Abstract
In this paper, we propose a novel matching method to establish dense correspondences automatically between two images in a hierarchical superpixel-to-pixel manner. Our method first estimates dense superpixel pairings between the two images in the coarse-grained level to overcome large patch displacements and then utilizes superpixel level pairings to drive the matchings in the pixel level to obtain fine texture details. In order to compensate for the influence of color and illumination variations, we apply a regularization technique to rectify images by a color transfer function. Experimental validation on benchmark data sets demonstrates that our approach achieves better visual quality outperforming the state-of-the-art dense matching algorithms.
Funding Information
  • National Basic Research Program of China (973 Program) (2013CB328805)
  • National Natural Science Foundation of China (61272359, 61528106)
  • Fok Ying-Tong Education Foundation for Young Teachers
  • Specialized Fund for Joint Building Program within the Beijing Municipal Education Commission

This publication has 41 references indexed in Scilit: