Imperial College London

STEFANOS ZAFEIRIOU, PhD

Faculty of EngineeringDepartment of Computing

Reader in Machine Learning and Computer Vision
 
 
 
//

Contact

 

+44 (0)20 7594 8461s.zafeiriou Website CV

 
 
//

Location

 

375Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Gecer,
author = {Gecer, B and Ploumpis, S and Kotsia, I and Zafeiriou, S},
publisher = {IEEE},
title = {GANFIT: generative adversarial network fitting for high fidelity 3D face reconstruction},
url = {http://hdl.handle.net/10044/1/69955},
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - In the past few years a lot of work has been done towardsreconstructing the 3D facial structure from single imagesby capitalizing on the power of Deep Convolutional NeuralNetworks (DCNNs). In the most recent works, differentiablerenderers were employed in order to learn the relationshipbetween the facial identity features and the parameters ofa 3D morphable model for shape and texture. The texturefeatures either correspond to components of a linear texturespace or are learned by auto-encoders directly fromin-the-wild images. In all cases, the quality of the facialtexture reconstruction of the state-of-the-art methods is stillnot capable of modelling textures in high fidelity. In thispaper, we take a radically different approach and harnessthe power of Generative Adversarial Networks (GANs) andDCNNs in order to reconstruct the facial texture and shapefrom single images. That is, we utilize GANs to train a verypowerful generator of facial texture in UV space. Then, werevisit the original 3D Morphable Models (3DMMs) fittingapproaches making use of non-linear optimization to findthe optimal latent parameters that best reconstruct the testimage but under a new perspective. We optimize the parameterswith the supervision of pretrained deep identity featuresthrough our end-to-end differentiable framework. Wedemonstrate excellent results in photorealistic and identitypreserving 3D face reconstructions and achieve for the firsttime, to the best of our knowledge, facial texture reconstructionwith high-frequency details.1
AU - Gecer,B
AU - Ploumpis,S
AU - Kotsia,I
AU - Zafeiriou,S
PB - IEEE
TI - GANFIT: generative adversarial network fitting for high fidelity 3D face reconstruction
UR - http://hdl.handle.net/10044/1/69955
ER -