Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Improve the denoise quality from hard thresholding #5

Merged
merged 10 commits into from
May 15, 2024
Merged

Conversation

KedoKudo
Copy link
Contributor

This PR introduces the following changes:

  • patch in a block is now ordered based on similarity instead of the naive search order
  • the missing threshold calculator is now added back in the hard thresholding function
  • the example notebook is updated
  • the second step, re-filtering is temporarily disabled as we need more time to understand how to properly compute the sigma for wiener_hadamard filter.

Example output from notebook (assuming 2% detector gain error):
bm3d_vs_bm3dornl_sino

Testing instructions

  • Create and activate the conda environment
  • Checkout the feature branch
  • Run unit test
  • Run the example notebook

EWM item: 5223

@KedoKudo KedoKudo self-assigned this May 15, 2024
@KedoKudo KedoKudo requested a review from jmborr May 15, 2024 14:42
Copy link

@jmborr jmborr left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I was able to run the notebook. Understanding the changes to the algorithms are currently above my pay grade 😊

@KedoKudo KedoKudo merged commit e5aa97d into next May 15, 2024
2 checks passed
@KedoKudo KedoKudo deleted the local_sigma branch May 15, 2024 18:54
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants