Uncertainty-aware Fourier Ptychography is published in LSA
July 7, 2025
July 7, 2025
Our latest work in Differentiable Imaging - “Uncertainty-Aware Fourier Ptychography”, has been published in Light: Science & Applications!
What makes this work special?
This research stands as the most comprehensive application of differentiable imaging methodology to date. We have successfully addressed three critical uncertainty challenges in tandem: modelable system misalignments, optical component aberrations, and low-quality data. The key breakthrough lies in our fully differentiable framework, which seamlessly integrates all these components.
Why it matters
Traditional computational imaging systems struggle with real-world uncertainties that create mismatches between theoretical models and actual hardwares. Our differentiable programming approach systematically addresses these uncertainties, paving the way for more robust and accurate imaging, and expanding the system perform beyond mere imaging.
 |
|---|
| Framework of the UA-FP |
Explore the research:
📄 Paper: Ni Chen, Yang Wu, Chao Tan, Liangcai Cao, Jun Wang, Edmund Lam, “Uncertainty-Aware Fourier Ptychography,” Light: Science & Applications 14 (236), 2025. https://doi.org/10.1038/s41377-025-01915-w
🌐 Project page: https://ni-chen.github.io/Differentiable-Imaging/
📝 Behind the paper: https://communities.springernature.com/posts/uncertainties-and-differentiable-imaging
📰 News on EurekAlert: https://www.eurekalert.org/news-releases/1090574
📰 EEE news: https://www.eee.hku.hk/20250714-1/
🇨🇳 News on WeChat (Chinese): https://mp.weixin.qq.com/s/2ajfCatOwq8QBoOpVRtFJQ
The bigger picture:
Differentiable Imaging is more than just an uncertainty management methodology. This work, together with other related research efforts, is converging toward a new paradigm in computational imaging integrated with digital twins—one that we believe will substantially accelerate the application of AI for Science across the entire imaging community.