Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Image quilting for texture synthesis and transfer
Proceedings of the 28th annual conference on Computer graphics and interactive techniques
Missing data correction in still images and image sequences
Proceedings of the tenth ACM international conference on Multimedia
Texture Synthesis by Non-Parametric Sampling
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Fragment-based image completion
ACM SIGGRAPH 2003 Papers
Image completion with structure propagation
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
Generating an /spl omega/-tile set for texture synthesis
CGI '05 Proceedings of the Computer Graphics International 2005
Region filling and object removal by exemplar-based image inpainting
IEEE Transactions on Image Processing
Mode Decomposition Evolution Equations
Journal of Scientific Computing
Accurate spatio-temporal reconstruction of missing data in dynamic scenes
Pattern Recognition Letters
Hi-index | 0.00 |
To suitably complete an image without seams, block effects, and artifacts, a novel exemplar-based image completion model employing partial differential equation (PDE) is proposed. Firstly, the novel model determines the processing order of exemplar according to a composite function, which is the product of the colour property and structure property in exemplar. Then the exemplar along a geometric structure is processed prior to other parts of the image. Secondly, the most similar exemplar is found in the CIELAB colour space, and the size of it is adaptively determined by the local textured information. Thirdly, a Poisson equation is adopted to remove the seams, block effects, and artifacts in the image generated by the exemplar-based model. Finally, a bi-directional diffusion PDE is used to assist the completion of lathy linear structure. Experimental results demonstrate that the novel model can properly reconstruct the target region while preserving the geometric structure without inducing block effects, which leads to its better performance than the conventional exemplar-based image completion models.