Simultaneous inpainting for image structure and texture using anisotropic heat transfer model
- 338 Downloads
We propose a PDE-based image inpainting method using anisotropic heat transfer model, which can simultaneously propagate the structure and texture information. In structure inpainting, the propagating direction and intensity are related to image contents, and the strength of propagation along gradient direction is made inversely proportional to the magnitude of gradient. In texture inpainting, the added texture term reflects periodicity along the texture and its perpendicular direction. For numerical implementation, the step size of finite difference is adaptively chosen according to the curvature, leading to fewer iteration steps and satisfactory inpainting quality. Compared with other high order PDE methods and layered methods, the proposed approach is more concise and doesn’t need image decomposition. Experiments are carried out to show effectiveness of the method.
KeywordsImage inpainting Structure Texture PDE Heat transfer Anisotropic Finite difference
This work was supported by the Natural Science Foundation of China (60872116, 60832010, and 60773079), the Shanghai Rising-Star Program (10QH14011), the Key Scientific Research Project of Shanghai Education Committee (10ZZ59), the Shanghai Specialized Research Foundation for Excellent Young Teacher in University (slg09005), and the OECE Innovation Foundation of USST (GDCX-Y-103).
- 2.Bertalmio M, Bertozzi AL, Sapiro G (2001) Navier-stokes, fluid dynamics, and image and video inpainting, in Proc. IEEE Int. Conf. Comput. Vision and Pattern Recognit., Dec., Kauai, HI I:355–362Google Scholar
- 3.Bertalmio M, Sapiro G, Caselles V, Ballester C (2000) Image inpainting, in Proc. ACM SIGGRAPH Conf. Comput. Graphics 417–424Google Scholar
- 14.Robles-Kelly A, Hancock ER (2004) Vector field smoothing via heat flow. in Proc. Int. Conf. Pattern Recognit 2:94–97Google Scholar
- 15.Shih TK (2004) Adaptive digital image inpainting. in Proc. Int. Conf. Advanced Inform. Networking and Applications 1:71–76Google Scholar