Inverse problem regularization with hierarchical variational autoencoders
Jean Prost, Antoine Houdard, Nicolas Papadakis, Andrés Almansa
ICCV 2023 , arxiv
About me
I am a PhD student at the Bordeaux university, working under the supervision of Nicolas Papadakis and Andrés Almansa. My main research interests include deep generative models and image inverse problems. In particular, I am working on developping optimization algorithms designed to incorporate deep generative models as a prior in variational problems.
Publications and preprints
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
CVPR 2023 , arxivDiverse super-resolution with pretrained deep hiererarchical VAEs
Jean Prost, Antoine Houdard, Nicolas Papadakis, Andrés Almansa
Preprint , arxivLearning 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
Talks
Mathematical Models for Plug-and-play Image Restoration
Diverse image super-resolution with hierarchical variational autoencoders
Cambridge Image Analysis seminar
Diverse image super-resolution with hierarchical variational autoencoders
Generative models: Control and (mis)Usage
Diverse image super-resolution with hierarchical variational autoencoders
3rd IMA Conference on Inverse Problems from Theory to Application
Diverse image super-resolution with hierarchical variational autoencoders
SIAM Conference on Imaging Science (IS22)
Learning local regularization for variational image restoration
ORASIS 2021
Apprentissage d'une fonction de régularisation locale pour la restauration d'images"