CN113393385B - Multi-scale fusion-based unsupervised rain removing method, system, device and medium - Google Patents
Multi-scale fusion-based unsupervised rain removing method, system, device and medium Download PDFInfo
- Publication number
- CN113393385B CN113393385B CN202110515593.5A CN202110515593A CN113393385B CN 113393385 B CN113393385 B CN 113393385B CN 202110515593 A CN202110515593 A CN 202110515593A CN 113393385 B CN113393385 B CN 113393385B
- Authority
- CN
- China
- Prior art keywords
- image
- rain
- scale
- micro
- clean
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000004927 fusion Effects 0.000 title claims abstract description 22
- 238000005070 sampling Methods 0.000 claims abstract description 18
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 230000006870 function Effects 0.000 claims description 36
- 230000004913 activation Effects 0.000 claims description 2
- 238000012549 training Methods 0.000 abstract description 17
- 238000012545 processing Methods 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000001514 detection method Methods 0.000 description 5
- 238000010276 construction Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
Classifications
-
- G06T5/73—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
Abstract
The invention discloses an unsupervised rain removing method, a system, a device and a medium based on multi-scale fusion, wherein the method comprises the following steps: preprocessing the rainy image to obtain micro rain-removing images with multiple scales; according to the micro-rain-removing image and the countermeasure model, determining clean images corresponding to the micro-rain-removing images with different scales; upsampling the clean image to determine an upsampled image; determining a loss function of the countermeasure model according to a reconstruction error between the current scale up-sampling image and the previous scale clean image; and iterating the loss function to the minimum value, converging the countermeasure model, and obtaining a clean image without rain according to the image with rain through the countermeasure model. According to the embodiment of the application, an unsupervised rain removing method is adopted, a large number of rainy and non-rainy image pairs are not required to be prepared to serve as a training set, the acquisition difficulty of the training set is reduced, the dependence on the training set is reduced, and the generalization of a rain removing system can be effectively provided. The method and the device can be widely applied to the field of image processing.
Description
Technical Field
The application relates to the field of image processing, in particular to an unsupervised rain removing method, system, device and medium based on multi-scale fusion.
Background
Computer vision systems currently exist in daily life of people generally, the vision systems acquire and capture images or videos of real environments, and detection, identification, prejudgment and the like of targets are realized through analysis processing means such as feature extraction and the like. For outdoor vision systems, images collected by the outdoor vision system are often affected by weather such as rain, fog, snow, etc., and rain is one of the three more common. The rainy image can influence the accuracy of image feature extraction and further influence the subsequent detection and identification, so that the rainy image needs to be subjected to image enhancement processing to achieve the purpose of removing rain.
In general, rain image enhancement algorithms can be divided into three general categories: the first is to use detection and repair to detect the rain position and repair the rain by using the correlation of surrounding pixels, and the second is to use the rain and background map as two signals based on layer separation, and to add different prior assumptions to the two signals for separation. The third is a method based on deep learning, which is popular in recent years, and the training of the network is mostly carried out by adopting a supervised mode, so that the mapping from rainy to non-rainy is learned. However, in the related art, a supervised learning algorithm is mostly used in a deep learning-based method, a large number of rainy and non-rainy image pairs are needed during training, the requirement on a training set is high, the trained network may have dependence on the training set, and the generalization capability is low.
Disclosure of Invention
The present application aims to solve, at least to some extent, one of the technical problems in the related art. Therefore, the application provides the non-supervision rain removing method, the system, the device and the medium based on multi-scale fusion, which can effectively improve the generalization of the rain removing method.
In a first aspect, an embodiment of the present application provides an unsupervised rain removal method based on multi-scale fusion, including: preprocessing the rainy image to determine micro rain-removing images with multiple scales; according to the micro-rain removing image and the countermeasure model, determining clean images corresponding to the micro-rain removing images with different scales; upsampling the clean image to determine an upsampled image; determining a loss function of the countermeasure model according to a reconstruction error between the current scale up-sampling image and the previous scale clean image; and iterating the loss function, and updating parameters of the countermeasure model according to the loss function until the countermeasure model converges.
