Julian Tachella
@tachellajulian.bsky.social
CNRS research scientist, based at ENS de Lyon
I'm interested in AI for imaging inverse problems
Looking to hire phds/postdocs!
🇦🇷🇬🇧🇫🇷
Website: https://tachella.github.io/
Deepinverter: https://deepinv.github.io/
I'm interested in AI for imaging inverse problems
Looking to hire phds/postdocs!
🇦🇷🇬🇧🇫🇷
Website: https://tachella.github.io/
Deepinverter: https://deepinv.github.io/
Pinned
Self-Supervised Learning for Inverse Problems - YouTube
Tutorial by Julián Tachella (CNRS, ENS Lyon) & Mike Davies (University of Edinburgh) given at the University of Edinburgh, February 2025.I. "Introduction"II....
youtube.com
🚀 Do you want to learn about self-supervised learning for inverse problems?
▶️ Check out the 3-hour tutorial presented by Mike Davies (University of Edinburgh) and myself (CNRS, ENS Lyon), covering all the recent advances in a unified and simplified framework!
youtube.com/playlist?lis...
▶️ Check out the 3-hour tutorial presented by Mike Davies (University of Edinburgh) and myself (CNRS, ENS Lyon), covering all the recent advances in a unified and simplified framework!
youtube.com/playlist?lis...
💥 DeepInverse is now part of the official PyTorch Landscape💥
We are excited to join an ecosystem of great open-source AI libraries, including @hf.co diffusers, MONAI, einops, etc.
pytorch.org/blog/deepinv...
We are excited to join an ecosystem of great open-source AI libraries, including @hf.co diffusers, MONAI, einops, etc.
pytorch.org/blog/deepinv...
DeepInverse Joins the PyTorch Ecosystem: the library for solving imaging inverse problems with deep learning – PyTorch
pytorch.org
November 5, 2025 at 5:31 PM
💥 DeepInverse is now part of the official PyTorch Landscape💥
We are excited to join an ecosystem of great open-source AI libraries, including @hf.co diffusers, MONAI, einops, etc.
pytorch.org/blog/deepinv...
We are excited to join an ecosystem of great open-source AI libraries, including @hf.co diffusers, MONAI, einops, etc.
pytorch.org/blog/deepinv...
DeepInverse: a Python library for imaging with deep learning — deepinv 0.3.4 documentation
deepinv.github.io
October 9, 2025 at 1:20 PM
☀️ Just wrapped up the DeepInverse Hackathon!
We had 30+ imaging scientists from all over the world coding during 3 days next to the beautiful Calanques in Marseille, France. It was a great moment to meet new people, discuss science, and code new imaging algorithms!
We had 30+ imaging scientists from all over the world coding during 3 days next to the beautiful Calanques in Marseille, France. It was a great moment to meet new people, discuss science, and code new imaging algorithms!
September 10, 2025 at 4:50 PM
☀️ Just wrapped up the DeepInverse Hackathon!
We had 30+ imaging scientists from all over the world coding during 3 days next to the beautiful Calanques in Marseille, France. It was a great moment to meet new people, discuss science, and code new imaging algorithms!
We had 30+ imaging scientists from all over the world coding during 3 days next to the beautiful Calanques in Marseille, France. It was a great moment to meet new people, discuss science, and code new imaging algorithms!
🔬 Are you working in computational imaging or interested in learning?
📖 DeepInverse just released a new 5-minute quickstart tutorial
deepinv.github.io/deepinv/auto...
which gets you started developing AI models for reconstructing images!
📖 DeepInverse just released a new 5-minute quickstart tutorial
deepinv.github.io/deepinv/auto...
which gets you started developing AI models for reconstructing images!
August 20, 2025 at 11:04 AM
🔬 Are you working in computational imaging or interested in learning?
📖 DeepInverse just released a new 5-minute quickstart tutorial
deepinv.github.io/deepinv/auto...
which gets you started developing AI models for reconstructing images!
📖 DeepInverse just released a new 5-minute quickstart tutorial
deepinv.github.io/deepinv/auto...
which gets you started developing AI models for reconstructing images!
New Feature in DeepInverse (deepinv.github.io):
🚀 Custom Diffusion Solver Design
DeepInverse now simplifies the process with:
✔ Standard SDEs (VP, VE, etc.)
✔ Pretrained denoisers for multiple noise levels
✔ ODE/SDE solvers (Euler, Heun)
✔ Noisy data fidelity terms for guidance
🚀 Custom Diffusion Solver Design
DeepInverse now simplifies the process with:
✔ Standard SDEs (VP, VE, etc.)
