[2602.21361] Towards single-shot coherent imaging via overlap-free ptychography

[2602.21361] Towards single-shot coherent imaging via overlap-free ptychography

arXiv - Machine Learning 4 min read Article

Summary

The paper presents a novel approach to single-shot coherent imaging using overlap-free ptychography, enhancing throughput and reducing dose in imaging applications.

Why It Matters

This research addresses a significant limitation in coherent imaging techniques, which often require overlapping scans that can compromise efficiency and increase radiation exposure. By enabling overlap-free imaging, this work has implications for advancements in synchrotron and XFEL imaging, potentially transforming practices in fields such as materials science and biology.

Key Takeaways

  • Introduces a framework for overlap-free, single-shot ptychographic imaging.
  • Achieves high structural similarity in reconstructions with fewer training images.
  • Demonstrates significant throughput improvements over traditional methods.
  • Validates findings with experimental data from leading light sources.
  • Supports dose-efficient imaging, crucial for sensitive applications.

Physics > Optics arXiv:2602.21361 (physics) [Submitted on 24 Feb 2026] Title:Towards single-shot coherent imaging via overlap-free ptychography Authors:Oliver Hoidn, Aashwin Mishra, Steven Henke, Albert Vong, Matthew Seaberg View a PDF of the paper titled Towards single-shot coherent imaging via overlap-free ptychography, by Oliver Hoidn and 4 other authors View PDF HTML (experimental) Abstract:Ptychographic imaging at synchrotron and XFEL sources requires dense overlapping scans, limiting throughput and increasing dose. Extending coherent diffractive imaging to overlap-free operation on extended samples remains an open problem. Here, we extend PtychoPINN (O. Hoidn \emph{et al.}, \emph{Scientific Reports} \textbf{13}, 22789, 2023) to deliver \emph{overlap-free, single-shot} reconstructions in a Fresnel coherent diffraction imaging (CDI) geometry while also accelerating conventional multi-shot ptychography. The framework couples a differentiable forward model of coherent scattering with a Poisson photon-counting likelihood; real-space overlap enters as a tunable parameter via coordinate-based grouping rather than a hard requirement. On synthetic benchmarks, reconstructions remain accurate at low counts ($\sim\!10^4$ photons/frame), and overlap-free single-shot reconstruction with an experimental probe reaches amplitude structural similarity (SSIM) 0.904, compared with 0.968 for overlap-constrained reconstruction. Against a data-saturated supervised model with the same backb...

Related Articles

[2506.22504] Patch2Loc: Learning to Localize Patches for Unsupervised Brain Lesion Detection
Machine Learning

[2506.22504] Patch2Loc: Learning to Localize Patches for Unsupervised Brain Lesion Detection

Abstract page for arXiv paper 2506.22504: Patch2Loc: Learning to Localize Patches for Unsupervised Brain Lesion Detection

arXiv - Machine Learning · 4 min ·
[2508.00307] Acoustic Imaging for Low-SNR UAV Detection: Dense Beamformed Energy Maps and U-Net SELD
Machine Learning

[2508.00307] Acoustic Imaging for Low-SNR UAV Detection: Dense Beamformed Energy Maps and U-Net SELD

Abstract page for arXiv paper 2508.00307: Acoustic Imaging for Low-SNR UAV Detection: Dense Beamformed Energy Maps and U-Net SELD

arXiv - AI · 4 min ·
[2603.25524] CHIRP dataset: towards long-term, individual-level, behavioral monitoring of bird populations in the wild
Computer Vision

[2603.25524] CHIRP dataset: towards long-term, individual-level, behavioral monitoring of bird populations in the wild

Abstract page for arXiv paper 2603.25524: CHIRP dataset: towards long-term, individual-level, behavioral monitoring of bird populations i...

arXiv - AI · 4 min ·
[2603.25170] Knowledge-Guided Adversarial Training for Infrared Object Detection via Thermal Radiation Modeling
Machine Learning

[2603.25170] Knowledge-Guided Adversarial Training for Infrared Object Detection via Thermal Radiation Modeling

Abstract page for arXiv paper 2603.25170: Knowledge-Guided Adversarial Training for Infrared Object Detection via Thermal Radiation Modeling

arXiv - AI · 4 min ·
More in Computer Vision: This Week Guide Trending

No comments

No comments yet. Be the first to comment!

Stay updated with AI News

Get the latest news, tools, and insights delivered to your inbox.

Daily or weekly digest • Unsubscribe anytime