Optionally, the preprocessing the rainy image to determine a micro rain-removing image with multiple scales includes: carrying out one-dimensional Gaussian convolution along the main direction of the rainy image to determine an initial micro-rain removal image; downsampling the initial micro-rain removal image to determine a sampling result; and carrying out one-dimensional Gaussian convolution on the sampling result along the main direction, and determining a micro-rain removal image of the next scale.
Optionally, the step of determining the main direction includes: calculating the gradient direction of raindrops in each pixel point in the image with rain; and determining the main direction of the rainy image according to the average value of the gradient directions.
Optionally, the countermeasure model specifically includes a generator and a discriminator; the generator is used for generating a clean image corresponding to the scale micro-rain removal image according to the micro-rain removal image; the discriminator is used for judging the clean image and outputting a judging result.
Optionally, the determining the loss function of the countermeasure model according to the reconstruction error between the current scale up-sampled image and the previous scale clean image includes:
the loss function of the countermeasure model is:
wherein L is the loss function, i is the scale sequence number of the micro rain-removing image,for the reconstruction error between the up-sampled image of the i+1th scale and the i-scale micro-rain-removed image,/and->And generating a countermeasures loss for the ith scale.
Optionally, the generating counter-lossThe method comprises the following steps:
wherein E represents a mathematical expectation, D i Represents the discriminator, G i Representing the generator, J i Representing said micro-raining images of different scales, I c Representing the clean image corresponding to the micro rain removal image, and c represents the serial number of the clean image.
Optionally, the generator includes a convolution layer, an activation layer, and a regularization layer.
In a second aspect, embodiments of the present application provide an unsupervised rain removal system based on multi-scale fusion, including: the preprocessing module is used for preprocessing the rainy image and determining micro rain-removing images with multiple scales; the rain removing module is used for determining clean images corresponding to the micro-rain removing images with different scales according to the micro-rain removing images and the countermeasure model; the loss function construction module is used for upsampling the clean image and determining an upsampled image; the method comprises the steps of obtaining a current scale up-sampling image, and determining a loss function of the countermeasure model according to a reconstruction error between the current scale up-sampling image and a previous scale clean image; and the model training module is used for iterating the loss function, and updating the parameters of the countermeasure model according to the loss function until the countermeasure model converges.
In a third aspect, an embodiment of the present application provides an apparatus, including: at least one processor; at least one memory for storing at least one program; the at least one program, when executed by the at least one processor, causes the at least one processor to implement an unsupervised rain-removal method based on multi-scale fusion as described in the first aspect.
In a fourth aspect, embodiments of the present application provide a computer storage medium having stored therein a processor-executable program which, when executed by the processor, is configured to implement the multi-scale fusion-based unsupervised rain-removal method according to the first aspect.
The beneficial effects of the embodiment of the application are as follows: preprocessing the rainy image to obtain a plurality of micro rain removal images with different scales; according to the micro-rain removing image and the countermeasure model, determining clean images corresponding to the micro-rain removing images with different scales; upsampling the obtained clean image to determine an upsampled image; determining a loss function of the countermeasure model according to a reconstruction error between the current scale up-sampling image and the previous scale clean image; in the continuous iterative training process, the loss function is iterated to the minimum value, the countermeasure model is converged, and a clean image without rain can be obtained according to the micro rain removal image through the countermeasure model. According to the embodiment of the application, an unsupervised rain removing method is adopted, a large number of image pairs with rain and without rain are not required to be prepared to serve as a training set, and compared with a supervised regional method, the regional method provided by the application reduces the acquisition difficulty of the training set, reduces the dependence on the training set, and can effectively provide generalization of a rain removing system. The method and the device can be widely applied to the field of image processing.
