图像和视频的低多边形渲染

doi:10.11772/j.issn.1001-9081.2020050626

计算机应用 ›› 2021, Vol. 41 ›› Issue (2): 504-510.DOI: 10.11772/j.issn.1001-9081.2020050626

所属专题：多媒体计算与计算机仿真

• 多媒体计算与计算机仿真 • 上一篇下一篇

图像和视频的低多边形渲染

韩艳茹¹, 尹梦晓^1,2, 覃子轩¹, 苏鹏¹, 杨锋^1,2

1. 广西大学计算机与电子信息学院, 南宁 530004;
2. 广西多媒体通信与网络技术重点实验室(广西大学), 南宁 530004

收稿日期:2020-05-12 修回日期:2020-08-03 出版日期:2021-02-10 发布日期:2020-08-26
通讯作者: 尹梦晓
作者简介:韩艳茹(1992-),女,山西朔州人,硕士研究生,主要研究方向:图像和视频处理;尹梦晓(1978-),女,河南南阳人,副教授,博士,CCF会员,主要研究方向:计算机图形学、数字几何处理、图像和视频编辑;覃子轩(1995-),男,广西南宁人,硕士研究生,主要研究方向:视觉SLAM;苏鹏(1987-),男,黑龙江哈尔滨人,硕士研究生,主要研究方向:计算机图形学;杨锋(1979-),男,广西玉林人,副教授,博士,CCF会员,主要研究方向:医学图像处理、人工智能。
基金资助:
国家自然科学基金资助项目（61762007， 61861004）；广西自然科学基金资助项目（2017GXNSFAA198269，2017GXNSFAA198267）。

Low-poly rendering for image and video

HAN Yanru¹, YIN Mengxiao^1,2, QIN Zixuan¹, SU Peng¹, YANG Feng^1,2

1. School of Computer, Electronics and Information, Guangxi University, Nanning Guangxi 530004, China;
2. Guangxi Key Laboratory of Multimedia Communications and Network Technology(Guangxi University), Nanning Guangxi 530004, China

Received:2020-05-12 Revised:2020-08-03 Online:2021-02-10 Published:2020-08-26
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61762007, 61861004), the Natural Science Foundation of Guangxi (2017GXNSFAA198269, 2017GXNSFAA198267).

摘要/Abstract

摘要： 低多边形是近来艺术设计界的热门风格。为了提高图像和视频低多边形风格化的质量，提出一种基于边缘特征和超像素分割的图像和视频低多边形渲染方法。首先提取相邻超像素的交点以及对特征边和超像素边界的差集的均匀采样点作为三角网格顶点，并执行Delaunay三角剖分来生成初始三角网格；然后采用带约束的二次误差度量方法对生成的网格进行简化，以生成最终三角网格；最后对三角网格填充颜色，得到了具有低多边形风格的图像。对于视频低多边形渲染，使用时间一致性超像素跨帧跟踪同一对象的相同部分，以建立视频帧之间的关联，降低视频渲染后的抖动。此外，采用视频分割方法分割视频中的移动对象，获得移动对象与背景之间不同密度的采样点，对移动对象进行渲染获从而得到视频的局部风格化效果。实验结果表明，所提方法能够生成具有较好视觉效果的低多边形渲染结果。

关键词: 三角剖分, 时间一致性超像素, 边缘特征, 低多边形渲染, 均匀采样

Abstract: Low-poly is a popular style in the art design field recently. In order to improve the quality of image and video low-poly stylization, an image and video low-poly rendering method based on edge features and superpixel segmentation was proposed. Firstly, the intersection points of adjacent superpixels and the uniform sampling points of the difference set between feature edges and superpixel boundaries were extracted as the vertices of the triangle mesh, and Delaunay triangulation was performed to generate the initial triangle mesh. Then, the constrained quadric error metric method was used to simplify the generated mesh in order to generate the final triangle mesh. Finally, the triangle mesh was filled with color to obtain the image with low-poly style. For video low-poly rendering, the temporally consistent superpixels were used to track the same part of the object across frames to establish associations between the video frames, reducing the jitter after video rendering. In addition, the video segmentation method was used to segment the moving objects in the video, so as to obtain sampling points with different densities between the moving objects and the background, and the local stylized effect of the video was obtained by rendering the moving objects. Experimental results show that the proposed method can generate low-poly rendering results with better visual effects.

