Thibaud Ehret

I am currently a post-doc at the Centre Borelli at ENS Paris-Saclay, where I work on anomaly detection and different projects linked with remote sensing.

I did my PhD at the CMLA at ENS Cachan, where I was advised by Jean-Michel Morel.

Email  /  GitHub  /  Google Scholar

profile photo


I'm interested in image and video processing, optimization and remote sensing.

project image

Global Tracking and Quantification of Oil and Gas Methane Emissions from Recurrent Sentinel-2 Imagery

Thibaud Ehret, Aurélien De Truchis, Matthieu Mazzolini, Jean-Michel Morel, Alexandre d'Aspremont, Thomas Lauvaux, Gabriele Facciolo
ACS, 2022
paper /

A study of super-emission of methane emissions related to oil and gas in the world.

project image

NeRF, meet differential geometry!

Thibaud Ehret, Roger Marí, Gabriele Facciolo
Preprint, 2022
paper /

Introducing differential geometry tools to NeRFs.

project image

L1B+: A Perfect Sensor Localization Model for Simple Satellite Stereo Reconstruction From Push-frame Image Strips

Roger Marí, Thibaud Ehret, Jérémy Anger, Carlo de Franchis, Gabriele Facciolo
ISPRS 2022, 2022
paper /

We emulates a perfect sensor to generate a single image strip from multiple image push-frame strips.

project image

Sat-NeRF: Learning Multi-View Satellite Photogrammetry With Transient Objects and Shadow Modeling Using RPC Cameras

Roger Marí, Gabriele Facciolo, Thibaud Ehret
CVPRW 2022, 2022
paper / code /

NeRF for 3D modeling of satellite scenes. Project page:

project image

Video Denoising by Combining Patch Search and CNNs

Axel Davy, Thibaud Ehret, Jean-Michel Morel, Pablo Arias, Gabriele Facciolo
JMIV, 2021
paper / code /

Video denoising using CNN and non-locality.

project image

Image anomalies: A review and synthesis of detection methods

Thibaud Ehret, Axel Davy, Mauricio Delbracio, Jean-Michel Morel
JMIV, 2019
paper / code /

A study of anomaly detection in images.

project image

Joint Demosaicking and denoising by fine-tuning of bursts of raw images

Thibaud Ehret, Axel Davy, Pablo Arias, Gabriele Facciolo
ICCV 2019, 2019
paper / code / poster /

Self-supervised learning of joint demosaicking and denoising using only raw bursts.

project image

Model-blind video denoising via frame-to-frame training

Thibaud Ehret, Axel Davy, Jean-Michel Morel, Gabriele Facciolo, Pablo Arias
CVPR 2019, 2019
paper / code / poster /

A model-blind video denoising method based on online learning from a single video.

project image

Non-local kalman: A recursive video denoising algorithm

Thibaud Ehret, Jean-Michel Morel, Pablo Arias
ICIP 2018, 2018
paper / poster /

We propose a new recursive video denoising method combining non-local denoising principles with recursive video denoising. Project website with video examples:

project image

On the convergence of PatchMatch and its variants

Thibaud Ehret, Pablo Arias
CVPR 2018, 2018
paper / poster /

A theoretical analysis of PatchMatch.

project image

Global patch search boosts video denoising

Thibaud Ehret, Pablo Arias, Jean-Michel Morel
VISAPP 2017, 2017
paper /

We study the impact of the local search in patch-based video denoising and show how a global search can improve the quality of the result.

Design and source code from Jon Barron's website and Leonid Keselman's website