All students planning to attend and/or validate this course in 2024 should:

  1. Fill in this registration form
  2. Subscribe to the mailing list for important announcements related to the course
  3. Register for this course at the secretary of the M2 MVA programme
  4. Create telecom-paris account following the instructions you shall receive by email from ip-paris.fr

Course Materials (slides, TPs, etc) will be made available here.

Course Materials for the previous edition (2023 course here)

Course Description and Objectives

The miniaturization of sensors and the evolution of computational capabilities has led to the ubiquitous presence of images. However, the increasing demand for image-based content also requires sophisticated post-processing (filtering, restoration etc.), in order to ensure good quality results. At the heart of these post-processings are image models, which allow us to establish powerful and efficient algorithms. Deep learning is the latest addition to a long list of such image models. The aim of this course is to present recent techniques based on deep learning for the quality of images, and to compare them to pre-existing methods. We will explore many applications such as denoising, super-resolution, deblurring, texture synthesis and natural image generation. In each case we will present the strengths and limitations of the different techniques studied. In particular, we will present a critical analysis of the methods and show some of the pitfalls in which they sometimes fall.


The course may be given in English or French depending on the audience’s preferences.


  • Applied Mathematics (Linear Algebra, Numerical Analysis, Differential Calculus, Fourier Analysis) Programming (Python, Matlab)
  • Basic concepts of image processing, optimization and deep learning are useful but will be introduced in the course.


  • Individual reports of Practical Work (TPs).
  • Individual project with report and oral defense at the end of the course.

Teaching team

Alasdair Newson (MdC Telecom Paris)
Said Ladjal (MdC Telecom Paris)
Andr̩s Almansa (DR CNRS РMAP5 РUniversit̩ de Paris)

Organization of the course

  • 8 sessions of 3 hours each (course+TP) + 3 review sessions + 1 project presentation session
  • When? every Tuesday from 1:30 pm to 4:30 pm, from January 9th to March 26th 2024.
  • Where? Telecom Paris, 19 place Marguerite Perey F-91120 Palaiseau.
  • Important: For the practical sessions starting at the second session, students may need a computer account at Telecom Paris, and a Google account to access https://colab.research.google.com/. If you do not have an account at Telecom Paris you shall receive (after your registration in this course) an email from ip-paris.fr with the instructions to create one.


  1. End-to-end deep learning and applications to super-resolution (S. Ladjal, 1 course + 1 TP)
  2. Plug & play deep priors for inverse problems (A. Almansa, 3x course + TP)
    1. Posterior Maximisation
    2. Posterior Sampling
    3. Generative Priors
  3. Variational Auto Encoders (A. Newson, 1 course + TP)
  4. Generative Adversarial Networks (A. Newson, 1 course + TP)
  5. Generative models for texture synthesis (S. Ladjal, 1 course+TP)

Detailed program…