Drawings
The accompanying drawings are included to provide a further understanding of the technical aspects of the present application, and are incorporated in and constitute a part of this specification, illustrate the technical aspects of the present application and together with the examples of the present application, and not constitute a limitation of the technical aspects of the present application.
FIG. 1 is a flow chart of steps of an unsupervised rain removal method based on multi-scale fusion provided in an embodiment of the present application;
FIG. 2 is a flowchart illustrating steps of preprocessing a rainy image according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a network architecture of a challenge model according to an embodiment of the present disclosure;
fig. 4 is a schematic architecture diagram of an unsupervised rain removal system based on multi-scale fusion according to an embodiment of the present application;
fig. 5 is a schematic diagram of an apparatus according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
It should be noted that although functional block diagrams are depicted as block diagrams, and logical sequences are shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the block diagrams in the system. The terms first, second and the like in the description and in the claims and in the above-described figures, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
The quality of the raw data is very important in the whole flow of the vision system, and the poor quality of the raw data may lead to inaccuracy of the extracted features, thereby affecting subsequent detection and recognition. For outdoor vision systems, images collected by the outdoor vision systems are often affected by rain, and all collected are images with rain. In order to improve accuracy of the later image detection and analysis, it is very important to perform image enhancement processing on the rainy image. In the rain image enhancement algorithm, a method based on deep learning is popular in recent years, and a supervised mode is adopted to train a network, so that a mapping from rain to no rain is learned. However, this method requires a large number of pairs of images with and without rain, and has high requirements on training sets, and the trained network may have dependency on the training sets, which is limited.
Based on the above, the embodiment of the application provides an unsupervised rain removing method, system, device and medium based on multi-scale fusion, which adopts an unsupervised mode to obtain a clean rain removing image through an countermeasure model, and the embodiment of the application does not need to use a large number of rainy and non-rainy image pairs, so that the dependence on a training set is effectively reduced, and the application has a positive effect on improving the generalization of a rain removing system.
Embodiments of the present application are further described below with reference to the accompanying drawings.
Referring to fig. 1, fig. 1 is a step flowchart of an unsupervised rain removal method based on multi-scale fusion provided in an embodiment of the present application, including, but not limited to, steps S100-S140:
s100, preprocessing the rainy image to determine micro rain-removing images with multiple scales;
specifically, the outdoor vision system can acquire a large number of rainy images in rainy days, and preprocesses the rainy images to obtain a plurality of micro rain removing images with different scales. The micro-rain removing image is not a clean image after complete rain removing, but is preprocessed on the basis of the image with rain, and the subsequent rain removing step is performed on the basis of the micro-rain removing image.
Referring to fig. 2, fig. 2 is a flowchart illustrating steps of preprocessing a rainy image according to an embodiment of the present application, where the method includes, but is not limited to, steps S101-S103:
s101, carrying out one-dimensional Gaussian convolution along a main direction of a rainy image, and determining an initial micro-rain removal image;
specifically, determining a main direction of the rainy image, and carrying out one-dimensional Gaussian convolution along the main direction of the rainy image to obtain an initial micro-rain removal image. The main direction of the rainy image refers to the main direction of the rainy drops in the rainy image, and the average value of the gradient directions of the rainy drops is determined according to the gradient directions of the rainy drops in each pixel point in the rainy image and is used as the main direction of the rainy image, and the main direction is also applied to the subsequent image convolution step.
S102, downsampling an initial micro-rain removal image to determine a sampling result;
specifically, downsampling is carried out on the initial micro-rain-removing image, the scale of the image is reduced, and a sampling result is obtained.
S103, carrying out one-dimensional Gaussian convolution on the sampling result along the main direction, and determining a micro-rain removal image of the next scale;
specifically, the sampling result obtained in step S102 is subjected to one-dimensional gaussian convolution along the above main direction, and a micro-rain-removed image of the next scale is determined.
