Welcome to the homepage of

Tobias Alt

Former Research Assistant

Position:    Former Research Assistant
E-mail: alt -at- mia.uni-saarland.de
(please replace anti-spam -at- by @)

  • Mathematical Foundations of Deep Learning
  • Learning-based Modelling
  • Connections between Partial Differential Equations and Convolutional Neural Networks
  • Inpainting-based Image Compression

Journal Papers

  1. T. Alt, K. Schrader, J. Weickert, P. Peter, M. Augustin:
    Designing rotationally invariant neural networks from PDEs and variational methods.
    Research in the Mathematical Sciences, Vol. 9, No. 3, Article 52, Sept. 2022.
    Also available as arXiv:2108.13993 [cs.LG], revised March 2022.
  2. T. Alt, K. Schrader, M. Augustin, P. Peter, J. Weickert:
    Connections between Numerical Algorithms for PDEs and Neural Networks.
    To appear in Journal of Mathematical Imaging and Vision.
    Invited Paper.
    Also available as arXiv:2107.14742 [math.NA], revised March 2022.
  3. Conference Papers

  4. K. Schrader, T. Alt, J. Weickert, M. Ertel:
    CNN-based Euler's elastica inpainting with deep energy and deep image prior.
    Proc. 10th European Workshop on Visual Information Processing (EUVIP 2022, Lisbon, Portugal, Sept. 2022), IEEE, 2022.
    Also available as arXiv:2207.07921 [cs.CV], July 2022.
  5. T. Alt, P. Peter, J. Weickert:
    Learning sparse masks for diffusion-based image inpainting.
    In A. J. Pinho, P. Georgieva, L. F. Teixeira, J. A. Sánchez (Eds.): Pattern Recognition and Image Analysis. Lecture Notes in Computer Science, Vol. 13256, Springer, Cham, 528-539, 2022.
    Also available as arXiv:2110.02636 [eess.IV], revised March 2022.
  6. S. Andris, J. Weickert, T. Alt, P. Peter:
    JPEG meets PDE-based image compression.
    Proc. 35th Picture Coding Symposium (PCS 2021, Bristol, UK, June 2021), IEEE Press, 2021.
    Also available as arXiv:2011.11289 [eess.IV], revised May 2021.
  7. T. Alt, P. Peter, J. Weickert, K. Schrader:
    Translating numerical concepts for PDEs into neural architectures.
    In A. Elmoataz, J. Fadili, Y. Quéau, J. Rabin, L. Simon (Eds.): Scale Space and Variational Methods in Computer Vision. Lecture Notes in Computer Science, Vol. 12679, Springer, Cham, 294-306, 2021.
    Also available as arXiv:2103.15419 [math.NA], March 2021.
  8. T. Alt, J. Weickert:
    Learning integrodifferential models for image denoising.
    To appear in Proc. 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2021, Toronto, Canada, June 2021), 2021.
    Also available as arXiv:2010.10888 [eess.IV], October 2020.
  9. T. Alt, J. Weickert:
    Learning a generic adaptive wavelet shrinkage function for denoising.
    Proc. 45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2020, Barcelona, Spain, May 2020), 2018-2022, 2020.
    Also available as arXiv:1910.09234 [eess.IV], October 2019.
  10. Technical Reports

  11. P. Peter, K. Schrader, T. Alt, J. Weickert:
    Deep Spatial and Tonal Optimisation for Homogeneous Diffusion Inpainting.
    arXiv:2208.14371 [eess.IV], revised September 2022.
  12. R. M. K. Mohideen, P. Peter, T. Alt, J. Weickert, A. Scheer:
    Compressing Colour Images with Joint Inpainting and Prediction.
    arXiv:2010.09866 [eess.IV], October 2020.
  13. T. Alt, J. Weickert, P. Peter:
    Translating Diffusion, Wavelets, and Regularisation into Residual Networks.
    arXiv:2002.02753 [cs.LG], February 2020.
  14. Theses

  15. T. Alt:
    Coupled Optical Flow.
    Bachelor's Thesis in Computer Science,
    Saarland University, Saarbrücken, Germany, August 2016.

MIA Group
The author is not
responsible for
the content of
external pages.

Imprint - Data protection