103 citations · 129 across the 11 of their papers we have counts for
12 papers
MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset
Benjamin Aubin, Gonzalo Iñaki Quintana, Onur Tasar +4
Training large text-to-image models requires high-quality, curated datasets with diverse content and detailed captions. Yet the cost and complexity of collecting, filtering, dedupl…
Fast, faithful and photorealistic diffusion-based image super-resolution with enhanced Flow Map models
Maxence Noble, Gonzalo Iñaki Quintana, Benjamin Aubin +1
Diffusion-based image super-resolution (SR) has recently attracted significant attention by leveraging the expressive power of large pre-trained text-to-image diffusion models (DMs…
LBM: Latent Bridge Matching for Fast Image-to-Image Translation
Clément Chadebec, Onur Tasar, Sanjeev Sreetharan +1
In this paper, we introduce Latent Bridge Matching (LBM), a new, versatile and scalable method that relies on Bridge Matching in a latent space to achieve fast image-to-image trans…
Controllable Shadow Generation with Single-Step Diffusion Models from Synthetic Data
Onur Tasar, Clément Chadebec, Benjamin Aubin
Realistic shadow generation is a critical component for high-quality image compositing and visual effects, yet existing methods suffer from certain limitations: Physics-based appro…
Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation
Clément Chadebec, Onur Tasar, Eyal Benaroche +1
In this paper, we propose an efficient, fast, and versatile distillation method to accelerate the generation of pre-trained diffusion models: Flash Diffusion. The method reaches st…
Improving Multimodal Joint Variational Autoencoders through Normalizing Flows and Correlation Analysis
Agathe Senellart, Clément Chadebec, Stéphanie Allassonnière
We propose a new multimodal variational autoencoder that enables to generate from the joint distribution and conditionally to any number of complex modalities. The unimodal posteri…
Variational Inference for Longitudinal Data Using Normalizing Flows
Clément Chadebec, Stéphanie Allassonnière
This paper introduces a new latent variable generative model able to handle high dimensional longitudinal data and relying on variational inference. The time dependency between the…
A Geometric Perspective on Variational Autoencoders
Clément Chadebec, Stéphanie Allassonnière
This paper introduces a new interpretation of the Variational Autoencoder framework by taking a fully geometric point of view. We argue that vanilla VAE models unveil naturally a R…
Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Case
Clément Chadebec, Louis J. Vincent, Stéphanie Allassonnière
In recent years, deep generative models have attracted increasing interest due to their capacity to model complex distributions. Among those models, variational autoencoders have g…
Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencoder
Clément Chadebec, Elina Thibeau-Sutre, Ninon Burgos +1
In this paper, we propose a new method to perform data augmentation in a reliable way in the High Dimensional Low Sample Size (HDLSS) setting using a geometry-based variational aut…
Data Augmentation with Variational Autoencoders and Manifold Sampling
Clément Chadebec, Stéphanie Allassonnière
We propose a new efficient way to sample from a Variational Autoencoder in the challenging low sample size setting. This method reveals particularly well suited to perform data aug…
Geometry-Aware Hamiltonian Variational Auto-Encoder
Clément Chadebec, Clément Mantoux, Stéphanie Allassonnière
Variational auto-encoders (VAEs) have proven to be a well suited tool for performing dimensionality reduction by extracting latent variables lying in a potentially much smaller dim…