optimize(dnn): parallelize Slice layer implementation (4.x) #28511
### Summary
Backport of PR #28447 to 4.x branch.
### Description
This PR optimizes the SliceLayer implementation for strided inputs (where step > 1). The original implementation used a recursive element-wise copy (getSliceRecursive) for any strided slice, which was extremely inefficient.
This PR introduces:
- **Parallelization**: Uses `cv::parallel_for_` to parallelize the outermost dimension of the slice operation.
- **Memcpy Optimization**: Automatically detects "pseudo-contiguous" blocks in strided slices (e.g., slicing an outer dimension but keeping inner dimensions intact) and uses `std::memcpy` instead of scalar loops.
- **Refactoring**: Replaces the recursive function with a dedicated `ParallelSlice` loop body.
### Impact
Significant performance improvement for strided slice operations (common in detection heads, strided sampling, etc.).
### Benchmark Results
Tested on CPU with 20 threads.
| Test Case | Baseline (ms) | Optimized (ms) | Speedup |
| :--- | :--- | :--- | :--- |
| Strided Axis 0 [::2, ...] | 1.10 | 0.02 | **~55x** |
| Strided Axis 2 [..., ::2] | 1.15 | 0.11 | **~10.5x** |
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
- [ ] The feature is well documented and sample code can be built with the project CMake
dnn: improve robustness of MVN layer#28308
This change adds small defensive improvements to the MVN layer implementation:
->Guard against zero-sized OpenCL kernel launches
->Add input validation in finalize()
->Use int64 for FLOPS computation to avoid overflow
No functional or performance changes are intended.
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
The TopK layer was incorrectly rejecting K values equal to the input
dimension size. According to ONNX specification, K should be allowed
to equal the dimension size (to retrieve all elements).
Changed validation from 'K < input_shape[axis]' to 'K <= input_shape[axis]'
This fixes the error when loading YOLOv10 ONNX models that use TopK
with K equal to the dimension size.
Fixes#28445
docs: fix spelling errors in documentation and code #28301
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
- [ ] The feature is well documented and sample code can be built with the project CMake
### Description
Fixed multiple spelling errors across documentation, comments, and code:
- 'colummn' → 'column' (cublas.hpp, 3 occurrences)
- 'points_per_colum' → 'points_per_column' (calib3d.hpp, 3 occurrences)
- 'Asignee' → 'Assignee' (sift files, 2 occurrences)
- 'compability' → 'compatibility' (face.hpp, 2 occurrences)
- 'orignal' → 'original' (aruco_detector.cpp)
- 'refrence' → 'reference' (chessboard.cpp)
- 'indeces' → 'indices' (stitching.hpp)
- 'OutputPrecison' → 'OutputPrecision' (test)
- 'tranform' → 'transform' (slice_layer.cpp, 3 occurrences)
Total: 24 fixes across 14 files. Documentation and comment changes only, no functional impact.
Added randomNormalLike layer to 4.x branch #28164
OpenCV Extra: https://github.com/opencv/opencv_extra/pull/1297
Backport of https://github.com/opencv/opencv/pull/28110 to 4.x
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
dnn(tflite): add support for MAXIMUM layer #28171Fixes#26433
This PR adds support for the `MAXIMUM` layer in the TFLite importer.
It maps the TFLite `MAXIMUM` opcode to the existing OpenCV Element-wise `Max` operation.
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
Enable KleidiCV on Linux and Mac Mx by default #27640
OpenCV Extra: https://github.com/opencv/opencv_extra/pull/1296
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [ ] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
resolves https://github.com/opencv/opencv/issues/27580
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
dnn: added neon intrinsics implementation of fastGEMM1T function #27785
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [X] The PR is proposed to the proper branch
- This PR improves the performance of the LSTM function on ARM64 targets.
- Added a NEON intrinsics implementation of the fastGEMM1T function and enabled its use in fully connected and recurrent layers file.
- As a result, ARM64 now benefits from vectorized matrix–vector multiplications, leading to measurable performance improvements in the LSTM layer.
- This change is limited to ARM64 and does not affect other architectures.
**Performance impact:**
- The optimization significantly improves the performance of lstm functions on ARM64 targets.
<img width="930" height="313" alt="image" src="https://github.com/user-attachments/assets/92e251cd-dc6c-4cda-9586-acc19bf16dfd" />
dnn: improve performance of softmax_3d with loop unrolling #27777
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- This PR applies loop unrolling in the softmax function.
- The change does not affect functional correctness.
**Performance Improvements**
- The optimization significantly improves the performance of softmax_3d on Windows ARM64 targets.
<img width="703" height="203" alt="image" src="https://github.com/user-attachments/assets/85997c15-f543-432c-95e5-69099d71fe71" />
dnn: Tune CONV_NR_FP32 size for WASM #27773
We can see ~20% inference time reduction on local benchmark.
The local benchmark includes face detection with res10_300x300_ssd_iter_140000_fp16.caffemodel and image classification with squeezenet.onnx .
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [ ] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
- Added vector_MatShape and vector_vector_MatShape to gen_dict.json
- Implemented MatShape_to_vector_MatShape, vector_MatShape_to_MatShape, MatShape_to_vector_vector_MatShape, and vector_vector_MatShape_to_MatShape conversion functions in dnn_converters.h/cpp and Converters.java
- Added testGetLayersShapes test to verify List<List<MatShape>> conversion
- Added vector_vector_Mat to gen_dict.json
- Implemented Mat_to_vector_vector_Mat and vector_vector_Mat_to_Mat conversion functions in converters.h/cpp and Converters.java
- Added DnnForwardAndRetrieve.java test to verify List<List<Mat>> conversion : Reference: C++ test in modules/dnn/test/test_misc.cpp - TEST(Net, forwardAndRetrieve)
Close https://github.com/opencv/opencv/issues/27413
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
Hanbin Bae
Alexander Smorkalov
Karnav Shah
Sikandar
Murat Raimbekov
Adrian Kretz
Vincent Rabaud
Alexander Smorkalov
Abhishek Gola
ramukhsuya
ramukhsuya
nishith-fujitsu
Dmitry Kurtaev
harunresit
satyam yadav
cudawarped
pratham-mcw
Jie Pan
Kavyansh Tyagi
Fanchen Kong
utibenkei
fengyuentau
Kumataro