Efficient seam carving for object removal
Bo Yan, Yiqi Gao, Kairan Sun, Bo Yang · 2013
This paper introduces a new object removal approach for images based on discontinuous seam carving. Existing seam carving based object removal methods generally are time-consuming and oftentimes cause image distortion or cutting off many more seams than is necessary. In order to solve these limitations, our proposed method only considers the energy of all the pixels outside the target region. Firstly, based on the discontinuous seam carving, we calculate the energy map of both directions, up-down and bottom-up. Then we carve the seam respectively from the upper bound of the target region to up, from the lower bound of the target region to down and the middle part within the region. Experimental results prove that our proposed method outperform others in terms of efficiency and image quality significantly.