ANASTASIOS (TASSOS) ROUSSOS

Academic Homepage

Anastasios (Tassos) Roussos, PhD, Dipl-Ing

Principal Researcher (equivalent to Associate Professor),
Institute of Computer Science,
Foundation for Research and Technology - Hellas (FORTH), Greece

Welcome to my homepage! My name is Anastasios (Tassos) Roussos. Since January 2019, I am a Principal Researcher (Associate Professor level) at the Institute of Computer Science (ICS) of the Foundation for Research and Technology - Hellas (FORTH), Crete, Greece. I am also affiliated with the Department of Computer Science, University of Exeter, UK and a a Fellow of the Alan Turing Institute, UK.

Prior to my current position at FORTH, I was a Lecturer (equivalent to Assistant Professor) in Computer Science at the University of Exeter, UK and before that, I was a postdoctoral researcher at Imperial College London (2014-2017), University College London (UCL) (2013-2014) and Queen Mary, University of London (2010-2013). I have studied Electrical and Computer Engineering (PhD 2010, Engineering Diploma 2005) at the National Technical University of Athens (NTUA), Greece.

My research specialises in the fields of Computer Vision, Machine Learning, Variational Methods and Partial Differential Equations. The focus of my current research is the development of novel methods for detailed 3D modelling and reconstruction of real-world objects from image data. The main motivation for my work stems from the vision of building robust 3D Computer Vision methodologies that would provide highly-accurate estimations in challenging real-world scenarios.

In more detail, my research interests include dense variational methods, convex and nonconvex optimization, statistical shape models and deep learning for 3D face modelling, dense 4D (3D+time) reconstruction of non-rigid scenes, motion estimation and more general inverse problems in Computer Vision. I am interested in various applications such as gesture and sign language recognition, computer-aided surgery, marker-less motion and performance capture, augmented reality, visual effects, facial expression recognition, and biomedical image processing.

Research Overview


A demo video with an overview of my research up to March 2017 (to be updated):




A presentation that overviews my research up to March 2017 (to be updated): pdf and video format:



Research Groups


PhD Students

  • Mohammad Rami Koujan,
    Subject of Research: 3D Computer Vision for Facial Shape Modelling and Analysis,
    PhD Student, University of Exeter, 2017-expected 2021.

MSc/BSc Theses Supervision (selected)

  • C. Tyson, 3D Facial Scanning and 3D Printing using a Single Commodity Camera,
    BSc Final Year Project, University of Exeter, 2018-2019.
  • E. Reeder, 3D Reconstruction of Hands,
    BSc Final Year Project, University of Exeter, 2018-2019.
  • Y. Haddadin, 3D Computer Vision for Video Games,
    BSc Final Year Project, University of Exeter, 2018-2019.
  • R. Durand-Delacre, Vision-based Creation of Realistic 3D Terrain Profiles,
    BSc Final Year Project, University of Exeter, 2018-2019.
  • James Badham, Monocular 3D Face Scanning,
    MSci Research Project, University of Exeter, 2017-2018.
  • Ibukun Akande, Video to 3D Facial Reenactment,
    BSc Final Year Project, University of Exeter, 2017-2018.
  • Nikolai Dochev, 4D Face Reconstruction from a Single Camera,
    BSc Final Year Project, University of Exeter, 2017-2018.
    Winner of the Computer Science Final Year Project Prize, University of Exeter.

Teaching

  • Machine Vision,
    MSc Data Science (Professional) course, University of Exeter, 2018-2019.
  • Computer Vision,
    MSc course, University of Exeter, 2017-2018.
  • Computer Graphics,
    3rd year course, University of Exeter, 2017-2019.

