Publications

Machine Learning

Personalized Convolutional Dictionary Learning of Physiological Time Series

Human physiological signals tend to exhibit both global and local structures: the former are shared across a population, while the latter reflect inter-individual variability. For instance, kinetic measurements of the gait cycle during locomotion…

Axel Roques, Samuel Gruffaz, Kyurae Kim, Alain O Durmus, Laurent Oudre

AISTATS 2025 - 2025

Methodology

Fusion of heterogeneous data for robust degradation prognostics

Assessing the degradation state of an industrial asset first requires evaluating its current condition and then to project the forecast model trajectory to a predefined prognostic threshold, thereby estimating its remaining useful life (RUL)…

Edgar Jaber, Emmanuel Remy, Vincent Chabridon, Mathilde Mougeot, Didier Lucor

Numerical Analysis

Selling's decomposition and the anisotropic wave equation

The design of efficient numerical schemes for anisotropic partial differential equations, featuring privileged directions in general not aligned with the coordinate axes, raises challenging discretization problems which can often be addressed with…

Malik Haloui, Ludovic Métivier, Jean-Marie Mirebeau

Error Control, Adaptive Discretizations, and Applications, Part 4 - 2025

Analysis of PDEs

Towards an Optimal Collocation Point Strategy for PINNs

Chourouk El Hassanieh, Mathilde Mougeot

Le Consortium Recherche & Industrie CIROQUO - 2025

Methods and statistics

On the Transmission of Texts: Written Cultures as Complex Systems

Our knowledge of past cultures relies considerably on written material. For centuries, texts have been copied, altered, then transmitted or lost - eventually, from surviving documents, philologists attempt to reconstruct text phylogenies ("stemmata"…

Jean-Baptiste Camps, Julien Randon-Furling, Ulysse Godreau

Mathematics

About ∆-numeration

In this article we study a numeration system previously used to prove combinatorial properties in discrete geometry: the ∆-numeration. Since this system, introduced via the fully subtractive algorithm, has been seen mainly as a tool, we propose here…

Bastien Laboureix, Eric Domenjoud

WORDS 2025 - 2025

Mathematics

Unsupervised learning from attributed networks

Unlike the plain network where only the topological structure is available, nodes of attributed networks possess rich attributed information. Thereby, the attributed networks ubiquitous in the real world have attracted much attention in recent years…

Lazhar Labiod, Mohamed Nadif

Advances in Data Analysis and Classification - 2025

Computer Vision and Pattern Recognition

S-EO: A Large-Scale Dataset for Geometry-Aware Shadow Detection in Remote Sensing Applications

We introduce the S-EO dataset: a large-scale, highresolution dataset, designed to advance geometry-aware shadow detection. Collected from diverse public-domain sources, including challenge datasets and government providers such as USGS, our dataset…

Elías Masquil, Roger Marí, Thibaud Ehret, Enric Meinhardt-Llopis, Pablo Musé, Gabriele Facciolo

2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2025) - 2025

Computer Vision and Pattern Recognition

Gaussian Splatting for Efficient Satellite Image Photogrammetry

Recently, Gaussian splatting has emerged as a strong alternative to NeRF, demonstrating impressive 3D modeling capabilities while requiring only a fraction of the training and rendering time. In this paper, we show how the standard Gaussian…

Luca Savant Aira, Gabriele Facciolo, Thibaud Ehret

2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025) - 2025

Computer Vision and Pattern Recognition

s2p-hd: Gpu-Accelerated Binocular Stereo Pipeline for Large-Scale Same-Date Stereo

The increasing availability of high-resolution satellite imagery has driven advances in 3D reconstruction techniques for the generation of Digital Elevation Models (DEM). Recent research focuses on opportunistic stereo, using sophisticated…

Tristan Amadei, Enric Meinhardt-Llopis, Carlo de Franchis, Jérémy Anger, Thibaud Ehret, Gabriele Facciolo

2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2025) - 2025