Improved Exemplar-Based Inpainting with Reduced Search Space Computation from Image Wavelet Decomposition

〈Summary〉 Image inpainting is very useful to restore or remove objects from digital images. Among several techniques to restore an image, exemplar-based inpainting is one of the most widely used. In instances in which large objects are removed, it dramatically outperforms earlier works in terms of both perceptual quality and computational efficiency. However, the exemplar-based approach has certain weaknesses such as high time cost and visual inconsistency in some cases with depth ambiguities. In this paper, we improve the exemplar-based approach by reducing the search space of exemplars. We obtain this reduction by using a combination of the wavelet transform of the image with an automatic computation of the search window. Numerical simulations show that the proposed approach considerably reduces the computational cost of original exemplar inpainting whilst keeps the quality of resulting images as good as in previous technique.

[1]  G. Sapiro,et al.  A variational model for filling-in gray level and color images , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[2]  Thierry Ranchin,et al.  The ARSIS method: a general solution for improving spatial resolution of images by the means of sensor fusion , 1996 .

[3]  Jeremy S. De Bonet,et al.  Multiresolution sampling procedure for analysis and synthesis of texture images , 1997, SIGGRAPH.

[4]  Sung Yong Shin,et al.  On pixel-based texture synthesis by non-parametric sampling , 2006, Comput. Graph..

[5]  L. Wald,et al.  Fusion of satellite images of different spatial resolutions: Assessing the quality of resulting images , 1997 .

[6]  Brendt Wohlberg,et al.  Inpainting with sparse linear combinations of exemplars , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[7]  Michael Ashikhmin,et al.  Synthesizing natural textures , 2001, I3D '01.

[8]  Guillermo Sapiro,et al.  Image inpainting , 2000, SIGGRAPH.

[9]  J. Chassery,et al.  The use of multiresolution analysis and wavelets transform for merging SPOT panchromatic and multisp , 1996 .

[10]  W. Sweldens.  The Lifting Scheme: A Custom - Design Construction of Biorthogonal Wavelets "Industrial Mathematics , 1996 .

[11]  Guillermo Sapiro,et al.  Navier-stokes, fluid dynamics, and image and video inpainting , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[12]  Qiang Chen,et al.  Image Inpainting with Improved Exemplar-Based Approach , 2007, MCAM.

[13]  Huawei Chen,et al.  Image Reconstruction Based on Combination of Wavelet Decomposition, Inpainting and Texture Synthesis , 2009, Int. J. Image Graph..

[14]  Paul A. Ardis,et al.  Inpainting quality assessment , 2010, J. Electronic Imaging.

[15]  I. Daubechies,et al.  Wavelet Transforms That Map Integers to Integers , 1998 .

[16]  Patrick Pérez,et al.  Region filling and object removal by exemplar-based image inpainting , 2004, IEEE Transactions on Image Processing.

[17]  Wim Sweldens,et al.  The lifting scheme: a construction of second generation wavelets , 1998 .