mirror of
https://github.com/opencv/opencv.git
synced 2026-07-21 19:33:03 +04:00
Merge pull request #27349 from abhishek-gola:deblurring_onnx_sample
Added DNN based deblurring samples #27349 Corresponding pull request adding quantized onnx model to opencv_zoo: https://github.com/opencv/opencv_zoo/pull/295 Model size: 88MB ### 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
This commit is contained in:
Abhishek Gola
GitHub
@@ -0,0 +1,136 @@
|
||||
/*
|
||||
This file is part of OpenCV project.
|
||||
It is subject to the license terms in the LICENSE file found in the top-level directory
|
||||
of this distribution and at http://opencv.org/license.html.
|
||||
|
||||
This sample deblurs the given blurry image.
|
||||
|
||||
Copyright (C) 2025, Bigvision LLC.
|
||||
|
||||
How to use:
|
||||
Sample command to run:
|
||||
`./example_dnn_deblurring`
|
||||
|
||||
You can download NAFNet deblurring model using
|
||||
`python download_models.py NAFNet`
|
||||
|
||||
References:
|
||||
Github: https://github.com/megvii-research/NAFNet
|
||||
PyTorch model: https://drive.google.com/file/d/14D4V4raNYIOhETfcuuLI3bGLB-OYIv6X/view
|
||||
|
||||
PyTorch model was converted to ONNX and then ONNX model was further quantized using block quantization from [opencv_zoo](https://github.com/opencv/opencv_zoo/blob/main/tools/quantize/block_quantize.py)
|
||||
|
||||
Set environment variable OPENCV_DOWNLOAD_CACHE_DIR to point to the directory where models are downloaded. Also, point OPENCV_SAMPLES_DATA_PATH to opencv/samples/data.
|
||||
*/
|
||||
|
||||
#include <iostream>
|
||||
#include <fstream>
|
||||
|
||||
#include <opencv2/imgproc.hpp>
|
||||
#include <opencv2/highgui.hpp>
|
||||
#include <opencv2/dnn.hpp>
|
||||
|
||||
#include "common.hpp"
|
||||
|
||||
using namespace cv;
|
||||
using namespace dnn;
|
||||
using namespace std;
|
||||
|
||||
const string about = "Use this script for image deblurring using OpenCV. \n\n"
|
||||
"Firstly, download required models i.e. NAFNet using `download_models.py` (if not already done). Set environment variable OPENCV_DOWNLOAD_CACHE_DIR to point to the directory where models are downloaded. Also, point OPENCV_SAMPLES_DATA_PATH to opencv/samples/data.\n"
|
||||
"To run:\n"
|
||||
"\t Example: ./example_dnn_deblurring [--input=<image_name>] \n\n"
|
||||
"Deblurring model path can also be specified using --model argument.\n\n";
|
||||
|
||||
const string param_keys =
|
||||
"{ help h | | show help message}"
|
||||
"{ @alias | NAFNet | An alias name of model to extract preprocessing parameters from models.yml file. }"
|
||||
"{ zoo | ../dnn/models.yml | An optional path to file with preprocessing parameters }"
|
||||
"{ input i | licenseplate_motion.jpg | image file path}";
|
||||
|
||||
const string backend_keys = format(
|
||||
"{ backend | default | Choose one of computation backends: "
|
||||
"default: automatically (by default), "
|
||||
"openvino: Intel's Deep Learning Inference Engine (https://software.intel.com/openvino-toolkit), "
|
||||
"opencv: OpenCV implementation, "
|
||||
"vkcom: VKCOM, "
|
||||
"cuda: CUDA, "
|
||||
"webnn: WebNN }");
|
||||
|
||||
const string target_keys = format(
|
||||
"{ target | cpu | Choose one of target computation devices: "
|
||||
"cpu: CPU target (by default), "
|
||||
"opencl: OpenCL, "
|
||||
"opencl_fp16: OpenCL fp16 (half-float precision), "
|
||||
"vpu: VPU, "
|
||||
"vulkan: Vulkan, "
|
||||
"cuda: CUDA, "
|
||||
"cuda_fp16: CUDA fp16 (half-float preprocess) }");
|
||||
|
||||
string keys = param_keys + backend_keys + target_keys;
|
||||
|
||||
|
||||
int main(int argc, char **argv)
|
||||
{
|
||||
CommandLineParser parser(argc, argv, keys);
|
||||
|
||||
if (!parser.has("@alias") || parser.has("help"))
|
||||
{
|
||||
cout<<about<<endl;
|
||||
parser.printMessage();
|
||||
return 0;
|
||||
}
|
||||
string modelName = parser.get<String>("@alias");
|
||||
string zooFile = findFile(parser.get<String>("zoo"));
