Publications

Preprints:

Representing Shape Collections with Alignment-Aware Linear Models, Romain Loiseau, Tom Monnier, Mathieu Aubry, Loic Landrieu arXiv project

Leveraging Class Hierarchies with Metric-Guided Prototype Learning, Vivien Sainte Fare Garnot, Loic Landrieu, 2020 preprint


Published papers:

Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks, Vivien Sainte Fare Garnot Loic Landrieu, ICCV 2021 [arXiv]

Vegetation Stratum Occupancy Prediction from Airborne LiDAR 3D Point Clouds, Ekaterina Kalinicheva, Loic Landrieu, Clement Mallet and Nesrine Chehata, SilviLaser 2021

Scalable Surface Reconstruction with Delaunay-Graph Neural Networks, Raphael Sulzer, Loic Landrieu, Renaud Marlet, and Bruno Vallet, Eurographics SGP 2021 [arXiv]

Torch-Points3D: A Modular Multi-Task Framework for Reproducible Deep Learning on 3D Point Clouds, Thomas Chaton, Nicolas Chaulet, Sofiane Horache, Loic Landrieu, 3DV (oral) 2020 [arXiv]

Improved Crop Classification with Rotation Knowledge using Sentinel-1 and-2 Time Series, Sébastien Giordano, Simon Bailly, Loic Landrieu, Nesrine Chehata, Photogrammetric Engineering & Remote Sensing 2020 [arXiv]

Lightweight Temporal Self-Attention for Classifying Satellite Image Time Series, Vivien Sainte Fare Garnot, Loic Landrieu, AALTD@ECML+KDD 2020 [arXiv]

Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attention, Vivien Sainte Fare Garnot, Loic Landrieu, Sebastien Giordano, Nesrine Chehata, CVPR (oral) 2020. [arXiv]

Parallel Cut Pursuit For Minimization of the Graph Total Variation, Hugo Raguet, Loic Landrieu, ICML-W Graph Reasoning Workshop 2019. [arXiv]

Supervized Segmentation with Graph-Structured Deep Metric Learning, Loic Landrieu, Mohamed Boussaha, ICML-W Graph Reasoning Workshop 2019. [arXiv]

Time-Space Tradeoff in Deep Learning Models for Crop Classification on Satellite Multi-Spectral Image Time Series, Vivien Sainte Fare Garnot, Loic Landrieu, Sebastien Giordano, Nesrine Chehata, IGARSS 2019. [arXiv]

Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning, Loic Landrieu, Mohamed Boussaha, CVPR 2019. [arXiv]

Piecewise-Planar Approximation Of Large 3d Data As Graph-structured Optimization, ISPRS GeoSpatial Week 2019. [link]

Cut-Pursuit Algorithm for Regularizing Nonsmooth Functionals with Graph Total Variation, Hugo Raguet and Loic Landrieu, ICML 2018  [arXiv]

* Segmentation Sémantique à Grande Échelle par Graphes de Superpoints, Loic landrieu and Martin Simonovsky, RFIAP 2018.

Temporal Structured Classification Using Sentinel Image Time Series for Crop Type Mapping, Simon Bailly, Sébastien Giordano, Loic Landrieu and Nesrine Chehata, IGARSS 2018.

Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs, Loic landrieu and Martin Simonovsky, CVPR 2018. [preprint]

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 Volume 132, October 2017, Pages 102-118 .[hal] [isprs]

Comparison of Belief Propagation and Graph-Cut Approaches for Contextual Classification of 3D LiDAR Point Cloud Data. Loic Landrieu, Clément Mallet, Martin Weinmann, IGARSS 2017. [hal]

Cut Pursuit: Fast Algorithms to Learn Piecewise Constant Functions on General Weighted Graphs. Loic Landrieu, Guillaume Obozinski, SIAM Journal on Imaging Science (SIIMS) 2017, Vol. 10, No. 4 : pp. 1724-1766 [siam] [hal]

* Pré-segmentation pour la Classification Faiblement Supervisée de Scènes Urbaines à partir de Nuages de Points 3D LiDAR. Stéphane Guinard, Loic Landrieu. ORASIS, Jun 2017. [hal]

Weakly Supervised Segmentation-Aided Classification of Urban Scenes from 3D LiDAR Point Clouds. Stéphane Guinard, Loic Landrieu.  ISPRS Archive, 2017. [hal]

Learning Structured Models on Weighted Graphs, with Application to Spatial Data Analysis. Loic landrieu, PhD Thesis, 2016 [hal]

Cut Pursuit: Fast Algorithms to Learn Piecewise Constant Functions on Weighted Graphs. Loic landrieu, Guillaume Obozinski, AISTAT 2016. [hal]

Preconditioning of a Generalized Forward-Backward Splitting and Application to Optimization on Graphs. Hugo Raguet, Loic Landrieu, SIAM Journal on Imaging Science (SIIMS) 8, 4(2706-2739), 2015.    [siam] [arxiv]

Continuously Indexed Potts Models on Unoriented Graphs. Loic landrieu, Guillaume Obozinsk, UAI 2014 – Quebec, Canada, [auai]  [hal]

Articles with a * are French translations of work previously published in English.