Through steps S101-S103, in the embodiment of the present application, a plurality of micro-rain-removing images with different scales are obtained through the alternation of one-dimensional gaussian convolution and downsampling. Taking steps S101-S103 as an example, assume that the initial micro-degritted image obtained by convolution of the rained image is J 0 Step S103 the micro rain-removing image obtained by 3 can be used as J 1 Expressed by J 1 Is J 0 An image of the next scale. And so on, for J 1 Downsampling and one-dimensional convolution processing are carried out to obtain a micro-rain-removing image J of the next scale 2 And then downsampling and convolution are carried out continuously, so that a plurality of micro-rain-removing images required by a user can be obtained, and multi-scale image processing is carried out.
S110, determining clean images corresponding to the micro-rain removal images with different scales according to the micro-rain removal images and the countermeasure model;
specifically, the micro-rain removing image obtained in step S100 is input into the countermeasure model, and the countermeasure model outputs clean images corresponding to the micro-rain removing images with different scales, wherein the clean images are rain-free images with different scales.
The countermeasure model in the embodiment of the application comprises a generator and a discriminator, wherein the generator is used for generating a clean image corresponding to the scale micro-rain removal image according to the micro-rain removal image; the discriminator is used for judging the clean image and outputting a judging result. The generator and the arbiter of the embodiments of the present application may use a network architecture in the related art, and the embodiments of the present application do not specifically limit the specific configuration of the generator and the arbiter. The object of the generator is to generate enough simulated data, the object of the discriminator is to judge the authenticity of the data generated by the generator, the generator and the discriminator continuously adjust parameters in the optimization process of the loss function of the whole countermeasure model, asynchronous iteration update is carried out, and the simulation degree of the data generated by the generator and the accuracy of the discriminator in judging the authenticity of the data are continuously improved.
S120, upsampling the clean image to determine an upsampled image;
specifically, up-sampling is performed on clean images of different scales to obtain up-sampled images of multiple scales.
S130, determining a loss function of the countermeasure model according to a reconstruction error between the current scale up-sampling image and the previous scale clean image;
specifically, as can be seen from step S102 and step S120, the present application obtains pictures of different scales through upsampling and downsampling, and thus, the upsampled image of the current scale can be compared with the clean image of the previous scale. Assuming that the scale of the current clean image is i+1, the corresponding up-sampled image can be compared with the clean image with the scale of i, in the embodiment of the application, a loss function is added in a multi-scale network architecture, the consistency between the up-sampled clean image with each scale and the clean image with the previous scale is restrained, and the loss function of the countermeasure model is determined according to the reconstruction error between the up-sampled image with the current scale and the clean image with the previous scale. The expression of the loss function is as follows:
wherein L is a loss function, i is a scale sequence number of the micro rain-removing image,for the reconstruction error between the up-sampled image of the i+1th scale and the clean image of the i scale,/and>and generating a countermeasures loss for the ith scale. The generation fights against lossesThe method comprises the following steps:
wherein E represents a mathematical expectation, D i Representative discriminator, G i Representative generator, J i Representing micro-rain-removed images of different scales, I c Representing a clean image corresponding to the micro-rain removing image, and c represents the serial number of the clean image.
And S140, iterating the loss function, and updating parameters of the countermeasure model according to the loss function until the countermeasure model converges.
Specifically, the loss function is iterated continuously, so that the loss function is minimized, and parameters of the generator and the discriminator in the countermeasure model are adjusted continuously in the process of the loss function iteration, and it is to be noted that in the embodiment of the application, the parameters of the generator and the discriminator which form the countermeasure network are iterated asynchronously, and the discriminator and the generator iterate circularly until the loss function reaches the minimum value, and the countermeasure model converges. After the convergence is completed, the countermeasure model is obtained, a rain image is input to the model, and the countermeasure model outputs a corresponding clean rain-free image.
