Abstract
Nowadays, facial expression synthesis is widely used in expression simulation, recognition and animation. While a variety of works available in literature are 3D based, these algorithms usually require face matching and trimming, are thus time consuming. In this work, an automatic algorithm for expression synthesis in 2D space is proposed, which mainly consists of three stages.The optimum matching of three sets of feature points on the faces of source neutral (F s n ), source expression (F s e ) and target neutral (F t n ) are obtained in the first stage. Different components on the target face are deformed by learning from not only the displacements but also the geometry shape of face F s e in the second stage. In the last stage, the details of the source expression are mapped onto the corresponding positions on the target face by fitting of the lighting differences. Experimental results on expression synthesis with large geometry deformation and lighting difference show that the proposed algorithm is able to accurately preserve the geometry deformation, and the synthesized expressions are visually realistic.
Similar content being viewed by others
References
Al-Osaimi F, Bennamoun M, Mian A (2009) An expression deformation approach to non-rigid 3d face recognition. Int J Comput Vis 81(3):302–316
Bando Y, Kuratate T, Nishita T (2002) A simple method for modeling wrinkles on human skin. In: the 10th Pacific Conference on Computer Graphics and Applications, IEEE Computer Society, p 166
Beier T, Neely S (1992) Feature-based image metamorphosis. In: ACM SIGGRAPH Computer Graphics, ACM, pp 35–42
Beymer D, Shashua A, Poggio T (1993) Example based image analysis and synthesis. PhD thesis, Artificial Intelligence Laboratory, Massachusetts Institute of Technology
Blanz V, Basso C, Poggio T, Vetter T (2003) Reanimating faces in images and video. Comput Graph Forum 22(3):641–650
Debevec P (1998) Rendering synthetic objects into real scenes: bridging traditional and image-based graphics with global illumination and high dynamic range photography. In: SIGGRAPH, ACM, pp 189–198
Gibbons J, Chakraborti S (2003) Nonparametric Statistical Inference. Marcel Dekker
Huang D, De la Torre F (2010) Bilinear kernel reduced rank regression for facial expression synthesis. In: the 11th European Conference on Computer Vision. Springer-Verlag, Verlag, pp 364–377
Kazemi V, Josephine S (2014) One millisecond face alignment with an ensemble of regression trees. In: IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp 1867–1874
Kotsia I, Pitas I (2007) Facial expression recognition in image sequences using geometric deformation features and support vector machines. IEEE Trans Image Process 16(1):172–187
Larboulette C, Cani M (2004) Real-time dynamic wrinkles. In: the Computer Graphics International, IEEE Computer Society, pp 522–525
Lee Y, Terzopoulos D, Waters K (1995) Realistic modeling for facial animation. In: the 22nd Annual Conference on Computer Graphics and Interactive Techniques, ACM, pp 55–62
Li K, Dai Q, Wang R, Liu Y, Xu F, Wang J (2014) A data-driven approach for facial expression retargeting in video. IEEE Trans Multimedia 16(2):299–310
Liao J, Lima R, Nehab D, Hoppe H, Sander P, Yu J (2014) Automating image morphing using structural similarity on a halfway domain. ACM Trans Graph 33(5):1–12
Liu Z, Shan Y, Zhang Z (2001) Expressive expression mapping with ratio images. In: the 28th Annual Conference on Computer Graphics and Interactive Techniques, ACM, pp 271–276
Lu X, Jain A (2008) Deformation modeling for robust 3d face matching. IEEE Trans Pattern Anal Mach Intell 30(8):1346–1356
Lucey P, Cohn J, Kanade T, Saragih J, Ambadar Z, Matthews I (2010) The extended cohn-kanade dataset (ck+): a complete dataset for action unit and emotion-specified expression. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW, IEEE, pp 94– 101
Matthews I, Xiao J, Baker S (2007) 2d vs. 3d deformable face models: representational power, construction, and real-time fitting. Int J Comput Vis 75(1):93–113
Pan G, Han S, Wu Z, Zhang Y (2010) Removal of 3d facial expressions: a learning-based approach. In: Computer Vision and Pattern Recognition, CVPR, IEEE, pp 2614–2621
Qian K, Wang B, Chen H (2014) Automatic flexible face replacement with no auxiliary data. Comput & Graph 45(0):64–74
Raouzaiou A, Tsapatsoulis N, Karpouzis K, Kollias S (2002) Parameterized facial expression synthesis based on mpeg-4. EURASIP J Appl Signal Processing 2002(1):1021–1038
Ren S, Cao X, Wei Y, Sun J (2014) Face alignment at 3000 fps via regressing local binary features. In: IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp 1685–1692
Sanchez A, Ruiz J, Moreno A, Montemayor A, Hernandez J, Pantrigo J (2011) Differential optical flow applied to automatic facial expression recognition. Neurocomputing 74(8):1272–1282
Seitz S, Dyer C (1996) View morphing. In: the 23rd Annual Conference on Computer Graphics and Interactive Techniques, ACM, pp 21–30
Song M, Dong Z, Theobalt C, Wang H, Liu Z, Seidel H (2007) A generic framework for efficient 2-d and 3-d facial expression analogy. IEEE Trans Multimedia 9(7):1384–1395
Sumner R, Popovic J (2004) Deformation transfer for triangle meshes. ACM Trans Graph 23(3):399–405
Tzimiropoulos G, Pantic M (2013) Optimization problems for fast aam fitting in-the-wild. In: IEEE International Conference on Computer Vision, ICCV, IEEE, pp 593–600
Vlasic D, Brand M, Pfister H, Popovic J (2005) Face transfer with multilinear models. ACM Trans Graph 24(3):426–433
Weise T, Bouaziz S, Li H, Pauly M (2011) Realtime performance-based facial animation. ACM Trans Graph 30(4):76–79
Weng Y, Xu W, Wu Y, Zhou K, Guo B (2006) 2d shape deformation using nonlinear least squares optimization. Visual Comput 22(9–11):653–660
Xie W, Shen L, Yang M, Hou Q (2015) Lighting difference based wrinkle mapping for expression synthesis. In: 2015 8th International Congress on Image and Signal Processing, CISP, IEEE, pp 636– 641
Yu H, Garrod O, Jack R, Schyns P (2015) A framework for automatic and perceptually valid facial expression generation. Multimed Tools Appl 74(21):9427–9447
Zhang Q, Liu Z, Guo B, Terzopoulos D, Shum H (2006) Geometry-driven photorealistic facial expression synthesis. IEEE Trans Vis Comput Graph 12(1):48–60
Zhang Y, Lin W, Zhou B, Chen Z, Sheng B, Wu J (2014) Facial expression cloning with elastic and muscle models. J Vis Commun Image Represent 25(5):916–927
Acknowledgments
The authors thank the anonymous reviewers for their helpful comments and suggestions. The work was supported by Natural Science Foundation of China under grand no. 61672357, 61602315, 61402289 and 61272050, China Postdoctoral Science Foundation under grant no. 2015M572363, the Science Foundation of Guangdong Province under grant no. 2014A030313556 and 2014A030313558.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Xie, W., Shen, L., Yang, M. et al. Facial expression synthesis with direction field preservation based mesh deformation and lighting fitting based wrinkle mapping. Multimed Tools Appl 77, 7565–7593 (2018). https://doi.org/10.1007/s11042-017-4661-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-017-4661-6