Julián Tachella

CNRS & ENS de Lyon



I am a research scientist at the French National Centre for Scientific Research CNRS, working at the Sisyph laboratory, École Normale Supérieure de Lyon (Lyon, France). My research lies at the intersection of signal processing and machine learning. I am particularly interested in the theory of imaging inverse problems and applications in computational imaging.

I am a lead developer of the deep inverse, a library for solving inverse problems with deep learning.

Open PhD and master positions can be found here.

Code and videos related to my publications can be found here.


Oct 23, 2023 Our paper on binary learning has been accepted in TMLR with a Featured certification!
Oct 20, 2023 We have two open master positions for next year. Find more details here.
Sep 26, 2023 Open postdoc position in multilevel unfolded networks for imaging inverse problems. Find more details here.
Jul 6, 2023 The UNLIP project will be funded by the ANR. Job openings are coming soon!
Feb 18, 2023 Accepted paper on efficient lidar sketching at ICASSP’23.

selected publications

  1. Equivariant Bootstrapping for Uncertainty Quantification in Imaging Inverse Problems
    Tachella, Julian, and Pereyra, Marcelo
    arXiv preprint arXiv:2310.11838 2023
  2. Imaging with Equivariant Deep Learning
    Chen, Dongdong, Davies, Mike, Ehrhardt, Matthias J, Schönlieb, Carola-Bibiane, Sherry, Ferdia, and Tachella, Julian
    IEEE Signal Processing Magazine 2023
  3. Sensing Theorems for Unsupervised Learning in Linear Inverse Problems
    Tachella, Julian, Chen, Dongdong, and Davies, Mike
    Journal of Machine Learning Research (JMLR) Jan 2023