Referring to fig. 3, fig. 3 is a schematic diagram of a network architecture of an countermeasure model according to an embodiment of the present application, and as shown in fig. 3, J is an input image with rain, and an initial micro-rain removal image J is obtained through one-dimensional gaussian convolution 0 From J 0 Starting to obtain micro-rain-removing images J with different scales by analogy 1 、J 2 The micro rain-removing images with different scales pass through generators G with different scales 0 、G 1 Etc. to generate clean images I of different scales 0 、I 1 Etc., the clean graphs generated by the generators are input into discriminators D with different scales 0 、D 1 And the like, comparing and judging with the real rain-free graph, and outputting a judging result, wherein when the loss function of the whole network reaches the minimum value, the generator can be considered to generate the rain-free graph which is sufficiently simulated to resist network convergence.
Referring to fig. 4, fig. 4 is a schematic architecture diagram of an unsupervised rain removal system based on multi-scale fusion according to an embodiment of the present application, where the system 400 includes: a preprocessing module 410, a rain removal module 420, a loss function construction module 430, and a model training module 440. The preprocessing module is used for preprocessing the rainy image and determining micro rain-removing images with multiple scales; the rain removing module is used for determining clean images corresponding to the micro-rain removing images with different scales according to the micro-rain removing images and the countermeasure model; the loss function construction module is used for upsampling the clean image and determining an upsampled image; the method comprises the steps of obtaining a current scale up-sampling image, obtaining a previous scale clean image, and determining a loss function of an countermeasure model according to a reconstruction error between the current scale up-sampling image and the previous scale clean image; the model training module is used for iterating the loss function, and updating the parameters of the countermeasure model according to the loss function until the countermeasure model converges.
Referring to fig. 5, fig. 5 is an apparatus provided in an embodiment of the present application, where the apparatus 500 includes at least one processor 510, and at least one memory 520 for storing at least one program; one processor and one memory are taken as examples in fig. 5.
The processor and the memory may be connected by a bus or otherwise, for example in fig. 5.
The memory, as a non-transitory computer readable storage medium, may be used to store non-transitory software programs as well as non-transitory computer executable programs. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory remotely located relative to the processor, the remote memory being connectable to the apparatus through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Another embodiment of the present application also provides an apparatus that may be used to perform the control method of any of the embodiments above, for example, to perform the method steps of fig. 1 described above.
The above described apparatus embodiments are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, i.e. may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The embodiment of the application also discloses a computer storage medium, wherein a program executable by a processor is stored, and the computer storage medium is characterized in that the program executable by the processor is used for realizing the multi-scale fusion-based unsupervised rain removing method.
Those of ordinary skill in the art will appreciate that all or some of the steps, systems, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as known to those skilled in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.
While the preferred embodiments of the present application have been described in detail, the present application is not limited to the above embodiments, and various equivalent modifications and substitutions can be made by those skilled in the art without departing from the spirit of the present application, and these equivalent modifications and substitutions are intended to be included in the scope of the present application as defined in the appended claims.
Claims (6)
1. An unsupervised rain removal method based on multi-scale fusion, which is characterized by comprising the following steps:
preprocessing the rainy image to determine micro rain-removing images with multiple scales;
according to the micro-rain removing image and the countermeasure model, determining clean images corresponding to the micro-rain removing images with different scales;
upsampling the clean image to determine an upsampled image;
determining a loss function of the countermeasure model according to a reconstruction error between the current scale up-sampling image and the previous scale clean image;
iterating the loss function, and updating parameters of the countermeasure model according to the loss function until the countermeasure model converges;
the countermeasure model specifically comprises a generator and a discriminator;
the generator is used for generating a clean image corresponding to the scale micro-rain removal image according to the micro-rain removal image;
the discriminator is used for judging the clean image and outputting a judging result;
wherein determining the loss function of the countermeasure model according to the reconstruction error between the current scale up-sampled image and the previous scale clean image comprises:
the loss function of the countermeasure model is:
wherein L is the loss function, i is the scale sequence number of the micro rain-removing image,for the reconstruction error between the up-sampled image of the i+1th scale and the i-scale micro-rain-removed image,/and->Generating a countermeasures loss for the corresponding ith scale;
the generation of countermeasures against lossThe method comprises the following steps:
wherein E represents a mathematical expectation, D i Represents the discriminator, G i Representing the generator, J i Representing said micro-raining images of different scales, I c Representing the clean image corresponding to the micro rain removing image, and c represents the serial number of the clean image.
