VCLab

 

RESEARCH AREAS   PEOPLE   PUBLICATIONS   COURSES   ABOUT US
Home / Publications

indicator

Computer Vision and Pattern Recognition (CVPR 2018)

 
Enhancing the Spatial Resolution of Stereo Images using a Parallax Prior
 
 
  Daniel S. Jeon Seung-Hwan Baek Inchang Choi Min H. Kim  
         
  Korea Advanced Institute of Science and Technology (KAIST)  
         
  teaser
  Compared to a naive approach of bicubic upsampling, Bhavsar et al. enhance the spatial resolution but suffer from jaggy aliasing artifacts. The proposed method can enhance the spatial resolution significantly by taking advantage of stereo input.  
     
   
  Abstract
   
  We present a novel method that can enhance the spatial resolution of stereo images using a parallax prior. While traditional stereo imaging has focused on estimating depth from stereo images, our method utilizes stereo images to enhance spatial resolution instead of estimating disparity. The critical challenge for enhancing spatial resolution from stereo images: how to register corresponding pixels with subpixel accuracy. Since disparity in traditional stereo imaging is calculated per pixel, it is directly inappropriate for enhancing spatial resolution. We, therefore, learn a parallax prior from stereo image datasets by jointly training two-stage networks. The first network learns how to enhance the spatial resolution of stereo images in luminance, and the second network learns how to reconstruct a high-resolution color image from high-resolution luminance and chrominance of the input image. Our two-stage joint network enhances the spatial resolution of stereo images significantly more than single-image super-resolution methods. The proposed method is directly applicable to any stereo depth imaging methods, enabling us to enhance the spatial resolution of stereo images.
   
  BibTeX
 
@InProceedings{Jeonetal:CVPR:2018,
  author  = {Daniel S. Jeon and Seung-Hwan Baek and Inchang Choi 
            and Min H. Kim},
  title   = {Enhancing the Spatial Resolution of Stereo Images 
            using a Parallax Prior},
  booktitle = {Proc. IEEE Computer Vision and Pattern Recognition
            (CVPR 2018)},
  publisher = {IEEE},  
  address = {Salt Lake City, Utah, United States},
  year = {2018},
  pages = {},
  volume  = {},
}    
   
   
icon
Preprint paper:
PDF (9.6MB)
icon
Supplemental:
PDF (19.9MB)
www IEEE CVF
website
www GitHub
website
 
 

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

KAIST