✔ Pretrained denoisers for multiple noise levels
✔ ODE/SDE solvers (Euler, Heun)
✔ Noisy data fidelity terms for guidance
Redirecting to https://deepinv.github.io/deepinv/
deepinv.github.io
May 19, 2025 at 2:48 PM
New Feature in DeepInverse (deepinv.github.io):
🚀 Custom Diffusion Solver Design
DeepInverse now simplifies the process with:
✔ Standard SDEs (VP, VE, etc.)
✔ Pretrained denoisers for multiple noise levels
✔ ODE/SDE solvers (Euler, Heun)
✔ Noisy data fidelity terms for guidance
🚀 Custom Diffusion Solver Design
DeepInverse now simplifies the process with:
✔ Standard SDEs (VP, VE, etc.)
✔ Pretrained denoisers for multiple noise levels
✔ ODE/SDE solvers (Euler, Heun)
✔ Noisy data fidelity terms for guidance
I'll be in Singapore this week for #ICLR2025 presenting "UNSURE: self-supervised learning with Unknown Noise level and Stein's Unbiased Risk Estimate"
Ping me if you are around too!
Ping me if you are around too!
April 21, 2025 at 4:44 AM
I'll be in Singapore this week for #ICLR2025 presenting "UNSURE: self-supervised learning with Unknown Noise level and Stein's Unbiased Risk Estimate"
Ping me if you are around too!
Ping me if you are around too!
🚀🚀 Reconstruct-Anything-Model: A single model to rule all imaging tasks!
We challenge current beliefs and show that a single U-Net can obtain impressive performance across a wide variety of tasks, **without** relying on expensive iterative schemes such as unrolling, PnP, diffusion
We challenge current beliefs and show that a single U-Net can obtain impressive performance across a wide variety of tasks, **without** relying on expensive iterative schemes such as unrolling, PnP, diffusion
April 16, 2025 at 8:23 AM
🚀🚀 Reconstruct-Anything-Model: A single model to rule all imaging tasks!
We challenge current beliefs and show that a single U-Net can obtain impressive performance across a wide variety of tasks, **without** relying on expensive iterative schemes such as unrolling, PnP, diffusion
We challenge current beliefs and show that a single U-Net can obtain impressive performance across a wide variety of tasks, **without** relying on expensive iterative schemes such as unrolling, PnP, diffusion
🚢🚢 deepinv v0.3.0 is here, with many new features! 🚢 🚢
Our passionate team of contributors keeps shipping more exciting tools!
Deepinverse (deepinv.github.io) is a library for solving imaging inverse problems with deep learning.
Our passionate team of contributors keeps shipping more exciting tools!
Deepinverse (deepinv.github.io) is a library for solving imaging inverse problems with deep learning.
Redirecting to https://deepinv.github.io/deepinv/
deepinv.github.io
April 14, 2025 at 6:33 AM
🚢🚢 deepinv v0.3.0 is here, with many new features! 🚢 🚢
Our passionate team of contributors keeps shipping more exciting tools!
Deepinverse (deepinv.github.io) is a library for solving imaging inverse problems with deep learning.
Our passionate team of contributors keeps shipping more exciting tools!
Deepinverse (deepinv.github.io) is a library for solving imaging inverse problems with deep learning.
Deriving Tweedie's formula from SURE let's you also derive other interesting generalisations, such as a formula that doesn't require knowledge about the noise level, and it can be generalized well beyond isotropic gaussian noise.
One more thing: Most people I've seen recently derive Tweedie from Stein's Unbiased Risk Estimator (SURE). I don't get that - it's messy and requires much stronger regularity conditions.
I mean - Tweedie invented the formula before Stein invented SURE after all!
@gabrielpeyre.bsky.social
FYI
I mean - Tweedie invented the formula before Stein invented SURE after all!
@gabrielpeyre.bsky.social
FYI
March 28, 2025 at 8:37 AM
Deriving Tweedie's formula from SURE let's you also derive other interesting generalisations, such as a formula that doesn't require knowledge about the noise level, and it can be generalized well beyond isotropic gaussian noise.
🚀 Do you want to learn about self-supervised learning for inverse problems?
▶️ Check out the 3-hour tutorial presented by Mike Davies (University of Edinburgh) and myself (CNRS, ENS Lyon), covering all the recent advances in a unified and simplified framework!
youtube.com/playlist?lis...
