Samuel Hurault
Samuel Hurault

Postdoctoral researcher

About Me

I am currently at ENS Paris working with with Gabriel Peyré. I obtained my Ph.D from Université de Bordeaux, co-supervised by Nicolas Papadakis and Arthur Leclaire. My research interests include image inverse problems, generative modeling, optimization. The main objective of my PhD was to develop inovative deep denoising priors along with convergent optimization schemes for solving image inverse problems. I am also one of the main developer of the Python library DeepInv, which provides a unified framework for solving inverse problems using deep neural networks.

Download CV
Interests
  • Optimization
  • Inverse Problems
  • Machine Learning
  • Optimal Transport
Education
  • PhD in Machine Learning & Image Processing

    University of Bordeaux, France

  • Master "Mathematiques, Vision, Appentissage" (MVA)

    Ecole Normale Superieure Paris-Saclay

  • Bachelor in Mathematics

    Ecole Normale Superieure Paris-Saclay

Recent Publications
(2024). A relaxed proximal gradient descent algorithm for convergent plug-and-play with proximal denoiser. In JMIV.
(2023). Convergent Bregman Plug-and-Play Image Restoration for Poisson Inverse Problems. In Neurips 2023.
(2023). A relaxed proximal gradient descent algorithm for convergent plug-and-play with proximal denoiser. In SSVM 2023.
(2023). Self-Consistent Velocity Matching of Probability Flows. In Neurips 2023.
(2022). An Analysis of Generative Methods for Multiple Image Inpainting. Handbook of Mathematical Models and Algorithms in Computer Vision and Imaging.
Recent & Upcoming Talks
Recent News