全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

结合特征适配与拉普拉斯形变的3维人脸重建

DOI: 10.11834/jig.20140912

Keywords: 可变形模型,特征适配,拉普拉斯方法,纹理合成,3维重建

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的数字娱乐产业的发展要求3维人脸重建技术能重建高分辨率3维人脸,并具有较高计算效率和重建准确性。针对这一情况,提出一种基于单幅图像的高分辨率3维人脸重建方法。方法该方法包含特征适配与拉普拉斯形变两部分。预先用1组3维人脸样本上的3维特征构造可变形模型。给定图像时,从其上自动提取2维特征点,并根据获得问题最优解的必要条件进行特征适配以重建个性化3维特征;然后基于拉普拉斯方法,用该3维特征对一般人脸模型进行变形以获得特定高分辨率3维人脸;最后通过纹理合成获得真实感人脸。结果用本文方法和已有方法分别进行可变形模型适配和模型变形,本文的特征适配方法具有更快的收敛速度和更高的准确性,拉普拉斯方法具有更小的重建误差。纹理映射后的3维人脸具有很好的视觉效果。结论本文方法将特征适配与拉普拉斯形变结合起来进行高分辨率3维人脸重建。实验结果表明所提出的方法具有较高的计算效率和准确性,能实现较为理想的高分辨率3维人脸重建。

References

[1]  Tomasi C, Kanade T. Shape and motion from image streams under orthography: a factorization method [J]. International Journal of Computer Vision, 1992, 9(2): 137-154. [DOI: 10.1007/BF00129684]
[2]  Bregler C, Hertzmann A, Biermann H. Recovering non-rigid 3D shape from image streams [C]// Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Los Alamitos:IEEE Computer Society Press, 2000,2:690-696. [DOI: 10.1109/CVPR.2000.854941]
[3]  Xiao J, Chai J X, Kanade T. A closed-form solution to non-rigid shape and motion recovery [J]. International Journal of Computer Vision, 2006, 67(2):233-246. [DOI: 10.1007/978-3-540-24673-2_46]
[4]  Zhang J. 3D facial expression reconstruction from video via SFM and dynamic texture mapping [J]. Journal of Computer-Aided Design & Computer Graphics, 2010, 22(6):949-958.[张剑. 融合SFM和动态纹理映射的视频流3维表情重建 [J]. 计算机辅助设计与图形学学报, 2010, 22(6):949-958.] [DOI: 10.3321/j.issn:0254-4164.2005.06.019]
[5]  Pighin F, Hecker J, Lischinski D, et al. Synthesizing realistic facial expressions from photographs [C]// Computer Graphics Proceedings, Annual Conference Series, ACM SIGGRAPH. New York:ACM Press, 1998:75-84. [DOI: 10.1145/280814.280825]
[6]  Blanz V, Grother P, Phillips P J, et al. Face recognition based on frontal views generated from non-frontal images [C]// Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Los Alamitos:IEEE Computer Society Press, 2005:454-461. [DOI: 10.1109/CVPR.2005.150]
[7]  Jiang D L, Hu Y X, Yan S C, et al. Efficient 3D reconstruction for face recognition [J]. Pattern Recognition, 2005, 38(6):787-798. [DOI: http://dx.doi.org/10.1016/j.patcog.2004.11.004]
[8]  Chai X J, Shan S G, Qing L Y, et al. Pose and illumination invariant face recognition based on 3D face reconstruction [J]. Journal of Software, 2006, 17(3):525-524.[柴秀娟, 山世光, 卿来云, 等. 基于3D人脸重建的光照、姿态不变人脸识别 [J]. 软件学报, 2006, 17(3):525-524.] [DOI: 10.3969/j.issn.1672-0520.2011.05.014]
[9]  Zhang J, Zhuang Y T. Sample-based 3D face reconstruction from a single frontal image by adaptive locally linear embedding [J]. Journal of Zhejiang University: Science A, 2007, 8(4):550-558. [DOI: 10.1631/jzus.2007.A0550]
[10]  Park U, Tong Y, Jain A K. Age invariant face recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(5):947-954. [DOI: 10.1109/TPAMI.2010.14]
[11]  Lee Y J, Lee S J, Park K R, et al. Single view-based 3D face reconstruction robust to self-occlusion [J]. EURASIP Journal on Advances in Signal Processing, 2012:176.[DOI: 10.1186/1687-6180-2012-176]
[12]  Lu X G, Hsu R, Jain A K, et al. Face recognition with 3D model-based synthesis [M]//Lecture Notes in Computer Science. Heidelberg: Springer, 2004, 3072:139-146. [DOI: 10.1007/978-3-540-25948-0_20]
[13]  Sheng Y, Sadka A H, Kondoz A M. Automatic single view-based 3D face synthesis for unsupervised multimedia applications [J]. IEEE Transactions on circuits and systems for video technology, 2008, 18(7):961-974. [DOI: 10.1109/TCSVT.2008.924101]
[14]  Sorkine O, Cohen-Or D, Lipman Y, et al. Laplacian surface editing [C]// ACM SIGGRAPH Symposium on Geometry Processing. Wellesley: A K Peters, 2004:175-184. [DOI: 10.1145/1057432.1057456]
[15]  Huang W, Yao S B, Guan S L, et al. A real-time image deformation method based on line handles [J]. Journal of Computer-Aided Design & Computer Graphics, 2010, 22(12):2067-2072.[黄武, 姚淑波, 关胜亮, 等. 利用控制线段的实时图像变形方法 [J]. 计算机辅助设计与图形学学报, 2010, 22(12):2067-2072.]
[16]  Cootes T F, Wheeler G V, Walker K N, et al. View-based active appearance models [J]. Image and Vision Computing, 2002, 20(9):657-664. [DOI: 10.1109/AFGR.2000.840639]
[17]  Gourier N, Maisonnasse J, Hall D, et al. Head pose estimation on low resolution images [C]// Proceedings of the 1st International Evaluation Conference on Classification of Events, Activities and Relationships. Heidelberg: Springer, 2007:270-280. [DOI: 10.1007/978-3-540-69568-4_24]
[18]  Dong H, Gu N. Asian face image database PF01 [R]. Pohang:Pohang University of Science and Technology. Department of Computer Science and Engineering, 2001.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133