▶️ Check out the 3-hour tutorial presented by Mike Davies (University of Edinburgh) and myself (CNRS, ENS Lyon), covering all the recent advances in a unified and simplified framework!
youtube.com/playlist?lis...
Self-Supervised Learning for Inverse Problems - YouTube
Tutorial by Julián Tachella (CNRS, ENS Lyon) & Mike Davies (University of Edinburgh) given at the University of Edinburgh, February 2025.I. "Introduction"II....
youtube.com
March 17, 2025 at 2:32 PM
🚀 Do you want to learn about self-supervised learning for inverse problems?
▶️ Check out the 3-hour tutorial presented by Mike Davies (University of Edinburgh) and myself (CNRS, ENS Lyon), covering all the recent advances in a unified and simplified framework!
youtube.com/playlist?lis...
▶️ Check out the 3-hour tutorial presented by Mike Davies (University of Edinburgh) and myself (CNRS, ENS Lyon), covering all the recent advances in a unified and simplified framework!
youtube.com/playlist?lis...
Generalized Recorrupted-to-Recorrupted is accepted at CVPR25 🚀
See a thread below:
See a thread below:
🔉New paper "Generalized Recorrupted-to-Recorrupted" 🔉
with @bemc22.bsky.social and Jorge Bacca
- Generalizes R2R self-supervised loss for noise belonging to the exponential family.
- Shows asymptotic equivalence with SURE.
paper: arxiv.org/abs/2412.04648
code: github.com/bemc22/Gener...
with @bemc22.bsky.social and Jorge Bacca
- Generalizes R2R self-supervised loss for noise belonging to the exponential family.
- Shows asymptotic equivalence with SURE.
paper: arxiv.org/abs/2412.04648
code: github.com/bemc22/Gener...
Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian Noise
Recorrupted-to-Recorrupted (R2R) has emerged as a methodology for training deep networks for image restoration in a self-supervised manner from noisy measurement data alone, demonstrating equivalence ...
arxiv.org
February 27, 2025 at 10:16 AM
Generalized Recorrupted-to-Recorrupted is accepted at CVPR25 🚀
See a thread below:
See a thread below:
🚀 "UNSURE: self-supervised learning with Unknown Noise level and Stein's Unbiased Risk Estimate"
is accepted at #ICLR2025
A thread!
📜 Paper: arxiv.org/abs/2409.01985
🖥️ Code: github.com/tachella/uns...
is accepted at #ICLR2025
A thread!
📜 Paper: arxiv.org/abs/2409.01985
🖥️ Code: github.com/tachella/uns...
January 30, 2025 at 4:53 PM
🚀 "UNSURE: self-supervised learning with Unknown Noise level and Stein's Unbiased Risk Estimate"
is accepted at #ICLR2025
A thread!
📜 Paper: arxiv.org/abs/2409.01985
🖥️ Code: github.com/tachella/uns...
is accepted at #ICLR2025
A thread!
📜 Paper: arxiv.org/abs/2409.01985
🖥️ Code: github.com/tachella/uns...
Deepinv v0.2.2 is out!
documentation: deepinv.github.io
repo: github.com/deepinv/deep...
v0.2.2 updates:
📚 New documentation
📊 Metrics classes
🧠 Advanced MRI: 3D and multicoil support
🔥 Bregman potentials
🌀 Advanced transforms: diffeomorphisms, time transforms
🖼️ New datasets
⚡ L12 prior
documentation: deepinv.github.io
repo: github.com/deepinv/deep...
v0.2.2 updates:
📚 New documentation
📊 Metrics classes
🧠 Advanced MRI: 3D and multicoil support
🔥 Bregman potentials
🌀 Advanced transforms: diffeomorphisms, time transforms
🖼️ New datasets
⚡ L12 prior
Redirecting to https://deepinv.github.io/deepinv/
deepinv.github.io
December 12, 2024 at 8:44 AM
Deepinv v0.2.2 is out!
documentation: deepinv.github.io
repo: github.com/deepinv/deep...
v0.2.2 updates:
📚 New documentation
📊 Metrics classes
🧠 Advanced MRI: 3D and multicoil support
🔥 Bregman potentials
🌀 Advanced transforms: diffeomorphisms, time transforms
🖼️ New datasets
⚡ L12 prior
documentation: deepinv.github.io
repo: github.com/deepinv/deep...
v0.2.2 updates:
📚 New documentation
📊 Metrics classes
🧠 Advanced MRI: 3D and multicoil support
🔥 Bregman potentials
🌀 Advanced transforms: diffeomorphisms, time transforms
🖼️ New datasets
⚡ L12 prior
🔉New paper "Generalized Recorrupted-to-Recorrupted" 🔉
with @bemc22.bsky.social and Jorge Bacca
- Generalizes R2R self-supervised loss for noise belonging to the exponential family.
