CN111127354B - Single-image rain removing method based on multi-scale dictionary learning - Google Patents
Single-image rain removing method based on multi-scale dictionary learning Download PDFInfo
- Publication number
- CN111127354B CN111127354B CN201911300714.3A CN201911300714A CN111127354B CN 111127354 B CN111127354 B CN 111127354B CN 201911300714 A CN201911300714 A CN 201911300714A CN 111127354 B CN111127354 B CN 111127354B
- Authority
- CN
- China
- Prior art keywords
- rain
- image
- network model
- rain line
- rough
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012549 training Methods 0.000 claims abstract description 37
- 238000000605 extraction Methods 0.000 claims abstract description 20
- 230000006870 function Effects 0.000 claims abstract description 14
- 238000000746 purification Methods 0.000 claims abstract description 14
- 230000004913 activation Effects 0.000 claims abstract description 7
- 238000005457 optimization Methods 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000005096 rolling process Methods 0.000 claims description 2
- 238000013527 convolutional neural network Methods 0.000 description 9
- 238000012360 testing method Methods 0.000 description 6
- 239000002131 composite material Substances 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000013519 translation Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 241000282326 Felis catus Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/28—Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides a multi-scale dictionary single-image rain removing method, which comprises the following steps: step 1, taking each pair of clean images and synthesized rain-carrying images as a training sample pair, and establishing a training set; step 2, constructing a network model, wherein the network model comprises a rough rain line extraction module and a fine rain line purification module, the rough rain line extraction module comprises two convolution layers and two ReLU activation function layers, and the rough rain line extraction module is used for realizing rough rain line extraction of combined rain images; the fine rain line purification module comprises seven convolution layers and four ReLU activation functions and is used for recovering a fine rain line graph from a noisy rain line image; and 3, training the network model by using the training set constructed in the step 1, and 4, inputting the image with rain to be tested into the trained network model to obtain a corresponding rain removing image. The invention comprehensively utilizes the sparse theory and the CNN learning ability, and greatly improves the solving efficiency and the reconstruction precision of the SC problem.
Description
Technical Field
The invention belongs to the field of image processing, and particularly relates to a method for removing rain from a single-frame image by using a dictionary learning method.
Background
In reality, most computer vision algorithms assume that input is clear, however, for most outdoor vision systems such as video monitoring and automatic driving, the rainy environment can seriously affect imaging quality, which causes problems of image blurring, deformation, poor visibility and the like, and the performance of the system can be greatly reduced, so that the effective elimination of the influence of rainwater on the image has important application value, and especially, the raining removal of a single image is important in a task of removing rain. At present, rain removing algorithms for single images are mainly divided into two types: a priori based and learning based methods.
The prior-based method usually needs to observe the characteristics of the rain line in advance, and design specific prior information, for example, the rain line is more inclined straight line in a certain range or has low-rank characteristics, but the rain removing performance of the algorithm depends on the selection of the prior information to a great extent, and the complex rainfall condition in reality is difficult to process.
The learning-based method is a research focus in recent years, and mainly comprises a Convolutional Neural Network (CNN) -based method, wherein the image rain removal task is regarded as a pixel-by-pixel regression task, the whole image is used as input, the rain removal image is used as output, and end-to-end training and testing are carried out. The method does not need manual design prior, utilizes the strong learning ability of the CNN to enable the network to learn the rain line characteristics, but the method lacks a guidance scheme and interpretability during network design, and is not beneficial to improvement and promotion of the network.
Disclosure of Invention
Based on the analysis, the invention aims to provide a single-image rain removing method for multi-scale dictionary learning, which introduces sparse prior into CNN network design and greatly improves rain removing effect
The invention provides a multi-scale dictionary single image rain removing method, which comprises the following specific steps:
step 2, constructing a network model, wherein the network model comprises a rough rain line extraction module and a fine rain line purification module, the rough rain line extraction module comprises two convolution layers and two ReLU activation function layers, and the rough rain line extraction module is used for realizing rough rain line extraction of combined rain images; the fine rain line purification module comprises seven convolution layers and four ReLU activation functions and is used for recovering a fine rain line graph from a noisy rain line image;
step 3, training the network model by using the training set constructed in the step 1,
and 4, inputting the rain-carrying image to be tested into the trained network model to obtain a corresponding rain-removing image.
