On pixel-based texture synthesis by non-parametric sampling

作     者：Shin, Seunghyup Nishita, Tomoyuki Shin, Sung Yong 

作者机构：Korea Adv Inst Sci & Technol Div CS Taejon 305701 South Korea Elect & Telecommun Res Inst Comp Graph Res Team Digital Content Res Div Taejon 305700 South Korea Univ Tokyo Grad Sch Frontier Sci Dept Complex Sci & Engn Bunkyo Ku Tokyo 1130033 Japan 

出 版 物：《COMPUTERS & GRAPHICS-UK》 (计算机与图形学)

年 卷 期：2006年第30卷第5期

页      面：767-778页

核心收录：

学科分类：08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Korea Science and Engineering Foundation, KOSEF Ministry of Education and Human Resources Development, MOEHRD 

主　　题：texture synthesis image processing non-parametric sampling 

摘      要：In this paper, we propose a pixel-based method for texture synthesis with non-parametric sampling. On top of the general framework of pixel-based approaches, our method has three distinguishing features: window size estimation, seed point planting, and iterative refinement. The size of a window is estimated to capture the structural components of the dominant scale embedded in the texture sample. To guide the pixel sampling process at the initial iteration, a grid of seed points are sampled from the example texture. Finally, an iterative refinement scheme is adopted to diffuse the non-stationarity artifact over the entire texture. Our objective is to enhance texture quality as much as possible with a minor sacrifice in efficiency in order to support our conjecture that the pixel-based approach would yield high quality images. (c) 2006 Elsevier Ltd. All rights reserved.