- July 2019: Introduction for general (french) audience to Image colorization, in Interstices.
- June 2019: Our paper GraphXNET - Chest X-Ray Classification Under Extreme Minimal Supervision has been accepted to MICCAI 2019.
- April 2019: Elsa
Cazelles has been awarded the 2018
Jacques Neveu Prize for her PHD on "Statistical properties
of barycenters in the Wasserstein space and fast algorithms for
optimal transport of measures"
- March 2019: Antoine Houdard has started his post-doc within the GOTMI project
- August 2018: Beginning of the 9 months stay in Cambridge with a NoMADS secondment at Mathworks
- May 2018: CNRS article on our work on Wasserstein Geodesic PCA (Actualités de l'INSMI)
- Inverse problems in Imaging sciences
Introduction of new variational and discrete models for image/video processing and analysis.
Keywords: Segmentation, superpixels, denoising, motion estimation, tracking, stereovision, 3D reconstruction, color transfer,
Applications: Satellite data, Football replay, Medical imaging, Movie post-production.
- Numerical methods for Optimal Transportation
Definition of generalized optimal transportation models for comparing and interpolating densities
Keywords: Physical-based regularity constraints, approximations for fast computation, data analysis in Wasserstein space.
Applications: Computational photography, Audio analysis, Neural Networks.
- Image Assimilation in Geosciences
Improving numerical prediction with the integration of structured image information in data assimilation systems.
Keywords: Variational and sequential assimilation, observation errors.
Applications: Meteorology and Oceanography
- Machine Learning and Graph representation
Algorithms for processing non structured data represented by graph.
Keywords: Graph cuts, cheeger cuts, clustering, label propagation, semi-supervized learning, unsupervised learning.
Applications: Hyperspectral and Medical data