Further, the rough rain line extraction module in step 2 is specifically realized as follows,
wherein, E 1 ,E 2 The number of the convolution layers is two,for convolution operations, r ∈ For the extracted noisy rain line image, y is the composite rain image.
Furthermore, the detailed implementation manner of the fine rain line purification module in the step 2 is as follows,
the fine rain line purification module comprises a sparse coding solving part and an HR characteristic reconstruction part, wherein the sparse coding solves the following minimization problem in a convolution mode:
wherein f is j,i I-th filter kernel, f, representing j-th dictionary j,i Three filter groups are provided, namely j is 3, and the practical meaning is three rain line dictionaries with different scales, which are marked as S 1 、S 2 、S 3 Its transpose dictionary is denoted G 1 、G 2 、G 3 In which S is 1 、S 2 、S 3 、G 1 、G 2 、G 3 All implemented by convolutional layers, c is the number of channels decomposed, z j,i For the convolution sparse coding to be solved, | | · | non-calculation 1 ,||·|| 2 Respectively represent l 1 Norm and l 2 Norm, lambda is sparse penalty coefficient;
after sparse coding is obtained, reconstructing a denoised rainchart:
wherein the content of the first and second substances,E 3 is a convolution layer, r is the final recovered fine rain image;
the specific process is as follows: firstly, the first step is toAre all initialized to r ∈ ,r ∈ Extracting a noisy rainline image for the feature extraction module; computingRespectively pass through S 1 、S 2 、S 3 From the sum of (a) and (b), adding this sum from r ∈ Subtracting, and respectively passing the difference value through G 1 、G 2 、G 3 Then respectively andadd to obtainRepeating the above process to obtainThe final convolution sparse code is obtained, wherein t is iteration times; at the time of reconstruction, calculatingRespectively pass through S 1 、S 2 、S 3 After ReLU and then E 3 I.e. to recover a fine rain image.
Furthermore, the relation of convolution and matrix multiplication is utilized to convert the expression (2) into the traditional sparse coding problem, and an ISTA algorithm is adopted to solve under the assumption of non-negative sparse coding,
wherein, the first and the second end of the pipe are connected with each other,in order to be the middle symbol,refers to a threshold value, and t is the number of iterations.
Further, in step 3, global residual learning is introduced into the network model, and an MSE loss function is selected to minimize the MSE loss function as a training target, where the MSE loss function has the following expression:
wherein, theta refers to the network model parameter, l is the index of the training sample in the training set, and y l -r l Rain-removed image output for network model, and real clean image x l And performing subtraction and accumulation to obtain a final error, so that the final error is minimized to realize optimization of the network model.
Further, in the step 1, the number of images in a training set is increased by means of turning, rotating, zooming and cutting, then rain lines are added to each clean image through Photoshop to obtain a composite rain image, and the corresponding clean image and the composite rain image are used as a training sample pair.
The invention provides a single image rain removing algorithm, which comprehensively utilizes a sparse theory and CNN learning capacity, obtains an iterative formula by solving an optimization problem in SC, and is realized by using CNN, thereby greatly improving the solving efficiency and the reconstruction precision of the SC problem.
Drawings
Fig. 1 is a general flowchart of network model construction according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of sparse coding solution.
Fig. 3 is a Rain removal comparison diagram of algorithms for cat images in Rain12 dataset.
FIG. 4 is a diagram of Rain removal contrast for each algorithm for forest images in the Rain1200 dataset.
Detailed Description
In order that the invention may be more clearly understood, the following detailed description is given.
As shown in fig. 1, the single-image rain removing method based on multi-scale dictionary learning provided by the present invention specifically includes four steps:
due to the limited training data set, data enhancement methods are required to effectively utilize the limited HR images. Data enhancement is an effective way to expand the size of data samples. Deep learning is a data-driven method, and the larger the training data set is, the stronger the generalization ability of the trained model is. However, in practice, it is difficult to cover all scenes when data is collected, and the data collection also requires a lot of cost, which results in a limited training set in practice. If various training data can be generated according to the existing data, better open source throttling can be achieved, and the purpose of data enhancement is achieved.