2. The multi-scale fusion-based unsupervised rain removal method according to claim 1, wherein the preprocessing of the rainy image to determine the micro-rainy image of a plurality of scales comprises:
carrying out one-dimensional Gaussian convolution along the main direction of the rainy image to determine an initial micro-rain removal image;
downsampling the initial micro-rain removal image to determine a sampling result;
and carrying out one-dimensional Gaussian convolution on the sampling result along the main direction, and determining a micro-rain removal image of the next scale.
3. The multi-scale fusion-based unsupervised rain removal method according to claim 2, wherein the determining of the main direction comprises:
calculating the gradient direction of raindrops in each pixel point in the image with rain;
and determining the main direction of the rainy image according to the average value of the gradient directions.
4. The multi-scale fusion-based unsupervised rain removal method of claim 3, wherein the generator comprises a convolution layer, an activation layer and a regularization layer.
5. An unsupervised rain removal device based on multi-scale fusion, comprising:
at least one processor;
at least one memory for storing at least one program;
the at least one program, when executed by the at least one processor, causes the at least one processor to implement the multi-scale fusion-based unsupervised rain-removal method according to any one of claims 1-4.
6. A computer storage medium in which a processor executable program is stored, characterized in that the processor executable program when executed by the processor is for implementing an unsupervised rain-removal method based on multiscale fusion according to any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110515593.5A CN113393385B (en) | 2021-05-12 | 2021-05-12 | Multi-scale fusion-based unsupervised rain removing method, system, device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110515593.5A CN113393385B (en) | 2021-05-12 | 2021-05-12 | Multi-scale fusion-based unsupervised rain removing method, system, device and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113393385A CN113393385A (en) | 2021-09-14 |
| CN113393385B true CN113393385B (en) | 2024-01-02 |
Family
ID=77617891
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110515593.5A Active CN113393385B (en) | 2021-05-12 | 2021-05-12 | Multi-scale fusion-based unsupervised rain removing method, system, device and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113393385B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116681625B (en) * | 2023-07-04 | 2024-02-02 | 广州工程技术职业学院 | Multi-scale contrast learning-based unsupervised image rain removing method, device and terminal |
| CN116883275B (en) * | 2023-07-07 | 2023-12-29 | 广州工程技术职业学院 | Image rain removing method, system, device and medium based on boundary guidance |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110163813A (en) * | 2019-04-16 | 2019-08-23 | 中国科学院深圳先进技术研究院 | A kind of image rain removing method, device, readable storage medium storing program for executing and terminal device |
| AU2020100196A4 (en) * | 2020-02-08 | 2020-03-19 | Juwei Guan | A method of removing rain from single image based on detail supplement |
| AU2020100460A4 (en) * | 2020-03-26 | 2020-04-30 | Huang, Shuying DR | Single image deraining algorithm based on multi-scale dictionary |
| CN111340738A (en) * | 2020-03-24 | 2020-06-26 | 武汉大学 | Image rain removing method based on multi-scale progressive fusion |
| CN111860782A (en) * | 2020-07-15 | 2020-10-30 | 西安交通大学 | Triple multi-scale CycleGAN, fundus fluorography generation method, computer device, and storage medium |
| CN112348762A (en) * | 2020-11-30 | 2021-02-09 | 上海海事大学 | Single image rain removing method for generating confrontation network based on multi-scale fusion |
| CN112508083A (en) * | 2020-12-02 | 2021-03-16 | 南京邮电大学 | Image rain and fog removing method based on unsupervised attention mechanism |
-
2021
