Multi-layer inpainting on Chinese artwork

Digital inpainting uses spatial or frequency information to restore partially damaged/removed photos and artworks. Most restoration algorithms take a picture as a single layer. We propose a new approach, which subdivides a Chinese painting into several layers. Each layer is inpainted separately. The layer fusion mechanism then finds the optimal inpaint among layers, which are restored layer-bylayer. We apply the algorithm on Chinese and western drawing. The result shows a high PSNR value as well as a high user satisfaction. The demonstration of our work is available at: http://www.mine.tku.edu.tw/demos/inpaint.

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

[2]  Manuel Menezes de Oliveira Neto,et al.  Fast Digital Image Inpainting , 2001, VIIP.

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

[4]  Patrick Pérez,et al.  Object removal by exemplar-based inpainting , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[5]  Ja-Ling Wu,et al.  Inpainting attacks against visible watermarking schemes , 2001, IS&T/SPIE Electronic Imaging.

[6]  Hans-Peter Seidel,et al.  Image restoration using multiresolution texture synthesis and image inpainting , 2003, Proceedings Computer Graphics International 2003.

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

[8]  Guillermo Sapiro,et al.  Navier-stokes, fluid dynamics, and image and video inpainting , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[9]  Louis Laborelli,et al.  Missing data correction in still images and image sequences , 2002, MULTIMEDIA '02.