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
21 papers · 1 filter
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…
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…
Holistic Parking Slot Detection with Polygon-Shaped Representations
Lihao Wang, Antonyo Musabini, Christel Leonet +6
Current parking slot detection in advanced driver-assistance systems (ADAS) primarily relies on ultrasonic sensors. This method has several limitations such as the need to scan the…
MDT3D: Multi-Dataset Training for LiDAR 3D Object Detection Generalization
Louis Soum-Fontez, Jean-Emmanuel Deschaud, François Goulette
Supervised 3D Object Detection models have been displaying increasingly better performance in single-domain cases where the training data comes from the same environment and sensor…