Dongdong Chen

Assistant Professor @HeriotWattUni, Edinburgh. I like machine learning and imaging inverse problems.

[PyTorch @PyTorch]

DeepInverse has joined the PyTorch Ecosystem, making imaging with deep learning easier and more reproducible across research and industry.

DeepInverse is an open source framework for solving imaging inverse problems in medical imaging, computational photography, remote sensing, astronomical imaging, microscopy and more. DeepInverse makes imaging with deep learning easy and is developed by a passionate community of researchers, practitioners and engineers.

🔗 Learn more & explore how to get involved: https://t.co/fkXkMqNJB1

#PyTorch #OpenSourceAI #DeepInverse #Imaging #DeepLearning

[Dongdong Chen @ddongchen]

@ukmlv Congrats!

[Dongdong Chen @ddongchen]

@ukmlv @IEEEsps Congrats! 🎉

[Samuel Hurault @HuraultSamuel]

Not coming back from Marseille empty handed #DeepInverse @TachellaJulian @MatthieuTerris @ddongchen @minhhai712

[CNRS Physique @CNRSphysique]

Toutes nos félicitations aux deux espoirs des prix science ouverte du logiciel libre de la recherche qui travaillent dans des laboratoires rattachés à @CNRSphysique : @TachellaJulian (DeepInverse) et Sébastien Weber (PyMoDAQ) 👏

Pour en savoir plus ⤵️
https://t.co/t0qEnkqlyh

[Julián Tachella @TachellaJulian]

🚀 deepinverse hackathon🚀

We just finished a couple of days working on deepinverse in the beautiful CIRM venue.

https://t.co/o7LpxJJjdz

Immensely grateful to the dream team of contributors that participated in the hackathon!

A thread 🧵

[Julián Tachella @TachellaJulian]

📢New preprint 📢

UNSURE: Unknown Noise level Stein's Unbiased Risk Estimator
https://t.co/oBnyTuSB6y

Optimal self-supervised losses (SURE, R2R) require exact knowledge of the noise distribution, and alternatives like Noise2Void are suboptimal.

There is middle ground🧵

[Julián Tachella @TachellaJulian]

Tomorrow we are giving a deepinverse + computational imaging tutorial in Bologna, Italy, with fellow deepinverters @HuraultSamuel @MatthieuTerris @ddongchen

https://t.co/TvtUQgeY8f

[Julián Tachella @TachellaJulian]

Attending EUSIPCO'24 in Lyon?

You can attend a 3-hour tutorial on self-supervised learning for imaging, given by Mike Davies and myself.
https://t.co/MkZrhspErE

A thread with some of the contents 🧵

[Dongdong Chen @ddongchen]

"pip install deepinv" to solve your inverse problems🥳🥳

[Julián Tachella @TachellaJulian]

📢 DeepInverse v0.2 is out!

New features:
📏 Physics for blind inverse + calibration problems
🕸️ Advanced blurs
💣 Random physics generators
🤖New modular Trainer
🪂 Phase retrieval
🎉 Patch and 3D priors

by new contributors!
A🧵
https://t.co/WGtMi24oqX

[Dongdong Chen @ddongchen]

@HuraultSamuel Congratulations 🎉🎉

[Julián Tachella @TachellaJulian]

🤗You can now check out some deepinverse denoisers with this interactive huggingface demo
https://t.co/PbQ81CADpN
More demos are coming!

[Julián Tachella @TachellaJulian]

💣The deepinverse library keeps growing!

Now you can train your model with the self-supervised loss 'recorrupted2recorrupted' by choosing the R2RLoss

[Samuel Hurault @HuraultSamuel]

People DeepIng into DeepInv at the DIPopt workshop 🤗

[Julián Tachella @TachellaJulian]

The group photo for DIPOpt at ENS Lyon, thanks everyone for coming and sharing ideas and research!

[Dongdong Chen @ddongchen]

Update: Diffusion Posterior Sampling (DPS) is now integrated with deep inverse library (https://t.co/bVYeT2ZaKx). Thanks @hyungjin_chung for the contribution!

'import deepinv as dinv' - one line of code to play with DPS.

[Julián Tachella @TachellaJulian]

🎁Diffusion Posterior Sampling (DPS) is now part of the deepinverse library.

Big thanks to @hyungjin_chung for the contribution!

The list of deepinv contributors keeps growing 🎉

[Julián Tachella @TachellaJulian]

🚆On my way to #ICCV2023

Tomorrow I'll be giving an intro to the deepinverse library in the morning https://t.co/o7LpxJJjdz

[Julián Tachella @TachellaJulian]

📢Happy to announce the "Deep learning, image analysis, inverse problems, and optimization" workshop on November 27-30 in Lyon, France.
https://t.co/mfDAcRq0mA

more details below 🧵

[Dongdong Chen @ddongchen]

Do you need a library for inverse problems, computational imaging, or image reconstruction/restoration?

try 'pip install deepinv', then

'import deepinv' is all you need! 🥳

https://t.co/FWWczy0k6C
#deepinverse

[Matthieu Terris @MatthieuTerris]

DiffPIR is a pretty exciting algorithm mixing diffusion & plug-and-play algorithms. By relying on an operator splitting strategy, it does not require any restrictive assumption on the measurement operator (e.g. no SVD) 🤸

[Julián Tachella @TachellaJulian]

📢📢 Release of DeepInverse library 📢📢

After months of intense work, we are releasing the first stable version of DeepInverse https://t.co/o7LpxJJjdz, a PyTorch library for solving inverse problems with deep learning.

with @HuraultSamuel, @MatthieuTerris and @ddongchen

A 🧵