Home

Hi! I am a researcher at IGN, the French National Geographical Institute, in the computer science department MATIS. The focus of my research is to exploit the graph structure of spatial/temporal data to improve the precision and speed of learning methods.

During my PhD I studied learning and optimization structured by large graphs (total variation, graphical models, etc). I now work on remote sensing application such as  semantic semantization of LiDAR point clouds, satellite hyperspectral imagery and surface reconstruction. I have also developed an interest for deep models structured by graphs such as recurrent networks (GRU, LSTM, ECC).

UPCOMING PRESENTATIONS:

– December 2018: University of Erlangen, Germany, Deep Metric Learning on Point Clouds
– February 2019: Kigali, Rwanda, Teaching assistant at African Matser of Machine Intelligence, Graphical Models with Guilaume Obozinski
– March 2019, Barcelona, Spain, EduServ, Deep Learning for Remote Sensing
– May 2019: Univ. Montpellier, Graph-Sructured Signals: Learning and Optimization

– June 2019: ISPRS Geospatial week,  Enschende, Netherlands, Tutorial on Deep Learning for Point Cloud Semantic Segmentation

– June 2019: EduServ remote course on Deep Learning for Remote Sensing

RECENT TALKS:

16/05/18 : FOSS-4G, ENSG: presentation of the SuperPointGraph repository
– 04/06/18 : NoMADS, Politecnico di Milano, Nonlocal Methods for Imaging
06/06/18 : SIAM symposium in Bologne, Graph Techniques for Image Processing
18/06/18: CVPR2018, Salt Lake City : Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs (Poster)
– 25/06/18 : RFIAP2018, ENSG: Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs
– 03/07/2018: ICML2018, Stockholm: Cut-pursuit algorithm for Regularizing Non smooth Functionals with Graph Total Variation
–  10-08/08/2018: Optimization in Image Analysis Summer School, Copenhagen

 

NEW: the new version of cut pursuit can now handle nonsmooth terms, and is considerably optimized (speed x1000 compared to state-of-the art for EEG inverse problems). The preprint is ready, the code as well!

NEW: our new framework superpoint graph, with Martin Simonovsky, is first in the Semantic3D challenge by 11.8 and 8.8 mIoU points. We also lead the S3DIS challenge by 12.4 mIoU  points. Check out the code here.

I teach machine learning at master DesiGéo and master PPMD at ENSG as a teaching assistant, and in the machine learning course et ENCP.

I review for ICML, NIPS, ICCV, Mathematical Reviews, IJDSA, ANR, ISPRS among many others.