图像驱动的三维人脸自动生成与编辑算法
|
摘要
针对图像驱动的三维人脸建模这个计算机图形学中的研究热点问题,提出一种采用三维人脸形变模型的三维人脸自动生成与编辑算法.首先建立三维人脸形变模型,由三维人脸数据库统计学习得到线性混合人脸模型,用一个低维的参数向量来描述一个人脸;然后通过人脸检测、人脸对齐、边缘提取等方法从人脸图像中提取人脸的特征,根据这些特征实现三维人脸形变模型与图像的匹配,重建出与图像对应的三维人脸模型;最后,通过改变参数向量的值实现人脸的编辑.对5个输入人脸照片进行了三维人脸模型重建和编辑并且将重建的人脸模型和真实人脸模型进行了对比,实验结果表明,该算法可实现真实化的人脸重建效果.
Image-driven 3D face modeling is a hot topic in computer graphics. This paper proposes an image driven automatic 3D human face modeling and editing algorithm, which is based on a 3D morphable face model. The 3D morphable face model is a blended shape model built through statistical learning from a 3D face database, through which a face can be represented by a low-dimensional parameter vector. Our method extracts the image features by the algorithms of face detection, face alignment and edge extraction, and then fits the 3D morphable face model with the image to reconstruct the corresponding 3D face model. Furthermore, the 3D face model can be edited by adjusting the parameter vector. The algorithm is verified by inputting 5 face pictures and reconstructing 3D face models, and then comparing the results between the real face model and the reconstructed model. The comparison results show that this method can generate realistic 3D human face and edit the face model with various styles.
Image-driven 3D face modeling is a hot topic in computer graphics. This paper proposes an image driven automatic 3D human face modeling and editing algorithm, which is based on a 3D morphable face model. The 3D morphable face model is a blended shape model built through statistical learning from a 3D face database, through which a face can be represented by a low-dimensional parameter vector. Our method extracts the image features by the algorithms of face detection, face alignment and edge extraction, and then fits the 3D morphable face model with the image to reconstruct the corresponding 3D face model. Furthermore, the 3D face model can be edited by adjusting the parameter vector. The algorithm is verified by inputting 5 face pictures and reconstructing 3D face models, and then comparing the results between the real face model and the reconstructed model. The comparison results show that this method can generate realistic 3D human face and edit the face model with various styles.
引文
[1]Parke F I.Parameterized models for facial animation[J].IEEEComputer Graphic and Applications,1982,2(9):61-68
[2]Terzopoulos D,Waters K.Physically-based facial modeling,analysis,and animation[J].Computer Animation and Virtual Worlds,1990,1(2):73-80
[3]Blanz V,Vetter T.A morphable model for the synthesis of 3Dfaces[C]//Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques.New York:ACM Press,1999:187-194
[4]Paysan P,Knothe R,Amberg B,et al.A 3D face model for pose and illumination invariant face recognition[C]//Proceedings of the IEEE International Conference on Advanced Video and Signal Base Surveillance.Los Alamitos:IEEE Computer Society Press,2009:296-301
[5]Ichim A E,Bouaziz S,Pauly M.Dynamic 3D avatar creation from hand-held video input[J].ACM Transactions on Graphics,2015,34(4):Article No.45
[6]Hsieh P L,Ma C Y,Yu J H,et al.Unconstrained realtime facial performance capture[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2015:1675-1683
[7]Shan S G,Gao W,Yan J,et al.Individual 3D face synthesis based on orthogonal photos and speech-driven facial animation[C]//Proceedings International Conference on Image Processing.Los Alamitos:IEEE Computer Society Press,2000,3:238-241
[8]Yin Baocai,Sun Yanfeng,Wang Chengzhang,et al.BJUT-3Dlarge scale 3D face database and information processing[J].Journal of Computer Research and Development,2009,46(6):1009-1018(in Chinese)(尹宝才,孙艳丰,王成章,等.BJUT-3D三维人脸数据库及其处理技术[J].计算机研究与发展,2009,46(6):1009-1018)
[9]Cao C,Weng Y L,Zhou S,et al.FaceWarehouse:a 3D facial expression database for visual computing[J].IEEE Transactions on Visualization and Computer Graphics,2014,20(3):413-425
[10]Cao C,Wu H Z,Weng Y L,et al.Real-time facial animation with image-based dynamic avatars[J].ACM Transactions on Graphics,2016,35(4):Article No.126
[11]Viola P,Jones M.Rapid object detection using a boosted cascade of simple features[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2001:Article No.7176899
