Speakers

360° Panorama Image Processing

dgif_2017_program_book_내지_171123_최종_확인용
Seungyong Lee
Pohang Univ. of Science and Technology (POSTECH)
Dec. 1 10:40~11:45

Abstract

With the recent advent of 360° cameras, spherical panorama images are becoming more popular and widely available. In this talk, I will begin with my recent result on upright adjustment of 360° spherical panoramas. In a spherical panorama, alignment of the scene orientation to the image axes is important for providing comfortable and pleasant viewing experiences using VR headsets and traditional displays. We developed an automatic method for upright adjustment of 360° spherical panorama images without any prior information, such as depths and Gyro sensor data. We take the Atlanta world assumption and use the horizontal and vertical lines in the scene to formulate a cost function for upright adjustment. In addition to fast optimization of the cost function, our method includes outlier handling to improve the robustness and accuracy of upright adjustment. Our method produces visually pleasing results for a variety of real-world spherical panoramas in less than a second and the accuracy is verified using ground-truth data. In the talk, I will also introduce some other recent results on 360° spherical panorama image processing.

 

Biography

Seungyong Lee is a professor of computer science and engineering at the Pohang University of Science and Technology (POSTECH), Korea. He received a PhD degree in computer science from the Korea Advanced Institute of Science and Technology (KAIST) in 1995. From 1995 to 1996, he worked at the City College of New York as a postdoctoral researcher. Since 1996, he has been a faculty member of POSTECH, where he leads the Computer Graphics Group. During his sabbatical years, he worked at MPI Informatik (2003-2004) and the Creative Technologies Lab at Adobe Systems (2010-2011). His technologies on image deblurring and photo upright adjustment have been transferred to Adobe Creative Cloud and Adobe Photoshop Lightroom. His current research interests include image and video processing, deep learning based computational photography, and 3D scene reconstruction.

 

Education

  • 1995, Ph.D. in Computer Science, KAIST
  • 1990, M.S. in Computer Science, KAIST
  • 1988, B.S. in Computer Science and Statistics, Seoul National University

 

Professional Career

  • 2009.03-Present, Professor, POSTECH
  • 2010.09-2011.08, Visiting professor, Adobe Research Seattle
  • 2003.03-2009.02, Associate professor, POSTECH
  • 2003.08-2004.08, Visiting professor, MPI Informatik, Germany
  • 2003.08-2004.08, Visiting senior researcher, MPI Informatik, Germany
  • 1995.03-1996.09, Research associate, City College of New York/CUNY
  • 1993.09-1994.08, Part-time lecturer, Chungnam National University
  • 1990.03-1994.02, Teaching and research assistant, KAIST

 

Awards and Honors

  • 2014, Gahun Academic Award, KIISE
  • 2014, Best Paper Award, Pacific Graphics
  • 2014, Best Paper Awards, Grand Prize, KCGS Conference
  • 2014, Samsung HumanTech Thesis Prize, Honor Prize (PhD student, Minjung Son)
  • 2013, Samsung HumanTech Thesis Prize, Gold Prize (PhD student, Yongjin Kim)
  • 2012, ACCV 2012 Special Session Best Kinect-Application Award
  • 2012, KIISE Paper Competition in Computer Science, Honor Prize (PhD student, Minjung Son)
  • 2011, Commendation, Ministry of Culture, Sports and Tourism
  • 2011, Best Science and Engineering Paper Award, KOFST
  • 2010, Samsung HumanTech Thesis Prize, Bronze Prize (PhD student, Minjung Son)
  • 2009, Best Paper Awards, Grand Prize, HCI Korea Conference
  • 2009, Samsung HumanTech Thesis Prize, Bronze Prize (PhD student, Mincheol Yoon)
  • 2008, Frontispiece Image of Conference Proceedings, ACM Siggraph Asia
  • 2008, Microsoft Research Asia, Fellow (PhD student, Sunghyun Cho)
  • 2007, KIISE Paper Competition in Computer Science, Honor Prize (MS student, Minjung Son)
  • 2007, Ph.D. Thesis Award, Dept. of Computer Sci. & Eng., POSTECH (PhD student, Minsu Ahn)
  • 2001, Samsung HumanTech Thesis Prize, Honor Prize (PhD student, Junho Kim)