Multiresolution Image Quilting for Texture Synthesis

D.S. Wickramanayake, E.A. Edirisinghe, and H.E. Bez (UK)


Texture synthesis, image processing, multi resolution, wavelets


In this paper we present a novel method for synthesizing texture in a multiresolution domain. Previous research has proposed numerous approaches for texture synthesis in the pixel domain, but little effort has been taken in the synthesis of texture in a multiresolution domain. We propose a multiresolution framework in which coefficient-blocks of the spatio-frequency components of the input texture are efficiently stitched together to form the corresponding components of the output texture. Special consideration has been given to the minimization of the computational cost, throughout the algorithm designs. We show that the adaptation of the multiresolution approach results in a fast, cost-effective, flexible texture synthesis algorithm that is capable of being used in modern, bandwidth-adaptive, real-time imaging applications. A collection of regular and stochastic test textures is used to prove the effectiveness of the proposed algorithm.

Important Links:

Go Back