- 2021-05-12 CN CN202110515593.5A patent/CN113393385B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110163813A (en) * | 2019-04-16 | 2019-08-23 | 中国科学院深圳先进技术研究院 | A kind of image rain removing method, device, readable storage medium storing program for executing and terminal device |
| AU2020100196A4 (en) * | 2020-02-08 | 2020-03-19 | Juwei Guan | A method of removing rain from single image based on detail supplement |
| CN111340738A (en) * | 2020-03-24 | 2020-06-26 | 武汉大学 | Image rain removing method based on multi-scale progressive fusion |
| AU2020100460A4 (en) * | 2020-03-26 | 2020-04-30 | Huang, Shuying DR | Single image deraining algorithm based on multi-scale dictionary |
| CN111860782A (en) * | 2020-07-15 | 2020-10-30 | 西安交通大学 | Triple multi-scale CycleGAN, fundus fluorography generation method, computer device, and storage medium |
| CN112348762A (en) * | 2020-11-30 | 2021-02-09 | 上海海事大学 | Single image rain removing method for generating confrontation network based on multi-scale fusion |
| CN112508083A (en) * | 2020-12-02 | 2021-03-16 | 南京邮电大学 | Image rain and fog removing method based on unsupervised attention mechanism |
Non-Patent Citations (3)
| Title |
|---|
| Intelligent Wide-Area Water Quality Monitoring and Analysis System Exploiting Unmanned Surface Vehicles and Ensemble Learning;Huiru Cao et al;《Water》;第12卷(第3期);第1-15页 * |
| 基于多尺度特征融合的单帧图像去雨生成算法研究;张峥;《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》;20200615(第6期);第I138-1062页 * |
| 恶劣天气条件下的图像复原算法研究;王应龙;《中国优秀博硕士学位论文全文数据库(博士)信息科技辑》;20210115(第1期);第I138-241页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113393385A (en) | 2021-09-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110135366B (en) | Shielded pedestrian re-identification method based on multi-scale generation countermeasure network | |
| Jiang et al. | Edge-enhanced GAN for remote sensing image superresolution | |
| CN110232394B (en) | Multi-scale image semantic segmentation method | |
| Li et al. | Survey of single image super‐resolution reconstruction | |
| CN110210513B (en) | Data classification method and device and terminal equipment | |
| Zhou et al. | Scale adaptive image cropping for UAV object detection | |
| CN109035172B (en) | Non-local mean ultrasonic image denoising method based on deep learning | |
| CN113393385B (en) | Multi-scale fusion-based unsupervised rain removing method, system, device and medium | |
| Wang et al. | Cycle-snspgan: Towards real-world image dehazing via cycle spectral normalized soft likelihood estimation patch gan | |
| CN113076871A (en) | Fish shoal automatic detection method based on target shielding compensation | |
| CN112215119B (en) | Small target identification method, device and medium based on super-resolution reconstruction | |
| WO2023082453A1 (en) | Image processing method and device | |
| CN115063786A (en) | High-order distant view fuzzy license plate detection method | |
| CN111507184B (en) | Human body posture detection method based on parallel cavity convolution and body structure constraint | |
| CN113052057A (en) | Traffic sign identification method based on improved convolutional neural network | |
| Zheng et al. | T-net: Deep stacked scale-iteration network for image dehazing | |
| CN114202473A (en) | Image restoration method and device based on multi-scale features and attention mechanism | |
| CN107729885B (en) | Face enhancement method based on multiple residual error learning | |
| CN116363535A (en) | Ship detection method in unmanned aerial vehicle aerial image based on convolutional neural network | |
| CN115293992B (en) | Polarization image defogging method and device based on unsupervised weight depth model | |
| CN115953312A (en) | Joint defogging detection method and device based on single image and storage medium | |
| CN115862119A (en) | Human face age estimation method and device based on attention mechanism | |
| CN116129417A (en) | Digital instrument reading detection method based on low-quality image | |
| CN112446345B (en) | Low-quality three-dimensional face recognition method, system, equipment and storage medium | |
| CN112734675A (en) | Image rain removing method based on pyramid model and non-local enhanced dense block |
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 |