About Me

I am a CNRS researcher at LIGM (Université Gustave Eiffel, France). My research focuses on generative modeling, image inverse problems, and optimization, with a particular interest in the theoretical analysis of denoising diffusion models. I am also a core developer of the Python library DeepInv, which provides a unified framework for solving inverse problems with deep neural networks.

Previously, I was a postdoctoral researcher at ENS Paris with Gabriel Peyré, and I obtained my Ph.D. from Université de Bordeaux, co-supervised by Nicolas Papadakis and Arthur Leclaire.

Download CV
Interests
  • Denoising diffusion models.
  • Flow Matching.
  • Deep priors for image inverse problems.
  • Proximal algorithms.
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
Samuel Hurault, Matthieu Terris, Thomas Moreau, Gabriel Peyré (2025). From Denoising Score Matching to Langevin Sampling: A Fine-Grained Error Analysis in the Gaussian Setting.
PDF Cite
Matthieu Terris, Samuel Hurault, Maxime Song, Julian Tachella (2025). Reconstruct Anything Model: a lightweight foundation model for computational imaging.
PDF Cite
Samuel Hurault, Antonin Chambolle, Arthur Leclaire, Nicolas Papadakis (2024). A relaxed proximal gradient descent algorithm for convergent plug-and-play with proximal denoiser. In JMIV.
PDF Cite
Samuel Hurault, Ulugbek Kamilov, Arthur Leclaire, Nicolas Papadakis (2023). Convergent Bregman Plug-and-Play Image Restoration for Poisson Inverse Problems. In Neurips 2023.
PDF Cite
Samuel Hurault, Antonin Chambolle, Arthur Leclaire, Nicolas Papadakis (2023). A relaxed proximal gradient descent algorithm for convergent plug-and-play with proximal denoiser. In SSVM 2023.
PDF Cite
Lingxiao Li, Samuel Hurault, Justin Solomon (2023). Self-Consistent Velocity Matching of Probability Flows. In Neurips 2023.
PDF Cite
Coloma Ballester, Aurelie Bugeau, Samuel Hurault, Simone Parisotto, Patricia Vitoria (2022). An Analysis of Generative Methods for Multiple Image Inpainting. Handbook of Mathematical Models and Algorithms in Computer Vision and Imaging.
PDF Cite
Samuel Hurault, Arthur Leclaire, Nicolas Papadakis (2022). Proximal denoiser for convergent plug-and-play optimization with nonconvex regularization. In ICML 2022.
PDF Cite Code Video
Samuel Hurault, Arthur Leclaire, Nicolas Papadakis (2021). Gradient Step Denoiser for convergent Plug-and-Play. In ICLR 2021.
PDF Cite Code Video
Samuel Hurault, Coloma Ballester, Gloria Haro (2020). Self-Supervised Small Soccer Player Detection and Tracking. ACM MMSports 2020.
PDF Cite Code
See all publications
Recent & Upcoming Talks
See all events