About me
I am a researcher in applied mathematics at the MAP5 laboratory at Paris-Cité university. My main research interest is combining mathematical methodology and novel deep learning approaches to solve challenging problems. I have defended my PhD thesis “Image restoration with deep generative models” at the Bordeaux Institute of Mathematics (IMB), under the supervision of Nicolas Papadakis and Andrés Almansa.
News
- [10/12/2023] Our paper Efficient posterior sampling for diverse super-resolution with hierarchical VAE Prior has been accepted as an oral at the 19th International Joint Conference on Computer Vision Theory and Applications (VISAPP2024). preprint
- [15/11/2023] I have defended my PhD thesis Image restoration with deep generative models. The manuscript is available on HAL
- [14/07/2023] Our paper Inverse problem regularization with hierarchical variational autoencoders has been accepted as a poster in the main track of ICCV 2023!
Publications and preprints
- Efficient posterior sampling for diverse super-resolution with hierarchical VAE Prior
Jean Prost, Antoine Houdard, Nicolas Papadakis, Andrés Almansa
19th International Joint Conference on Computer Vision Theory and Applications (VISAPP2024) [arxiv] - Inverse problem regularization with hierarchical variational autoencoders
Jean Prost, Antoine Houdard, Nicolas Papadakis, Andrés Almansa
International Conference on Computer Vision (ICCV 2023) [arxiv] [paper] [code] - SCOTCH and SODA: A Transformer Video Shadow Detection Framework
Lihao Liu, Jean Prost, Lei Zhu, Nicolas Papadakis, Pietro Lio, Carola-Bibiane Schönlieb, Angelica I Aviles-Rivero
Computer Vision and Pattern Recognition (CVPR 2023) [arxiv] [paper] [code] - Learning Local Regularization for Variational Image Restoration
Jean Prost, Antoine Houdard, Andrés Almansa, Nicolas Papadakis
Scale Space and Variational Methods in Computer Vision: 8th International Conference, (SSVM 2021) [arxiv] [paper] [code]
Talks
- Mathematical Models for Plug-and-play Image Restoration
08/12/2022, Paris
Diverse image super-resolution with hierarchical variational autoencoders - Cambridge Image Analysis seminar
02/09/2022, Cambridge
Diverse image super-resolution with hierarchical variational autoencoders - Generative models: Control and (mis)Usage
31/05/2022, CNRS Ile-de-France Villejuif
Diverse image super-resolution with hierarchical variational autoencoders - SIAM Conference on Imaging Science (IS22)
22/03/2022, Virtual conference
Learning local regularization for variational image restoration - ORASIS 2021
17/09/2021, Saint-Ferréol
Apprentissage d'une fonction de régularisation locale pour la restauration d'images"