• Corpus ID: 247084167

A Note on Machine Learning Approach for Computational Imaging

@article{Dong2022ANO,
  title={A Note on Machine Learning Approach for Computational Imaging},
  author={Bin Dong},
  journal={ArXiv},
  year={2022},
  volume={abs/2202.11883}
}
  • Bin Dong
  • Published 24 February 2022
  • Computer Science
  • ArXiv
Computational imaging has been playing a vital role in the development of natural sciences. Advances in sensory, information, and computer technologies have further extended the scope of influence of imaging, making digital images an essential component of our daily lives. For the past three decades, we have witnessed phenomenal developments of mathematical and machine learning methods in computational imaging. In this note, we will review some of the recent developments of the machine learning… 

References

SHOWING 1-10 OF 86 REFERENCES

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

On learning optimized reaction diffusion processes for effective image restoration

This work extends conventional nonlinear reaction diffusion models by several parametrized linear filters as well as several parametsrized influence functions, and proposes to train the parameters of the filters and the influence functions through a loss based approach.

Image reconstruction by domain-transform manifold learning

A unified framework for image reconstruction—automated transform by manifold approximation (AUTOMAP)—which recasts image reconstruction as a data-driven supervised learning task that allows a mapping between the sensor and the image domain to emerge from an appropriate corpus of training data is presented.

Active MR k-space Sampling with Reinforcement Learning

This paper focuses on learning acquisition trajectories given a fixed image reconstruction model and forms the problem as a sequential decision process and proposes the use of reinforcement learning to solve it.

Deep Image Prior

It is shown that a randomly-initialized neural network can be used as a handcrafted prior with excellent results in standard inverse problems such as denoising, super-resolution, and inpainting.

Deep Unfolded Robust PCA with Application to Clutter Suppression in Ultrasound

A new approach to clutter removal based on robust principle component analysis (PCA) and deep learning is proposed and an iterative algorithm based on this model exhibits improved separation of microbubble signal from the tissue signal over commonly practiced methods.

Algorithmic Guarantees for Inverse Imaging with Untrained Network Priors

It is shown both theoretically as well as empirically that with deep network priors, one can achieve better compression rates for the same image quality compared to hand crafted priors.

Brain Segmentation from k-Space with End-to-End Recurrent Attention Network

A novel learning framework that performs magnetic resonance brain image segmentation directly from k-space data and introduces a novel workflow to generate labeled training data for segmentation by exploiting imaging modality simulators and digital phantoms to address the challenge of manual labeling.

Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing

The increasing popularity of unrolled deep networks is due, in part, to their potential in developing efficient, high-performance (yet interpretable) network architectures from reasonably sized training sets.

Learning to Scan: A Deep Reinforcement Learning Approach for Personalized Scanning in CT Imaging

This paper proposes to use Reinforcement Learning (RL) to learn a personalized scanning policy to select the angles and the dose at each chosen angle for each individual subject in CT scanning, and shows strong generalization to be combined with different reconstruction algorithms.
...