building https://teapawt.net/t.co/vq0SKxwF3Z
Paris
Joined February 2011
- Tweets74
- Following772
- Followers209
- Likes3.2K
🧵 I'll be at CVPR next week presenting our FiRe work 🔥
TL;DR: We go beyond denoising models in PnP with more general restoration (e.g. deblurring) models!
A starting point observation is that images are not fixed-points of restoration models:
But a cool feature inherited from this fixed-point approach is the ability to combine restoration models!
Our results suggest that combining SR, deblurring and denoising priors works best.
As a summary, don't forget to degrade your images before applying a restoration model 😁 For more details, come chat with me in Nashville!
Last but not least, this is joint work with Thomas Moreau and @ukmlv 🫡
Paper: arxiv.org/abs/2411.18970
Code: next week!
Matthieu Terris retweeted
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!
🧵 What if a single UNet could solve all inverse problems?
In our latest preprint with @HuraultSamuel, Maxime Song, and @TachellaJulian, we build a single multitask UNet for computational imaging — and show it generalizes surprisingly well 👇
arxiv.org/abs/2503.08915
And in challenging real-world imaging problems where there’s no ground truth and limited samples, we can still fine-tune… ✨ fully unsupervised! ✨
Using recent ideas from equivariant imaging + SURE, we adapt the model to a single noisy image, e.g. on this tough SPAD problem:
The code and demo are live!
🔗 Paper: arxiv.org/abs/2503.08915
🔗 Code: github.com/matthieutrs/ram
🔗 Demo: huggingface.co/spaces/deepin…
Matthieu Terris retweeted
🚢🚢 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.
Matthieu Terris retweeted
⚡ Last days to apply for this exciting project to make significant contributions to space-based telescopes like Euclid and JWST using statistics and machine learning! 🪐
Deadline: 1st April! ⏳
📢 PhD project alert 📢
🚀 We have a new open PhD position to work with François Lanusse and myself on "Point Spread Function Modelling for Space Telescopes with a Differentiable Optical Model".
- Project details: tobias-liaudat.github.io/opp…
Thread 🧵
Matthieu Terris retweeted
🚀 Do you want to learn about self-supervised learning for inverse problems?
▶️ Check out the 3-hour tutorial presented by Mike Davies and myself, covering recent advances in a unified and simplified framework!
youtube.com/playlist?list=PL…
