Add learning-based super-resolution module: final phase #2231
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
Adds the module plus loading classes for SR data Complete with docs, tutorials and tests.
alalek
reviewed
Sep 29, 2019
There was a problem hiding this comment.
@Saafke @fannymonori Please take a look on merged changes from #2229
| When building OpenCV, run the following command to build the 'dnn_superres' module: | ||
|
|
||
| ```make | ||
| cmake -DOPENCV_EXTRA_MODULES_PATH=<opencv_contrib>/modules -Dopencv_dnn_superres=ON <opencv_source_dir> |
There was a problem hiding this comment.
-Dopencv_dnn_superres=ON
There is no such option.
There are similar BUILD_ options, but adding them here is redundant (=ON be default).
It is better to mention -DBUILD_EXAMPLES=ON here and in other tutorials (=OFF be default).
3 tasks
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Outdated suggestions cannot be applied.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.
Merge with extra: opencv/opencv_extra#664
'Learning-based Super Resolution' project for Google Summer of Code 2019 by Xavier Weber.
This pull request completes my project and also includes all the code from my previous two PR's (#2164 and #2200). Part of this code is implemented by Fanny Monori who worked on the same project (it was hard to split the code between two PR's perfectly without problems).
This pullrequest changes
This module provides an interface so that users can easily upscale images via neural networks. Four trained models are supported. I implemented EDSR and FSRCNN. Fanny Monori implemented ESPCN and LapSRN.
This PR is closely related to Fanny's PR (#2229) who provides the same basic functionality but with other additions.