Liu-Jia Padding #934
Draft
Liu-Jia Padding #934
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #934 +/- ##
==========================================
- Coverage 84.81% 84.44% -0.38%
==========================================
Files 208 208
Lines 21352 21588 +236
Branches 2878 2931 +53
==========================================
+ Hits 18110 18229 +119
- Misses 2347 2429 +82
- Partials 895 930 +35 ☔ View full report in Codecov by Sentry. |
Contributor
|
Hi @jscanvic is this ready for review ? Do you need any help for the last TODOs ? 😄 |
Collaborator
Author
|
Almost I'll wrap it up shortly but thanks for offering your help! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Towards #898
Liu-Jia padding reduces ringing artefacts introduced by spectral deconvolution methods that generally assume a periodic blur model that is unsuitable for real-world deblurring where opposite edges are decorrelated.
TODO
deepinv.utils.liu_jia_padSimple experiment
I blur a 256x256 RGB image using a Gaussian filter with a standard deviation of 1px and compare the effect of using no padding vs using Liu-Jia padding before using one of two deconvolution method (simple inverse filtering and Wiener deconvolution). We see that Liu-Jia padding prevents the ringing artifacts in Wiener deconvolution.
Inverse filtering
Wiener deconvolution
