paper-with-me

홈 › Papers

High-Resolution Image Reconstruction with Unsupervised Learning and Noisy Data Applied to Ion-Beam Dynamics for Particle Accelerators

2026-03-04 · Francis Osswald, Mohammed Chahbaoui, Xinyi Liang arxiv

Image reconstruction in the presence of severe degradation remains a challenging inverse problem, particularly in beam diagnostics for high-energy physics accelerators. As modern facilities demand precise detection of beam halo structures to control losses, traditional analysis tools have reached their performance limits. This work reviews existing image-processing techniques for data cleaning, contour extraction, and emittance reconstruction, and introduces a novel approach based on convolutional filtering and neural networks with optimized early-stopping strategies in order to control overfitting. Despite the absence of training datasets, the proposed unsupervised framework achieves robust denoising and high-fidelity reconstruction of beam emittance images under low signal-to-noise conditions. The method extends measurable amplitudes beyond seven standard deviations, enabling unprecedented halo resolution.

📄 PDF Abstract BibTeX arXiv:2603.06689

Code (0)

등록된 구현이 없습니다.

Tasks

Image Reconstruction

Similar Papers 제목 키워드 기반

Unsupervised Low-dose CT Reconstruction with One-way Conditional Normalizing Flows

2024-10-23 · Ran An, Ke Chen, Hongwei Li

Deep-learning methods have shown promising performance for low-dose computed tomography (LDCT) reconstruction. However, supervised methods face the problem of lacking labeled data in clinical scenarios, and the CNN-based…

CT ReconstructionDenoising

Residual Contrastive Learning for Image Reconstruction: Learning Transferable Representations from Noisy Images

2021-06-18 · Nanqing Dong, Matteo Maggioni, Yongxin Yang, Eduardo Pérez-Pellitero 외

This paper is concerned with contrastive learning (CL) for low-level image restoration and enhancement tasks. We propose a new label-efficient learning paradigm based on residuals, residual contrastive learning (RCL), an…

Contrastive LearningDemosaickingDenoisingImage Reconstruction+5

LRIP-Net: Low-Resolution Image Prior based Network for Limited-Angle CT Reconstruction

2022-07-30 · Qifeng Gao, Rui Ding, Linyuan Wang, Bin Xue 외

In the practical applications of computed tomography imaging, the projection data may be acquired within a limited-angle range and corrupted by noises due to the limitation of scanning conditions. The noisy incomplete pr…

CT Reconstruction

MR-EIT: Multi-Resolution Reconstruction for Electrical Impedance Tomography via Data-Driven and Unsupervised Dual-Mode Neural Networks

2025-03-02 · Fangming Shi, Jinzhen Liu, Xiangqian Meng, Yapeng Zhou 외

This paper presents a multi-resolution reconstruction method for Electrical Impedance Tomography (EIT), referred to as MR-EIT, which is capable of operating in both supervised and unsupervised learning modes. MR-EIT inte…

Image ReconstructionSSIMSuper-Resolution

Unsupervised Deep Image Stitching: Reconstructing Stitched Features to Images

2021-06-24 · Lang Nie, Chunyu Lin, Kang Liao, Shuaicheng Liu 외

Traditional feature-based image stitching technologies rely heavily on feature detection quality, often failing to stitch images with few features or low resolution. The learning-based image stitching solutions are rarel…

Image ReconstructionImage Stitching