Corpus ID: 58004741

Neumann Networks for Inverse Problems in Imaging

@article{Gilton2019NeumannNF,
  title={Neumann Networks for Inverse Problems in Imaging},
  author={Davis Gilton and Greg Ongie and R. Willett},
  journal={ArXiv},
  year={2019},
  volume={abs/1901.03707}
}
  • Davis Gilton, Greg Ongie, R. Willett
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
    • Many challenging image processing tasks can be described by an ill-posed linear inverse problem: deblurring, deconvolution, inpainting, compressed sensing, and superresolution all lie in this framework. Traditional inverse problem solvers minimize a cost function consisting of a data-fit term, which measures how well an image matches the observations, and a regularizer, which reflects prior knowledge and promotes images with desirable properties like smoothness. Recent advances in machine… CONTINUE READING
    View PDF on arXiv
    13 Citations
    Background Citations
    7
    Methods Citations
    6

    Supplemental Code

    Github Repo
    Via Papers with Code
    dgilton/neumann_networks_code
    Neumann Networks for Inverse Problems in Imaging
    8 Stars • 2 Forks
    Explore Further
    Discover more papers related to the topics discussed in this paper
    13 Citations
    Citation Type

    Citation Type

    Learning to Regularize Using Neumann Networks
    Learning to Solve Linear Inverse Problems in Imaging with Neumann Networks
    Learned Patch-Based Regularization for Inverse Problems in Imaging
    • Davis Gilton, Greg Ongie, R. Willett
    • Computer Science
    • 2019 IEEE 8th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)
    • 2019
    • 1
    Solving Inverse Problems by Joint Posterior Maximization with a VAE Prior
    • 2
    • PDF
    Deep learning architectures for nonlinear operator functions and nonlinear inverse problems
    • 2
    • PDF
    Deep Unrolled Network for Video Super-Resolution
    AHP-Net: adaptive-hyper-parameter deep learning based image reconstruction method for multilevel low-dose CT
    • PDF
    Solving inverse problems using data-driven models
    • 88
    • PDF
    Model-Based Deep Learning
    • 1
    • PDF
    Wide-band butterfly network: stable and efficient inversion via multi-frequency neural networks
    • PDF

    References

    SHOWING 1-10 OF 82 REFERENCES
    Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems
    • 145
    • PDF
    One Network to Solve Them All — Solving Linear Inverse Problems Using Deep Projection Models
    • 202
    • PDF
    Unrolled Optimization with Deep Priors
    • 87
    • PDF
    Neural Proximal Gradient Descent for Compressive Imaging
    • 60
    • PDF
    Learned D-AMP: Principled Neural Network based Compressive Image Recovery
    • 126
    • PDF
    MoDL: Model-Based Deep Learning Architecture for Inverse Problems
    • 216
    • Highly Influential
    • PDF
    Deep Convolutional Neural Network for Image Deconvolution
    • 555
    • PDF
    Learned Primal-Dual Reconstruction
    • 230
    • PDF
    Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
    • C. Ledig, L. Theis, +6 authors W. Shi
    • Computer Science, Mathematics
    • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2017
    • 4,264
    • PDF
    Learning Deep CNN Denoiser Prior for Image Restoration
    • 683
    • PDF