diff --git a/models/inpainting_lama/CMakeLists.txt b/models/inpainting_lama/CMakeLists.txt new file mode 100644 index 00000000..5eee867c --- /dev/null +++ b/models/inpainting_lama/CMakeLists.txt @@ -0,0 +1,11 @@ +cmake_minimum_required(VERSION 3.22.1) +project(opencv_zoo_inpainting_lama) + +set(OPENCV_VERSION "5.0.0") +set(OPENCV_INSTALLATION_PATH "" CACHE PATH "Where to look for OpenCV installation") + +# Find OpenCV +find_package(OpenCV ${OPENCV_VERSION} REQUIRED HINTS ${OPENCV_INSTALLATION_PATH}) + +add_executable(demo demo.cpp) +target_link_libraries(demo ${OpenCV_LIBS}) diff --git a/models/inpainting_lama/LICENSE b/models/inpainting_lama/LICENSE new file mode 100644 index 00000000..f542a480 --- /dev/null +++ b/models/inpainting_lama/LICENSE @@ -0,0 +1,201 @@ + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright [2021] Samsung Research + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. \ No newline at end of file diff --git a/models/inpainting_lama/README.md b/models/inpainting_lama/README.md new file mode 100644 index 00000000..4a5c0856 --- /dev/null +++ b/models/inpainting_lama/README.md @@ -0,0 +1,49 @@ +# Lama + +LaMa is a very lightweight yet powerful image inpainting model. + +Notes: + +- Model source: [ONNX](https://huggingface.co/Carve/LaMa-ONNX/blob/main/lama_fp32.onnx). + +## Requirements +Install latest OpenCV >=5.0.0 and CMake >= 3.22.1 to get started with. + +## Demo + +### Python + +Run the following command to try the demo: + +```shell +# usage +python demo.py --input /path/to/image + +# get help regarding various parameters +python demo.py --help +``` + +### C++ + +```shell +# A typical and default installation path of OpenCV is /usr/local +cmake -B build -D OPENCV_INSTALLATION_PATH=/path/to/opencv/installation . +cmake --build build + +# usage +./build/demo --input=/path/to/image +# get help messages +./build/demo -h +``` + +### Example outputs + +![chicky](./example_outputs/squirrel_output.jpg) + +## License + +All files in this directory are licensed under [Apache License](./LICENSE). + +## Reference + +- https://github.com/advimman/lama \ No newline at end of file diff --git a/models/inpainting_lama/demo.cpp b/models/inpainting_lama/demo.cpp new file mode 100644 index 00000000..303ee251 --- /dev/null +++ b/models/inpainting_lama/demo.cpp @@ -0,0 +1,174 @@ +/* +This sample inpaints the masked area in the given image. + +Copyright (C) 2025, Bigvision LLC. +*/ + +#include +#include + +#include +#include +#include + +using namespace cv; +using namespace dnn; +using namespace std; + +class Lama { +public: + Lama(const string& modelPath) { + loadModel(modelPath); + } + + // Function to set up the input image and process it + void process(const Mat& image, const Mat& mask, Mat& result) { + double aspectRatio = static_cast(image.rows) / static_cast(image.cols); + + Mat image_blob = blobFromImage(image, 1.0/255.0, Size(512, 512), Scalar(0, 0, 0), false, false, CV_32F); + Mat mask_blob = blobFromImage(mask, 1.0, Size(512, 512), Scalar(0), false, false); + + mask_blob = (mask_blob > 0); + mask_blob.convertTo(mask_blob, CV_32F); + mask_blob = mask_blob/255.0; + + net.setInput(image_blob, "image"); + net.setInput(mask_blob, "mask"); + + Mat output = net.forward(); + + postProcess(output, result, aspectRatio); + } +private: + Net net; + + // Load Model + void loadModel(const string modelPath) { + net = readNetFromONNX(modelPath); + net.setPreferableBackend(DNN_BACKEND_DEFAULT); + net.setPreferableTarget(DNN_TARGET_CPU); + } + + void postProcess(const Mat& output, Mat& result, double aspectRatio) { + Mat output_transposed(3, &output.size[1], CV_32F, const_cast(reinterpret_cast(output.ptr()))); + + vector channels; + for (int i = 0; i < 3; ++i) { + channels.push_back(Mat(output_transposed.size[1], output_transposed.size[2], CV_32F, + output_transposed.ptr(i))); + } + merge(channels, result); + result.convertTo(result, CV_8U); + + int h = static_cast(512 * aspectRatio); + resize(result, result, Size(512, h)); + } +}; + + +const string about = "This sample demonstrates image inpainting with lama inpainting technique.