Hierarchical super-resolution-based inpainting

Olivier Le Meur 1        Mounira Ebdelli 2        Christine Guillemot 2

1IRISA/univsersity of Rennes 1, France
2IRISA/INRIA, France

IEEE Transactions on Image Processing (2013)

Back

Abstract

This paper introduces a novel framework for examplar-based inpainting. It consists in performing first the inpainting on a coarse version of the input image. A hierarchical super-resolution algorithm is then used to recover details on the missing areas. The advantage of this approach is that it is easier to inpaint low-resolution picture than a high one. The gain is both in terms of computational complexity and visual quality. However, to be less sensitive to the setting of the inpainting method, the low-resolution input picture is inpainted several times with different configurations. Results are efficiently combined with a loopy belief propagation and details are recovered by a single-image super-resolution algorithm. Experimental results in a context of image editing and texture synthesis demonstrate the effectiveness of the proposed method. Results are compared to five state-of-the-art inpainting methods.

Results


Click on the picture above to visit the gallery of example images

Comparison with existing methods


Click on the picture above to visit the gallery of example images

Citation

Le Meur, Olivier and Ebdelli, Mounira and Guillemot, Christine (2013). Hierarchical super-resolution-based inpainting, IEEE Transactions on Image Processing, vol. 22(10), pp. 3779-3790. 
@ARTICLE{LeMeur2013,
 author = {Le Meur, Olivier and Ebdelli, Mounira and Guillemot, Christine},
 title  = {Hierarchical super-resolution-based inpainting},
 journal= {IEEE Transactions on Image Processing},
 volume = {22},
 number = {10},
 pages = {3779-3790},
 year   = {2013},
 doi    = {10.1109/TIP.2013.2261308}
}

Software

Related