Please wait a minute...
浙江大学学报（理学版）
浙江大学学报（理学版）  2016, Vol. 43 Issue (6): 638-646    DOI: 10.3785/j.issn.1008-9497.2016.06.003
Chinagraph 2016——数字图像处理     
基于GPU加速的几何纹理合成方法
桂彦1,2, 王培玉1,2, 李峰1,2, 刘杨1,2
1. 长沙理工大学 综合交通运输大数据智能处理湖南省重点实验室, 湖南 长沙 410114;
2. 长沙理工大学 计算机与通信工程学院, 湖南 长沙 410114
GPU-based geometry texture synthesis
GUI Yan1,2, WANG Peiyu1,2, LI Feng1,2, LIU Yang1,2
1. Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation, Changsha University of Science and Technology, Changsha 410114, China;
2. School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha 410114, China
 全文: PDF(1844 KB)  
摘要： 提出了一种基于GPU加速的几何纹理合成方法，以解决几何纹理合成过程中高计算量、高存储占用和高耗时等问题.首先，对样本几何纹理数据进行子块划分，并根据子块在样本中的位置关系设计可重用样本顶点数据的数据结构，优化存储以降低内存的占用率；然后，采用GPU多线程并发技术设计并行加速算法，将串行的几何纹理合成过程并行化，从而实现快速生成任意尺寸的新的几何纹理.实验结果表明，该算法不仅占用存储较少，而且在保证合成质量的同时极大地降低了几何纹理的合成耗时.
关键词： 纹理合成;  几何纹理合成;  虚拟现实;  GPU加速;  并行运算    
Abstract: A geometry texture synthesis method based on GPU technique is proposed to solve the problems of high computation, high memory occupancy, and high time consuming in synthesis process. Firstly, the geometry texture sample can be divided into sub-blocks, and the data structure reusing the vertex data of the geometry texture sample is designed according to the positions of these sub-blocks in the geometry texture sample, in that the storage optimization can reduce the memory occupancy rate. Then, based on multithreaded GPU technique, we design parallel acceleration algorithm, and develop the sequential geometry texture synthesis in parallel, which can generate a new synthesized geometry texture with arbitrary sizes fastly and efficiently. The experimental results show that our algorithm not only can use less memory, but also can greatly reduce the time consuming for geometric texture synthesis and guarantee the quality of the synthesize geometry texture.
Key words: texture synthesis    geometry texture synthesis    virtual reality    GPU acceleration    parallel operation
收稿日期: 2016-07-15 出版日期: 2017-03-07
CLC:  TP391.41  
基金资助: 国家自然科学基金青年科学基金资助项目(61402053).
作者简介: 桂彦(1985-),ORCID:http://orcid.org/0000-0001-8323-4571,女,博士,讲师,主要从事计算机图形学、计算机视觉、可视媒体编辑与处理等研究,E-mail:guiyan122@163.com.
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　
桂彦
王培玉
李峰
刘杨

引用本文:

桂彦, 王培玉, 李峰, 刘杨. 基于GPU加速的几何纹理合成方法[J]. 浙江大学学报（理学版）, 2016, 43(6): 638-646.

GUI Yan, WANG Peiyu, LI Feng, LIU Yang. GPU-based geometry texture synthesis. Journal of Zhejiang University (Science Edition), 2016, 43(6): 638-646.

链接本文:

https://www.zjujournals.com/sci/CN/10.3785/j.issn.1008-9497.2016.06.003    或    https://www.zjujournals.com/sci/CN/Y2016/V43/I6/638