Publications

Journal Papers

  • J. Deng, A. Roussos, G. Chrysos, E. Ververas, I. Kotsia, J. Shen, and S. Zafeiriou,
    The Menpo Benchmark for Multi-pose 2D and 3D Facial Landmark Localisation and Tracking,
    International Journal of Computer Vision, accepted with minor revisions.
    [article]
  • J. Booth, A. Roussos, E. Ververas, E. Antonakos, S. Ploumpis, Y. Panagakis, and S. Zafeiriou,
    3D Reconstruction of "In-the-Wild" Faces in Images and Videos,
    Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), accepted for publication.
    [article] [code & data]
  • J. Booth, A. Roussos, A. Ponniah, D. Dunaway, and S. Zafeiriou,
    Large Scale 3D Morphable Models,
    International Journal of Computer Vision (IJCV), Volume 126, Issue 2-4, pp 233-254, April 2018.
    [pdf] [web]
  • S. Lefkimmiatis*, A. Roussos*, P. Maragos, M. Unser, *Joint first authorship
    Structure Tensor Total Variation,
    SIAM J. Imaging Sc., vol. 8, issue 2, pp. 1090-1122, May 2015.
    [pdf] [code]
  • R. Garg, A. Roussos, L. Agapito,
    A Variational Approach to Video Registration with Subspace Constraints,
    International Journal of Computer Vision (IJCV), vol. 104, issue 3, pp. 286-314, Sept. 2013,
    [pdf] [web] [code]
  • A. Roussos, S. Theodorakis, V. Pitsikalis and P. Maragos,
    Dynamic Affine-Invariant Shape-Appearance Handshape Features and Classification in Sign Language Videos,
    Journal of Machine Learning Research (JMLR), 14(Jun):1627-1663, 2013.
    [pdf] [web]
  • A. Roussos and P. Maragos,
    Reversible Interpolation of Vectorial Images by an Anisotropic Diffusion-Projection PDE,
    International Journal of Computer Vision (IJCV), vol. 84, no. 2, pp. 130-145, Aug. 2009.
    [pdf] [results] [code by P. Getreuer]

