基于kuwahara滤波的视频风格化框架

doi:10.3969/j.issn.0372-2112.2020.03.017

电子学报 ›› 2020, Vol. 48 ›› Issue (3): 538-544.DOI: 10.3969/j.issn.0372-2112.2020.03.017

基于kuwahara滤波的视频风格化框架

李大锦¹, 高文冉², 高俊杰²

1. 山东师范大学传媒学院, 山东济南 250014;
2. 山东师范大学物理与电子科学学院, 山东济南 250014

收稿日期:2019-05-17 修回日期:2019-11-25 出版日期:2020-03-25
- 作者简介:
- 李大锦 男,1971年11月生于江苏省连云港,现为山东师范大学传媒学院数字媒体系副教授,硕士生导师,研究方向为计算机图形学,虚拟现实与计算机动画技术.E-mail:ldjwqc@163.com;高文冉 男,1996年12月生于山东省济宁市,现为山东师范大学物理与电子科学学院硕士研究生,研究方向为数字图像处理、计算机视觉.;高俊杰 男,1995年9月生于山东省泰安市,现为山东师范大学物理与电子科学学院硕士研究生,研究方向为数字图像处理.
- 基金资助:
- 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）

Artistic Video Stylization Based on Kuwahara Filter

LI Da-jin¹, GAO Wen-ran², GAO Jun-jie²

1. College of Communication, Shandong Normal University, Jinan, Shandong 250014, China;
2. College of Physics and Electronics Science, Shandong Normal University, Jinan, Shandong 250014, China

Received:2019-05-17 Revised:2019-11-25 Online:2020-03-25 Published:2020-03-25
- Supported by:
- National Natural Science Foundation of China (No.61340019); Science and Technology Development Project of Shandong Provicne (No.2014GG201004); Key R&D Program of Shandong Province (No.2015GGB01295)

摘要/Abstract

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.

关键词: 各向异性滤波, 非真实感渲染, 风格转换, 笔画纹理

Abstract: 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.

Key words: anisotropic filter, nonphotorealistic rendering, style transfer, strokes texture

中图分类号:

TP391

李大锦, 高文冉, 高俊杰. 基于kuwahara滤波的视频风格化框架[J]. 电子学报, 2020, 48(3): 538-544.

LI Da-jin, GAO Wen-ran, GAO Jun-jie . Artistic Video Stylization Based on Kuwahara Filter[J]. Acta Electronica Sinica, 2020, 48(3): 538-544.

参考文献

[1] Kang H,Lee S,Chui CK.Flow-based image abstraction[J].IEEE Transactions on Visualization and Computer Graphics,2009,15(1):62-76.
[2] Campisi P.Artistic edge and corner enhancing Smoothing[J].IEEE Transactions on Image Processing,2007,16(10):2449-2462.
[3] Kyprianidis J E,Kang H,Döllner D.Image and video abstraction by anisotropic kuwahara filtering[J].Computer Graphics Forum,2009,28(7):1955-1963.
[4] Hertzmann A.A survey of stroke-based rendering[J].IEEE Computer Graphics and Applications,2003,23(4):70-81.
[5] Zeng K,Zhao M,Xiong C,Zhu S-C.From image parsing to painterly rendering[J].ACM Transactions on Graphics,2009,29(1):1-11
[6] Umenhoffer,Tamás,Szirmay-Kalos,et al.An image-based method for animated stroke rendering[J].The Visual Computer,2018,34(6-8):817-827.
[7] Hertzmann A.Paint by relaxation[A].Computer Graphics International[C].Washington,DC:IEEE Computer Society Press,2001.47-54.
[8] Chen J,Guennebaud,Gaël,Barla P,et al.Non-oriented MLS gradient fields[J].Computer Graphics Forum,2013,32(8):98-109.
[9] 钱文华,徐丹,岳昆,等.重要度引导的抽象艺术风格绘制[J]. 计算机辅助设计与图形学学报,2015,27(5):915-923. Qian W,Xu D,Yue K,et al.Sketch artistic rendering based on significance map[J].Journal of Computer-Aided Design & Computer Graphic,2015,27(5):915-923.(in Chinese)
[10] Hertzmann A.Fast paint texture[A].2nd International Symposium on Non-photorealistic Animation and Rendering[C].New York:ACM Press,2002.91-96.
[11] Semmo A, Limberger D, Kyprianidis JE,Döllner J.Image stylization by interactive oil paint filtering[J].Computers & Graphics,2016,55(1):157-171.
[12] Yang L,Du J,Wu E.Easydrawing:generation of artistic chinese flower painting by stroke-based stylization[J].IEEE Access,2019,7(3):35449-35456.
[13] Yan C R,Chi M T,Lee T Y,et al.Stylized rendering using samples of a painted image[J].IEEE Transactions on Visualization and Computer Graphics,2008,14(2):468-480.
[14] Dollár P,Zitnick C L.Fast edge detection using structured forests[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2014,37(8):1558-1570.
[15] Ni K,Wu Y.Adaptive patched L0 gradient minimisation model applied on image smoothing[J].IET Image Processing,2018,12(10):1892-1902.
[16] Min D,Choi S,Lu J,et al.Fast global image smoothing based on weighted least squares[J].IEEE Transactions on Image Processing,2014,23(12):5638-5653.
[17] Kim Y,Ham B,Do M N,et al.Structure-texture image decomposition using deep variational priors[J].IEEE Transactions on Image Processing,2019,28(6):2692-2704.
[18] Kyprianidis J E,Döllner J.Image abstraction by structure adaptive filtering[A] EG UK Theory and Practice of Computer Graphics[C].Hoboken,New Jersey:Eurographics Assoiciation,2008.051-058.
[19] Zang Y,Huang H,Zhang L.Guided adaptive image smoothing via directional anisotropic structure measurement[J].IEEE Transactions on Visualization and Computer Graphics,2015,21(9):1015-1027.
[20] 丁颖,刘延伟,刘金霞,等.虚拟现实全景图像显著性检测研究进展综述[J].电子学报,2019,47(7):1575-1583. Ding Y,Liu Y W,Liu J X,et al.An overview of research progress on saliency detection of panoramic VR images[J].Acta Electronica Sinica,2019,47(7):1575-1583.(in Chinese)
[21] Zou B J,Liu Q,Yue K J,et al.Saliency-based segmentation of optic disc in retinal mages[J].Chinese Journal of Electronics,2019,28(1):71-75.
[22] Yang C,Zhang L,Lu H,et al.Saliency detection via graph-based manifold ranking[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Washington,DC:IEEE Computer Society Press,2013.3166-3173.
[23] Achanta R,Hemami S,Estrada F,Susstrunk S.Frequency-tuned salient region detection[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Washington,DC:IEEE Computer Society,2009.1597-1604.
[24] Cabral B,Leedom L C.Imaging vector fields using line integral convolution[A].ACM SIGGRAPH[C].NewYork:ACM Press,1993.263-270.
[25] Lang M,Hornung A,Wang O,et al.Nonlinear disparity mapping for stereoscopic 3D[J].ACM Transaction on Graphics,2010,29(4):Article No.75.

基于kuwahara滤波的视频风格化框架

Artistic Video Stylization Based on Kuwahara Filter

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics