ABSTRACT:A new algorithm is proposed for removing large objects from digital images. The challenge is to fill in the hole that is left behind in a visually plausible way. This has been addressed by two classes of algorithms: (i) "inpainting algorithms" for filling in small image gaps, and (ii) "super resolution" techniques" for creating one enhanced resolution image. This paper presents a novel and efficient algorithm that combines the advantages of these two approaches. We first note that exemplar-based texture synthesis contains the essential process required to replicate both texture and structure; the success of structure propagation, however, is highly dependent on the order in which the filling proceeds. We propose a best-first algorithm in which the confidence in the synthesized pixel values is propagated in a manner similar to the propagation of information in inpainting.
Key Words: exemplar-based inpainting framework, non parametric patch sampling.
[1] Ashikhmin, M, ―Synthesizing natural textures‖, In I3D'01. (2001).
[2] Bertalmio, M., Sapiro, G., Caselles, V., Ballester, C. ―Image inpainting‖, In SIG-GRAPH 2000. (2000).
[3] Chan, T., Shen, J ,―Variational restoration of non-flat image features: models and algorithms‖, SIAM J. Appl. Math. 61 (2001) 1338-1361.
[4] Chang, H., Yeung, D.Y., Xiong, Y., ―Super-resolution through neighbor embedding‖, In Computer Vision and Pattern Recognition Volume I. (2004) 275-282.
[5] Criminisi, A., P´erez, P., Toyama, K, ―Region filling and object removal by examplar- based image inpainting‖, IEEE Trans. On Image Processing 13 (2004) 1200-1212.
[6] Efros, A.A., Leung, T.K, ―Texture synthesis by non-parametric sampling‖, In International Conference on Computer Vision. (1999) 1033-1038.
[7] Freeman,W.T., Jones, T.R., Pasztor, E.C, ―Example-based super resolution‖, IEEE Computer Graphics and Applications 22 (2002) 56-65.