Publications

Machine Learning

Can Push-forward Generative Models Fit Multimodal Distributions?

Many generative models synthesize data by transforming a standard Gaussian random variable using a deterministic neural network. Among these models are the Variational Autoencoders and the Generative Adversarial Networks. In this work, we call them …

Antoine Salmona, Valentin de Bortoli, Julie Delon, Agnès Desolneux

NeurIPS 2022, The Thirty-sixth Annual Conference on Neural Information Processing Systems - 2022

Human health and pathology

Walking Speed at the Acute and Subacute Stroke Stage: A Descriptive Meta-Analysis.

Gait disorders are one of the leading patient complaints at the sub-acute stroke stage (SSS) and a main determinant of disability. Walking speed (WS) is a major vital and functional index, and the Ten-Meter Walk Test is considered the gold standard…

Sophie Tasseel-Ponche, Arnaud Delafontaine, Olivier Godefroy, Alain P. Yelnik, Pierre-Louis Doutrellot, Charline Duchossoy, Marie Hyra, Thibaud Sader, Momar Diouf

Frontiers in Neurology - 2022

Image Processing

La vie secrète des images JPEG : Détection de falsification via les traces de compression

With the advent of digital photography and the progress of photo editing tools, modifying an image has become easy and accessible to all. Most of these modifications aim at improving the image, but some are intended at altering its meaning. Such…

Tina Nikoukhah

Computer Vision and Pattern Recognition

Sat-NeRF: Learning Multi-View Satellite Photogrammetry With Transient Objects and Shadow Modeling Using RPC Cameras

We introduce the Satellite Neural Radiance Field (Sat-NeRF), a new end-to-end model for learning multi-view satellite photogrammetry in the wild. Sat-NeRF combines some of the latest trends in neural rendering with native satellite camera models,…

Roger Marí, Gabriele Facciolo, Thibaud Ehret

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) - 2022

Computer Vision and Pattern Recognition

L1B+: A Perfect Sensor Localization Model for Simple Satellite Stereo Reconstruction from Push-Frame Image Strips

We propose a novel method to generate a single image product from a multi-image strip acquired by a push-frame satellite imaging system. The images of the push-frame strips are combined into a large scale mosaic simulating a perfect sensor geometry…

Roger Marí, Thibaud Ehret, Jérémy Anger, Carlo de Franchis, Gabriele Facciolo

ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences - 2022

Analysis of PDEs

Traveling wave solution for a coupled incompressible Darcy's free boundary problem with surface tension

We study an incompressible Darcy's free boundary problem, recently introduced in [22]. Our goal is to prove the existence of non-trivial traveling wave solutions and thus validate the interest of this model to describe cell motility. The model…

Thomas Alazard, Martina Magliocca, Nicolas Meunier

Computer Vision and Pattern Recognition

Disparity Estimation Networks for Aerial and High-Resolution Satellite Images: A Review

This article describes a generic bundle adjustment methodology for multi-view stereo pipelines for 3D reconstruction from high-resolution optical satellite imagery. The Rational Polynomial Camera (RPC) model of each input view is refined by…

Roger Marí, Thibaud Ehret, Gabriele Facciolo

Image Processing On Line - 2022

Image Processing

Non-Semantic Evaluation of Image Forensics Tools: Methodology and Database

We propose a new method to evaluate image forensics tools, that characterizes what image cues are being used by each detector. Our method enables effortless creation of an arbitrarily large dataset of carefully tampered images in which controlled…

Quentin Bammey, Tina Nikoukhah, Marina Gardella, Rafael Grompone von Gioi, Miguel Colom, Jean-Michel Morel

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) - 2022

Image Processing

A Reliable JPEG Quantization Table Estimator

JPEG compression is a commonly used method of lossy compression for digital images. The degree of compression can be adjusted by the choice of a quality factor QF. Each software associates this value to a quantization table, which is a 8 × 8 matrix…

Tina Nikoukhah, Miguel Colom, Jean-Michel Morel, Rafael Grompone von Gioi

Image Processing On Line - 2022

Statistics

Can Push-forward Generative Models Fit Multimodal Distributions?

Many generative models synthesize data by transforming a standard Gaussian random variable using a deterministic neural network. Among these models are the Variational Autoencoders and the Generative Adversarial Networks. In this work, we call them …

Antoine Salmona, Valentin de Bortoli, Julie Delon, Agnès Desolneux

NeurIPS 2022 - 2022