I am a researcher at IGN, the French National Geographical Institute, in the machine learning team STRUDEL (LaSTIG, Univ. Gustave Eiffel). I am interested in optimization and machine learning for geospatial data such as 3D point clouds or satellite images time-series analysis.
I am the principal investigator of the ReADy3D ANR project on Dynamic 3D analysis for autonomous driving.
I am also co-program chair of the XXIVth ISPRS congress in Nice in 2022.
See my academic_CV for more details (updated in Apr 2022).
➡️ Our paper on interpretable sound discovery segmentation with Romain Loiseau has been accepted at ISMIR2022
➡️ Our paper on Online LiDAR segmentation with Romain Loiseau et Mathieu Aubry has been accepted at ECCV2022.
➡️ Our paper Deep View Aggregation with Damien Robert has been accepted at CVPR2022 for an oral 🎤, and was selected as a best paper finalist
➡️ 3 workshop papers at CVPR2022 with my Romain Loiseau and Ekaterina Kalinicheva : Transformers for Vision, Sight and Sound, and EarthVision.
➡️ Our Workshop EarthVision has been renewed at CVPR2022. A great line-up of speakers, contests, and a must-attend event for researchers interested in both remote-sensing and computer vision.
➡️ Our paper on surface reconstruction with Raphael Sulzer, Renaud Marlet, Alexandre Boulch and Bruno Vallet is accepted at ICPR2022.
➡️ Our paper on multimodal SITS analysis with Vivien Sainte-Fare Garnot has been published in IJPRS.
➡️ Our paper with Vivien Sainte-Fare Garnot on leveraging class hierarchies has been accepted at BMVC2021.
➡️ Our paper on the unsupervised and visual representation of large shape collections with Romain Loiseau, Tom Monnier, and Mathieu Aubry has been accepted at 3DV2021.
➡️ Our paper on panoptic segmentation of satellite time series, with Vivien Sainte-Fare Garnot has been accepted at ICCV2021. Check out PASTIS: the first SITS panoptic-ready dataset.
Selected Articles
A Model You Can Hear: Audio Identification with Playable Prototypes, Romain Loiseau, Baptiste Bouvier, Yann Teytaut, Elliot Vincent, Mathieu Aubry, Loic Landrieu ISMIR 2022
[project] [arXiv] [github]
Online Segmentation of LiDAR Sequences: Dataset and Algorithm, Romain Loiseau, Mathieu Aubry, Loic Landrieu, ECCV 2022
[arXiv][github] [data] [project]
Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation, Damien Robert, Bruno Vallet, Loic Landrieu CVPR 2022 (oral 🎤, best paper finalist 🏅)
[arXiv] [github]
Multi-Layer Modeling of Dense Vegetation from Aerial LiDAR Scans, Ekaterina Kalinicheva, Loic Landrieu, Clement Mallet, Nesrine Chehata, CVPR Workshop EarthVision (oral 🎤) 2022
[arXiv] [github]
Deep Surface Reconstruction from Point Clouds with Visibility Information. Raphael Sulzer, Loic Landrieu, Alexandre Boulch, Renaud Marlet, Bruno Vallet, ICPR 2022
[arXiv] [github]
Multi-Modal Temporal Attention Models for Crop Mapping from Satellite Time Series, Vivien Sainte Fare Garnot, Loic Landrieu, ISPRS Journal of Photogrammetry and Remote Sensing 2022
[arXiv] [data] [github]
Representing Shape Collections with Alignment-Aware Linear Models, Romain Loiseau, Tom Monnier, Mathieu Aubry, Loic Landrieu 3DV 2021
[arXiv] [project] [github]
Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks, Vivien Sainte Fare Garnot Loic Landrieu, ICCV 2021
[arXiv] [github] [data]
Scalable Surface Reconstruction with Delaunay-Graph Neural Networks, Raphael Sulzer, Loic Landrieu, Renaud Marlet, and Bruno Vallet, Eurographics SGP 2021
[arXiv] [github]
Leveraging Class Hierarchies with Metric-Guided Prototype Learning, Vivien Sainte Fare Garnot, Loic Landrieu, BMVC 2021
[arXiv] [github]
Torch-Points3D: A Modular Multi-Task Framework for Reproducible Deep Learning on 3D Point Clouds, Thomas Chaton, Nicolas Chaulet, Sofiane Horache, Loic Landrieu, 3DV 2020 (oral 🎤)
[arXiv] [github]
Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attention, Vivien Sainte Fare Garnot, Loic Landrieu, Sebastien Giordano, Nesrine Chehata, CVPR 2020 (oral 🎤).
[arXiv] [github]
Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning, Loic Landrieu, Mohamed Boussaha, CVPR 2019.
[arXiv] [github]
Cut-Pursuit Algorithm for Regularizing Nonsmooth Functionals with Graph Total Variation, Hugo Raguet and Loic Landrieu, ICML 2018
[arXiv] [github]
Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs, Loic landrieu and Martin Simonovsky, CVPR 2018.
[arXiv] [github]
Cut Pursuit: Fast Algorithms to Learn Piecewise Constant Functions on General Weighted Graphs. Loic Landrieu, Guillaume Obozinski, SIAM Journal on Imaging Science, 2017
[hal][github]
A Structured Regularization Framework for Spatially Smoothing Semantic Labelings of 3D Point Clouds. Loic Landrieu, Hugo Raguet , Bruno Vallet , Clément Mallet, Martin Weinmann, ISPRS Journal of Photogrammetry and Remote Sensing, 2017
[hal] [github]
Preconditioning of a Generalized Forward-Backward Splitting and Application to Optimization on Graphs. Hugo Raguet, Loic Landrieu, SIAM Journal on Imaging Science, 2015 [arxiv] [github]
STUDENTS:
List of current and past PhD/Post Doc students:
Stéphane Guinard (Univ. Laval)
Mohamed Boussaha (Gambi-M)
Vivien Sainte-Fare Garnot (Univ. of Zurich)
Raphael Sulzer
Romain Loiseau
Damien Robert
Ekaterina Kalinicheva (post doc)
List of current and past interns:
Stephane Guinard, Simon Bailly, Omar Lahbib, Joana Roussillon, Thomas Luo (Helix.Re), Anna Kondracka (Vermessung AVT), Lamiae El-Mendili, Ameur Zaibi, Julien Baconat, Cédric Baron, Félix Quinton, Yaping Lin, Dina El-Zein.
I teach machine learning at master level at ENSG and ENPC.
I am a technical advisor for SAMP, a startup using machine learning for producing digital twins of industrial facilities.
I review for ICML (top reviewer 2021), NeurIPS, ICCV, CVPR (outstanding reviewer 2021), ACCV, BMVC, IJCV, PAMI, ANRT, IJPRS, TIP, ISPRS (outstanding reviewer 2022) etc…
I am on the editorial board of IJPRS (Elsevier) and reviewing committee of Remote Sensing (MDPI).
Loic Landrieu 