359 citations
- École Nationale Supérieure des Mines de ParisFR32 papers
- Hôpital Saint-MichelFR28 papers
- Université Paris Sciences et LettresFR23 papers
- Centre de Robotique Intégrée d'Ile de FranceFR9 papers
- Valeo (France)FR5 papers
- École nationale des ponts et chausséesFR4 papers
- Safran (France)FR4 papers
- Sorbonne UniversitéFR4 papers
- Centre Automatique et SystèmesFR3 papers
- Institut national de recherche en sciences et technologies du numériqueFR3 papers
- University of EdinburghGB3 papers
- Aix-Marseille UniversitéFR2 papers
73 papers
Learning Physically Consistent Lagrangian Control Models Without Acceleration Measurements
Ibrahim Laiche, Mokrane Boudaoud, Patrick Gallinari +1
This article investigates the modeling and control of Lagrangian systems involving non-conservative forces using a hybrid method that does not require acceleration calculations. It…
HARP-NeXt: High-Speed and Accurate Range-Point Fusion Network for 3D LiDAR Semantic Segmentation
Samir Abou Haidar, Alexandre Chariot, Mehdi Darouich +2
LiDAR semantic segmentation is crucial for autonomous vehicles and mobile robots, requiring high accuracy and real-time processing, especially on resource-constrained embedded syst…
Multiple-Frequencies Population-Based Training
Waël Doulazmi, Auguste Lehuger, Marin Toromanoff +3
Reinforcement Learning's high sensitivity to hyperparameters is a source of instability and inefficiency, creating significant challenges for practitioners. Hyperparameter Optimiza…
3DLabelProp: Geometric-Driven Domain Generalization for LiDAR Semantic Segmentation in Autonomous Driving
Jules Sanchez, Jean-Emmanuel Deschaud, François Goulette
Domain generalization aims to find ways for deep learning models to maintain their performance despite significant domain shifts between training and inference datasets. This is pa…
AVS-Net: Audio-Visual Scale Net for Self-supervised Monocular Metric Depth Estimation
Xiaohu Liu, Sascha Hornauer, Fabien Moutarde +1
Metric depth prediction from monocular videos suffers from bad generalization between datasets and requires supervised depth data for scale-correct training. Self-supervised traini…
HD-OOD3D: Supervised and Unsupervised Out-of-Distribution object detection in LiDAR data
Louis Soum-Fontez, Jean-Emmanuel Deschaud, François Goulette
Autonomous systems rely on accurate 3D object detection from LiDAR data, yet most detectors are limited to a predefined set of known classes, making them vulnerable to unexpected o…