Bruno Lecouat

PhD student

INRIA Thoth, Willow

Email: name dot lastname at gmail dot com
Google scholar / GitHub

I am currently in my fourth year of pursuing a PhD at INRIA , where I am a part of the Willow and Thoth research team, under the guidance of Julien Mairal and Jean Ponce. I am scheduled to defend my thesis in November 2023, and you can access a draft of my thesis here [70Mb]. My research interests revolve around machine learning and imaging.

In addition to my academic pursuits, I serve as the CTO of Enhance Lab, a startup I co-founded with my PhD advisors. At Enhance Lab, we specialize in providing software solutions designed to enhance image quality, utilizing cutting-edge algorithms developed during the course of my doctoral research.

I received an engineering degree in Applied Mathematics from Télécom ParisTech and a M.Sc. degree in Electrical Engineering from the National University of Singapore. Before doing my PhD I had the chance to work with Dr. Chuan-Sheng Foo and Dr. Vijay Chandrasekhar at the Institute for Infocomm Research (I2R).

News


Check out our project on super-resolution from raw bursts. You can see a typical example of the result that we get below (mouse over the left image):

Left: jpeg output of the camera for one frame (high-quality setting); Right: our result (merging 30 raw frames).
Frames are acquired with a handheld Panasonic Lumix GX9 camera. More results can be see here!

Publications


Dense Image Registration, Camera Pose and Depth Estimation from Bursts

Bruno Lecouat*, Yann Dubois de Mont-Marin*, Théo Bodrito*, Jean Ponce, Julien Mairal.
[soon] [soon]

High Dynamic Range and Super-Resolution From Raw Image Bursts

Bruno Lecouat, Thomas Eboli, Jean Ponce, Julien Mairal.
SIGGRAPH 2022
[arxiv]

Lucas Kanade Reloaded : End-to-End Super-Resolution from Raw Image Bursts

Bruno Lecouat, Jean Ponce, Julien Mairal.
ICCV 2021
[arxiv] [project page]

A Flexible Framework for Designing Trainable Priors with Adaptive Smoothing and Game Encoding

Bruno Lecouat, Jean Ponce, Julien Mairal.
NeurIPS 2020
[arxiv] [code]

Fully Trainable and Interpretable Non-Local Sparse Models for Image Restoration

Bruno Lecouat, Jean Ponce, Julien Mairal.
ECCV 2020
[arxiv] [code]

Optimistic mirror descent in saddle-point problems: Going the extra (-gradient) mile

Panayotis Mertikopoulos, Bruno Lecouat, Houssam Zenati, Chuan-Sheng Foo, Vijay Chandrasekhar, Georgios Piliouras.
ICLR 2020
[arxiv] [code]

Semi-Supervised Deep Learning for Abnormality Classification in Retinal Images

Bruno Lecouat, Ken Chang, Chuan-Sheng Foo, Balagopal Unnikrishnan, James M. Brown, Houssam Zenati, Andrew Beers, Vijay Chandrasekhar, Jayashree Kalpathy-Cramer, Pavitra Krishnaswamy.
NeurIPS 2019 - Workshop on Machine Learning for Health
[arxiv]

Adversarially Learned Anomaly Detection

Houssam Zenati, Manon Romain, Chuan-Sheng Foo, Bruno Lecouat, Vijay Chandrasekhar.
ICDM 2019
[arxiv] [code]

Semi-supervised learning with gans: Revisiting manifold regularization

Bruno Lecouat*, Chuan-Sheng Foo*, Houssam Zenati, Vijay Chandrasekhar.
ICLR 2019 - Workshop Track
[arxiv] [code]

Efficient gan-based anomaly detection

Houssam Zenati*, Chuan Sheng Foo*, Bruno Lecouat, Gaurav Manek, Vijay Chandrasekhar.
Preprint
[arxiv] [code]

Manifold regularization with GANs for semi-supervised learning

Bruno Lecouat*, Chuan Sheng Foo*, Houssam Zenati, Vijay Chandrasekhar.
Preprint
[arxiv] [code]