Skip to content

Code accompanying paper titled "Algorithmic Guarantees for Inverse Imaging with Untrained Network Priors"

Notifications You must be signed in to change notification settings

wszc-2021/invimaging-deeppriors

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Code accompanying paper G. Jagatap and C. Hegde, "Algorithmic Guarantees for Inverse Imaging with Untrained Network Priors", Advances in Neural Information Processing Systems (NeurIPS), 2019.

For details please refer to the preprint available at: https://arxiv.org/abs/1906.08763

Run the python notebook compressive_imaging.ipynb. The code works in 3 modes:

  • Mode 1: model fitting. Find the best network weights w that approximate image x as G(w,z), with fixed code z. Solves the obective function min_w || x - G(w,z) ||2^2. Can also be used for denoising type applications such as super-resolution, inpainting, denoising.
  • Mode 2: inverting linear compressive measurements. Reconstruct an image x from linear compressive measurements y=Ax. Solves the objective function min_x ||y - Ax||2^2 such that x = G(w,z).
  • Mode 3: inverting magnitude-only compressive measurements. Reconstruct an image x from magnitude-only compressive measurements y=|Ax|. Solves the objective function min_x ||y - |Ax|||2^2 such that x = G(w,z).

Datasets used: MNIST and CelebA

The untrained generative network G(w,z) can assume a decoder architecture (set decodetype='decoder')described in "Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks", ICLR 2019, https://arxiv.org/abs/1810.03982; or can also assume a DCGAN architecture (set decodetype='transposeconv').

About

Code accompanying paper titled "Algorithmic Guarantees for Inverse Imaging with Untrained Network Priors"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 68.9%
  • Python 31.1%