07, Engineering degree in Computer Science at Université de Technologie de Compiègne (UTC), France
    – Specialization: Computer Vision and Artificial Intelligence
    – Minor: Philosophy and Cognitive Science
    – Exchange student in Computer Science, at KAIST, South Korea (one semester, 2004)
    – Exchange student in Aeronautics, at NEWI, Great Britain (one semester, 2002)
  • 2005.09-2006.07, Master degree (“master recherche”) at UTC, France
    – Specialization: Computer Vision and Artificial Intelligence
  • 2001.06, Scientific high school diploma (“baccalauréat”), Rennes, France
    – Major: mathematics – graduated with honors

 

Professional Career

  • 2017.06–Present, Assistant Professor at KAIST, Korea
  • 2014.08–2017.05, Associate Research Scientist at Disney Research Zurich, Switzerland
    – Collaborators: Markus Gross and Alexander Sorkine-Hornung
    – Member of the Imaging and Video Group
    – Adjunct Lecturer at ETH Zurich
  • 2011.09-2014.07, Senior Researcher (Oberassistent) at Computer Graphics Lab (CGL) and Computer Vision and Geometry Group (CVG), ETH Zurich, Switzerland
    – Collaborators: Prof. Markus Gross and Prof. Marc Pollefeys
    – 2011.09–2013.12, Postdoctoral researcher
    Member of the BeingThere Center, a US$18 million international joint research effort between ETHZ in Switzerland, UNC in USA and NTU in Singapore
    Development of 2D/3D image and video processing tools in the context of 3D telepresence
    Supervision of bachelor, master and PhD students
    – Adjunct Lecturer at ETH Zurich
  • 2010.09-2011.04, Postdoctoral fellow at Computer Vision Lab, University of Tokyo, Japan
    – Collaborator: Professor Katsushi Ikeuchi
    – Topic: 3D reconstruction, omnidirectional vision and global optimization in the context of e-Heritage applications
    Omnidirectional video stabilization and virtual view synthesis
    Registration of 3D range data for large scale 3D merging
  • 2006.09-2010.08, Graduate student researcher at RCV Lab, KAIST, South Korea
    – Omnidirectional vision: calibration, motion estimation, 3D reconstruction, virtual view synthesis
    – Robust estimation and global optimization
    – Supervision of internship students

 

Awards and Honors

  • Top5 of the most promising ETH innovations of the year (2013) for our work on “gaze correction for home video-conferencing”
  • Silver prize at the prestigious 2011 Samsung Human-Tech competition (out of about 1300 papers) for the work on “rotation estimation by omnidirectional vision” with a US$5000 prize money. This competition aims “to search for creative and driven young people who will lead the field of science into the future for Korea”
  • “Honorable Jang Lyeo Sang Prize” at Samsung Techwin 2010 for the work on “object tracking in omnidirectional images”
  • 2008, 2009, “Outstanding PhD research award” at KAIST for my 2nd and 3rd years of PhD
  • 2006, Award of 6000 Euros from the French Ministry of Education based on the academic merit (master course)