高级检索

基于结构的纹理合成

Structure-Based Texture Synthesis

  • 摘要: 提出一种纹理合成算法.首先将经验模型分解(EMD)算法引入到纹理合成领域,对样本图像的纹理结构进行提取;然后应用分片采样算法和Markov随机场(MRF)模型生成输出纹理的结构.对于结构之间的空白区域,采用距离变换方法分片提取其不规则的形状并进行填充.实验结果表明,该算法不仅简单、快速、合成质量高,而且具有广泛的适用性.

     

    Abstract: Inspired by brushwork, we presented a novel algorithm for synthesizing textures from an input sample. First, empirical mode decomposition(EMD) algorithm was introduced and texture structure of sample was extracted. Second, we synthesized texture structure with patch-based sampling and Markov random field(MRF). For the spaces among structures, we extracted their irregular forms with distance transform and filled in them. Our method is not only simple, fast, ensures good quality, but also robust.

     

/

返回文章
返回