190 citations · 432 across the 36 of their papers we have counts for
43 papers
Convergent Bregman Plug-and-Play Image Restoration for Poisson Inverse Problems
Samuel Hurault, Ulugbek Kamilov, Arthur Leclaire +1
Plug-and-Play (PnP) methods are efficient iterative algorithms for solving ill-posed image inverse problems. PnP methods are obtained by using deep Gaussian denoisers instead of th…
Inverse problem regularization with hierarchical variational autoencoders
Jean Prost, Antoine Houdard, Andrés Almansa +1
In this paper, we propose to regularize ill-posed inverse problems using a deep hierarchical variational autoencoder (HVAE) as an image prior. The proposed method synthesizes the a…
A relaxed proximal gradient descent algorithm for convergent plug-and-play with proximal denoiser
Samuel Hurault, Antonin Chambolle, Arthur Leclaire +1
This paper presents a new convergent Plug-and-Play (PnP) algorithm. PnP methods are efficient iterative algorithms for solving image inverse problems formulated as the minimization…
SCOTCH and SODA: A Transformer Video Shadow Detection Framework
Lihao Liu, Jean Prost, Lei Zhu +4
Shadows in videos are difficult to detect because of the large shadow deformation between frames. In this work, we argue that accounting for shadow deformation is essential when de…
A patch-based architecture for multi-label classification from single label annotations
Warren Jouanneau, Aurélie Bugeau, Marc Palyart +2
In this paper, we propose a patch-based architecture for multi-label classification problems where only a single positive label is observed in images of the dataset. Our contributi…
Multi-Modal Hypergraph Diffusion Network with Dual Prior for Alzheimer Classification
Angelica I. Aviles-Rivero, Christina Runkel, Nicolas Papadakis +2
The automatic early diagnosis of prodromal stages of Alzheimer's disease is of great relevance for patient treatment to improve quality of life. We address this problem as a multi-…
Proximal Denoiser for Convergent Plug-and-Play Optimization with Nonconvex Regularization
Samuel Hurault, Arthur Leclaire, Nicolas Papadakis
Plug-and-Play (PnP) methods solve ill-posed inverse problems through iterative proximal algorithms by replacing a proximal operator by a denoising operation. When applied with deep…
Gradient Step Denoiser for convergent Plug-and-Play
Samuel Hurault, Arthur Leclaire, Nicolas Papadakis
Plug-and-Play methods constitute a class of iterative algorithms for imaging problems where regularization is performed by an off-the-shelf denoiser. Although Plug-and-Play methods…
POPCORN: Progressive Pseudo-labeling with Consistency Regularization and Neighboring
Reda Abdellah Kamraoui, Vinh-Thong Ta, Nicolas Papadakis +3
Semi-supervised learning (SSL) uses unlabeled data to compensate for the scarcity of annotated images and the lack of method generalization to unseen domains, two usual problems in…
Learning local regularization for variational image restoration
Jean Prost, Antoine Houdard, Andrés Almansa +1
In this work, we propose a framework to learn a local regularization model for solving general image restoration problems. This regularizer is defined with a fully convolutional ne…
On the Existence of Optimal Transport Gradient for Learning Generative Models
Antoine Houdard, Arthur Leclaire, Nicolas Papadakis +1
The use of optimal transport cost for learning generative models has become popular with Wasserstein Generative Adversarial Networks (WGAN). Training of WGAN relies on a theoretica…
GraphXCOVID: Explainable Deep Graph Diffusion Pseudo-Labelling for Identifying COVID-19 on Chest X-rays
Angelica I Aviles-Rivero, Philip Sellars, Carola-Bibiane Schönlieb +1
Can one learn to diagnose COVID-19 under extreme minimal supervision? Since the outbreak of the novel COVID-19 there has been a rush for developing Artificial Intelligence techniqu…
A Generative Model for Texture Synthesis based on Optimal Transport between Feature Distributions
Antoine Houdard, Arthur Leclaire, Nicolas Papadakis +1
We propose GOTEX, a general framework for texture synthesis by optimization that constrains the statistical distribution of local features. While our model encompasses several exis…
Multi-task deep learning for image segmentation using recursive approximation tasks
Rihuan Ke, Aurélie Bugeau, Nicolas Papadakis +3
Fully supervised deep neural networks for segmentation usually require a massive amount of pixel-level labels which are manually expensive to create. In this work, we develop a mul…
Nonlinear Power Method for Computing Eigenvectors of Proximal Operators and Neural Networks
Leon Bungert, Ester Hait-Fraenkel, Nicolas Papadakis +1
Neural networks have revolutionized the field of data science, yielding remarkable solutions in a data-driven manner. For instance, in the field of mathematical imaging, they have…
Variational Osmosis for Non-linear Image Fusion
Simone Parisotto, Luca Calatroni, Aurélie Bugeau +2
We propose a new variational model for non-linear image fusion. Our approach is based on the use of an osmosis energy term related to the one studied in Vogel et al. (2013) and Wei…
GraphX Chest X-Ray Classification Under Extreme Minimal Supervision
Angelica I. Aviles-Rivero, Nicolas Papadakis, Ruoteng Li +4
The task of classifying X-ray data is a problem of both theoretical and clinical interest. Whilst supervised deep learning methods rely upon huge amounts of labelled data, the crit…
Learning to segment microscopy images with lazy labels
Rihuan Ke, Aurélie Bugeau, Nicolas Papadakis +2
The need for labour intensive pixel-wise annotation is a major limitation of many fully supervised learning methods for segmenting bioimages that can contain numerous object instan…
Energy Models for Better Pseudo-Labels: Improving Semi-Supervised Classification with the 1-Laplacian Graph Energy
Angelica I. Aviles-Rivero, Nicolas Papadakis, Ruoteng Li +4
Semi-supervised classification is a great focus of interest, as in real-world scenarios obtaining labels is expensive, time-consuming and might require expert knowledge. This has m…
Refitting solutions promoted by sparse analysis regularization with block penalties
Charles-Alban Deledalle, Nicolas Papadakis, Joseph Salmon +1
In inverse problems, the use of an analysis regularizer induces a bias in the estimated solution. We propose a general refitting framework for removing this artifact wh…
Robust superpixels using color and contour features along linear path
Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis
Superpixel decomposition methods are widely used in computer vision and image processing applications. By grouping homogeneous pixels, the accuracy can be increased and the decreas…
SuperPatchMatch: an Algorithm for Robust Correspondences using Superpixel Patches
Rémi Giraud, Vinh-Thong Ta, Aurélie Bugeau +2
Superpixels have become very popular in many computer vision applications. Nevertheless, they remain underexploited since the superpixel decomposition may produce irregular and non…
An Optimized PatchMatch for Multi-scale and Multi-feature Label Fusion
Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis +4
Automatic segmentation methods are important tools for quantitative analysis of Magnetic Resonance Images (MRI). Recently, patch-based label fusion approaches have demonstrated sta…
Evaluation Framework of Superpixel Methods with a Global Regularity Measure
Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis
In the superpixel literature, the comparison of state-of-the-art methods can be biased by the non-robustness of some metrics to decomposition aspects, such as the superpixel scale.…