\n\n"; + +const string keys = + "{help h | | show help message}" + "{input i | | Path to input image}" + "{ model | inpainting_lama_2024jan.onnx | Path to the lama onnx model file }"; + +bool drawing = false; +Mat maskGray; +int brush_size = 25; + +static void drawMask(int event, int x, int y, int, void*) { + if (event == EVENT_LBUTTONDOWN) { + drawing = true; + } else if (event == EVENT_MOUSEMOVE) { + if (drawing) { + circle(maskGray, Point(x, y), brush_size, Scalar(255), -1); + } + } else if (event == EVENT_LBUTTONUP) { + drawing = false; + } +} + +int main(int argc, char **argv) +{ + CommandLineParser parser(argc, argv, keys); + + if (parser.has("help")) + { + cout<("model"); + + int height = 512; + int width = 512; + int stdSize = 20; + int stdWeight = 400; + int stdImgSize = 512; + int imgWidth = -1; // Initialization + int fontSize = 50; + int fontWeight = 500; + + FontFace fontFace("sans"); + Lama lama(model); + + Mat image = imread(parser.get("input")); + if (image.empty()) { + cerr << "Error: Input image could not be loaded." << endl; + return -1; + } + + imgWidth = min(image.rows, image.cols); + fontSize = min(fontSize, (stdSize*imgWidth)/stdImgSize); + fontWeight = min(fontWeight, (stdWeight*imgWidth)/stdImgSize); + + maskGray = Mat::zeros(image.size(), CV_8U); + + namedWindow("Draw Mask"); + setMouseCallback("Draw Mask", drawMask); + + const string label = "Draw the mask on the image. Press space bar when done "; + + for(;;) { + Mat displayImage = image.clone(); + Mat overlay = image.clone(); + + double alpha = 0.5; + Rect r = getTextSize(Size(), label, Point(), fontFace, fontSize, fontWeight); + r.height += 2 * fontSize; // padding + r.width += 10; // padding + rectangle(overlay, r, Scalar::all(255), FILLED); + addWeighted(overlay, alpha, displayImage, 1 - alpha, 0, displayImage); + putText(displayImage, label, Point(10, fontSize), Scalar(0,0,0), fontFace, fontSize, fontWeight); + putText(displayImage, "Press 'i' to increase and 'd' to decrease brush size", Point(10, 2*fontSize), Scalar(0,0,0), fontFace, fontSize, fontWeight); + + displayImage.setTo(Scalar(255, 255, 255), maskGray > 0); // Highlight mask area + imshow("Draw Mask", displayImage); + + char key = waitKey(1); + if (key == 'i') { + brush_size += 1; + cout << "Brush size increased to " << brush_size << endl; + } else if (key == 'd') { + brush_size = max(1, brush_size - 1); + cout << "Brush size decreased to " << brush_size << endl; + } else if (key == ' ') { + break; + } else if (key == 27){ + return -1; + } + } + destroyAllWindows(); + + Mat result; + lama.process(image, maskGray, result); + + imshow("Inpainted Output", result); + waitKey(0); + + return 0; +} diff --git a/models/inpainting_lama/demo.py b/models/inpainting_lama/demo.py new file mode 100644 index 00000000..82576abd --- /dev/null +++ b/models/inpainting_lama/demo.py @@ -0,0 +1,87 @@ +import cv2 as cv +import numpy as np +import argparse +from lama import Lama + +def get_args_parser(func_args): + parser = argparse.ArgumentParser(add_help=False) + parser.add_argument('--input', help='Path to input image', default=0, required=False) + parser.add_argument('--model', help='Path to lama onnx', default='inpainting_lama_2025jan.onnx', required=False) + + parser = argparse.ArgumentParser(parents=[parser], + description='', formatter_class=argparse.RawTextHelpFormatter) + return parser.parse_args(func_args) + +drawing = False +mask_gray = None +brush_size = 15 + +def draw_mask(event, x, y, flags, param): + global drawing, mask_gray, brush_size + if event == cv.EVENT_LBUTTONDOWN: + drawing = True + elif event == cv.EVENT_MOUSEMOVE: + if drawing: + cv.circle(mask_gray, (x, y), brush_size, (255), thickness=-1) + elif event == cv.EVENT_LBUTTONUP: + drawing = False + +def main(func_args=None): + global mask_gray, brush_size + args = get_args_parser(func_args) + + lama = Lama(modelPath=args.model) + input_image = cv.imread(args.input) + mask_gray = np.zeros((input_image.shape[0], input_image.shape[1]), dtype=np.uint8) + + stdSize = 0.6 + stdWeight = 2 + stdImgSize = 512 + imgWidth = min(input_image.shape[:2]) + fontSize = min(1.5, (stdSize*imgWidth)/stdImgSize) + fontThickness = max(1,(stdWeight*imgWidth)//stdImgSize) + + cv.namedWindow("Draw Mask") + cv.setMouseCallback("Draw Mask", draw_mask) + + label = "Draw the mask on