Key words: triangulation, temporally consistent superpixel, edge feature, low-poly rendering, uniform sampling

中图分类号:

TP391

韩艳茹, 尹梦晓, 覃子轩, 苏鹏, 杨锋. 图像和视频的低多边形渲染[J]. 计算机应用, 2021, 41(2): 504-510.

HAN Yanru, YIN Mengxiao, QIN Zixuan, SU Peng, YANG Feng. Low-poly rendering for image and video[J]. Journal of Computer Applications, 2021, 41(2): 504-510.

参考文献

[1] XIAO L,HUANG X X,LU Y C. Non-photorealistic rendering from real video sequences with discontinuity reduction using fast video segmentation[C]//Proceedings of the 2016 International SoC Design Conference. Piscataway:IEEE,2016:327-328.
[2] LOPEZ-MORENO J. Non-photorealistic rendering[M]//LUO M R. Encyclopedia of Color Science and Technology. New York:Springer,2016:968-972.
[3] HAEBERLI P. Paint by numbers:abstract image representations[C]//Proceedings of the 17th Annual Conference on Computer Graphics and Interactive Techniques. New York:ACM,1990:207-214.
[4] SALISBURY M P, ANDERSON S E, BARZEL R, et al. Interactive pen and ink illustration[C]//Proceedings of the 21st Annual Conference on Computer Graphics and Interactive Techniques. New York:ACM,1994:101-108.
[5] COLLOMOSSE J P, HALL P M. Salience adaptive painterly rendering using genetic search[J]. International Journal on Artificial Intelligence Tools,2006,15(4):551-575.
[6] COLLOMOSSE J P,HALL P M. Painterly rendering using image salience[C]//Proceedings of the 20th Eurographics UK Conference. Piscataway:IEEE,2002:122-128.
[7] GOOCH B,COOMBE G,SHIRLEY P. Artistic vision:painterly rendering using computer vision techniques[C]//Proceedings of the 2nd International Symposium on Non-photorealistic Animation and Rendering. New York:ACM,2002:83-90.
[8] MOULD D. A stained glass image filter[C]//Proceedings of the 14th Eurographics Workshop on Rendering. Goslar:Eurographics Association,2003:20-25.
[9] ASHLOCK D, KARTHIKEYAN B, BRYDEN K. Nonphotorealistic rendering of images as evolutionary stained glass[C]//Preceedings of the 2006 IEEE International Congress on Evolutionary Computation. Piscataway,IEEE,2006:2087-2094.
[10] HUANG H,ZHANG L,ZHANG H. Arcimboldo-like collage using internet images[J]. ACM Transactions on Graphics,2011,30(6):1-8.
[11] SONG Y, PICKUP D, LI C, et al. Abstract art by shape classification[J]. IEEE Transactions on Visualization and Computer Graphics,2013,19(8):1252-1263.
[12] CHEN Z, XIAO Y, CAO J. Approximation by piecewise polynomials on Voronoi tessellation[J]. Graphical Models,2014, 76(5):522-531.
[13] BITENCOURT B. Low poly sir[EB/OL].[2019-11-02]. https://dribbble.com/Bitencourt.
[14] ABHIKREATIONZ. Low poly illustration[EB/OL].[2019-11-02]. https://www.behance.net/abhikreationz.
[15] YUN D Y H. Dmexh,Triangulation image generator[EB/OL].[2019-11-02]. http://dmesh.thedofl.com/.
[16] APPLE. Art camera TRIGRAFF[CP/OL].[2019-11-02]. https://itunes.apple.com/cn/app/art-camera-trigraff.
[17] GAI M,WANG G. Artistic low poly rendering for images[J]. The Visual Computer,2016,32(4):491-500.
[18] MA Y,CHEN X,BAI Y. An interactive system for low-poly illustration generation from images using adaptive thinning[C]//Proceedings of the 2017 IEEE International Conference on Multimedia and Expo. Piscataway:IEEE,2017:1033-1038.
[19] NG R,WONG L K,SEE J. Pic2Geom:a fast rendering algorithm for low-poly geometric art[C]//Proceedings of the 2017 Pacific Rim Conference on Multimedia,10736. Cham:Springer,2017:368-377.
[20] 吴凯琳. 计算机绘制低多边形风格肖像[D]. 杭州:浙江大学, 2018:1-53.(WU K L. Computer rendering of portrait with the style of low poly[D]. Hangzhou:Zhejiang University,2018:1-53.)
[21] ZHANG W,XIAO S,SHI X. Low-poly style image and video processing[C]//Proceedings of the 2015 International Conference on Systems,Signals and Image Processing. Piscataway:IEEE, 2015:97-100.
[22] LAWONN K,GÜNTHER T. Stylized image triangulation[J]. Computer Graphics Forum,2019,38(1):221-234.
[23] ACHANTA R,SHAJI A,SMITH K,et al. SLIC superpixels compared to state-of-the-art superpixel methods[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2012, 34(11):2274-2282.
[24] CANNY J. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1986, PAMI-8(6):679-698.
[25] WATSON D F. Computing the n-dimensional Delaunay tessellation with application to Voronoi polytopes[J]. The Computer Journal,1981,24(2):167-172.
[26] 陈爱芬, 李桂清, 王宇攀, 等. 误差可控的细分曲面图像矢量化[J]. 计算机辅助设计与图形学学报,2017,29(12):2197-2203.(CHEN A F,LI G Q,WANG Y P,et al. Towards errorcontrollable image vectorization based on subdivision surfaces[J]. Journal of Computer-Aided Design and Computer Graphics,2017, 29(12):2197-2203.)
[27] 赖敬文. 重心坐标嵌入变形[D]. 广州:华南理工大学,2009:23-24. (LAI J W. Embedded deformation using barycentric coordinates[D]. Guangzhou:South China University of Technology,2009:23-24.)
[28] CHANG J,WEI D L,FISHER J W Ⅲ. A video representation using temporal superpixels[C]//Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2013:2051-2058.
[29] PAPAZOGLOU A,FERRARI V. Fast object segmentation in unconstrained video[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision. Piscataway:IEEE, 2013:1777-1784.

