Add SRGAN and RDN Models to dnn_superres Module #3907
Closed
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
Update dnn_superres.hpp to include new SRGAN and RDN models in API documentation and constants
Implement processing logic for SRGAN and RDN super-resolution models
Add documentation, references and citation information for new models
New sample application demonstrating the use of SRGAN and RDN models
Add comprehensive test functions for SRGAN and RDN models: - Add basic model loading and API tests - Add SRGAN_x4 model tests - Add RDN_x3 model tests - Add parameter validation tests - Add different input size and channel tests - Enhance test coverage for the new models
Extend Python API tests to include SRGAN and RDN models: - Add test_srgan() function for SRGAN_x4 model testing - Add test_rdn() function for RDN_x3 model testing - Verify model loading, scale setting, and upsampling - Test input/output dimensions and model properties - Complete test coverage for Python API integration
Add build configuration for models demo application
- Fixed header guard structure (#ifndef, #define, #endif) - Corrected comment formatting in constructor documentation - Cleaned up class member organization and spacing - Ensured proper namespace closure
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
Add SRGAN and RDN Models to dnn_superres Module
This PR adds two new super-resolution models to OpenCV's dnn_superres module:
Changes
dnn_superres.hpp: Added new model types and documentation to the APIdnn_superres.cpp: Added processing support for SRGAN and RDN models in the upsample functionREADME.md: Added information, academic references, and documentation for the new modelstest_dnn_superres.cpp: Added new tests for SRGAN and RDN modelstest_dnn_superres.py: Added tests for the Python APIdnn_superres_srgan_rdn_demo.cpp: Added a sample application demonstrating the new modelsCMakeLists.txt: Added the new sample application to the buildTest Results
Model Files
This PR includes only code changes, not model files. During testing and development, existing OpenCV model files were used to verify API integration.
Trained model files for SRGAN and RDN can be obtained from these sources:
Academic References
Patent Review
The added models are derived from academic papers and, to our knowledge, have no patent restrictions.