VCLab

 
RESEARCH AREAS   PEOPLE   PUBLICATIONS   COURSES   ABOUT US
Home / Publications

indicator

Computer Vision and Pattern Recognition (CVPR 2016)
 
Multiview Image Completion with Space Structure Propagation
 
 
  Seung-Hwan Baek Inchang Choi Min H. Kim  
         
  Korea Advanced Institute of Science and Technology (KAIST)  
         
  teaser
  Schematic diagram of our multiview patch-based synthesis. Structure propagation: after completing the current view (a), we select a next nearest target view (b), and propagate the previous completion to (b). Structure-guided completion: we utilize multiple photographs (a), (b) and (c) to complete a target view.  
     
   
  Abstract
   
  We present a multiview image completion method that provides geometric consistency among different views by propagating space structures. Since a user specifies the region to be completed in one of multiview photographs casually taken in a scene, the proposed method enables us to complete the set of photographs with geometric consistency by creating or removing structures on the specified region. The proposed method incorporates photographs to estimate dense depth maps. We initially complete color as well as depth from a view, and then facilitate two stages of structure propagation and structure-guided completion. Structure propagation optimizes space topology in the scene across photographs, while structure-guide completion enhances, and completes local image structure of both depth and color in multiple photographs with structural coherence by searching nearest neighbor fields in relevant views. We demonstrate the effectiveness of the proposed method in completing multiview images.
   
  BibTeX
  
@InProceedings{BaekChoiKim:CVPR:2016,
  author  = {Seung-Hwan Baek and Inchang Choi and Min H. Kim},
  title   = {Multiview Image Completion with Space Structure Propagation},
  booktitle = {Proc. IEEE Computer Vision and Pattern Recognition (CVPR 2016)},
  publisher = {IEEE},  
  address = {Las Vegas, USA},
  year = {2016},
  pages = {488--496},
}
   
   
icon
 Preprint paper:
PDF (5.7MB)
icon
 Supplemental:
PDF (15.9MB)
www IEEE CVF
website
 
 

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

 KAIST