研究论文

基于混合梯度最小化的铅笔画生成

展开
  • 1. 上海大学 机电工程与自动化学院, 上海 200444
    2. 上海市电站自动化技术重点实验室, 上海 200072
    3. 上海大学 微电子研究与开发中心, 上海 200072

收稿日期: 2016-05-01

  网络出版日期: 2018-05-07

Pencil drawing production based on hybrid gradient minimization

Expand
  • 1. School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China
    2. Shanghai Key Laboratory of Power Station Automation Technology, Shanghai 200072, China
    3. Microelectronic Research and Development Center, Shanghai University, Shanghai 200072, China

Received date: 2016-05-01

  Online published: 2018-05-07

摘要

利用计算机模拟铅笔画生成的算法主要存在两个问题: 其一是画面细节易丢失, 边缘重点线条不够突出; 二是笔画单一不能很好地展示原画中的层次信息. 针对以上问题, 提出了一种基于混合梯度最小化的铅笔画生成算法, 通过结合 $L_{0}$ 梯度最小化和 $L_{1}$ 范数约束, 既突出显示了图像边缘和重点线条, 又不影响图像的整体锐度, 同时可与原图像结构保持高度一致, 充分展现了图像的层次性和丰富的细节信息. 实验结果表明, 本算法能够生成质量更高、真实感更强的的铅笔画效果, 相比于已有的其他算法具有一定的优越性.

本文引用格式

王权, 胡越黎, 燕明, 胡云生, 陈朋 . 基于混合梯度最小化的铅笔画生成[J]. 上海大学学报(自然科学版), 2018 , 24(2) : 314 -321 . DOI: 10.12066/j.issn.1007-2861.1780

Abstract

Algorithms for creating pencil drawing effect from an image have two major problems: details are often missing so that important edge lines are not clearly shown, and lines are monotonous without hierarchical information. To solve these problems, this paper proposes a pencil drawing generation algorithm based on hybrid gradient minimization. By combining $L_0$ gradient minimization and $L_1$ norm, prominent edges are maintained and enhanced without affecting the overall sharpness. This way, rich and hierarchical details in the image are fully retained. Experimental results indicate that the proposed method can generate high quality and more realistic pencil drawing effect. It is superior to several other existing method.

参考文献

[1] Decarlo D, Finkelstein A, Rusinliewicz S, et al. Suggestive contours for conveyingshape[J]. ACM Transactions on Graphics, 2003,22(3):848-855.
[2] Judd T, Durand F, Adelson E. Apparent ridges for line drawing[J]. ACM Transactions on Graphics, 2007,26(3):19.
[3] Lee Y J, Markosian L, Lee S Y, et al. Line drawings via abstracted shading[J]. ACM Transactions on Graphics, 2007, DOI: 10.1145/1276377.1276400.
[4] Grabli S, Turquin E, Durand F, et al. Programmable rendering of line drawing from 3D scence[J]. ACM Transactions on Graphics, 2010,29(2):397-408.
[5] Hertzmann A, Zorin D. Illustrating smooth surfaces [C] //Proceedings of the 27th Annual Conference on Computer Graphics and lnteractive Techniques. 2000: 517-526.
[6] Praun E, Hoppe H, Webb M, et al. Real-time hatching [C]//Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques. 2001: 581-586.
[7] Klee H, Kwon S, Lee S. Real-time pencil rendering [C]//The 4th International Symposium on Non-Photorealistic Animation and Rendering. 2006: 37-45.
[8] Mao X, Nagasaka Y, Lmamaya A. Automatic generation of pencildrawing from 2D images using line integral convolution [C]//Proceedings of the International Conference on Computer Aided Design and Computer Graphics. 2001: 240-248.
[9] Yamamoto S, Mao X, Lmamiva A. Enhanced LIC pencil fliter [C]// Proceedings of the International Conference on Computer Graphics, Imaging and Visualization. 2004: 251-256.
[10] Kang H, Lee S, Chui C K. Coherent line drawing [C]//The 5th International Symposium on Non-Photorealistic Animation and Rendering. 2007: 43-50.
[11] Orzan A, Bousseau A, Barla P, et al. Structure-preserving manipulation of photo-graphs [C]//The 5th International Symposium on Non-Photorealistic Animation and Rendering. 2007: 103-110.
[12] Lu C W, Li X, Jia J Y. Combining sketch and tone for pencildrawing production [C]//The 10th International Symposium on Non-Photorealistic Animation and Rendering. 2012: 65-73.
[13] 黄志勇, 姚远, 张晶晶, 等. 改进的自然图像铅笔画效果生成[J]. 中国图象图形学报, 2015,20(3):437-444.
[14] Rudin L I, Osher S, Fatemi E. Nonlinear total variation based noise removal algorithms[J]. Physica D, 1992,60(1):259-268.
[15] Xu L, Lu C, Xu Y, et al. Image smoothing via $L_{0}$ gradient minimization[J]. ACM Transactions on Graphics, 2011,30(6):174-185.
[16] 徐美婷, 杨士颖. 结合轮廓和纹理特征的铅笔画自动生成系统[J]. 电子测量技术, 2015,6(6):48-53.
[17] 庞学舜, 王怀彬. 基于改进的 $L_{0}$ 梯度最小化的图像平滑[J]. 天津理工大学学报, 2016,32(1):35-39.
[18] 桑桑, 郝鹏翼, 丁友东, 等. 基于纹理和轮廓的铅笔素描画生成方法[J]. 上海大学学报(自然科学版), 2010,16(3):312-317.
文章导航

/