Mathematical Models for Plug-and-play Image Restoration
Talk. Title: Diverse image super-resolution with hierarchical variational autoencoders
Talks and presentations
Cambridge Image Analysis seminar
Talk. Title: Diverse image super-resolution with hierarchical variational autoencoders
Generative models: Control and (mis)Usage
Talk. Title: Diverse image super-resolution with hierarchical variational autoencoders
3rd IMA Conference on Inverse Problems from Theory to Application
Poster. Title: Diverse image super-resolution with hierarchical variational autoencoders
Image super-resolution is an ill-posed inverse problem in the sense that diverse high- resolution candidates are plausible solutions for each single low-resolution image. In this work we propose to make use of deep hierarchical variational autoencoders (VAE) to produce diverse super resolution. Hierarchical VAEs have shown impressive results for the task of high-resolution image synthesis and provide a strong prior image model via a self- organized hierarchy of latent variables. We find that these structured latent variables are related with the image information at different scales. Based on this observation, we show that pretrainded hierarchical VAEs can be repurposed to perform diverse super-resolution.
SIAM Conference on Imaging Science (IS22)
Mini-symposium. Title: Learning local regularization for variational image restoration
In this talk, I will be presenting my work: “Learning local regularization for variational image restoration”
ORASIS 2021
Talk. Title: Apprentissage d'une fonction de régularisation locale pour la restauration d'images"