초대의 말씀
  Program at a Glance
  초청강연
  기조연설
  협력워크샵
  공통워크샵
  분과워크샵
  특별세션I
  특별세션II
  튜토리얼
  논문발표
  조직 및 후원
  행사장소/교통/숙박
 
 
HOME > 행사안내 > Robust Depth Map Estimation for Radiometrically...
 
  Robust Depth Map Estimation for Radiometrically...

 

 

 

 

 

 

 

 

 

  

 

 

 

 

 

  

 

 

 

 

 

 

 허용석 교수 (아주대학교)

 학력: 2012.08   서울대학교 전기컴퓨터공학부 박사

         2007.02   서울대학교 전기컴퓨터공학부 석사

         2005.02   서울대학교 전기공학부 학사

 

 주요경력: 2014.09–현재       아주대학교 전자공학과 조교수

               2012.10-2014.08   삼성전자 DMC 연구소 책임연구원

               2012.06–2012.09   Microsoft Research Intern

               2011.09–2012.03   Microsoft Research Asia Intern   

 

 연구분야: computer vision, image processing, computational photography

 

 주요논문: Simultaneous Depth Reconstruction and Restoration of Noisy Stereo Images using Non-local Pixel Distribution, IEEE CVPR 2007, Illumination and Camera Invariant Stereo Matching, IEEE CVPR 2008, Mutual Information-based Stereo Matching Combined with SIFT Descriptor in Log-chromaticity Color Space, IEEE CVPR 2009, Simultaneous Color Consistency and Depth Map Estimation for Radiometrically Varying Stereo Images, IEEE ICCV 2009, Ghost-free High Dynamic Range Imaging, ACCV 2010, Superpixel Coherency and Uncertainty Models for Semantic Segmentation, IEEE ICCV Workshop 2013, Robust Stereo Matching using Adaptive Normalized Cross Correlation, IEEE TPAMI 2011, Joint Depth Map and Color Consistency Estimation for Stereo Images with Different Illuminations and Cameras, IEEE TPAMI 2013.등 국내외 논문 12편

 

제목

Robust Depth Map Estimation for Radiometrically Varying Stereo Images

요약

Stereo matching aims to obtain depth map or 3D information by finding correct correspondence between images captured from different point of views or at different times. In general, most stereo algorithms assume radiometrically calibrated images. For these calibrated images, simple matching costs such as absolute difference of intensities do not degrade the performance of stereo algorithms. However, there exist many real and practical situations or challenging applications in which radiometric variations between stereo images are inevitable.

 In this presentation, we present several robust depth map estimation and color correction methods for solving these problems.  Experimental

results show that our methods outperform other state-of-the-art stereo

methods under severely different radiometric conditions between stereo images.

 

 
 
 
Untitled Document