Pour le second séminaire scientifique "Mathématiques & Informatique pour l'observation de la Terre" de la COMET TSI, nous avons le plaisir de recevoir Jean Prost, chercheur post doctorant au laboratoire CRIStAL de Centrale Lille, le mardi 18 juin de 13h30 à 14h30 en visioconférence.
Titre : Efficient posterior sampling for diverse super-resolution with hierarchical VAE Prior
Abstract : In this presentation, we will consider the problem of producing diverse super-resolved images corresponding to a low-resolution observation. From a probabilistic perspective, this amounts to sample from the posterior distribution of the super-resolution inverse problem. As a prior model on the solution, we propose to use pretrained hierarchical variational autoencoder (HVAE), a powerful class of deep generative model. We train a lightweight stochastic encoder to encode low-resolution images in the latent space of a pretrained HVAE. At inference, we combine the low-resolution encoder and the pretrained generative model to super-resolve an image. We demonstrate on the task of face super-resolution that our method provides an advantageous trade-off between the computational efficiency of conditional normalizing flows techniques and the sample quality of diffusion based methods.
Lien de la visio-conférence : https://rendez-vous.renater.fr/COMETTSISeminaireMI2_4006a4-0ac3b3-55439f
En espérant vous voir nombreux, n'oubliez pas de bloquer le créneau dans vos agendas !
Partager :
