Combining Texture Synthesis and Diffusion for Image Inpainting

Image inpainting or image completion consists in filling in the missing data of an image in a visually plausible way. Many works on this subject have been proposed these recent years. They can mainly be decomposed into two groups: geometric methods and texture synthesis methods. Texture synthesis methods work best with images containing only textures while geometric approaches are limited to smooth images containing strong edges. In this paper, we first present an extended state of the art. Then a new algorithm dedicated to both types of images is introduced. The basic idea is to decompose the original image into a structure and a texture image. Each of them is then filled in with some extensions of one of the best methods from the literature. A comparison with some existing methods on different natural images shows the strength of the proposed approach.

[1]  Yves Meyer,et al.  Oscillating Patterns in Image Processing and Nonlinear Evolution Equations: The Fifteenth Dean Jacqueline B. Lewis Memorial Lectures , 2001 .

[2]  Marcelo Bertalmío,et al.  Strong-continuation, contrast-invariant inpainting with a third-order optimal PDE , 2006, IEEE Transactions on Image Processing.

[3]  Joachim Weickert,et al.  Anisotropic diffusion in image processing , 1996 .

[4]  Folkmar Bornemann,et al.  Fast Image Inpainting Based on Coherence Transport , 2007, Journal of Mathematical Imaging and Vision.

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

[6]  Guillermo Sapiro,et al.  Simultaneous structure and texture image inpainting , 2003, IEEE Trans. Image Process..

[7]  D. Mumford Algebraic Geometry and Its Applications , 1994 .

[8]  David Tschumperlé,et al.  Fast Anisotropic Smoothing of Multi-Valued Images using Curvature-Preserving PDE's , 2006, International Journal of Computer Vision.

[9]  Tony F. Chan,et al.  The digital TV filter and nonlinear denoising , 2001, IEEE Trans. Image Process..

[10]  Jean-Michel Morel,et al.  Level lines based disocclusion , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[11]  Guillermo Sapiro,et al.  Filling-in by joint interpolation of vector fields and gray levels , 2001, IEEE Trans. Image Process..

[12]  Harry Shum,et al.  Image completion with structure propagation , 2005, ACM Trans. Graph..

[13]  Jianhong Shen,et al.  EULER'S ELASTICA AND CURVATURE BASED INPAINTINGS , 2002 .

[14]  Rachid Deriche,et al.  Vector-valued image regularization with PDEs: a common framework for different applications , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[16]  Simon Masnou,et al.  Disocclusion: a variational approach using level lines , 2002, IEEE Trans. Image Process..

[17]  Tony F. Chan,et al.  Nontexture Inpainting by Curvature-Driven Diffusions , 2001, J. Vis. Commun. Image Represent..

[18]  Alexandru Telea,et al.  An Image Inpainting Technique Based on the Fast Marching Method , 2004, J. Graphics, GPU, & Game Tools.

[19]  Stanley Osher,et al.  Modeling Textures with Total Variation Minimization and Oscillating Patterns in Image Processing , 2003, J. Sci. Comput..

[20]  Paul Harrison,et al.  A Non-Hierarchical Procedure for Re-Synthesis of Complex Textures , 2001, WSCG.