Neural Face Editing with Intrinsic Image Disentangling

Traditional face editing methods often require a number of sophisticated and task specific algorithms to be applied one after the other — a process that is tedious, fragile, and computationally intensive. In this paper, we propose an end-to-end generative adversarial network that infers a face-specific disentangled representation of intrinsic face properties, including shape (i.e. normals), albedo, and lighting, and an alpha matte. We show that this network can be trained on in-the-wild images by incorporating an in-network physically-based image formation module and appropriate loss functions. Our disentangling latent representation allows for semantically relevant edits, where one aspect of facial appearance can be manipulated while keeping orthogonal properties fixed, and we demonstrate its use for a number of facial editing applications.

[1]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[2]  Ira Kemelmacher-Shlizerman,et al.  Transfiguring portraits , 2016, ACM Trans. Graph..

[3]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[4]  H. Barrow,et al.  RECOVERING INTRINSIC SCENE CHARACTERISTICS FROM IMAGES , 1978 .

[5]  Zicheng Liu,et al.  Expressive expression mapping with ratio images , 2001, SIGGRAPH.

[6]  Ira Kemelmacher-Shlizerman,et al.  Illumination-Aware Age Progression , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Jitendra Malik,et al.  Shape, Illumination, and Reflectance from Shading , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Takeo Kanade,et al.  Multi-PIE , 2008, 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition.

[9]  Tomaso A. Poggio,et al.  Reanimating Faces in Images and Video , 2003, Comput. Graph. Forum.

[10]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[11]  Jason M. Saragih Principal regression analysis , 2011, CVPR 2011.

[12]  Zicheng Liu,et al.  Face relighting with radiance environment maps , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[13]  E. Land,et al.  Lightness and retinex theory. , 1971, Journal of the Optical Society of America.

[14]  Qinping Zhao,et al.  Face illumination transfer through edge-preserving filters , 2011, CVPR 2011.

[15]  Shree K. Nayar,et al.  Attribute and simile classifiers for face verification , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[16]  Yann LeCun,et al.  Energy-based Generative Adversarial Networks , 2016, ICLR.

[17]  Kun Zhou,et al.  AutoHair: fully automatic hair modeling from a single image , 2016, ACM Trans. Graph..

[18]  Tim Weyrich,et al.  Analysis of human faces using a measurement-based skin reflectance model , 2006, ACM Trans. Graph..

[19]  Joshua B. Tenenbaum,et al.  Deep Convolutional Inverse Graphics Network , 2015, NIPS.

[20]  Andrew Zisserman,et al.  Deep Face Recognition , 2015, BMVC.

[21]  Honglak Lee,et al.  Attribute2Image: Conditional Image Generation from Visual Attributes , 2015, ECCV.

[22]  Matt J. Kusner,et al.  Deep Manifold Traversal: Changing Labels with Convolutional Features , 2015, ArXiv.

[23]  Justus Thies,et al.  Demo of Face2Face: real-time face capture and reenactment of RGB videos , 2016, SIGGRAPH Emerging Technologies.

[24]  G. Stiny Shape , 1999 .

[25]  Tal Hassner,et al.  Viewing Real-World Faces in 3D , 2013, 2013 IEEE International Conference on Computer Vision.

[26]  Tal Hassner,et al.  Effective face frontalization in unconstrained images , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Dimitris Samaras,et al.  EyeOpener: Editing Eyes in the Wild , 2017, ACM Trans. Graph..

[28]  Yann LeCun,et al.  Energy-based Generative Adversarial Network , 2016, ICLR.

[29]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Gang Hua,et al.  Face Re-Lighting from a Single Image under Harsh Lighting Conditions , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[31]  Fei Yang,et al.  Expression flow for 3D-aware face component transfer , 2011, ACM Trans. Graph..

[32]  Scott E. Reed,et al.  Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis , 2015, NIPS.

[33]  Hanspeter Pfister,et al.  Face transfer with multilinear models , 2005, ACM Trans. Graph..

[34]  Matthew Turk,et al.  A Morphable Model For The Synthesis Of 3D Faces , 1999, SIGGRAPH.

[35]  Tal Hassner,et al.  Do We Really Need to Collect Millions of Faces for Effective Face Recognition? , 2016, ECCV.

[36]  Thomas Brox,et al.  Multi-view 3D Models from Single Images with a Convolutional Network , 2015, ECCV.

[37]  Kun Zhou,et al.  High-quality hair modeling from a single portrait photo , 2015, ACM Trans. Graph..

[38]  Gang Hua,et al.  Face Relighting from a Single Image under Arbitrary Unknown Lighting Conditions , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[39]  Ming Yang,et al.  DeepFace: Closing the Gap to Human-Level Performance in Face Verification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[40]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  M. Gross,et al.  Analysis of human faces using a measurement-based skin reflectance model , 2006, ACM Trans. Graph..

[42]  Ira Kemelmacher-Shlizerman,et al.  Face reconstruction in the wild , 2011, 2011 International Conference on Computer Vision.

[43]  Justus Thies,et al.  Face2Face: real-time face capture and reenactment of RGB videos , 2019, Commun. ACM.

[44]  Yiying Tong,et al.  FaceWarehouse: A 3D Facial Expression Database for Visual Computing , 2014, IEEE Transactions on Visualization and Computer Graphics.

[45]  Ronen Basri,et al.  Lambertian reflectance and linear subspaces , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[46]  P. Hanrahan,et al.  On the relationship between radiance and irradiance: determining the illumination from images of a convex Lambertian object. , 2001, Journal of the Optical Society of America. A, Optics, image science, and vision.