Leo Lebrat

I am a Postdoc at CSIRO, in the ICV group and the MIA team where I work on Geometric Deep Learning and Medical Imaging. I am currently living in Brisbane where I spend my time between the AEHRC and QUT.

In 2019, I have completed my PhD thesis at Institut de Mathematiques de Toulouse (IMT) under the supervision of Frederic de Gournay and Jonas Kahn.

Email  /  GitHub  /  LinkedIn

profile photo

AI and Deep Learning

I'm interested in Computer Vision, Geometric Deep Learning, Optimization and its applications in medical DL.

project image

Cortical Flow: A Diffeomorphic Mesh Deformation Network for Cortical Surface Reconstruction


Leo Lebrat, Rodrigo Santa Cruz, Frederic de Gournay, Pierrick Bourgeat, Jurgen Fripp, Darren Fu, Clinton Fookes, Olivier Salvado.
Conference on Neural Information Processing Systems (NeurIPS), 2021

project image

MongeNet: Efficient Sampler for Geometric Deep Learning


Leo Lebrat, Rodrigo Santa Cruz, Clinton Fookes, Olivier Salvado.
Conference on Computer Vision and Pattern Recognition (CVPR), 2021
website / arxiv / code / slides

project image

Going Deeper with Brain Morphometry using Neural Networks


Rodrigo Santa Cruz, Leo Lebrat, Pierrick Bourgeat, Vincent Doré, Jason Dowling, Jurgen Fripp, Clinton Fookes, Olivier Salvado.
IEEE 18th International Symposium on Biomedical Imaging (ISBI), 2021
arxiv / paper / poster

project image

SMOCAM: SMOoth Conditional Attention Mask for 3D-Regression Models


Salamata Konate, Leo Lebrat, Rodrigo Santa Cruz, Pierrick Bourgeat, Vincent Doré, Jurgen Fripp, Andrew Bradley, Clinton Fookes, Olivier Salvado.
IEEE 18th International Symposium on Biomedical Imaging (ISBI), 2021
paper / poster

project image

DeepCSR: A 3D Deep Learning Approach for Cortical Surface Reconstruction


Rodrigo Santa Cruz, Leo Lebrat, Pierrick Bourgeat, Jurgen Fripp, Clinton Fookes, Olivier Salvado.
IEEE Winter Conference on Applications of Computer Vision (WACV), 2021
arxiv / code / slides




Math publications

Before joining CSIRO my research focused on Optimal Transport and Optimization.

project image

3/4-Discrete Optimal Transport


Leo Lebrat, Frederic de Gournay, Jonas Kahn.
SIAM Journal on Scientific Computing, 2020
arxiv / paper / code

project image

Optimal Transport Approximation of 2-Dimensional Measures


Leo Lebrat, Frederic de Gournay, Jonas Kahn, Pierre Weiss.
SIAM Journal on Imaging Sciences, 2019
arxiv / paper / code

project image

Differentiation and regularity of semi-discrete optimal transport with respect to the parameters of the discrete measure


Frederic de Gournay, Jonas Kahn, Leo Lebrat.
Numerische Mathematik, 2018
arxiv / paper



Design and source code from Jon Barron's website