Commonly used data enhancement techniques are:
(1) turning: flipping includes both horizontal flipping and vertical flipping.
(2) Rotating: rotation is clockwise or counterclockwise, and it is noted that rotation is preferably 90-180 ° during rotation, otherwise dimensional problems may occur.
(3) Zooming: the image may be enlarged or reduced. When enlarged, the size of the enlarged image will be larger than the original size. Most image processing architectures crop the enlarged image to its original size.
(4) Cutting: the region of interest of the picture is cut out, and different regions are cut out randomly and are replayed to the original size during training.
(5) Translation: translation is the movement of the image in either the x or y direction (or both). The background needs to be assumed, for example, black is assumed, etc. when translating, because a part of the image is empty when translating, the translation enhancement method is very useful because an object in the image may appear at an arbitrary position.
(6) Noise addition: overfitting usually occurs when the neural network learns the high frequency features (because the low frequency features are easily learned by the neural network and the high frequency features are learned only at the last time) and these features may not help the task that the neural network does and may have an impact on the low frequency features that we randomly add noisy data to eliminate them in order to eliminate the high frequency features.
First, in order to train the CNN model, the present embodiment needs to construct training sample pairs. And adding rain lines to the clean image through Photoshop software to obtain a synthetic rain-carrying image. After obtaining a clean and synthetic image pair, the number of training sample pairs is increased by means of turning, rotating, zooming and clipping, and then the model can be input for training.
And 2, constructing a network model, specifically comprising a rough rain line extraction module and a fine rain line purification module.
Step 2a, the rough rain line extraction module is realized by a simple two-layer convolution layer and two ReLU layers, and the rough rain line extraction with rain images is realized;
wherein, E 1 ,E 2 The number of the rolling layers is two,for convolution operations, r ∈ For the extracted noisy rain line image, y is the composite rain image.
Step 2b, constructing a fine rain line purification module which comprises seven convolution layers and four ReLU activation functions and is used for denoising the rough (noisy) rain line image to obtain a clean rain line;
the key point of the invention is to solve three dictionaries S 1 、S 2 、S 3 And its transposed dictionary G 1 、G 2 、G 3 :
Wherein f is j,i I-th filter kernel, f, representing j-th dictionary j,i Three filter groups are provided, namely j is 3, and the practical meaning is three rain line dictionaries with different scales, which are marked as S 1 、S 2 、S 3 Its transposed dictionary is denoted G 1 、G 2 、G 3 (S 1 、S 2 、S 3 、G 1 、G 2 、G 3 All implemented by convolutional layers), c is the number of channels decomposed, z j,i For the convolution sparse coding to be solved, | | · | non-calculation 1 ,||·|| 2 Respectively represent l 1 Norm and l 2 The norm, λ, is a sparse penalty coefficient, and is set to 1 in this embodiment.
After sparse coding is obtained, a denoised rain image can be reconstructed;
wherein, the first and the second end of the pipe are connected with each other,E 3 is a convolution layer, r is the final recovered fine rain image;
for the first minimization problem, the conventional sparse coding problem can be converted by using the convolution and matrix multiplication relation, and under the assumption of non-negative sparse coding, the solution is carried out by adopting an ISTA algorithm:
wherein, the first and the second end of the pipe are connected with each other,in the middle of the symbol, is the middle symbol,finger threshold, t is the number of iterations, S 1 、S 2 、S 3 For dictionaries of different dimensions, corresponding to transpose dictionary as G 1 、G 2 、G 3 。
Accordingly, a sparse code iterative solution process in the fine rain purification module can be obtained, a CNN implementation schematic diagram is shown in figure 2, and S 1 、S 2 、S 3 And G 1 、G 2 、G 3 All can be realized by a convolution layer. After passing through the rough rain line extraction module, the rough rain line image r ∈ Is input into a fine rain purification module part which mainly comprises two steps: sparse coding solution and HR characteristic reconstruction, solving sparse coding corresponding to the graph 2, and outputting optimal sparse coding after a certain number of times through an ISTA algorithm realized by iterative convolution.
