Zerotree Wavelet Based Image Quilting for Fast Texture Synthesis
In this paper we propose a fast DWT based multi-resolution texture synthesis algorithm in which coefficient blocks of the spatio-frequeny components of the input texture are efficiently stitched together (quilted) to form the corresponding components of the synthesised output texture. We propose the use of an automatically generated threshold to determine the significant coefficients which acts as elements of a matching template used in the texture quilting process. We show that the use of a limited set of, visually significant coefficients, regardless of their level of resolution, not only reduces the computational cost, but also results in more realistic texture synthesis. We use popular test textures to compare our results with that of the existing state-or-the-art techniques. Many application scenarios of the proposed algorithm are also discussed.
Unable to display preview. Download preview PDF.
- 1.Witkin, A., Kass, M.: Reaction-diffusion textures. In: Computer Graphics (SIGGRAPH 1991 Proceedings) (July 1991)Google Scholar
- 2.Efros, A., Leung, T.: Texture synthesis by non-parametric sampling. In: International Conference for Computer Vision, September 1999, vol. 2, pp. 1033–1038 (1999)Google Scholar
- 3.Turk, G.: Generating textures on arbitrary surfaces using reaction-diffusion. In: Computer Graphics (SIGGRAPH 1991 Proceedings, July 1991, pp. 289–298 (1991)Google Scholar
- 4.Lewis, J.P.: Texture synthesis for digital painting. In: Computer Graphics (SIGGRAPH 1984 Proc.), July 1984, pp. 245–252 (1984)Google Scholar
- 5.Fournier, A., Fussel, D., Carpenter, L.: Computer rendering of stochastic models. Commun. ACM, 371–384 (June 1982)Google Scholar
- 6.Efros, A., Freeman, W.T.: Image Quilting for Texture Synthesis and Transfer. In: Proceedings of SIGGRAPH 2001, Los Angeles, California, August 2001, pp. 341–346 (2001)Google Scholar
- 8.Wickramanayake, D.S., Edirisinghe, E.A., Bez, H.E.: Fast Wavelet Transform Domain Texture Synthesis. In: Proceedings of the SPIE International Conference on Visual Communications & Image Processing, 5308, VCIP 2004, San Jose, California, January 2004, pp. 979–987 (2004)Google Scholar
- 10.Salomie, I.A., Munteanu, A., Gavrilescu, A., Lafruit, G., Schelkens, P., Deklerck, R., Cornelis, J.: MESHGRID – A Compact, Multiscalable and Animation-Friendly Surface Representation. IEEE Trans. on CSVT 14(7), 950–966 (2004)Google Scholar