Hi! I am a researcher at IGN, the French Nation Geographical Institute, in the computer science department MATIS. The focus of my research is to exploit the graph structure of spatial 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: See me at the SIAM symposium in Bologne the 5-8 june and at Politecnico di Milano the 4th of June, where I will present my latest research on graph-structured optimization. See me at CVPR2018 presenting Superpoint Graph as well.

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 will come very soon!

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 5.8 mIoU  points. Check out the code here.

I teach machine learning at master DesiGéo and master PPMD at ENSG as a teaching assistant.

I review for ICML, NIPS, ICCV, IJDSA, ANR, among others.