A Denoising Method for X-ray Ptychography Combining a Physical Diffraction Model with a Deep Image Prior Network

Mengnan Liu, Yu Han,Xiaoqi Xi, Qi Zhong, Liyang Zhang,Lei Li,Zijian Xu,Xiangzhi Zhang,Bin Yan

IEEE Transactions on Nuclear Science（2025）

Cited 0|Views0

Abstract

X-ray ptychography is a lensless imaging technology with promising applications that can achieve nanometer resolution. However, the noise in the diffraction patterns degrades the performance of the phase recovery algorithms for ptychography. In reconstructed objects, the artifacts can affect details. We categorize the noise in the diffraction patterns into static intensity (SI) and dynamic random noise (DRN), which lead to periodic artifacts (PAs) and random noise in the reconstructed object. A denoising method for X-ray ptychography is therefore proposed to suppress the SI and DRN by a unified mathematical model. An explicit noise constraint based on the physical diffraction model and an implicit prior regarding the object for network extraction are integrated to construct a joint noise constraint. Simulations and soft X-ray experiments demonstrate the advanced capability of the proposed method for noise suppression. Compared with other methods (extended ptychographical iterative engine and periodic-artifact suppressing algorithm), the proposed method has high robustness and generality.

Translated text

Key words

X-ray ptychography,denoise,physical constraint,implicit image priors,joint noise constraints

求助PDF

上传PDF

Bibtex

AI Read Science

AI Summary

AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.

Example

Background

Key content

Introduction

Methods

Results

Related work

Fund

Key content

Pretraining has recently greatly promoted the development of natural language processing (NLP)
We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance

Upload PDF to Generate Summary

Must-Reading Tree

Example

Generate MRT to find the research sequence of this paper

Data Disclaimer

The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn

Chat Paper

【要点】：本文提出了一种结合物理衍射模型与深度图像先验网络的X射线衍射成像去噪方法，有效抑制静态强度噪声和动态随机噪声，提高了相位恢复算法的性能和重构物体的细节清晰度。

【方法】：通过将基于物理衍射模型的显式噪声约束和针对物体特性的隐式先验网络相结合，构建了一个统一的数学模型来进行去噪。

【实验】：通过仿真和软X射线实验验证了所提方法的有效性，该方法在各种噪声条件下均展现出高鲁棒性和通用性，实验使用的数据集未在文中明确提及。