Robustness of data-driven approaches in limited angle tomography

Yiran Wang, Yimin Zhong
3/17/2024
math.NAcs.LG

No official code found. Best implementation: lowrank/robustness-limited-angle-tomography (0 stars, MIT, last commit 2024-10-14).

Abstract

The limited angle Radon transform is notoriously difficult to invert due to its ill-posedness. In this work, we give a mathematical explanation that data-driven approaches can stably reconstruct more information compared to traditional methods like filtered backprojection. In addition, we use experiments based on the U-Net neural network to validate our theory.

View on arXivView PDF

Code Implementations(1)

lowrank/robustness-limited-angle-tomographyCommunity100%
MIT

code for limited angle tomography with vanilla U-net structure

00Jupyter NotebookJul 5, 20242 years agoMIT

Similar Papers

The method of the approximate inverse for limited-angle CT

82% match2025

Limited-Angle Tomography Reconstruction via Deep End-To-End Learning on Synthetic Data

82% match1 repo42023

Stretched sinograms for limited-angle tomographic reconstruction with neural networks

81% match2023

Revisiting ΨDONet: microlocally inspired filters for incomplete-data tomographic reconstructions

78% match2025

TomoSelfDEQ: Self-Supervised Deep Equilibrium Learning for Sparse-Angle CT Reconstruction

77% match1 repo42025

Low-resolution Prior Equilibrium Network for CT Reconstruction

77% match2024

Cite this paper

@article{wang2024robustness,
  title  = {Robustness of data-driven approaches in limited angle tomography},
  author = {Yiran Wang and Yimin Zhong},
  year   = {2024},
  eprint = {2403.11350},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2403.11350v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2403.11350.svg)](https://codeofpaper.com/paper/2403.11350)

Discussion