期刊文献+

基于kuwahara滤波的视频风格化框架 被引量:3

Artistic Video Stylization Based on Kuwahara Filter
下载PDF
导出
摘要 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. 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.
作者 李大锦 高文冉 高俊杰 LI Da-jin;GAO Wen-ran;GAO Jun-jie(College of Communication,Shandong Normal University,Jinan,Shandong 250014,China;College of Physics and Electronics Science,Shandong Normal University,Jinan,Shandong250014,China)
出处 《电子学报》 EI CAS CSCD 北大核心 2020年第3期538-544,共7页 Acta Electronica Sinica
基金 国家自然科学基金(No.61340019) 山东省科技发展计划(No.2014GG201004) 山东省重点研发计划(No.2015GGB01295)。
关键词 各向异性滤波 非真实感渲染 风格转换 笔画纹理 anisotropic filter nonphotorealistic rendering style transfer strokes texture
  • 相关文献

参考文献3

二级参考文献23

  • 1DeCarlo D, Santella A. Stylization and abstraction of photo- graphs[C]// Computer Graphics Proceedings, Annual Confer- ence Series, ACM SIGGRAPH. New York: ACM Press, 2002: 769-776. 被引量:1
  • 2Gavilan D, Takahashi H, Saito S, et al. Sketch based fine-tuning of image segmentation methods[C]//Proceedings of the International Workshop on Advanced Image Technology. New York: ACM Press, 2006:393-398. 被引量:1
  • 3Wang J, Thiesson B, Xu Y Q, et al. Image and video segmenta- tion by anisotropic kernel mean shift[M]// Lecture Notes in Computer Science. Heidelberg: Springer, 2004, 3022:238-249. 被引量:1
  • 4Winnemoller H, Olsen S C, Gooch B. Real-time video abstrac- tion[C]//Computer Graphics Proceedings, Annual Conference Series, ACM SIGGRAPH. New York: ACM Press, 2006: 1221- 1226. 被引量:1
  • 5Kyprianidis J E, Dollner J. Image abstraction by structure adaptive filtering[C]//Proceedings of the EG UK Theory and Practice of Computer Graphics. Aire-la-Ville: Eurogmphics Association Press, 2008:51-58. 被引量:1
  • 6Kang H, Lee S, Chui C K. Flow-based image abstraction [J]. IEEE Transactions on Visualization and Computer Graphics, 2009, 15(1): 62-76. 被引量:1
  • 7Collomosse J P, Hall P M. Salience-adaptive painterly render- ing using genetic search [J]. International Journal of Artificial Intelligence Tools, 2006, 15 (4): 551-575. 被引量:1
  • 8Papari G, Petkov N. Continuous Glass patterns for painterly rendering [J]. IEEE Transactions on Image Processing, 2009, 18(3): 652-664. 被引量:1
  • 9Zhao H L, Mao X Y, Jin X G, et al. Real-time saliency-aware video abstraction[J]. The Visual Computer, 2009, 25(11): 973-984. 被引量:1
  • 10Hothersall D. History of psychology [M]. 4th ed. New York: McGraw Hill, 2004. 被引量:1

共引文献25

同被引文献29

引证文献3

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部