基于自遮挡的三维人脸重建优化
摘要
三维形变模型(3D Morphable Model,3DMM)广泛被用于单视图的三维人脸重建,这种三维人脸重建方法需要正视图和先验模型,会受到计算复杂度高、容易陷入局部极小值和易受姿态变化的影响。一种基于稀疏的三维人脸形状的简化三维形变模型,可降低计算复杂度,然而它容易受自身遮挡的影响,对于侧脸的鲁棒性不高。因此,我们提出了一个基于简化三维形变模型来处理自身遮挡的的解决方案,并应用在三维人脸重建问题上。我们的研究主要包括以下几步:首先,用柱形头部模型对输入图像的头部姿态进行自动检测;其次,根据选择的可见脸部特征点重建三维稀疏模型,这样使得自身遮挡的影响得到去除;最后,重建最后的三维人脸,用稀疏的三维模型作为初始化的姿态参数加强了三维重建的性能。实验结果显示自身遮挡的检测具有高的精度,应用在三维人脸重建上与之前的方法相比也得到了完善。
引文
[1]X.Zhang,Y.Gao,Face recognition across pose:a review,Pattern recognition.42(2009)2876–2896
[2]A Moeini,Hossein Moeini,Karim Faez.Unrestricted pose-invariant face recognition by sparse dictionary matrix[J].Image and Vision Computing.36(2015)9-22
[3]U.Park,Y.Tong,A.K.Jain,Age invariant face recognition,IEEE.Trans.Pattern Anal.Mach.Intell.32(5)(2010)947–954
[4]Ira Kemelmacher-Shlizerman,Ronen Basri,3DFace Reconstruction from a Single Image Using a Single Reference Face Shape,IEEE.Trans.Pattern Anal.Mach.Intell.33(2)(2011)394-405
[5]Jaeik Jo,Heeseung Choi,Ig-jae Kim,Jaihie Kim,Single-viewbased 3D facial reconstruction method robust against post variations,Pattern Recognition,Voume48,Issue 1(2015)73-85
[6]S.Lee,K.Park.J.Kim,A SFM-based 3D face reconstruction method robust to self-occlusion by using a shape conversion matrix,Pattern Recognit.44(7)(2011)1470-1486
[7]ELLEN C.HILDRETH,HIROSHI ANDO,Recovering Threedimensional Structure from Motion with Suface Reconstruction,Vision Res,Vol 35(1)(1994)117-137
[8]Chapter 4-3D Morphable face model:a unified approach for analysis and synthesis of images,Face Processing,(2005)127-158
[9]Hai-bin Liao,Qing-hu chen,Qian-jin Zhou,Lin Guo,Rapid 3D face reconstruction by fusion of SFS and Local Morphable Model,Journal of Visual Communication and Image Representation,Volume 23(2012)924-931
[10]Blanz V,Vetter T,Face recognition based on fitting a 3D morphable model,IEEE Trans.Pattern Anal.Mach.Intell,25(9)(2003)1063-1074
[11]Ankur Patel,William A.P.Smith,Driving 3D morphable models using shading cues,Pattern Recognition,Volume 45,Issue 5(2012)1993-2004
[12]Aldrian,O.Smith,W.A.P,Inverse rendering of faces with a 3D morphable model,IEEE Trans.Pattern Anal.Mach.Intell,33(6)(2012)1080-1093
[13]Romdhani,S.,Vetter,T.,Efficient,robust and accurate fitting of a3D morphable model,IEEE Computer Vision,1,(2003)59-66
[14]Romdhani,S.,Vetter,T.,Estimating 3D shape and texture using pixel intensity,edges,specular highlights,texture constraints and a prior,IEEE Computer Vision and Pattern Recognition,2(2005)986-993
[15]Qu.C,Monari.E,Schuchert.T,Beyerer.J,Realistic texture extraction for 3D face models robust to self-occlusion,Machine Vision Application VIII(2015)
[16]Youn Joo Lee,Sung Joo Lee,Kang Ryoung Park,Jaeik Jo,Jaihie Kim,Single view-based 3D face reconstruction robust to self-occlusion,EURASIP J.Adv.Signal Process,2012(176)(2012)1-20
[17]Ying Chen,Chunjian Hua,Ruilin Bai,Regression-based Active Appearance Model initialization for facial feature tracking with missing frames,Pattern Recognition,Volume 38(2014)113-119
[18]I.Matthews,S.Baker,Active appearance models revis-ited,IJCV,60(2)(2004)135-164
[19]Murphy-Chutorian.E,Trivedi,M.M,Head pose estimation in computer vision:A survey,IEEE Trans.Pattern Anal.Mach.Intell,31(4)(2009)607-626
[20]Ben Ghorbel.M,Baklouti.M,Couvet.S,3D head pose estimation and tracking using particle filtering and ICP algorithm,Articulated Motion and Deformable Objects,(2010)224-237
[21]K.Ohue,Y.Yamada,S.Uozumi,S.Tokoro,A.Hattori,T.Hayashi,Development of a new pre-crash safety system,SAE World Congress(2006)
[22]Fukui,K,Yamaguchi,O,Facial feature point extraction method based on combination of shape extraction and pattern matching,Systems and Computers in Japan,29(6)(1998)49-58
[23]Arandjelovic,O,Copolla,R,A pose-wise linear illumination manifold model for face recognition using video,Computer Vision and Image Understanding,113(1)(2009)113-125
[24]3D scanner specification.(http://cyberware.com/products/pdf/head Face.pdf)(accessed November 2013)
[25]BJUT.http://www.bjut.edu.cn/sci/multimedia/mul-lab/3dface/face_database.htm
[26]C.Tomasi,T.Kanade,Shape and motion from image streams under orthography:a factorization method,Int.J.Comput.Vis.9(2)(1992)137-154
[27]Zhong Huang,Fuji Ren,Facial expression recognition based on active appearance model and scale-invariantfeature transform,System Integration(SII),2013 IEEE/SICE International Symposium om,pp.94-99,15-17,2013