Finally, the whole network flow is as follows: inputting the composite rain-bearing image y through two convolutions E 1 ,E 2 And two ReLUs to obtain a rough rainline image r ∈ Will beAre all initialized to r ∈ . ComputingRespectively pass through S 1 、S 2 、S 3 From the sum of (a) and (b), adding the sum from r ∈ Subtracting, and respectively passing the difference value through G 1 、G 2 、G 3 Then respectively andadd to obtainRepeating the above process to obtainThe final convolution sparse code is obtained, wherein t is the iteration number, and the value of t is preferably 25. At the time of reconstruction, calculatingRespectively pass through S 1 、S 2 、S 3 After ReLU and then E 3 The fine rain image can be recovered.
And 3, training the network model by using the training set constructed in the step 1. Meanwhile, in this embodiment, the MSE loss function is selected:
wherein, theta refers to the network model parameter, l is the index of the training data in the training set, and y l -r l Rain-removed image output for network model, and real clean image x l And performing difference and accumulation to obtain a final error, and performing network optimization according to the final error.
And 4, inputting the rain-carrying image to be tested into the trained network model to obtain a corresponding rain-removing image.
In the test process, a peak signal-to-noise ratio (PSNR) and a Structural Similarity (SSIM) are used as measurement standards, and the measurement standards are specifically defined as follows:
PSNR=10*log10(255 2 /mean(mean((X-Y) 2 )))
SSIM=[L(X,Y) a ]×[C(X,Y) b ]×[S(X,Y) c ]
wherein the content of the first and second substances,μ x and mu Y Represents the mean, σ, of X and Y, respectively X 、σ Y And σ XY Representing the variance of X and Y and the covariance of the two, respectively.
Wherein, the higher the PSNR and SSIM values are, the better the reconstruction effect is.
In the test process, CNN, JORDER and DIDMDN are selected as comparison algorithms, visual comparison is shown in an attached figure 4, the method can remove rain lines in the image more easily, good detail information is stored at the same time, the rain removing effect of the comparison algorithms is not ideal, the rain is removed incompletely or a fuzzy result is generated, and even artifacts are generated. As for the quantitative index, two commonly used data sets (Rain12 and Rain1200) were selected as the test set, and the test results are shown in table 1, and it can be seen that: the method of the patent greatly improves the PSNR and SSIM of the rain removing result, and the effectiveness of the method of the patent is demonstrated.
TABLE 1 test results
It should be understood that the above description is for illustrative purposes only and should not be taken as limiting the scope of the present invention, which is defined by the appended claims.
Claims (3)
1. A single image rain removing method based on multi-scale dictionary learning is characterized by comprising the following steps:
step 1, according to the existing clean images, obtaining corresponding synthetic rain-carrying images by adding rain lines, taking each pair of clean images and synthetic rain-carrying images as a training sample pair, and establishing a training set;
step 2, constructing a network model, wherein the network model comprises a rough rain line extraction module and a fine rain line purification module, the rough rain line extraction module comprises two convolution layers and two ReLU activation function layers, and the rough rain line extraction module is used for realizing rough rain line extraction of combined rain images; the fine rain line purification module comprises seven convolution layers and four ReLU activation functions and is used for recovering a fine rain line graph from a noisy rain line image;
the rough rain line extraction module in step 2 is implemented as follows,
wherein E is 1 ,E 2 The number of the rolling layers is two,for convolution operations, r ∈ The extracted noisy rain line image is used, and y is a synthesized rain image;
the detailed implementation manner of the fine rain line purification module in the step 2 is as follows,
the fine rain line purification module comprises a sparse coding solving part and an HR characteristic reconstruction part, wherein the sparse coding solves the following minimization problem in a convolution mode:
wherein f is j,i Ith filter kernel, f, representing the jth dictionary j,i Three filter groups are provided, namely j is 3, and the practical meaning is three rain line dictionaries with different scales, which are marked as S 1 、S 2 、S 3 Its transposed dictionary is denoted G 1 、G 2 、G 3 In which S is 1 、S 2 、S 3 、G 1 、G 2 、G 3 All implemented by convolutional layers, c is the number of channels decomposed, z j,i For the convolution sparse coding to be solved, | | · | non-calculation 1 ,||·|| 2 Respectively represent l 1 Norm and l 2 Norm, lambda is sparse penalty coefficient;
after sparse coding is obtained, reconstructing a denoised rainchart:
wherein the content of the first and second substances,E 3 is a convolution layer, r is the final recovered fine rain image;
the formula (2) is converted into the traditional sparse coding problem by utilizing the multiplication relation of convolution and matrix, and is solved by adopting an ISTA algorithm under the assumption of non-negative sparse coding,
wherein the content of the first and second substances,in order to be the middle symbol,a threshold value is designated, and t is the iteration number;
the specific process comprises the following steps: firstly, the first step is toAre all initialized to r ∈ ,r ∈ Extracting a noisy rainline image for the feature extraction module; computingRespectively pass through S 1 、S 2 、S 3 From the sum of (a) and (b), adding the sum from r ∈ Subtracting, and passing the difference value through G 1 、G 2 、G 3 Then respectively andadd to obtainRepeating the above process to obtainThe final convolution sparse code is obtained, wherein t is iteration times; at the time of reconstruction, calculateRespectively pass through S 1 、S 2 、S 3 After ReLU and then E 3 Recovering a fine rain image;
step 3, training the network model by using the training set constructed in the step 1,
and 4, inputting the rain-carrying image to be tested into the trained network model to obtain a corresponding rain-removing image.
2. The single-image rain removal method based on multi-scale dictionary learning as claimed in claim 1, wherein: in step 3, global residual learning is introduced into the network model, an MSE loss function is selected, the minimum loss function is taken as a training target, and the expression of the MSE loss function is as follows:
wherein, theta refers to the network model parameter, l is the index of the training sample in the training set, and y l -r l Rain-removed image output for network model, and real clean image x l And performing subtraction and accumulation to obtain a final error, so that the final error is minimized to realize optimization of the network model.
3. The single-image rain removal method based on multi-scale dictionary learning as claimed in claim 1, wherein: in the step 1, the number of images in a training set is increased by means of turning, rotating, zooming and cutting, then rain lines are added to each clean image through Photoshop to obtain a synthetic rain image, and the corresponding clean image and the synthetic rain image are used as a training sample pair.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911300714.3A CN111127354B (en) | 2019-12-17 | 2019-12-17 | Single-image rain removing method based on multi-scale dictionary learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911300714.3A CN111127354B (en) | 2019-12-17 | 2019-12-17 | Single-image rain removing method based on multi-scale dictionary learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111127354A CN111127354A (en) | 2020-05-08 |
CN111127354B true CN111127354B (en) | 2022-07-26 |
Family
ID=70498195
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911300714.3A Expired - Fee Related CN111127354B (en) | 2019-12-17 | 2019-12-17 | Single-image rain removing method based on multi-scale dictionary learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111127354B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111738932A (en) * | 2020-05-13 | 2020-10-02 | 合肥师范学院 | Automatic rain removing method for photographed image of vehicle-mounted camera |
CN111861935B (en) * | 2020-07-29 | 2022-06-03 | 天津大学 | Rain removing method based on image restoration technology |
CN112712486B (en) * | 2020-11-26 | 2024-04-26 | 贵州大学 | Radio astronomical image reconstruction method based on activation function |
CN113222888B (en) * | 2021-03-19 | 2022-07-22 | 复旦大学 | Textile yarn weaving size detection method based on depth texture characteristics |
CN113902931B (en) * | 2021-09-17 | 2022-07-12 | 淮阴工学院 | Image rain removing method based on learning type convolution sparse coding |
