用自回归(AR)和分层采样生成草书笔画纹理

Generating Brush Texture for Cursive Style Calligraphy with Autoregressive and Stratified Sampling

提出一种基于自回归和分层采样的草书纹理生成方法,从草书作品中采集一些典型的笔画纹理,构建一个纹理笔画库;然后基于自回归模型生成新的草书纹理,并引入分层采样方法来控制纹理宽度;最后将生成的草书纹理映射到字上,得到满意的草书风格作品.

To generate cursive style calligraphy, we first collect a number of typical brush texture patches （BTP） to build a BTP library from the masterpiece of great calligraphers. Then new BTP is generated from the BTP library based on the autoregressive model. We also proposed a control mechanism for the width of BTP through stratified sampling method. The results demonstrate that satisfactory calligraphy works can be produced by our method.