🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

The CIG team at the inauguration of Ulugbek S. Kamilov. Eddy, Chicago, and Shirin Shoushtari.

📄 “Stochastic Deep Restoration Priors for Imaging Inverse Problems” was accepted to ICML 2025 (ICML Conference)! Joint work with Yuyang Hu, Albert Peng, Weijie Gan, and colleagues from the Google’s Computational Imaging team, mauricio delbracio and Peyman Milanfar. wustl-cig.github.io/sharpwww/

Happy to announce that our work, ShaRP, has been accepted to #ICML2025! 🎉 Huge thanks to my collaborators Ulugbek S. Kamilov mauricio delbracio Peyman Milanfar Weijie Gan Albert Peng. Can't wait to see everyone in Vancouver!

Soren being relevant, as usual

Two academics from the same area meeting at a conference

Friends, I’m planning a trip to Carmel-by-the-Sea, CA, this October. If you have any recommendations for hotels, restaurants, or must-see spots, I’d love to hear them!

Nice! There is a lot of beauty in the right application of probabilistic reasoning

Well deserved, Lei! I remember being a guest lecturer in your class in 2015 (or 2014, don’t remember) and how much students appreciated you.

I would love to re-visit Edinburgh, but I am not sure that I will be able to attend this year. However, very excited for all these papers to be presented at IEEE SSP.

Friends, I finally opened a #BlueskySocial account. If you are also using it let’s connect: ukmlv.

Our ICIP submission was just accepted. This work was a nice collaboration involving Chicago and Yuyang, along with the LANL's "computational imaging" team.

New paper from our team. We use denoising to learn scores over subsampled measurements, but show how we can use it to generate fully-sampled measurements by taking expectation over partial scores. Collaboration with Chicago Park, Shirin Shoushtari, and Hongyu An.

Our new paper, Measurement Score-Based Diffusion Model, is now online! Learn how to train a diffusion model to sample fully-sampled measurements—without needing any clean data. Thanks to our authors Ulugbek S. Kamilov, Shirin Shoushtari , and Professor. Hongyu An.

Happy to share that "Plug-and-Play Priors as a Score-Based Method" has been accepted to IEEE ICIP 2025! We show how to integrate diffusion priors into PnP algorithms and how they boost image restoration performance. Project page: wustl-cig.github.io/scorepnp/

New paper from our team. We use score-based diffusion models to quantify the KL divergence between distributions using only corrupted measurements. Nice work led by Shirin Shoushtari (Shirin Shoushtari), Eddie Chandler, in collaboration with Salman Asif (Salman Asif).

Assistant Professor in Signal and Image Processing or Robotics position at Heriot-Watt University. Several colleagues work there, including Yves Wiaux (Yves Wiaux). enzj.fa.em3.oraclecloud.com/hcmUI/Candidat…

Come say hi to Matthieu Terris at CVPR. This work was the result of a great collaboration during my sabbatical at ENS Paris last year.

On 20 June at 2pm CEST, I will give a EURASIP Webinar with the title “Computational Imaging: Restoration Deep Networks as Implicit Priors”. More info here: eurasip.org/seminars.

First paper from our collaboration with Prof. Monica Shokeen. Let me highlight the excellent work by the PhD student Flora Sun.

Uzbekistan qualified to the FIFA World Cup 2026. First time. Incredible.