Sunghyun Cho

I am an assistant professor at DGIST. Before joining DGIST, I worked for Samsung Electronics from April 2014 to April 2017, and worked as a post-doctoral research scientist at Adobe Research in Seattle from March 2012 to March 2014. I received my Ph.D. degree in Computer Science from POSTECH in Feb. 2012 and my B.S. degrees in Computer Science, and in Mathematics from POSTECH in 2005. My research interest includes computational photography, image/video processing, image restoration, etc.


Work Experience

  • Assistant Professor at DGIST
    • April 2017 –
    • Daegu, South Korea
  • Senior engineer at Samsung Electronics
    • April 2014 ~ April 2017
    • Suwon, South Korea
  • Post-doctoral research scientist at Adobe Research
    • March 2012 ~ March 2014
    • Seattle, WA, US
  • Intern at Creative Technologies Lab, Adobe Systems Inc
    • Jul. 2010 ~ Nov. 2010
    • Worked on video deblurring with Dr. Jue Wang
    • Seattle, WA, US
  • Intern at Microsoft Research Asia
    • Aug. 2006 ~ Feb. 2007
    • Worked on removing non-uniform motion blur from images with Dr. Yasuyuki Matsushita
    • Beijing, China



Professional Activities

  • Organizer of IREw 2014 (a workshop program at ACCV 2014)
  • Journal reviewer: ACM Trans. on Graphics, IEEE Trans. on Pattern Analysis and Machine Intelligence, IEEE Trans. on Image Processing, The Visual Computer, Computers & Graphics, Signal Processing: Image Communication, Journal of Computing Science and Engineering, IEEE Signal Processing Letters, Graphical Models, Journal of Computer Science and Technology, Korean Computer Graphics Society (KCGS) Journal, etc…
  • Conference reviewer: ACM SIGGRAPH, ACM SIGGRAPH Asia, Computer Vision and Pattern Recognition (CVPR), International Conference on Computer Vision (ICCV), European Conference on Computer Vision (ECCV), British Machine Vision Conference (BMVC), Visual Communications and Image Processing (VCIP), International Confererence on Pattern Recognition (ICPR), IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), etc…



  • KCGS 2017 Best Paper Award
    • July 14, 2017
    • 한국 컴퓨터그래픽스 학회
    • 딥러닝을 이용한 수평 보정, 홍은빈, 전준호, 조성현, 이승용
  • Outstanding Reviewer for CVPR 2017
    • July 2017
  • Outstanding Reviewer for CVPR 2013
    • June 2013
  • Nominated for KCGS (Korea Computer Graphics Society) Young Researcher Award
    • July 2011
  • BK21 국제부문 우수실적상
    • Feb. 26, 2009
    • 포항공과대학교 미래정보기술사업단
  • HCI 2009 Best Paper Award (최우수논문상)
    • Feb. 10, 2009
    • A domestic conference
    • Efficient Image Deblurring using Edge Prediction
    • 국문: 에지 예측을 기반으로 한 효율적인 영상 디블러링
  • Microsoft Research Asia 2008 Graduate Research Fellowship Award
    • Oct. 30, 2008
  • Graduated from POSTECH with honor (Magna Cum Laude)
    • Aug. 17, 2005
  • 10th place at the 2005 ACM International Collegiate Programming Contest
    • Asia regional (Seoul)
    • Team: The Love Bug
  • 12th place at the 2004 ACM International Collegiate Programming Contest
    • Asia regional (Seoul)
    • Team: BugInside
  • Bronze award (10th place) at the 2003 ACM International Collegiate Programming Contest
    • Asia regional (Seoul)
    • Team: The Artists of Programming
  • 2002 Korea Information Security Agency (KISA) 2002 대학동아리 정보보호 기술지원 개발사업 특별상
    • SNMP project of POSTECH Laboratory for Unix Security (PLUS)



  • Pil Joong Lee, POSTECH Laboratory for Unix Security (PLUS), Dae Hyun Yum, “Advanced Security PLUS for UNIX,” 2003,, I wrote Ch.3 Kernel Hacking.




Some of my past projects

Image deblurring

Since my Ph.D. study, I’ve been trying to make image deblurring more practical solution for consumer photography. Specifically, I’ve worked on blind deconvolution, non-blind deconvolution, noise & outlier handling, and non-uniform deblurring. Especially, my efficient blind deconvolution method, which was presented at SIGGRAPH Asia 2009, has been proven to be one of the fastest and most reliable methods by several following works by other researchers, and it is still one of the state-of-the-arts.
For the complete list of my published papers, please refer to Publications.
When I was a postdoc at Adobe Research, I had worked on a tech transfer project, which aimed at shipping deblurring technology with Adobe Photoshop. The first version of “Shake Reduction”, which was based on my research, was first released in the summer of 2013 as a new feature of Photoshop CC.

Below is a demo presented at Adobe MAX 2011 Sneak Peek, which sparked huge buzz on the internet.