|
||||
keys += genPreprocArguments(modelName, zooFile);
|
||||
parser = CommandLineParser(argc, argv, keys);
|
||||
parser.about("Use this script to run image deblurring using OpenCV.");
|
||||
|
||||
const string sha1 = parser.get<String>("sha1");
|
||||
const string modelPath = findModel(parser.get<String>("model"), sha1);
|
||||
string imgPath = parser.get<String>("input");
|
||||
const string backend = parser.get<String>("backend");
|
||||
const string target = parser.get<String>("target");
|
||||
float scale = parser.get<float>("scale");
|
||||
bool swapRB = parser.get<bool>("rgb");
|
||||
Scalar mean_v = parser.get<Scalar>("mean");
|
||||
|
||||
EngineType engine = ENGINE_AUTO;
|
||||
if (backend != "default" || target != "cpu"){
|
||||
engine = ENGINE_CLASSIC;
|
||||
}
|
||||
|
||||
Net net = readNetFromONNX(modelPath, engine);
|
||||
net.setPreferableBackend(getBackendID(backend));
|
||||
net.setPreferableTarget(getTargetID(target));
|
||||
|
||||
Mat inputImage = imread(findFile(imgPath));
|
||||
if (inputImage.empty()) {
|
||||
cerr << "Error: Input image could not be loaded." << endl;
|
||||
return -1;
|
||||
}
|
||||
Mat image = inputImage.clone();
|
||||
|
||||
Mat image_blob = blobFromImage(image, scale, Size(image.cols, image.rows), mean_v, swapRB, false);
|
||||
|
||||
net.setInput(image_blob);
|
||||
Mat output = net.forward();
|
||||
|
||||
// Post Processing
|
||||
Mat output_transposed(3, &output.size[1], CV_32F, output.ptr<float>());
|
||||
|
||||
vector<Mat> channels = {
|
||||
Mat(output_transposed.size[1], output_transposed.size[2], CV_32F, output_transposed.ptr<float>(2)),
|
||||
Mat(output_transposed.size[1], output_transposed.size[2], CV_32F, output_transposed.ptr<float>(1)),
|
||||
Mat(output_transposed.size[1], output_transposed.size[2], CV_32F, output_transposed.ptr<float>(0))
|
||||
};
|
||||
|
||||
Mat outputImage;
|
||||
merge(channels, outputImage);
|
||||
outputImage.convertTo(outputImage, CV_8UC3, 255.0);
|
||||
|
||||
imshow("Input Image", inputImage);
|
||||
imshow("Output Image", outputImage);
|
||||
waitKey(0);
|
||||
return 0;
|
||||
}
|
||||
@@ -0,0 +1,115 @@
|
||||
#!/usr/bin/env python
|
||||
'''
|
||||
This file is part of OpenCV project.
|
||||
It is subject to the license terms in the LICENSE file found in the top-level directory
|
||||
of this distribution and at http://opencv.org/license.html.
|
||||
|
||||
This sample deblurs the given blurry image.
|
||||
|
||||
Copyright (C) 2025, Bigvision LLC.
|
||||
|
||||
How to use:
|
||||
Sample command to run:
|
||||
`python deblurring.py`
|
||||
|
||||
You can download NAFNet deblurring model using
|
||||
`python download_models.py NAFNet`
|
||||
|
||||
References:
|
||||
Github: https://github.com/megvii-research/NAFNet
|
||||
PyTorch model: https://drive.google.com/file/d/14D4V4raNYIOhETfcuuLI3bGLB-OYIv6X/view
|
||||
|
||||
PyTorch model was converted to ONNX and then ONNX model was further quantized using block quantization from [opencv_zoo](https://github.com/opencv/opencv_zoo/blob/main/tools/quantize/block_quantize.py)
|
||||
|
||||
Set environment variable OPENCV_DOWNLOAD_CACHE_DIR to point to the directory where models are downloaded. Also, point OPENCV_SAMPLES_DATA_PATH to opencv/samples/data.
|
||||
'''
|
||||
|
||||
import argparse
|
||||
import cv2 as cv
|
||||
import numpy as np
|
||||
from common import *
|
||||
|
||||
def help():
|
||||
print(
|
||||
'''
|
||||
Use this script for image deblurring using OpenCV.
|
||||
|
||||
Firstly, download required models i.e. NAFNet using `download_models.py` (if not already done). Set environment variable OPENCV_DOWNLOAD_CACHE_DIR to specify where models should be downloaded. Also, point OPENCV_SAMPLES_DATA_PATH to opencv/samples/data.
|
||||
|
||||
To run:
|
||||
Example: python deblurring.py [--input=<image_name>]
|
||||
|
||||
Deblurring model path can also be specified using --model argument.
