Jérémy Scanvic
/ʒeʁemi skãvik/, /d͡ʒɛɹəmi skɑnvik/
Hi there. 👋 I’m a PhD student at ENSL and Foxstream, working on self-supervised learning for imaging inverse problems including image super-resolution and deblurring, and most specifically focused on adapting equivariant imaging techniques to scale-invariance. Feel free to contact me if you have any question.
“Aren’t programs simpler than logical formulas? The answer is no. Logic is the formalization of everyday mathematics, and everyday mathematics is simpler than programs.”
— Leslie Lamport (1994)
News
- Dec 8'25 - Release of the Equational Theories Project on arXiv
- Oct 1'25 - Release of Equivariant Splitting on arXiv (!!)
- Sep 7-10'25 - Participation at the DeepInverse hackathon
- Jun 28'25 - Workshop paper accepted at COLT'25
Posts
Talks
Scale-Equivariant Imaging: Self-Supervised Learning for Image Super-Resolution and Deblurring
May 13, 2025, GdR IASIS, INRIA Paris
Image Deblurring and Super-Resolution by Learning from Blurry and Low-Resolution Images Only
July 9, 2024 at ENSL
Research
Self-Supervised Learning for Image Super-Resolution and Deblurring
Jérémy Scanvic, Mike Davies, Patrice Abry, Julián Tachella
arXiv 2023
Prefix Palindromic Length of the Sierpinski Word
Dora V. Bulgakova, Anna E. Frid, Jérémy Scanvic
LNCS 2022
Contributed projects
Deep Inverse
- An open-source PyTorch library for solving imaging inverse problems using deep learning
- Written by Julián Tachella, Dongdong Chen, Samuel Hurault and Matthieu Terris
Equational Theories
- A collaborative research project in Universal Algebra
- Lead by Terrence Tao
Personal projects
Spectrogram