Fast Texture Synthesis in Adaptive Wavelet Packet Trees

Abstract

Wavelet packet transform known as a substantial extension of wavelet transform has drawn a lot of attention to visual applications. In this paper, we advocate using adaptive wavelet packet transform for texture synthesis. The adaptive wavelet packet coefficients of an image are organized into hierarchical trees called adaptive wavelet packet trees, based on which an efficient algorithm has been proposed to speed up the synthesis process, from the low-frequency tree nodes representing the global characteristics of textures to the high-frequency tree nodes representing the local details. Experimental results show that the texture synthesis in the adaptive wavelet packet trees (TSIAWPT) algorithm is suitable for a variety of textures and is preferable in terms of computation time.

Inverse texture synthesis in wavelet packet trees

“…Specifically, the objective of this paper is to generate a small compaction image given a large textured image, which is different to that of our previous paper [20] aiming to synthesise a large textured image given a small sample image. In addition, the idea behind this paper is to extend the ITS algorithm [12] in the WP domain for improvement in speed, the TSIAWPT algorithm [20], on the other hand, is a modification of the widely used image quilting algorithm [4]. Moreover, the difference in technique between the ITS algorithm and the image quilting algorithm is that the former is based on the optimisation of an energy function in an iterative manner, and the latter is a block-wise processing algorithm in raster scan order.…”

“…We propose using WP coefficients as texture features on account of the great success of WP transform. Although the algorithms proposed in this paper and the texture synthesis in adaptive wavelet packet trees (TSIAWPT) algorithm [20] are based on WP transform, their objectives and problem-solving strategies are different. Specifically, the objective of this paper is to generate a small compaction image given a large textured image, which is different to that of our previous paper [20] aiming to synthesise a large textured image given a small sample image.…”

“…Although the algorithms proposed in this paper and the texture synthesis in adaptive wavelet packet trees (TSIAWPT) algorithm [20] are based on WP transform, their objectives and problem‐solving strategies are different. Specifically, the objective of this paper is to generate a small compaction image given a large textured image, which is different to that of our previous paper [20] aiming to synthesise a large textured image given a small sample image. In addition, the idea behind this paper is to extend the ITS algorithm [12] in the WP domain for improvement in speed, the TSIAWPT algorithm [20], on the other hand, is a modification of the widely used image quilting algorithm [4].…”