期刊文献+

基于改进Candide-3模型的眼部动画建模 被引量:4

Eye animation modeling based on the improved Candide-3 model
下载PDF
导出
摘要 针对在Candide-3模型上进行三维人脸重建时不能表达人眼部细节动作的问题,提出了一种改进Candide-3模型重建人脸的方法。该方法首先在Candide-3模型上对眼部进行建模,其中眼部的建模具体分为眼球的建模以及眼睑的建模。对于眼球采用2个半球结合的方式进行建模。对于眼睑的建立,分别在Candide-3的模型上对眼睑的内边缘、外边缘以及上眼睑沟用Bezier曲线进行建模。然后结合人脸特征点的信息和局部最小二乘法匹配原理建立了与输入人脸图像相仿的三维人脸模型。接着,对脸部进行特征点约束的方法贴纹理,眼球分别用局部球形纹理贴图以及球形纹理贴图的方法贴图。最后,在该模型上用分段线性插值的方法,逼真地完成了眼睑的睁闭、眨眼以及眼球的旋转等相关动作。 A face reconstruction approach based on the improved Candide-3 model is presented in order to solve the problems that the details of eye movements cannot be expressed when reconstructing a three-dimensional facial mod-el in Candide-3 model.First, the eye model was built in the Candied-3 model.It was specifically divided into two parts:the eyeball modeling and the eyelid modeling.The eyeball modeling was conducted in combination with two hemispheres.For the modeling of the eyelid, the Bezier curve was used to model the inner and outer edges of eyelid and the upper lid groove in the Candide-3 model.Next, by combining the information of facial feature points and lo-cal least squares matching principle, the 3D face model similar to the input face image was built.After that, paste facial texture by feature point constraint methods and paste texture to eyeball by the spherical and partially spherical texture mapping methods, respectively.Finally, some actions, such as closing and opening of eyelid, blinking, ro-tation of eyeball and other related actions were realistically completed by the piecewise linear interpolation method in the built model.
出处 《哈尔滨工程大学学报》 EI CAS CSCD 北大核心 2015年第4期581-586,共6页 Journal of Harbin Engineering University
基金 国家自然科学基金资助项目(60902023 61171096) 计算机软件新技术国家重点实验室开放课题基金资助项目(KFKT2013B22) 四川省动漫研究中心2012年度科研资助项目(DM201204)
关键词 Candide-3模型 眼部动画建模 模型改进 局部最小二乘法匹配 纹理贴图 插值动画 Candide-3 model eye animation modeling model improvement local least squares matching texture mapping interpolated animation
  • 相关文献

参考文献12

  • 1曾丹,程义民,葛仕明,李杰.人眼3D肌肉控制模型[J].计算机辅助设计与图形学学报,2006,18(11):1710-1716. 被引量:10
  • 2STOIBER N, BRETON G, SEGUIER R. Modeling short-term dynamics and variability for realistic interactive facial animation[ J ]. IEEE Computer Graphics and Applications, 2010, 30(4): 51-61.
  • 3WEISSENFELD A, LIU K, OSTERMANN J. Video-realistic image-based eye animation via statistically driven state ma- chines[ J]. The Visual Computer, 2010, 26(9) : 1201-1216.
  • 4TU C T, LIEN J J. Automatic location of facial feature points and synthesis of facial sketches using direct combined model [ J]. IEEE Transactions on Systems, Man and Cybernetics, 2010, 40(4) : 1158-1169.
  • 5SONG M L, TAO D C, SUN S P, et al. Joint sparse learning for 3-D facial expression generation [ J ]. IEEE Transactions on Image Processing, 2013, 22(8) : 3283-3295.
  • 6MAX H, DENG Z G. Natural eye motion synthesis by mod- eling gaze-head coupling [ C ]//IEEE Virtual Reality. Lafa- yette, USA, 2009: 143-150.
  • 7STEPTOE W, OYEKOYA O, STEED A. Eyelid kinematics for virtual characters [ J]. Computer Animation and Virtual Worlds, 2010, 21(10) :161-171.
  • 8尹宝才,王恺,王立春.基于MPEG-4的融合多元素的三维人脸动画合成方法[J].北京工业大学学报,2011,37(2):266-271. 被引量:7
  • 9范懿文,柳学成,夏时洪.人脸表情动画与语音的典型相关性分析[J].计算机辅助设计与图形学学报,2011,23(5):805-812. 被引量:4
  • 10TANG H, HUANG T S. Mpeg4 performance-driven avatar via robust facial motion tracking [ C ]//IEEE 15th Interna- tional Conference on Image Processing. Sandiego, USA, 2008 : 249-252.

二级参考文献50

  • 1孙权森,曾生根,杨茂龙,王平安,夏德深.基于典型相关分析的组合特征抽取及脸像鉴别[J].计算机研究与发展,2005,42(4):614-621. 被引量:29
  • 2王志明,蔡莲红,艾海舟.基于数据驱动方法的汉语文本-可视语音合成(英文)[J].软件学报,2005,16(6):1054-1063. 被引量:16
  • 3贺云辉,赵力,邹采荣.一种基于KCCA的小样本脸像鉴别方法[J].应用科学学报,2006,24(2):140-144. 被引量:8
  • 4Ahlberg J. CANDIDE-3--an updated parameterized face [ R]. Report No. LiTH-ISY-R-2326, Sweden: Dept of Electrical Engineering, Linkoping University, 2001.
  • 5Bookstein F. Principle warps: Thin-plate splines and the decomposition of deformation[J]. IEEE transactions on Pattern Analysis and Machine Intelligence, 1989, 11(6): 567-585.
  • 6ISO/IEC 14496-1, 1999, Coding of audio-visual objects: Systems, Amendment 1 [S].
  • 7Du C H, Yang J, Wu Q, et al. Extended fitting methods of active shape model for the location of facial feature points[C]//Lecture Notes in Computer Science. Berlin Heidelberg: Springer-Verlag, 2006: 610-618.
  • 8Wei C O, Changwon J, Kihyeon K, et al. Effective lip localization and tracking for achieving multimodal speech recognition[C]//Proeeedings of IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems. Seoul, Korea: IEEE Press, 2008: 20-22.
  • 9Chen J X. Automatic face animation with linear model [D]. NY: Rensselaer Polytechnic Institute, 2007.
  • 10PARKE F I. Computer generated animation of faces[ C ] //Proceedings of the ACM Annual Conference. New York: ACM Press, 1972: 451-457.

共引文献19

同被引文献11

引证文献4

二级引证文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部