[1] EFROS A A, LEUNG T K. Texture synthesis by non-parametric sampling[J]. IEEE International Conference on Computer Vision,1999:1033-1038.
[2] WEI L Y, LEVOY M. Fast texture synthesis using tree-structured vector quantization[C]//Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques.New York:ACM Press, 2000:479-488.
[3] EFROS A A, FREEMAN W T. Image quilting for texture synthesis and transfer[J]. Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques, 2001:341-346.
[4] KWATRA V, SCHÖDL A, ESSA I, et al. Graphcut textures:Image and video synthesis using graph cuts[J]. ACM Transactions on Graphics,2003,22(3):277-286.
[5] COHEN M F, SHADE J, HILLER S, et al. Wang tiles for image and texture generation[J]. ACM Transactions on Graphics,2003,22(3):287-294.
[6] 张军,朱为,黄伟强.一种新的结构自适应纹理合成算法[J].小型微型计算机系统,2011,32(2):351-355. ZHANG Jun, ZHU Wei, HUANG Weiqiang. Novel structure adaptive algorithm for texture synthesis[J]. Journal of Chinese Computer Systems,2011,32(2):351-355.
[7] QIN X, YANG Y H. Aura 3D textures[J]. IEEE Transactions on Visualization & Computer Graphics,2007,13(2):379-389.
[8] 严志程,陈为.基于二维纹理样本的方向场引导的体纹理合成[J].计算机辅助设计与图形学学报,2008,20(9):1104-1109. YAN Zhicheng, CHEN Wei. Vector field guided solid texture synthesis from 2D example[J]. Journal of Computer-Aided Design & Computer Graphics,2008,20(9):1104-1109.
[9] PIETRONI N, CIGNONI P, OTADUY M, et al. Solid-texture synthesis:A survey[J]. IEEE Engineering in Medicine & Biology Magazine the Quarterly Magazine of the Engineering in Medicine & Biology Society,2010,30(4):74-89.
[10] WANG L, ZHOU K, YU Y, et al. Vector solid textures[J]. ACM Transactions on Graphics,2010,29(4):1-8.
[11] 江巨浪,薛峰,郑江云,等.一种基于样图的体纹理快速生成算法[J].计算机辅助设计与图形学学报,2011,23(8):1311-1318. JIANG Julang, XUE Feng, ZHENG Jiangyun, et al. A fast algorithm for solid texture generation from 2D sample[J]. Journal of Computer-Aided Design & Computer Graphics,2011,23(8):1311-1318.
[12] BHAT P, INGRAM S, TURK G. Geometric texture synthesis by example[J]. Eurographics Symposium on Geometry Processing,2004:43-46.
[13] ZHOU K, HUANG X, WANG X, et al. Mesh quilting for geometric texture synthesis[J]. ACM Transactions on Graphics, 2006,25(3):690-697.
[14] 韩建伟,王青,周昆,等.基于WangTiles的几何纹理合成[J].软件学报,2009,20(12):3254-3264. HAN Jianwei, WANG Qing, ZHOU Kun, et al. Wang Tiles based geometric texture synthesis[J]. Journal of Software,2009,20(12):3254-3264.
[15] MA C, WEI L Y, TONG X. Discrete element textures[J]. ACM Transactions on Graphics,2011,30(4):76-79.
[16] MA C, WEI L Y, LEFEBVRE S, et al. Dynamic element textures[J]. ACM Transactions on Graphics,2013,32(4):96.
[17] ALMERAJ Z, KAPLAN C S, ASENTE P. Patch-based geometric texture synthesis[C]//Proceedings of the Symposium on Computational Aesthetics. New York:ACM,2013:15-19.
[18] 陈国栋,何汉鑫.CUDA加速的肝脏体纹理合成与映射方法研究[J].系统仿真学报,2015,27(6):1280-1287. CHEN Guodong, HE Hanxin. Research of liver solid texture synthesis and mapping method with CUDA acceleration[J]. Journal of System Simulation,2015,27(6):1280-1287.
[19] KWATRA V, SCHÖDL A, ESSA I, et al. Graphcut textures:Image and video synthesis using graph cuts[J]. ACM Transactions on Graphics,2003,22(3):277-286.
[20] YU Y, ZHOU K, XU D, et al. Mesh editing with poisson-based gradient field manipulation[J]. ACM Transactions on Graphics,2004,23(3):641-648.
[21] VINEET V, NARAYANAN P J. CUDA cuts:Fast graph cuts on the GPU[C]//IEEE Computer Society Conference on Computer Vision & Pattern Recognition Workshops. Anchorage:IEEE Computer Society,2008:1-8.
[1] 罗月童, 韩承村, 杜华, 严伊蔓. 基于拉伸特征的B-Rep→CSG转换算法及其应用[J]. 浙江大学学报（理学版）, 2021, 48(2): 151-158.
[2] 陈佳舟, 王宇航, MohammedAmal Ahmed Hasan, 黄可妤, 卢周扬, 彭群生. 基于图像的二维剪纸自动生成方法[J]. 浙江大学学报（理学版）, 2020, 47(3): 274-283.
[3] 卢家品, 罗月童, 黄兆嵩, 张延孔, 陈为. 基于排名学习和多源信息的地图匹配方法[J]. 浙江大学学报（理学版）, 2020, 47(1): 27-35.
[4] 刘一璟, 张旭斌, 张建伟, 周哲磊, 冯元力, 陈为. DenseNet-centercrop: 一个用于肺结节分类的卷积网络[J]. 浙江大学学报（理学版）, 2020, 47(1): 20-26.
[5] 李丽, 高若婉, 梅树立, 赵海英. 基于Shannon-Cosine小波精细积分法的壁画降噪修复方法[J]. 浙江大学学报（理学版）, 2019, 46(3): 279-287.
[6] 傅红普, 邹北骥. 一种方向梯度直方图的降维方法[J]. 浙江大学学报（理学版）, 2017, 44(2): 134-138.
[7] 张莉, 赵林, 檀结庆. 带互异权值的渐进迭代逼近算法及其应用[J]. 浙江大学学报（理学版）, 2017, 44(1): 22-27.
[8] 刘玉杰, 庞芸萍, 李宗民, 李华. 融合抽象层级变换和卷积神经网络的手绘图像检索方法[J]. 浙江大学学报（理学版）, 2016, 43(6): 657-663.