In this paper, we propose a novel matching method to establish dense correspondences automatically between two images in a hierarchical superpixel-to-pixel (HSP2P) manner. Our method first estimates dense superpixel pairings between the two images in the coarse-grained level to overcome large patch displacements and then utilize 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 datasets demonstrates that our approach achieves better visual quality outperforming state-of-theart dense matching algorithms.
|Journal||IEEE Transactions on Circuits and Systems for Video Technology|
|Early online date||27 Jul 2016|
|Publication status||Published - Dec 2017|