Image inpainting with improved exemplar-based approach

Authors:
Qiang Chen;Yingxiang Zhang;Yuncai Liu
Affiliations:
Institute of Image Processing and Pattern Recognition, Department of Automation, Shanghai Jiao Tong University, Shanghai, The People's Republic of China;Institute of Image Processing and Pattern Recognition, Department of Automation, Shanghai Jiao Tong University, Shanghai, The People's Republic of China;Institute of Image Processing and Pattern Recognition, Department of Automation, Shanghai Jiao Tong University, Shanghai, The People's Republic of China
Venue:
MCAM'07 Proceedings of the 2007 international conference on Multimedia content analysis and mining
Year:
2007

Citing 7
Cited 2

Image inpainting

Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Color Transfer between Images

IEEE Computer Graphics and Applications
Texture Synthesis by Non-Parametric Sampling

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Animating pictures with stochastic motion textures

ACM SIGGRAPH 2005 Papers
Image Completion Using Global Optimization

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Object Removal By Cross Isophotes Exemplar-based Inpainting

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
Region filling and object removal by exemplar-based image inpainting

IEEE Transactions on Image Processing

Image inpainting with nonsubsampled contourlet transform

Pattern Recognition Letters
Combining anisotropic diffusion, transport equation and texture synthesis for inpainting textured images

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

Image Inpainting is widely used to restore a damaged paintings and photographs or remove unwanted objects. Criminisi's exemplar-based inpainting combined "texture synthesis" and PDE-based inpainting that showed great efficiency on removal of large objects. However, this approach has certain weakness such as high time cost, visual inconsistency in some cases. In this paper, we improve the Criminsi's exemplar-based inpainting based on Search Strategy and Color Transfer. This new method is also suitable to all exemplar-based methods and the results show its effectiveness.