3D Morphable Face Models - Past, Present and Future B. Egger, W. A.P. Smith, A. Tewari, S. Wuhrer, M. Zollhöfer, T. Beeler, F. Bernard, T. Bolkart, A. Kortylewski, S. Romdhani, C. Theobalt, V. Blanz and T. Vetter arXiv 2019 We provide a detailed survey of 3D Morphable Face Models over the 20 years since they were first proposed. [arXiv]

DEMEA: Deep Mesh Autoencoders for Non-Rigidly Deforming Objects E. Tretschk, A. Tewari, M. Zollhöfer, V. Golyanik and C. Theobalt arXiv 2019 We propose a general-purpose DEep MEsh Autoencoder (DEMEA) which adds a novel embedded deformation layer to a graph-convolutional mesh autoencoder. [arXiv] [video] [project page]

Text-based Editing of Talking-head Video O. Fried, A. Tewari, M. Zollhöfer, A. Finkelstein, E. Schectman, D. Goldman, K. Genova, C. Theobalt and M. Agrawala ACM Transactions on Graphics (Proc. of SIGGRAPH 2019)   —   SIGGRAPH 2019 We propose a novel method to edit talking-head video based on its transcript to produce a realistic output video in which the dialogue of the speaker has been modified. [paper] [video] [project page]

FML: Face Model Learning from Videos A. Tewari, F. Bernard, P. Garrido, G. Bharaj, M. Elgharib, H-P. Seidel, P. Perez, M. Zollhöfer and C.Theobalt Proc. Computer Vision and Pattern Recognition 2019   —   CVPR 2019 (Oral) We propose multi-frame video-based self-supervised training of a deep network that (i) learns a face identity model both in shape and appearance while (ii) jointly learning to reconstruct 3D faces. [paper] [video] [project page]

High-Fidelity Monocular Face Reconstruction based on an Unsupervised Model-based Face Autoencoder A. Tewari, M. Zollhöfer, F. Bernard, P. Garrido, H. Kim, P. Perez and C.Theobalt Transactions on Pattern Analysis and Machine Intelligence   —   TPAMI special issue on The Best of ICCV 2017 This work is an extended version of our ICCV17 paper, where we additionally present a stochastic vertex sampling technique for faster training of our networks, and moreover, we propose and evaluate analysis-by-synthesis and shape-from-shading refinement approaches to achieve a high-fidelity reconstruction. [paper] [project page]

A Hybrid Model for Identity Obfuscation by Face Replacement Q. Sun, A. Tewari, W. Xu, Mario Fritz, C. Theobalt and B. Schiele European Conference on Computer Vision (ECCV), 2018   —   ECCV 2018 We propose a new hybrid approach to obfuscate identities in photos by head replacement. Our approach combines state of the art parametric face synthesis with latest advances in Generative Adversarial Networks (GANs) for data-driven image synthesis. [paper] [project page]

Deep Video Portraits H. Kim, P. Garrido, A. Tewari, W. Xu, J. Thies, M. Nießner, P. Perez, C. Richardt M. Zollhöfer and C. Theobalt ACM Transactions on Graphics (Proc. SIGGRAPH 2018)   —   SIGGRAPH 2018 We present a novel approach that enables full photo-realistic re-animation of portrait videos using only an input video. [paper] [video] [project page]

Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hz A. Tewari, M. Zollhöfer, P. Garrido, F. Bernard, H. Kim, P. Perez and C.Theobalt Proc. Computer Vision and Pattern Recognition 2018   —   CVPR 2018 (Oral) We propose the first approach that jointly learns 1) a regressor for face shape, expression, reflectance and illumination on the basis of 2) a concurrently learned parametric face model. [paper] [video] [project page]

InverseFaceNet: Deep Single-Shot Inverse Face Rendering From A Single Image H. Kim, M. Zollhöfer, A. Tewari, J. Thies, C. Richardt and C.Theobalt Proc. Computer Vision and Pattern Recognition 2018   —   CVPR 2018 We introduce InverseFaceNet, a deep convolutional inverse rendering framework for faces that jointly estimates facial pose, shape, expression, reflectance and illumination from a single input image in a single shot. [paper] [video] [project page]

MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction A. Tewari, M. Zollhöfer, H. Kim, P. Garrido, F. Bernard, P. Perez and C.Theobalt Proc. of the International Conference on Computer Vision 2017   —   ICCV 2017 (Oral) In this work we propose a novel model-based deep convolutional autoencoder that addresses the highly challenging problem of reconstructing a human face from a single image. [paper] [video] [project page]

• October 2016 - present:
  Ph. D. student in Computer Science at the Universität des Saarlandes, Saarbrücken, Germany and the Max-Planck-Institut für Informatik
  


• 2014 - 2015:
  Masters student in Computer Science at ENSIMAG, Grenoble.
  Title of Masters Thesis: Image Blending using Local Phase


• 2010 - 2014
  Undergraduate student in Computer Science at IIIT Hyderabad, India