Computational Imaging Group (CIG) at UW-Madison. Computational Imaging, Biomedical Imaging, Optimization, and AI. Director @ukmlv.
Madison, WI
Joined November 2017
- Tweets500
- Following155
- Followers1.5K
- Likes125
Pinned Tweet
Overview of the Computational Imaging Group (CIG) at WashU by @ukmlv, @s_shirin_s, and @YuyangHu_666.
youtu.be/D4cZcid51fM?feature…
The new website of UW-Madison CIG welcomes you.
The new website of the Computational Imaging Group (CIG) at University of Wisconsin–Madison is now live.
uw-cig.github.io
Computational Imaging Group (CIG) retweeted
🎤 I'll be giving a talk tomorrow at the IEEE SPS Webinar on diffusion models as plug-and-play priors! Welcome to join!
🔗 landing.signalprocessingsoci…
Sam Cook, a summer intern at CIG, presented his poster on image restoration in quantitative MRI using diffusion models. Sam is an undergraduate student at UW-Madison ECE and will continue his project in Fall.
New paper by the CIG member @chicagoypark on autoregressive models for imaging. This work was done as part of his internship at GE Health.
🚀 New preprint: Next-Dense-Stride Prediction for Multimodal Autoregressive Visual Modeling
Better Autoregressive visual modeling via coarse-to-fine on a single compact grid: sparse tokens first, then denser strides, decoded in parallel.
🌐 Project page: uw-cig.github.io/densear_pag…
New paper by our team 🔥
Work with Xiao Shi, Edward P. Chandler, Chicago Y. Park (@chicagoypark), Shirin Shoushtari (@s_shirin_s) (Computational Imaging Group - @uwcig).
Paper: arxiv.org/abs/2606.22696
Excited to share that our paper “RELD: Regularization by Latent Denoising” has been accepted to IEEE Signal Processing Letters!
➛ Preprint: arxiv.org/abs/2503.22563
Computational Imaging Group (CIG) retweeted
I’ll be presenting our work, “Measurement Score-Based Diffusion Model,” at #ICLR2026 in Rio 🇧🇷!
I am happy to chat about diffusion/flow models, inverse problems, and generative modeling.
(Poster session: Friday, P3-#705, 3:15–5:45 PM)
New paper "Measurement Score-Based Diffusion Model". We propose MSM a framework that learns partial measurement scores using only noisy and subsampled measurements. MSM can do unconditional sampling and solve inverse problems.
📄 wustl-cig.github.io/msmwww
Congratulations to the CIG alum - Yu Sun (@YuSunMark) - for being awarded the NSF CAREER. Yu is currently an assistant professor at Johns Hopkins University.
engineering.jhu.edu/ece/news…
Congratulations to Dr. Yuyang Hu for successfully defending his PhD at WashU ESE. We are very impressed with all the research you have done over the past few years and wishing you even greater achievements in the years to come! 🎉
We introduce SGPnP, an optimization-based framework for highly ill-posed inverse problems. By injecting controlled noise into denoisers, SGPnP smooths the objective landscape, avoids strict saddles, and improves convergence—without diffusion sampling.
> uw-cig.github.io/sgpnp_page
"ADOBI: Adaptive Diffusion Bridge For Blind Inverse Problems with Application to MRI Reconstruction" was accepted to IEEE Transactions on Computational Imaging.
> Project Page: wustl-cig.github.io/adobiwww
> Paper: ieeexplore.ieee.org/document…
Congratulations to Anqi Li who will join the Rice ECE PhD program. Anqi worked with us as an MS researcher, while completing his MS in CS at WashU.
Excited to see what he will do next.
Congratulations to the former CIG undergraduate researcher – Eugene Joo – for accepting the offer to join the @Penn GRASP Lab as a PhD student. We are looking forward to hear more about his future achievements.
Congratulations to two former CIG undergraduate researchers – Dijkstra Liu and Jason Zhao – for getting into the UC Berkeley / UCSF PhD program in Computational Precision Health. We are looking forward to hear more about their future achievements.
Two superstars of computational imaging – and now with papers at ICLR! Chicago Park (@chicagoypark) and Xiao Shi (xiaoshi2610.github.io).
"EigenScore: OOD Detection using Posterior Covariance in Diffusion Models" was accepted to ICLR 2026 (@iclr_conf). Great work by the CIG team – @s_shirin_s, Yi Wang, Xiao Shi, @ukmlv – and our collaborator @salmanasif.
‣ Read here: wustl-cig.github.io/eigensco…
"Measurement Score-Based Diffusion Model" was accepted to ICLR 2026 (@iclr_conf). Great work by the CIG team – @chicagoypark, @s_shirin_s, @ukmlv – and our collaborator Hongyu An (@an_hongyu).
‣ Read here: wustl-cig.github.io/msmwww.
Congratulations to CIG alum Yuyang Hu (@YuyangHu_666) on starting an exciting new chapter as a Research Scientist at Google. We’re sad to see you, but proud of your journey and can’t wait to see the impact you’ll make. Wishing you continued success, Yuyang!
