Publications

2019

Time-Space Tradeoff in Deep Learning Models for Crop Classification on Satellite Multi-Spectral Image Time Series, 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]

2018

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]

2017

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, IGARSS2017. [hal]

Cut Pursuit: Fast Algorithms to Learn Piecewise Constant Functions on General Weighted Graphs. Loic Landrieu, Guillaume Obozinski, SIAM Journal on Imaging Science 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]

2016

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

Cut Pursuit: Fast Algorithms to Learn Piecewise Constant Functions on Weighted Graphs. Loic landrieu, Guillaume Obozinski, AIStats2016, Cadiz, Spain.   [jmlr] [hal]

2015

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

2014

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.