[1]贾 瑶,靳雁霞,马 博,等.基于机器学习合成高分辨率布料褶皱[J].计算机技术与发展,2021,31(03):106-110.[doi:10. 3969 / j. issn. 1673-629X. 2021. 03. 018]
　JIA Yao,JIN Yan-xia,MA Bo,et al.Synthesis of High-resolution Cloth Folds Based on Machine Learning[J].,2021,31(03):106-110.[doi:10. 3969 / j. issn. 1673-629X. 2021. 03. 018]
点击复制

基于机器学习合成高分辨率布料褶皱()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
31
期数:
2021年03期
页码:
106-110
栏目:
图形与图像
出版日期:
2021-03-10

文章信息/Info

Title:
Synthesis of High-resolution Cloth Folds Based on Machine Learning
文章编号:
1673-629X(2021)03-0106-05
作者:
贾 瑶; 靳雁霞; 马 博; 陈治旭; 芦 烨
中北大学 大数据学院,山西 太原 030051
Author(s):
JIA Yao; JIN Yan-xia; MA Bo; CHEN Zhi-xu; LU Ye
School of Big Data,North University of China,Taiyuan 030051,China
关键词:
机器学习; 高分辨率; 布料褶皱; 卷积神经网络; 布料动画
Keywords:
machine learning; high resolution; cloth folds; convolutional neural network (CNN); cloth animation
分类号:
TP391.9
DOI:
10. 3969 / j. issn. 1673-629X. 2021. 03. 018
摘要:
为了精化布料网格得到逼真的布料模拟效果,提出了一种基于机器学习的方法合成高分辨率布料褶皱。首先模拟真实的布料运动, 获取布料运动的帧数据信息, 将布料运动的帧数据信息转换为图像信息的形式进行存储。 然后将图像信息作为输入,输入到卷积神经网络(CNN)中进行训练,通过将卷积神经网络与缩小网络相结合,最终得到高分辨率布料图像。 最后将高分辨率布料图像转换为高分辨率布料网格, 对布料进行模拟。 实验结果表明, 与初始的低分辨率布料网格对比,合成的高分辨率布料网格模拟出的布料有着大量且细微的褶皱,并且能够模拟出真实的布料效果, 与真实场景中的布料模拟效果相似。 该方法在不同的场景中都可以模拟出高质量的布料动画效果, 而且减少了仿真速度,验证了该方法的有效性。
Abstract:
In order to refine the cloth mesh and get a realistic cloth simulation effect,a method based on machine lear-ning to synthesize high-resolution cloth folds is proposed. First,we simulate the real cloth movement, obtain the frame data information of the cloth movement,and convert the frame data of the cloth movement into an image for storage. Then the image information is input into the convolutional neural network (CNN)? ?for trai-ning. By combining the CNN and the reduction network,a high-resolution cloth image is finally obtained. Finally,the high-resolution cloth image is converted into a high - resolution cloth grid to simulate the cloth.? ?The experiment shows that compared with the original low-resolution cloth grid,the synthesized high-resol-ution cloth grid simulates a large number of fine folds,and can simulate the real cloth effect,similar to the cloth simulation effect in the real scene. The high-quality cloth animation effects of this method can be simulated in different scenes,and the simulation speed is reduced,which verifies its effectiveness.

相似文献/References:

[1]陈全 赵文辉 李洁 江雨燕.选择性集成学习算法的研究[J].计算机技术与发展,2010,(02):87.
　CHEN Quan,ZHAO Wen-hui,LI Jie,et al.Research of Selective Ensemble Learning Algorithm[J].,2010,(03):87.
[2]黄秀丽 王蔚.SVM在非平衡数据集中的应用[J].计算机技术与发展,2009,(06):190.
　HUANG Xiu-li,WANG Wei.Application of SVM in Imbalances Dataset[J].,2009,(03):190.
[3]鲁晓南 接标.一种基于个性化邮件特征的反垃圾邮件系统[J].计算机技术与发展,2009,(08):155.
　LU Xiao-nan,JIE Biao.An Individual Anti- Spam Technology[J].,2009,(03):155.
[4]张苗 张德贤.多类支持向量机文本分类方法[J].计算机技术与发展,2008,(03):139.
　ZHANG Miao,ZHANG De-xian.Research on Text Categorization Based on. M- SVMs[J].,2008,(03):139.
[5]汤萍萍 王红兵.基于强化学习的Web服务组合[J].计算机技术与发展,2008,(03):142.
　TANG Ping-ping,WANG Hong-bing.Web Service Composition Based on Reinforcement -Learning[J].,2008,(03):142.
[6]杨雪洁 赵姝 张燕平.基于商空间理论的冬小麦产量预测和分析[J].计算机技术与发展,2008,(03):249.
　YANG Xue-jie,ZHAO Shu,ZHANG Yan-ping.Analysis on Winter Wheat Yield Based on Quotient Space Theory[J].,2008,(03):249.
[7]汤伟 程家兴 纪霞.一种基于概率推理的邮件过滤系统的研究与设计[J].计算机技术与发展,2008,(08):76.
　TANG Wei,CHENG Jia-xing,JI Xia.Research and Design of a Spam Filtering System Based on Probability Inference[J].,2008,(03):76.
[8]孙海虹 丁华福.基于模糊粗糙集的Web文本分类[J].计算机技术与发展,2010,(07):21.
　SUN Hai-hong,DING Hua-fu.Web Document Classification Based on Fuzzy-Rough Set[J].,2010,(03):21.
[9]汤伟 程家兴 纪霞.统计学理论在邮件分类中的应用研究[J].计算机技术与发展,2008,(12):231.
　TANG Wei,CHENG Jia-xing,JI Xia.Research and Design of a Spam Filtering System Based on Statistical Learning Theory[J].,2008,(03):231.
[10]张高胤 谭成翔 汪海航.基于K-近邻算法的网页自动分类系统的研究及实现[J].计算机技术与发展,2007,(01):21.
　ZHANG Gao-yin,TAN Cheng-xiang,WANG Hai-hang.Design and Implementation of Web Page Automation Classification System Based on K- Nearest Neighbor Algorithm[J].,2007,(03):21.

更新日期/Last Update: 2020-03-10