图像和视频的低多边形渲染

Low-poly rendering for image and video

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 14

编辑推荐

Metrics

[1]	张一飞, 李新福, 田学东. 基于图像分割的立体匹配算法[J]. 计算机应用, 2020, 40(5): 1415-1420.
[2]	夏俊, 李映华. 球面凸类图形Delaunay三角剖分再分算法及其收敛性分析[J]. 计算机应用, 2017, 37(12): 3558-3562.
[3]	杨健李若楠黄晨阳王刚丁闯. 基于局部显著边缘特征的快速图像配准算法[J]. 计算机应用, 2014, 34(1): 149-153.
[4]	刘付民张治斌. 基于色彩和边缘特征的图像检索方法[J]. 计算机应用, 2012, 32(05): 1280-1282.
[5]	陈敏张志毅田素垒张娴. 基于三角形外接圆的轮廓对应算法[J]. 计算机应用, 2012, 32(03): 722-724.
[6]	曾宇燕何建农. 基于小波包和边缘特征的遥感图像融合算法[J]. 计算机应用, 2011, 31(10): 2742-2744.
[7]	金文标王旭松张智丰. 基于特征的图像网格生成方法[J]. 计算机应用, 2010, 30(9): 2427-2430.
[8]	孙继忠胡艳马永强. 基于Delaunay三角剖分生成Voronoi图算法[J]. 计算机应用, 2010, 30(1): 75-77.
[9]	林奕新刘东峰. 基于符号体积值的Delaunay逐点插入法[J]. 计算机应用, 2009, 29(2): 459-461.
[10]	纪小刚. 基于Delaunay三角剖分的半径补偿新算法[J]. 计算机应用, 2009, 29(08): 2046-2048.
[11]	吕佳. 基于Delaunay三角剖分密度度量的聚类算法[J]. 计算机应用, 2009, 29(05): 1380-1384.
[12]	陈永萍朱庆生葛垚. 结合变步长的两阶段视频镜头边界检测方法[J]. 计算机应用, 2008, 28(6): 1501-1503.
[13]	訾方李言俊张科赵大炜. 矩形非均匀采样算法和对数级坐标变换算法的比较分析[J]. 计算机应用, 2007, 27(7): 1619-1622.
[14]	江力胡永祥 . 非均匀采样曲线的支持向量机重建[J]. 计算机应用, 2006, 26(12): 2832-2834.