초대의 말씀
  Program at a Glance
  초청강연
  기조연설
  협력워크샵
  공통워크샵
  분과워크샵
  특별세션I
  특별세션II
  튜토리얼
  논문발표
  조직 및 후원
  행사장소/교통/숙박
 
 
HOME > 행사안내 > Don't Believe Anything You See: Modern Digital ...
 
  Don't Believe Anything You See: Modern Digital ...

 

 

 

 

   

 

 김선주 교수 (연세대학교) 

학력: 연세대학교 전자공학과 학사(‘97), 석사(’01)

        University of North Carolina at Chapel Hill, Ph. D in Computer

        Science('08)

 

경력: National University of Singapore, Research Fellow ('09~'11)

        한국뉴욕주립대학교 컴퓨터과학과, 조교수 (‘12)

        연세대학교 컴퓨터과학과, 조교수 (‘13~현재)

 

연구분야: Computer Vision, Computational Photography, Machine Learning

 

제목

Don't Believe Anything You See: Modern Digital Photography and the Camera Imaging Pipeline

요약

In this talk, I will present a study of the in-camera image processing through an extensive analysis of more than 10,000 images from over 30 cameras. The goal of this work is to investigate if image values can be transformed to physically meaningful values, and if so, when and how this can be done. From our analysis, we found a major limitation of the imaging model employed in conventional radiometric calibration methods and propose a new in-camera imaging model that fits well with today's cameras. With the new model, we present associated calibration procedures that allow us to convert sRGB images back to their original CCD RAW responses in a manner that is significantly more accurate than any existing methods. Additionally, we show how this new imaging model can be used to build an image correction application that converts an sRGB input image captured with the wrongcamera settings to an sRGB output image that would have been recorded under the correct settings of a specificcamera.

I will also talk about several recent work on color transfer and computational photography.

 

 
 
 
Untitled Document