- Shows asymptotic equivalence with SURE.
paper: arxiv.org/abs/2412.04648
code: github.com/bemc22/Gener...
with @bemc22.bsky.social and Jorge Bacca
- Generalizes R2R self-supervised loss for noise belonging to the exponential family.
- Shows asymptotic equivalence with SURE.
paper: arxiv.org/abs/2412.04648
code: github.com/bemc22/Gener...
Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian Noise
Recorrupted-to-Recorrupted (R2R) has emerged as a methodology for training deep networks for image restoration in a self-supervised manner from noisy measurement data alone, demonstrating equivalence ...
arxiv.org
December 9, 2024 at 1:22 PM
🔉New paper "Generalized Recorrupted-to-Recorrupted" 🔉
with @bemc22.bsky.social and Jorge Bacca
- Generalizes R2R self-supervised loss for noise belonging to the exponential family.
- Shows asymptotic equivalence with SURE.
paper: arxiv.org/abs/2412.04648
code: github.com/bemc22/Gener...
with @bemc22.bsky.social and Jorge Bacca
- Generalizes R2R self-supervised loss for noise belonging to the exponential family.
- Shows asymptotic equivalence with SURE.
paper: arxiv.org/abs/2412.04648
code: github.com/bemc22/Gener...
Yesterday I was very lucky to present in this beautiful seminar room at la universidad de la república 🇺🇾
November 28, 2024 at 10:39 PM
Yesterday I was very lucky to present in this beautiful seminar room at la universidad de la república 🇺🇾
🎉The open source library deepinverse has been awarded the best documentation prize of the open source code awards in France!
www.inp.cnrs.fr/fr/cnrsinfo/...
www.inp.cnrs.fr/fr/cnrsinfo/...
DeepInverse et PyMoDAQ espoirs du Prix science ouverte du logiciel libre de la recherche
Julián Tachella, chercheur CNRS au Laboratoire de Physique de l’ENS de Lyon (LPENSL, CNRS / EN
www.inp.cnrs.fr
November 26, 2024 at 8:47 PM
🎉The open source library deepinverse has been awarded the best documentation prize of the open source code awards in France!
www.inp.cnrs.fr/fr/cnrsinfo/...
www.inp.cnrs.fr/fr/cnrsinfo/...
Reposted by Julian Tachella
Hi -- I have a postdoc position open in Computational MRI -- looking for experience and interest in MRI acquisition (in addition to reconstruction). Offer competitive pay. Opportunity to collaborate with Center for GenAI and Dell Med School. Bonus if you get your app in before Dec 1!
November 25, 2024 at 9:26 PM
Hi -- I have a postdoc position open in Computational MRI -- looking for experience and interest in MRI acquisition (in addition to reconstruction). Offer competitive pay. Opportunity to collaborate with Center for GenAI and Dell Med School. Bonus if you get your app in before Dec 1!
Para los hispanoparlantes, pueden encontrar una charla en el IAR sobre mi investigación en métodos de aprendizaje no supervisado aquí:
www.youtube.com/live/-y-QCO9...
www.youtube.com/live/-y-QCO9...
YouTube
Share your videos with friends, family, and the world
www.youtube.com
November 25, 2024 at 8:58 PM
Para los hispanoparlantes, pueden encontrar una charla en el IAR sobre mi investigación en métodos de aprendizaje no supervisado aquí:
www.youtube.com/live/-y-QCO9...
www.youtube.com/live/-y-QCO9...
Let me know if you want me to add you to the list :)
I've made a starter pack of people I found here working on imaging inverse problems and computational imaging!
go.bsky.app/QNkDcXE
go.bsky.app/QNkDcXE
November 20, 2024 at 2:54 PM
Let me know if you want me to add you to the list :)
I've made a starter pack of people I found here working on imaging inverse problems and computational imaging!
go.bsky.app/QNkDcXE
go.bsky.app/QNkDcXE
November 20, 2024 at 11:25 AM
I've made a starter pack of people I found here working on imaging inverse problems and computational imaging!
go.bsky.app/QNkDcXE
go.bsky.app/QNkDcXE