基于kuwahara滤波的视频风格化框架

保边滤波被广泛应用于图像的艺术化风格转换,但目前的方法大都只能产生类似卡通的绘画风格,对于具有明显笔画形状的绘画风格转换都无能为力.文章在kuwahara滤波的基础上提出了一种尺度可控的各向异性kuwahara滤波,可以生成具有明显笔画形状的艺术效果.为了更好的模拟画家的绘画技法,文章以图像显著性作为控制信息来实时调整滤波核大小,可以产生丰富的笔画尺度.基于该算法,文章还给出了一个视频的艺术化风格渲染框架.该渲染框架可以保持良好的帧间一致性,自动的将视频转换为水粉画或油画效果.同时利用图像的边缘切方向场图、边缘梯度和显著性控制凹凸映射,产生油画和水粉画笔触的厚重感和层次感,能很好的模拟"厚涂技法"的艺术风格.

Artistic Video Stylization Based on Kuwahara Filter

Edge-preserving filters have been extensive used to image artistic stylization,but most of the existing filters can only generate cartoon-like style and can do nothing about the painting styles with clear brush stroke shape.Based on kuwahara filter,the paper proposes a multi-scale anisotropic kuwahara filter to generate some painting styles with obvious brush stroke shape.To simulate the painting techniques,saliency is used to control the size of the filter kernel and can produce strokes with rich geometrical scales.Based on the multi-scale anisotropic kuwahara filter,we also propose an artistic rendering framework for video stylization,which can keep frame-to-frame coherence well and automatically convert video into gouache or oil painting effect.To produce brush strokes a thick and layered feel,bump mapping is used to produce the stroke touch effects.The edge tangent vector field map,edge gradient magnitude and image saliency are combined to control the bump mapping,which can simulate the "impasto technique" well in oil or gouache paintings.