[12]Lienhart R,Maydt J.An extended set of Haar-like features for rapid object detection[C]//Proceedings of International Conference on Image Processing.Los Alamitos:IEEE Computer Society Press,2002:Article No.7596261
[13]Kazemi V,Sullivan J.One millisecond face alignment with an ensemble of regression trees[C]//Proceedings of the IEEEConference on Computer Vision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2014:1867-1874
[14]Le V,Brandt J,Lin Z,et al.Interactive facial feature localization[C]//Proceedings of the European Conference on Computer Vision.Heidelberg:Springer,2012,7574:679-692
[15]Canny J F.A computational approach to edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,PAMI-8(6):679-698
[16]Bas A,Smith W A P,Bolkart T,et al.Fitting a 3D morphable model to edges:a comparison between hard and soft correspondences[C]//Proceedings of Asian Conference on Computer Vision.Heidelberg:Springer,2016,10117:377-391
[17]Floater M S.Parametrization and smooth approximation of surface triangulations[J].Computer Aided Geometric Design,1997,14(3):231-250
(1)http://www.facemore.net/page/average/en-us
(2)https://github.com/HunterSteward/3D-Mesh
[2]Terzopoulos D,Waters K.Physically-based facial modeling,analysis,and animation[J].Computer Animation and Virtual Worlds,1990,1(2):73-80
[3]Blanz V,Vetter T.A morphable model for the synthesis of 3Dfaces[C]//Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques.New York:ACM Press,1999:187-194
[4]Paysan P,Knothe R,Amberg B,et al.A 3D face model for pose and illumination invariant face recognition[C]//Proceedings of the IEEE International Conference on Advanced Video and Signal Base Surveillance.Los Alamitos:IEEE Computer Society Press,2009:296-301
[5]Ichim A E,Bouaziz S,Pauly M.Dynamic 3D avatar creation from hand-held video input[J].ACM Transactions on Graphics,2015,34(4):Article No.45
[6]Hsieh P L,Ma C Y,Yu J H,et al.Unconstrained realtime facial performance capture[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2015:1675-1683
[7]Shan S G,Gao W,Yan J,et al.Individual 3D face synthesis based on orthogonal photos and speech-driven facial animation[C]//Proceedings International Conference on Image Processing.Los Alamitos:IEEE Computer Society Press,2000,3:238-241
[8]Yin Baocai,Sun Yanfeng,Wang Chengzhang,et al.BJUT-3Dlarge scale 3D face database and information processing[J].Journal of Computer Research and Development,2009,46(6):1009-1018(in Chinese)(尹宝才,孙艳丰,王成章,等.BJUT-3D三维人脸数据库及其处理技术[J].计算机研究与发展,2009,46(6):1009-1018)
[9]Cao C,Weng Y L,Zhou S,et al.FaceWarehouse:a 3D facial expression database for visual computing[J].IEEE Transactions on Visualization and Computer Graphics,2014,20(3):413-425
[10]Cao C,Wu H Z,Weng Y L,et al.Real-time facial animation with image-based dynamic avatars[J].ACM Transactions on Graphics,2016,35(4):Article No.126
[11]Viola P,Jones M.Rapid object detection using a boosted cascade of simple features[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2001:Article No.7176899
[12]Lienhart R,Maydt J.An extended set of Haar-like features for rapid object detection[C]//Proceedings of International Conference on Image Processing.Los Alamitos:IEEE Computer Society Press,2002:Article No.7596261
[13]Kazemi V,Sullivan J.One millisecond face alignment with an ensemble of regression trees[C]//Proceedings of the IEEEConference on Computer Vision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2014:1867-1874
[14]Le V,Brandt J,Lin Z,et al.Interactive facial feature localization[C]//Proceedings of the European Conference on Computer Vision.Heidelberg:Springer,2012,7574:679-692
[15]Canny J F.A computational approach to edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,PAMI-8(6):679-698
[16]Bas A,Smith W A P,Bolkart T,et al.Fitting a 3D morphable model to edges:a comparison between hard and soft correspondences[C]//Proceedings of Asian Conference on Computer Vision.Heidelberg:Springer,2016,10117:377-391
[17]Floater M S.Parametrization and smooth approximation of surface triangulations[J].Computer Aided Geometric Design,1997,14(3):231-250
(1)http://www.facemore.net/page/average/en-us
(2)https://github.com/HunterSteward/3D-Mesh