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/
🫂 This is an important milestone for the deepinv maintainer team and contributors, who keep shipping new features!
November 5, 2025 at 5:31 PM
🫂 This is an important milestone for the deepinv maintainer team and contributors, who keep shipping new features!
✨ If you like the library, give us a star of support in GitHub: github.com/deepinv/deep...
November 5, 2025 at 5:31 PM
✨ If you like the library, give us a star of support in GitHub: github.com/deepinv/deep...
Interested?
1- pip install deepinv
2- Get started with our 5-minute tutorial: deepinv.github.io/deepinv/auto...
3- Go deeper by checking examples and our extensive documentation: deepinv.github.io/deepinv/inde...
1- pip install deepinv
2- Get started with our 5-minute tutorial: deepinv.github.io/deepinv/auto...
3- Go deeper by checking examples and our extensive documentation: deepinv.github.io/deepinv/inde...
5 minute quickstart tutorial — deepinv 0.3.5 documentation
deepinv.github.io
November 5, 2025 at 5:31 PM
Interested?
1- pip install deepinv
2- Get started with our 5-minute tutorial: deepinv.github.io/deepinv/auto...
3- Go deeper by checking examples and our extensive documentation: deepinv.github.io/deepinv/inde...
1- pip install deepinv
2- Get started with our 5-minute tutorial: deepinv.github.io/deepinv/auto...
3- Go deeper by checking examples and our extensive documentation: deepinv.github.io/deepinv/inde...
📸 DeepInverse provides state-of-the-art AI models for image reconstruction across many imaging modalities, such as computational photography, astronomical imaging, microscopy, and medical imaging.
November 5, 2025 at 5:31 PM
📸 DeepInverse provides state-of-the-art AI models for image reconstruction across many imaging modalities, such as computational photography, astronomical imaging, microscopy, and medical imaging.
Read more about this new feature in the docs: deepinv.github.io/deepinv/user...
and check out a Jupyter notebook demo: deepinv.github.io/deepinv/auto...
This is a great example of the under-the-hood features that make large-scale training seamless with the library!
and check out a Jupyter notebook demo: deepinv.github.io/deepinv/auto...
This is a great example of the under-the-hood features that make large-scale training seamless with the library!
Unfolded Algorithms — deepinv 0.3.4 documentation
deepinv.github.io
October 9, 2025 at 1:20 PM
Read more about this new feature in the docs: deepinv.github.io/deepinv/user...
and check out a Jupyter notebook demo: deepinv.github.io/deepinv/auto...
This is a great example of the under-the-hood features that make large-scale training seamless with the library!
and check out a Jupyter notebook demo: deepinv.github.io/deepinv/auto...
This is a great example of the under-the-hood features that make large-scale training seamless with the library!
The new feature leverages closed-form formulas for computing gradients without storing intermediate steps, only requiring an additional call to the least squares solver.
October 9, 2025 at 1:20 PM
The new feature leverages closed-form formulas for computing gradients without storing intermediate steps, only requiring an additional call to the least squares solver.
DeepInverse provided access to state-of-the-art matrix-free least squares solvers (eg, conjugate gradient, BiCGStab, lsqr, etc), but backproping through their steps required significant memory and slowed down training.
October 9, 2025 at 1:20 PM
DeepInverse provided access to state-of-the-art matrix-free least squares solvers (eg, conjugate gradient, BiCGStab, lsqr, etc), but backproping through their steps required significant memory and slowed down training.
Many reconstruction models rely on a differentiable least squares solver, such as unfolded networks with proximal steps or reconstruct-anything-model.
October 9, 2025 at 1:20 PM
Many reconstruction models rely on a differentiable least squares solver, such as unfolded networks with proximal steps or reconstruct-anything-model.
🔎 A focus on the new implicit backprop for least squares solvers (by Minh Hai Nguyen), which unlocks training in large-scale imaging settings:
Unfolded Algorithms — deepinv 0.3.4 documentation
deepinv.github.io
October 9, 2025 at 1:20 PM
🔎 A focus on the new implicit backprop for least squares solvers (by Minh Hai Nguyen), which unlocks training in large-scale imaging settings:
🚀 New Features:
- Implicit backprop for least squares solvers
- noise statistics for SAR imaging
- Multi-coil MRI coil-map estimation acceleration via CuPy
- RicianNoise model
- Self-supervised super-resolution loss
- Implicit backprop for least squares solvers
- noise statistics for SAR imaging
- Multi-coil MRI coil-map estimation acceleration via CuPy
- RicianNoise model
- Self-supervised super-resolution loss
Unfolded Algorithms — deepinv 0.3.4 documentation
deepinv.github.io
October 9, 2025 at 1:20 PM
🚀 New Features:
- Implicit backprop for least squares solvers
- noise statistics for SAR imaging
- Multi-coil MRI coil-map estimation acceleration via CuPy
- RicianNoise model
- Self-supervised super-resolution loss
- Implicit backprop for least squares solvers
- noise statistics for SAR imaging
- Multi-coil MRI coil-map estimation acceleration via CuPy
- RicianNoise model
- Self-supervised super-resolution loss
Stay tuned for more hackathons to come!
🫂If you are interested in joining the community
- join the discord discord.gg/qBqY5jKw3p
- open an issue or a pull request deepinv.github.io
- drop us a message!