the image. Press space bar when done." + labelSize, _ = cv.getTextSize(label, cv.FONT_HERSHEY_SIMPLEX, fontSize, fontThickness) + while True: + display_image = input_image.copy() + overlay = input_image.copy() + + alpha = 0.5 + cv.rectangle(overlay, (0, 0), (labelSize[0]+10, labelSize[1]+int(30*fontSize)), (255, 255, 255), cv.FILLED) + cv.addWeighted(overlay, alpha, display_image, 1 - alpha, 0, display_image) + + cv.putText(display_image, label, (10, int(25*fontSize)), cv.FONT_HERSHEY_SIMPLEX, fontSize, (0, 0, 0), fontThickness) + cv.putText(display_image, "Press 'i' to increase and 'd' to decrease brush size.", (10, int(50*fontSize)), cv.FONT_HERSHEY_SIMPLEX, fontSize, (0, 0, 0), fontThickness) + display_image[mask_gray > 0] = [255, 255, 255] + cv.imshow("Draw Mask", display_image) + + key = cv.waitKey(1) & 0xFF + if key == ord('i'): # Increase brush size + brush_size += 1 + print(f"Brush size increased to {brush_size}") + elif key == ord('d'): # Decrease brush size + brush_size = max(1, brush_size - 1) + print(f"Brush size decreased to {brush_size}") + elif key == ord(' '): # Press space bar to finish drawing + break + elif key == 27: + exit() + cv.destroyAllWindows() + + tm = cv.TickMeter() + tm.start() + result = lama.infer(input_image, mask_gray) + tm.stop() + label = 'Inference time: {:.2f} ms'.format(tm.getTimeMilli()) + cv.putText(result, label, (0, 15), cv.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 0)) + + cv.imshow("Inpainted Output", result) + cv.waitKey(0) + cv.destroyAllWindows() + +if __name__ == '__main__': + main() diff --git a/models/inpainting_lama/example_outputs/squirrel.jpg b/models/inpainting_lama/example_outputs/squirrel.jpg new file mode 100644 index 00000000..0a3909e3 --- /dev/null +++ b/models/inpainting_lama/example_outputs/squirrel.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20bb6e8ae96918a36c9886b6d48e54eedeb3948591e1485c206bc1dc60c8dc8b +size 62311 diff --git a/models/inpainting_lama/example_outputs/squirrel_output.jpg b/models/inpainting_lama/example_outputs/squirrel_output.jpg new file mode 100644 index 00000000..982f019e --- /dev/null +++ b/models/inpainting_lama/example_outputs/squirrel_output.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaa765b3ef286f8de34efc7302e49b078d720c3eb6adf79ee8a2df73f3889f52 +size 63086 diff --git a/models/inpainting_lama/inpainting_lama_2025jan.onnx b/models/inpainting_lama/inpainting_lama_2025jan.onnx new file mode 100644 index 00000000..425f3a0e --- /dev/null +++ b/models/inpainting_lama/inpainting_lama_2025jan.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7df918ac3921d3daf0aae1d219776cf0dc4e4935f035af81841b40adcf74fdf2 +size 92591623 diff --git a/models/inpainting_lama/lama.py b/models/inpainting_lama/lama.py new file mode 100644 index 00000000..c242ef0c --- /dev/null +++ b/models/inpainting_lama/lama.py @@ -0,0 +1,43 @@ +import cv2 as cv +import numpy as np + +class Lama: + def __init__(self, modelPath='inpainting_lama_2025jan.onnx', backendId=0, targetId=0): + self._modelPath = modelPath + self._backendId = backendId + self._targetId = targetId + + # Load the model + self._model = cv.dnn.readNetFromONNX(self._modelPath) + self.setBackendAndTarget(self._backendId, self._targetId) + + @property + def name(self): + return self.__class__.__name__ + + def setBackendAndTarget(self, backendId, targetId): + self._backendId = backendId + self._targetId = targetId + self._model.setPreferableBackend(self._backendId) + self._model.setPreferableTarget(self._targetId) + + def infer(self, image, mask): + image_blob = cv.dnn.blobFromImage(image, 0.00392, (512, 512), (0,0,0), False, False) + mask_blob = cv.dnn.blobFromImage(mask, scalefactor=1.0, size=(512, 512), mean=(0,), swapRB=False, crop=False) + mask_blob = (mask_blob > 0).astype(np.float32) + + self._model.setInput(image_blob, "image") + self._model.setInput(mask_blob, "mask") + + output = self._model.forward() + + # Postprocessing + aspect_ratio = image.shape[0]/image.shape[1] + result = output[0] + result = np.transpose(result, (1, 2, 0)) + result = (result).astype(np.uint8) + width = result.shape[1] + height = int(width*aspect_ratio) + result = cv.resize(result, (width, height)) + + return result