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/
You can now solve inverse problems with SOTA diffusion models with DeepInverse and the brand new integration of @hf.co HF diffusers!
Get started with an example: deepinv.github.io/deepinv/auto...
Get started with an example: deepinv.github.io/deepinv/auto...
November 25, 2025 at 1:46 PM
You can now solve inverse problems with SOTA diffusion models with DeepInverse and the brand new integration of @hf.co HF diffusers!
Get started with an example: deepinv.github.io/deepinv/auto...
Get started with an example: deepinv.github.io/deepinv/auto...
☀️ 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!
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!
Want to see UNSURE in action?
We tested it on real cryo electron microscopy images buried in noise (nothing but noise to the human eye), and no information on how they were captured. As of magic, the trained denoiser finds lots of interesting structures!
We tested it on real cryo electron microscopy images buried in noise (nothing but noise to the human eye), and no information on how they were captured. As of magic, the trained denoiser finds lots of interesting structures!
January 30, 2025 at 4:53 PM
Want to see UNSURE in action?
We tested it on real cryo electron microscopy images buried in noise (nothing but noise to the human eye), and no information on how they were captured. As of magic, the trained denoiser finds lots of interesting structures!
We tested it on real cryo electron microscopy images buried in noise (nothing but noise to the human eye), and no information on how they were captured. As of magic, the trained denoiser finds lots of interesting structures!
The answer is the new UNSURE family of self-supervised losses that exploit this approximate knowledge, bridging the gap.
January 30, 2025 at 4:53 PM
The answer is the new UNSURE family of self-supervised losses that exploit this approximate knowledge, bridging the gap.
We present a new common and simple mathematical framework to understand all these methods, elucidating the constraints imposed by each method on the learned network. The more we know about the noise distribution corrupting the measurements, the fewer constraints are needed!
January 30, 2025 at 4:53 PM
We present a new common and simple mathematical framework to understand all these methods, elucidating the constraints imposed by each method on the learned network. The more we know about the noise distribution corrupting the measurements, the fewer constraints are needed!
🚀 "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...
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 🇺🇾