|
||||
'''
|
||||
)
|
||||
|
||||
def get_args_parser():
|
||||
backends = ("default", "openvino", "opencv", "vkcom", "cuda")
|
||||
targets = ("cpu", "opencl", "opencl_fp16", "ncs2_vpu", "hddl_vpu", "vulkan", "cuda", "cuda_fp16")
|
||||
|
||||
parser = argparse.ArgumentParser(add_help=False)
|
||||
parser.add_argument('--zoo', default=os.path.join(os.path.dirname(os.path.abspath(__file__)), 'models.yml'),
|
||||
help='An optional path to file with preprocessing parameters.')
|
||||
parser.add_argument('--input', '-i', default="licenseplate_motion.jpg", help='Path to image file.', required=False)
|
||||
parser.add_argument('--backend', default="default", type=str, choices=backends,
|
||||
help="Choose one of computation backends: "
|
||||
"default: automatically (by default), "
|
||||
"openvino: Intel's Deep Learning Inference Engine (https://software.intel.com/openvino-toolkit), "
|
||||
"opencv: OpenCV implementation, "
|
||||
"vkcom: VKCOM, "
|
||||
"cuda: CUDA, "
|
||||
"webnn: WebNN")
|
||||
parser.add_argument('--target', default="cpu", type=str, choices=targets,
|
||||
help="Choose one of target computation devices: "
|
||||
"cpu: CPU target (by default), "
|
||||
"opencl: OpenCL, "
|
||||
"opencl_fp16: OpenCL fp16 (half-float precision), "
|
||||
"ncs2_vpu: NCS2 VPU, "
|
||||
"hddl_vpu: HDDL VPU, "
|
||||
"vulkan: Vulkan, "
|
||||
"cuda: CUDA, "
|
||||
"cuda_fp16: CUDA fp16 (half-float preprocess)")
|
||||
args, _ = parser.parse_known_args()
|
||||
add_preproc_args(args.zoo, parser, 'deblurring', prefix="", alias="NAFNet")
|
||||
parser = argparse.ArgumentParser(parents=[parser],
|
||||
description='Image deblurring using OpenCV.',
|
||||
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
|
||||
return parser.parse_args()
|
||||
|
||||
def main():
|
||||
if hasattr(args, 'help'):
|
||||
help()
|
||||
exit(1)
|
||||
|
||||
args.model = findModel(args.model, args.sha1)
|
||||
|
||||
engine = cv.dnn.ENGINE_AUTO
|
||||
|
||||
if args.backend != "default" or args.target != "cpu":
|
||||
engine = cv.dnn.ENGINE_CLASSIC
|
||||
|
||||
net = cv.dnn.readNetFromONNX(args.model, engine)
|
||||
net.setPreferableBackend(get_backend_id(args.backend))
|
||||
net.setPreferableTarget(get_target_id(args.target))
|
||||
|
||||
input_image = cv.imread(findFile(args.input))
|
||||
image = input_image.copy()
|
||||
height, width = image.shape[:2]
|
||||
|
||||
image_blob = cv.dnn.blobFromImage(image, args.scale, (width, height), args.mean, args.rgb, False)
|
||||
net.setInput(image_blob)
|
||||
out = net.forward()
|
||||
|
||||
# Postprocessing
|
||||
output = out[0]
|
||||
output = np.transpose(output, (1, 2, 0))
|
||||
output = np.clip(output * 255.0, 0, 255).astype(np.uint8)
|
||||
out_image = cv.cvtColor(output, cv.COLOR_RGB2BGR)
|
||||
|
||||
cv.imshow("input image: ", input_image)
|
||||
cv.imshow("output image: ", out_image)
|
||||
cv.waitKey(0)
|
||||
|
||||
if __name__ == '__main__':
|
||||
args = get_args_parser()
|
||||
main()
|
||||
@@ -492,3 +492,17 @@ mcc:
|
||||
sha1: "8350cb8f078ecefa1cd566e89930ede25a192310"
|
||||
config: "graph.pbtxt"
|
||||
sample: "mcc"
|
||||
|
||||
################################################################################
|
||||
# Deblurring model.
|
||||
################################################################################
|
||||
|
||||
NAFNet:
|
||||
load_info:
|
||||
url: "https://drive.google.com/uc?export=dowload&id=1ZLRhkpCekNruJZggVpBgSoCx3k7bJ-5v"
|
||||
sha1: "7dabf3d4ede0770ef326afc4511f7e67a791286d"
|
||||
model: "deblurring_nafnet_2025may.onnx"
|
||||
mean: [0, 0, 0]
|
||||
scale: 0.00392
|
||||
rgb: true
|
||||
sample: "deblurring"
|
||||
|
||||
Reference in New Issue
Block a user