VCLab

 

RESEARCH AREAS   PEOPLE   PUBLICATIONS   COURSES   ABOUT US
Home / Publications

indicator

Elsevier Computer Vision and Image Understanding (CVIU)

 
Stereo Fusion: Combining Refractive and Binocular Disparity
 
 
  Seung-Hwan Baek Min H. Kim  
         
  KAIST  
         
  teaser
  (a) The schematic diagram of our stereo fusion system. A point p is captured by both the refractive stereo and the binocular stereo module. (b) Our prototype of the proposed stereo fusion system using a refractive medium on a binocular base.  
     
   
  Abstract
   
  The performance of depth reconstruction in binocular stereo relies on how adequate the predefined baseline for a target scene is. Wide-baseline stereo is capable of discriminating depth better than the narrow-baseline stereo, but it often suffers from spatial artifacts. Narrow-baseline stereo can provide a more elaborate depth map with fewer artifacts, while its depth resolution tends to be biased or coarse due to the short disparity. In this paper, we propose a novel optical design of heterogeneous stereo fusion on a binocular imaging system with a refractive medium, where the binocular stereo part operates as wide-baseline stereo, and the refractive stereo module works as narrow-baseline stereo. We then introduce a stereo fusion workflow that combines the refractive and binocular stereo algorithms to estimate fine depth information through this fusion design. In addition, we propose an efficient calibration method for refractive stereo. The quantitative and qualitative results validate the performance of our stereo fusion system in measuring depth in comparison with homogeneous stereo approaches.
   
  BibTeX
 
@Article{BaekKim:CVIU:2016,
  author  = {Seung-Hwan Baek and Min H. Kim},
  title   = {Stereo Fusion: Combining Refractive and Binocular Disparity},
  journal = {Computer Vision and Image Understanding (CVIU)},
  year    = {2016},
  publisher = {Elsevier},
  volume  = {146},
  pages   = {52--66}
}          
   
   
icon
Preprint paper:
PDF (5.4MB)
icon
Elsevier
Audioslides
www ScienceDirect
website
 

Hosted by Visual Computing Laboratory, School of Computing, KAIST.

KAIST