🫂If you are interested in joining the community
- join the discord discord.gg/qBqY5jKw3p
- open an issue or a pull request deepinv.github.io
- drop us a message!
Join the deepinv library Discord Server!
Check out the deepinv library community on Discord – hang out with 189 other members and enjoy free voice and text chat.
discord.gg
September 10, 2025 at 4:50 PM
Stay tuned for more hackathons to come!
🫂If you are interested in joining the community
- join the discord discord.gg/qBqY5jKw3p
- open an issue or a pull request deepinv.github.io
- drop us a message!
🫂If you are interested in joining the community
- join the discord discord.gg/qBqY5jKw3p
- open an issue or a pull request deepinv.github.io
- drop us a message!
❔ Uncertainty Quantification
- coverage plots + conformal prediction
🏫 Trainer v2!
- coverage plots + conformal prediction
🏫 Trainer v2!
September 10, 2025 at 4:50 PM
❔ Uncertainty Quantification
- coverage plots + conformal prediction
🏫 Trainer v2!
- coverage plots + conformal prediction
🏫 Trainer v2!
💥 Self-supervised learning
- Noise2Self
- MERLIN for SAR
- Noise2Self
- MERLIN for SAR
September 10, 2025 at 4:50 PM
💥 Self-supervised learning
- Noise2Self
- MERLIN for SAR
- Noise2Self
- MERLIN for SAR
📖 Datasets
- PETRIC challenge dataset
- BSD500 dataset
- Calgary MRI dataset
- PETRIC challenge dataset
- BSD500 dataset
- Calgary MRI dataset
September 10, 2025 at 4:50 PM
📖 Datasets
- PETRIC challenge dataset
- BSD500 dataset
- Calgary MRI dataset
- PETRIC challenge dataset
- BSD500 dataset
- Calgary MRI dataset
🚀 More optimizers
- implicit differentiation for linear solvers
- more noisy data fidelities for diffusion
- SPECT preconditioned reconstruction
- phase unwrapping reconstruction
- implicit differentiation for linear solvers
- more noisy data fidelities for diffusion
- SPECT preconditioned reconstruction
- phase unwrapping reconstruction
September 10, 2025 at 4:50 PM
🚀 More optimizers
- implicit differentiation for linear solvers
- more noisy data fidelities for diffusion
- SPECT preconditioned reconstruction
- phase unwrapping reconstruction
- implicit differentiation for linear solvers
- more noisy data fidelities for diffusion
- SPECT preconditioned reconstruction
- phase unwrapping reconstruction
🖼️ More image priors/regularizers
- latent diffusion models
- general restoration models for PnP
- complex wavelets prior
- weakly convex regularisers
- latent diffusion models
- general restoration models for PnP
- complex wavelets prior
- weakly convex regularisers
September 10, 2025 at 4:50 PM
🖼️ More image priors/regularizers
- latent diffusion models
- general restoration models for PnP
- complex wavelets prior
- weakly convex regularisers
- latent diffusion models
- general restoration models for PnP
- complex wavelets prior
- weakly convex regularisers
🌌 Large-scale imaging:
- multi-GPU distributed denoising/reconstruction
- 3D TV/TGV denoising in example
- 3D DRUNet
- multi-GPU distributed denoising/reconstruction
- 3D TV/TGV denoising in example
- 3D DRUNet
September 10, 2025 at 4:50 PM
🌌 Large-scale imaging:
- multi-GPU distributed denoising/reconstruction
- 3D TV/TGV denoising in example
- 3D DRUNet
- multi-GPU distributed denoising/reconstruction
- 3D TV/TGV denoising in example
- 3D DRUNet
🔬 New forward operators
- ultrasound physics
- MRI-NUFFT physics wrapper
- ++ ASTRA integration
- near & far field radar operators
- pytomography wrapper SPECT
- SAR noise models
- multiview operators
- single-pixel spyrit wrapper
- spatial unwrapping operators
- multiscale
- ultrasound physics
- MRI-NUFFT physics wrapper
- ++ ASTRA integration
- near & far field radar operators
- pytomography wrapper SPECT
- SAR noise models
- multiview operators
- single-pixel spyrit wrapper
- spatial unwrapping operators
- multiscale
September 10, 2025 at 4:50 PM
🔬 New forward operators
- ultrasound physics
- MRI-NUFFT physics wrapper
- ++ ASTRA integration
- near & far field radar operators
- pytomography wrapper SPECT
- SAR noise models
- multiview operators
- single-pixel spyrit wrapper
- spatial unwrapping operators
- multiscale
- ultrasound physics
- MRI-NUFFT physics wrapper
- ++ ASTRA integration
- near & far field radar operators
- pytomography wrapper SPECT
- SAR noise models
- multiview operators
- single-pixel spyrit wrapper
- spatial unwrapping operators
- multiscale
Also available on Google Colab colab.research.google.com/drive/11YKc_...
August 20, 2025 at 11:04 AM
Also available on Google Colab colab.research.google.com/drive/11YKc_...
For every step, you can either i) use a preexisting {operator,model,dataset} or ii) define a custom one yourself.
August 20, 2025 at 11:04 AM
For every step, you can either i) use a preexisting {operator,model,dataset} or ii) define a custom one yourself.