Conference Papers

  • M.R. Koujan and A. Roussos.
    Combining Dense Nonrigid Structure from Motion and 3D Morphable Models for Monocular 4D Face Reconstruction,
    The 15th ACM SIGGRAPH European Conference on Visual Media Production (CVMP), London, UK, December 2018.
    [pdf] [web]
  • S. Zafeiriou*, G. Chrysos*, A. Roussos*, E. Ververas, J. Deng, and G. Trigeorgis, *Joint first authorship
    The 3D menpo facial landmark tracking challenge,
    International Conference on Computer Vision 3D Menpo Facial Landmark Tracking Challenge Workshop, Venice, Italy, October 2017.
    [pdf] [Challenge webpage]
  • J. Booth, A. Roussos, S. Zafeiriou, A. Ponniah, and D. Dunaway.
    A 3D Morphable Model learnt from 10,000 faces,
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, June 2016.
    [pdf] [web]
  • Y. Zhou, E. Antonakos, J. Alabort-i-medina, A. Roussos, S. Zafeiriou.
    Estimating Correspondences of Deformable Objects "In-the-wild",
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, June 2016.
    [pdf] [web]
  • P. Snape, A. Roussos, Y. Panagakis, S. Zafeiriou.
    Face Flow,
    International Conference on Computer Vision (ICCV), Santiago, Chile, December 2015.
    [pdf]
  • E. Antonakos*, A. Roussos*, S. Zafeiriou*, *Joint first authorship
    A Survey on Mouth Modeling and Analysis for Sign Language Recognition,
    IEEE International Conference on Automatic Face and Gesture Recognition (FG'15), Ljubljana, Slovenia, May 2015.
    [pdf]
  • R. Garg, A. Roussos, L. Agapito,
    Dense Variational Reconstruction of Non-Rigid Surfaces from Monocular Video,
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Portland, Oregon, USA, June 23-28, 2013.
    [pdf] [web]
  • S. Lefkimmiatis*, A. Roussos*, M. Unser, P. Maragos, *Joint first authorship
    Convex Generalizations of Total Variation based on the Structure Tensor with Applications to Inverse Problems,
    Int'l Conference on Scale Space and Variational Methods in Computer Vision (SSVM), Schloss Seggau, Graz region, Austria, June 2-6, 2013.
    [pdf] [supp.material]
  • A. Roussos, C. Russell, R. Garg, L. Agapito,
    Dense Multibody Motion Estimation and Reconstruction from a Handheld Camera,
    IEEE Int’l Symposium on Mixed and Augmented Reality (ISMAR), Atlanta, Georgia, USA, November 5-8, 2012.
    [pdf] [web]
  • R. Garg, A. Roussos and L. Agapito,
    Robust Trajectory-space TV-L1 Optical Flow for Non-rigid Sequences,
    Proc. 8th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), Saint Petersburg, Russia, July 25-27, 2011.
    [pdf] [ground truth & videos]
  • A. Roussos and P. Maragos,
    Tensor-Based Image Diffusions Derived from Generalizations of the Total Variation and Beltrami Functionals,
    Proc. IEEE Int'l Conf. on Image Processing (ICIP), Hong Kong, Sep. 26-29, 2010.
    [pdf] [presentation]
  • A. Roussos, S. Theodorakis, V. Pitsikalis and P. Maragos,
    Affine-Invariant Modeling of Shape-Appearance Images applied on Sign Language Handshape Classification,
    Proc. IEEE Int'l Conf. on Image Processing (ICIP), Hong Kong, Sep. 26-29, 2010.
    [pdf]
  • A. Roussos, S. Theodorakis, V. Pitsikalis and P. Maragos,
    Hand Tracking and Affine Shape-Appearance Handshape Sub-Units in Continuous Sign Language Recognition,
    Workshop on Sign, Gesture and Activity, 11th European Conference on Computer Vision (ECCV), Crete, Greece, September 2010.
    [pdf]
  • A. Roussos, A. Katsamanis, P. Maragos,
    Tongue Tracking in Ultrasound Images with Active Appearance Models,
    Proc. IEEE Int'l Conf. on Image Processing (ICIP), Cairo, Egypt, Nov. 7-11, 2009.
    [pdf] [poster]
  • A. Katsamanis, A. Roussos, P. Maragos, M. Aron and M.-O. Berger
    Inversion from Audiovisual Speech to Articulatory Information by Exploiting Multimodal Data,
    International Seminar on Speech Production (ISSP), Strasbourg, France, Dec. 2008.
    [pdf] [bib] [presentation]
  • M. Aron, A. Roussos, M.-O. Berger, E. Kerrien and P. Maragos,
    Multimodality Acquisition of Articulatory Data and Processing,
    16th European Conference on Signal Processing (EUSIPCO), August 25-29, 2008, Lausanne - Switzerland.
    [pdf]
  • A. Roussos and P. Maragos,
    Vector-Valued Image Interpolation by an Anisotropic Diffusion-Projection PDE,
    1st Int'l Conference on Scale Space and Variational Methods in Computer Vision (SSVM), Ischia, Italy, May 30 - June 2, 2007.
    Received the Best Student Paper Award of the conference.
    [pdf] [presentation] [results]

Book Chapters

  • A. Roussos, S. Theodorakis, V. Pitsikalis and P. Maragos,
    Dynamic Affine-Invariant Shape-Appearance Handshape Features and Classification in Sign Language Videos,
    In S. Escalera, I. Guyon, and V. Athitsos, editors, Gesture Recognition, pages 231--271. Springer International Publishing, Cham, 2017.
    [SpringerLink]

Theses

  • A. Roussos,
    Nonlinear Diffusion in Computer Vision and Statistical Shape Models, with Applications in Image Analysis of Articulators of Voiced and Signed Speech,
    PhD thesis, ECE School, NTUA, October 2010. Thesis supervisor: P. Maragos.
    [pdf (in greek)] [presentation in greek] [presentation in english]

  • A. Roussos,
    Theory and Applications of Partial Differential Equations in Computer Vision   (in greek),
    Diploma thesis, ECE School, NTUA, October 2005. Thesis supervisor: P. Maragos.
    [zip]


CONTACT

Anastasios (Tassos) Roussos

Institute of Computer Science (ICS),
Foundation for Research and Technology - Hellas (FORTH),
N. Plastira 100, Vassilika Vouton,
GR70013 Heraklion, Crete, Greece

email: troussos at ics.forth.gr