CN115131452A (en) * | 2022-04-19 | 2022-09-30 | 腾讯医疗健康(深圳)有限公司 | Image processing method and device for artifact removal |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107657593A (en) * | 2017-04-20 | 2018-02-02 | 湘潭大学 | A kind of removing rain based on single image method |
CN108765344A (en) * | 2018-05-30 | 2018-11-06 | 南京信息工程大学 | A method of the single image rain line removal based on depth convolutional neural networks |
CN110570351A (en) * | 2019-08-01 | 2019-12-13 | 武汉大学 | Image super-resolution reconstruction method based on convolution sparse coding |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8340461B2 (en) * | 2010-02-01 | 2012-12-25 | Microsoft Corporation | Single image haze removal using dark channel priors |
CN107133935B (en) * | 2017-05-25 | 2019-07-02 | 华南农业大学 | A kind of fine rain removing method of single image based on depth convolutional neural networks |
CN109360155B (en) * | 2018-08-17 | 2020-10-13 | 上海交通大学 | Single-frame image rain removing method based on multi-scale feature fusion |
-
2019
- 2019-12-17 CN CN201911300714.3A patent/CN111127354B/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107657593A (en) * | 2017-04-20 | 2018-02-02 | 湘潭大学 | A kind of removing rain based on single image method |
CN108765344A (en) * | 2018-05-30 | 2018-11-06 | 南京信息工程大学 | A method of the single image rain line removal based on depth convolutional neural networks |
CN110570351A (en) * | 2019-08-01 | 2019-12-13 | 武汉大学 | Image super-resolution reconstruction method based on convolution sparse coding |
Non-Patent Citations (2)
Title |
---|
A Coarse-to-fine Multi-stream Hybrid Deraining Network for Single Image Deraining;Yanyan Wei et.al;《Arxiv》;20190827;第1-9页 * |
多尺度卷积神经网络的单幅图像去雨方法;郭继昌 等;《哈尔滨工业大学学报》;20180330;第50卷(第3期);第185-191页 * |
Also Published As
Publication number | Publication date |
---|---|
CN111127354A (en) | 2020-05-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111127354B (en) | Single-image rain removing method based on multi-scale dictionary learning | |
CN112200750B (en) | Ultrasonic image denoising model establishing method and ultrasonic image denoising method | |
Tian et al. | Lightweight image super-resolution with enhanced CNN | |
CN108537733B (en) | Super-resolution reconstruction method based on multi-path deep convolutional neural network | |
Wang et al. | Haze concentration adaptive network for image dehazing | |
CN111340738B (en) | Image rain removing method based on multi-scale progressive fusion | |
CN110570351B (en) | Image super-resolution reconstruction method based on convolution sparse coding | |
CN113066025B (en) | Image defogging method based on incremental learning and feature and attention transfer | |
CN110807744B (en) | Image defogging method based on convolutional neural network | |
CN112419174B (en) | Image character removing method, system and device based on gate cycle unit | |
CN107590779A (en) | Image denoising and deblurring method based on image block clustering dictionary training | |
CN114723631A (en) | Image denoising method, system and device based on depth context prior and multi-scale reconstruction sub-network | |
Yang et al. | A two-stage network with wavelet transformation for single-image deraining | |
CN113962905A (en) | Single image rain removing method based on multi-stage feature complementary network | |
Hussain et al. | Image denoising to enhance character recognition using deep learning | |
CN117422878A (en) | Remote sensing image semantic segmentation method based on double-branch dynamic attention | |
CN111612803B (en) | Vehicle image semantic segmentation method based on image definition | |
CN115689958A (en) | Synthetic radar image denoising method based on deep learning | |
Li et al. | Distribution-transformed network for impulse noise removal | |
CN110288525B (en) | Multi-dictionary super-resolution image reconstruction method | |
CN113379641A (en) | Single image rain removing method and system based on self-coding convolutional neural network | |
CN112927151A (en) | Image denoising method based on edge enhancement and convolutional neural network | |
CN105139353B (en) | A kind of blind separating method for replacing aliased image | |
CN114723614B (en) | Image restoration method based on wavelet domain ADMM depth network | |
CN112288738B (en) | Single image snowflake removing method and device based on deep learning and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220726 |