mlsanityData to 14 Oct 2026

An Adversarial Learning Based Approach for Unknown View Tomographic Reconstruction

arXiv 2108.09873 ↗First posted 23 Aug 2021eess.IV cs.LG eess.SPcited by 0

Not on the map. Why?

Abstract (arXiv)

The goal of 2D tomographic reconstruction is to recover an image given its projections from various views. It is often presumed that projection angles associated with the projections are known in advance. Under certain situations, however, these angles are known only approximately or are completely unknown. It becomes more challenging to reconstruct the image from a collection of random projections. We propose an adversarial learning based approach to recover the image and the projection angle distribution by matching the empirical distribution of the measurements with the generated data. Fitting the distributions is achieved through solving a min-max game between a generator and a critic based on Wasserstein generative adversarial network structure. To accommodate the update of the projection angle distribution through gradient back propagation, we approximate the loss using the Gumbel-Softmax reparameterization of samples from discrete distributions. Our theoretical analysis verifies the unique recovery of the image and the projection distribution up to a rotation and reflection upon convergence. Our extensive numerical experiments showcase the potential of our method to accurately recover the image and the projection angle distribution under noise contamination.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 65 references that are in the map. First posted on arXiv 23 Aug 2021.

Builds on

23 of 65 references.

References · 23

  1. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  2. 2017Improved Training of Wasserstein GANscited by 2,235
  3. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  4. 2017Deep Image Priorcited by 1,098
  5. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 519
  6. 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 433
  7. 2017Learned Primal-dual Reconstructioncited by 251
  8. 2017Image reconstruction by domain transform manifold learningcited by 232
  9. 2017Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)cited by 224
  10. 2017Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Losscited by 162
  11. 2017Solving ill-posed inverse problems using iterative deep neural networkscited by 145
  12. 2017Framing U-Net via Deep Convolutional Framelets: Application to Sparse-view CTcited by 88
11 more
  1. 2017Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Losscited by 82
  2. 2020Computed Tomography Reconstruction Using Deep Image Prior and Learned Reconstruction Methodscited by 56
  3. 2018Can Deep Learning Outperform Modern Commercial CT Image Reconstruction Methods?cited by 54
  4. 2014Fast Steerable Principal Component Analysiscited by 12
  5. 20173D ab initio modeling in cryo-EM by autocorrelation analysiscited by 4
  6. 2018Geometric Invariants for Sparse Unknown View Tomographycited by 4
  7. 20203D unknown view tomography via rotation invariantscited by 4
  8. 2013A Fourier-based Approach for Iterative 3D Reconstruction from Cryo-EM Imagescited by 2
  9. 2019Two-Dimensional Tomography From Noisy Projection Tilt Series Taken At Unknown View Angles With Non-Uniform Distributioncited by 1
  10. 2021UVTomo-GAN: An adversarial learning based approach for unknown view X-ray tomographic reconstructioncited by 1
  11. 2021MSR-GAN: Multi-Segment Reconstruction via Adversarial Learningcited by 1

Built on by

Not cited yet.