[28]J.Alabort-i-medina,S.Zafeiriou,Bayesian active appearance models.in:Proceedings of IEEE int’l Conf.On Computer Vision and Pattern Recognition(CVPR 2014,Accepted),2014
[2]A Moeini,Hossein Moeini,Karim Faez.Unrestricted pose-invariant face recognition by sparse dictionary matrix[J].Image and Vision Computing.36(2015)9-22
[3]U.Park,Y.Tong,A.K.Jain,Age invariant face recognition,IEEE.Trans.Pattern Anal.Mach.Intell.32(5)(2010)947–954
[4]Ira Kemelmacher-Shlizerman,Ronen Basri,3DFace Reconstruction from a Single Image Using a Single Reference Face Shape,IEEE.Trans.Pattern Anal.Mach.Intell.33(2)(2011)394-405
[5]Jaeik Jo,Heeseung Choi,Ig-jae Kim,Jaihie Kim,Single-viewbased 3D facial reconstruction method robust against post variations,Pattern Recognition,Voume48,Issue 1(2015)73-85
[6]S.Lee,K.Park.J.Kim,A SFM-based 3D face reconstruction method robust to self-occlusion by using a shape conversion matrix,Pattern Recognit.44(7)(2011)1470-1486
[7]ELLEN C.HILDRETH,HIROSHI ANDO,Recovering Threedimensional Structure from Motion with Suface Reconstruction,Vision Res,Vol 35(1)(1994)117-137
[8]Chapter 4-3D Morphable face model:a unified approach for analysis and synthesis of images,Face Processing,(2005)127-158
[9]Hai-bin Liao,Qing-hu chen,Qian-jin Zhou,Lin Guo,Rapid 3D face reconstruction by fusion of SFS and Local Morphable Model,Journal of Visual Communication and Image Representation,Volume 23(2012)924-931
[10]Blanz V,Vetter T,Face recognition based on fitting a 3D morphable model,IEEE Trans.Pattern Anal.Mach.Intell,25(9)(2003)1063-1074
[11]Ankur Patel,William A.P.Smith,Driving 3D morphable models using shading cues,Pattern Recognition,Volume 45,Issue 5(2012)1993-2004
[12]Aldrian,O.Smith,W.A.P,Inverse rendering of faces with a 3D morphable model,IEEE Trans.Pattern Anal.Mach.Intell,33(6)(2012)1080-1093
[13]Romdhani,S.,Vetter,T.,Efficient,robust and accurate fitting of a3D morphable model,IEEE Computer Vision,1,(2003)59-66
[14]Romdhani,S.,Vetter,T.,Estimating 3D shape and texture using pixel intensity,edges,specular highlights,texture constraints and a prior,IEEE Computer Vision and Pattern Recognition,2(2005)986-993
[15]Qu.C,Monari.E,Schuchert.T,Beyerer.J,Realistic texture extraction for 3D face models robust to self-occlusion,Machine Vision Application VIII(2015)
[16]Youn Joo Lee,Sung Joo Lee,Kang Ryoung Park,Jaeik Jo,Jaihie Kim,Single view-based 3D face reconstruction robust to self-occlusion,EURASIP J.Adv.Signal Process,2012(176)(2012)1-20
[17]Ying Chen,Chunjian Hua,Ruilin Bai,Regression-based Active Appearance Model initialization for facial feature tracking with missing frames,Pattern Recognition,Volume 38(2014)113-119
[18]I.Matthews,S.Baker,Active appearance models revis-ited,IJCV,60(2)(2004)135-164
[19]Murphy-Chutorian.E,Trivedi,M.M,Head pose estimation in computer vision:A survey,IEEE Trans.Pattern Anal.Mach.Intell,31(4)(2009)607-626
[20]Ben Ghorbel.M,Baklouti.M,Couvet.S,3D head pose estimation and tracking using particle filtering and ICP algorithm,Articulated Motion and Deformable Objects,(2010)224-237
[21]K.Ohue,Y.Yamada,S.Uozumi,S.Tokoro,A.Hattori,T.Hayashi,Development of a new pre-crash safety system,SAE World Congress(2006)
[22]Fukui,K,Yamaguchi,O,Facial feature point extraction method based on combination of shape extraction and pattern matching,Systems and Computers in Japan,29(6)(1998)49-58
[23]Arandjelovic,O,Copolla,R,A pose-wise linear illumination manifold model for face recognition using video,Computer Vision and Image Understanding,113(1)(2009)113-125
[24]3D scanner specification.(http://cyberware.com/products/pdf/head Face.pdf)(accessed November 2013)
[25]BJUT.http://www.bjut.edu.cn/sci/multimedia/mul-lab/3dface/face_database.htm
[26]C.Tomasi,T.Kanade,Shape and motion from image streams under orthography:a factorization method,Int.J.Comput.Vis.9(2)(1992)137-154
[27]Zhong Huang,Fuji Ren,Facial expression recognition based on active appearance model and scale-invariantfeature transform,System Integration(SII),2013 IEEE/SICE International Symposium om,pp.94-99,15-17,2013
[28]J.Alabort-i-medina,S.Zafeiriou,Bayesian active appearance models.in:Proceedings of IEEE int’l Conf.On Computer Vision and Pattern Recognition(CVPR 2014,Accepted),2014