Leo Lebrat

I am a senior research fellow at QUT in the School of Electrical Engineering and Robotics.

I used to work at Data 61 in the Imaging and Computer Vision Group and at the Australian e-Health Research Centre in the Neuroimaging Group.

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

AI and Deep Learning

I have a strong interest in Computer Vision, Optimization, Artificial Intelligence, and their applications in healthcare.

	NeRF Director Wenhui Xiao, Rodrigo Santa Cruz, David Ahmedt-Aristizabal, Olivier Salvado, Clinton Fookes, Leo Lebrat. CVPR, 2024 website / code / paper
	Syn3DWound: A Synthetic Dataset for 3D Wound Bed Analysis Leo Lebrat, Rodrigo Santa Cruz, Remi Chierchia, Yulia Arzhaeva, Mohammad Ali Armin, Joshua Goldsmith, Jeremy Oorloff, Prithvi Reddy, Chuong Nguyen, Lars Petersson, Michelle Barakat-Johnson, Georgina Luscombe, Clinton Fookes, Olivier Salvado, David Ahmedt-Aristizabal. ISBI, 2024 website / arxiv / paper
	Generalization Properties of Geometric 3D Deep Learning Models for Medical Segmentation Leo Lebrat, Rodrigo Santa Cruz, Reuben Dorent, Javier Urriola Yaksic, Alex Pagnozzi, Gregg Belous, Pierrick Bourgeat, Jurgen Fripp, Clinton Fookes, Olivier Salvado. ISBI, 2023 paper
	DBCE: a saliency method for medical deep learning through anatomically-consistent free-form deformations Joshua Peters, Leo Lebrat, Rodrigo Santa Cruz, Aaron Nicolson, Gregg Belous, Salamata Konate, Parnesh Raniga, Vincent Dore, Pierrick Bourgeat, Jurgen Mejan-Fripp, Clinton Fookes, Olivier Salvado. WACV, 2023 paper
	Quantifiable brain atrophy synthesis for benchmarking of cortical thickness estimation methods Filip Rusak, Rodrigo Santa Cruz, Leo Lebrat, Ondrej Hlinka, Jurgen Fripp, Elliot Smith, Clinton Fookes, Andrew P Bradley, Pierrick Bourgeat. Medical Image Analysis, 2022 dataset / paper
	CorticalFlow++: Boosting Cortical Surface Reconstruction Accuracy, Regularity, and Interoperability Rodrigo Santa Cruz, Leo Lebrat, Darren Fu, Pierrick Bourgeat, Jurgen Fripp, Clinton Fookes, Olivier Salvado. MICCAI, 2022 arxiv / code / paper
	Generative Model of Brain Microbleeds for MRI Detection of Vascular Marker of Neurodegenerative Diseases Saba Momeni, Amir Fazlollahi, Leo Lebrat, Paul Yates, Chistopher Rowe, Yongsheng Gao, Alan Wee-Chung Liew, Olivier Salvado. Frontiers in Neurosciences, 2021 paper
	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 website / code / paper / slides
	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
	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
	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
	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 Optimisation.

3/4-Discrete Optimal Transport

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

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

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

Leo Lebrat

AI and Deep Learning

NeRF Director

Syn3DWound: A Synthetic Dataset for 3D Wound Bed Analysis

Generalization Properties of Geometric 3D Deep Learning Models for Medical Segmentation

DBCE: a saliency method for medical deep learning through anatomically-consistent free-form deformations

Quantifiable brain atrophy synthesis for benchmarking of cortical thickness estimation methods

CorticalFlow++: Boosting Cortical Surface Reconstruction Accuracy, Regularity, and Interoperability

Generative Model of Brain Microbleeds for MRI Detection of Vascular Marker of Neurodegenerative Diseases

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

MongeNet: Efficient Sampler for Geometric Deep Learning

Going Deeper with Brain Morphometry using Neural Networks

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

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

Math publications

3/4-Discrete Optimal Transport

Optimal Transport Approximation of 2-Dimensional Measures

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