CN118175238A - Image generation method and device based on AIGC - Google Patents
Image generation method and device based on AIGC Download PDFInfo
- Publication number
- CN118175238A CN118175238A CN202410592132.1A CN202410592132A CN118175238A CN 118175238 A CN118175238 A CN 118175238A CN 202410592132 A CN202410592132 A CN 202410592132A CN 118175238 A CN118175238 A CN 118175238A
- Authority
- CN
- China
- Prior art keywords
- image
- aigc
- area
- generating
- original image
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000007547 defect Effects 0.000 claims abstract description 35
- 238000012549 training Methods 0.000 claims abstract description 24
- 230000008439 repair process Effects 0.000 claims abstract description 18
- 230000002950 deficient Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 230000001960 triggered effect Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 6
- 238000013507 mapping Methods 0.000 description 6
- 230000003068 static effect Effects 0.000 description 6
- 208000004350 Strabismus Diseases 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The application discloses an image generation method and device based on AIGC, which finish training of generating an countermeasure network model in a photographing preview stage, so that the generated countermeasure network model can generate a corresponding repair area according to the characteristics of a defect area when the defect area exists in an original image acquired by a target camera, and a repaired target image is obtained. Thereby greatly improving the quality and success rate of the mobile phone snapshot. The application provides more intelligent and convenient photographing experience for users, and ensures that every beautiful moment can be perfectly captured.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a AIGC-based image generating method and apparatus.
Background
With the widespread popularization and technical innovation of smart phones, the photographing function has become an indispensable part of the use of the phones. The mobile phone photographing is favored by the majority of users in terms of convenience and instantaneity, and plays a vital role in recording daily life, capturing good moments and sharing social networks. Modern smartphones not only are equipped with cameras with high resolution, but also integrate various photographing modes and optimization algorithms, so that photographing becomes simpler and has excellent effect. However, in the actual shooting process, especially when a person is snap shot, there are still some technical challenges.
Although mobile phone photographing technology is advancing continuously, when a person is photographed, the quality of the photo is often affected due to the dynamic characteristics of the person and the difficulty in grasping photographing timing. Particularly, at the moment of pressing the shutter, if the person closes eyes or the limbs move, the photographed picture is likely to have quality problems such as the person closes eyes, the limbs are blurred, and the like. In this case, even if the hardware configuration of the cell phone camera is further high, it is difficult to avoid such problems.
Disclosure of Invention
The object of the present application is to provide a AIGC-based image generation method and apparatus, which can improve the above problems.
In a first aspect, the present application provides an image generating method based on AIGC, which includes steps S1 to S4. The steps S1, S2, etc. are only step identifiers, and the execution sequence of the method is not necessarily performed in the order from small to large, for example, the step S2 may be performed first and then the step S1 may be performed, which is not limited by the present application.
S1, if a preset condition is met, storing at least N continuous current preview pictures of a target camera to a temporary gallery, wherein N is a positive integer;
S2, responding to shooting operation, and acquiring an original image through the target camera;
s3, if the defect area in the original image is detected, generating a corresponding repair area aiming at the defect area in the original image through a generated countermeasure network model obtained through the temporary gallery training;
S4, merging the repair area into the original image to obtain a target image.
It can be appreciated that the application discloses an image generation method based on AIGC, which completes training of generating an countermeasure network model in a photographing preview stage, so that the generated countermeasure network model can generate a corresponding repair area according to the characteristics of the defect area when the defect area exists in an original image acquired by a target camera, thereby obtaining a repaired target image. Thereby greatly improving the quality and success rate of the mobile phone snapshot. The application provides more intelligent and convenient photographing experience for users, and ensures that every beautiful moment can be perfectly captured.
In an optional embodiment of the present application, the meeting a preset condition includes at least one of: receiving a storage instruction triggered by a user; and monitoring that the change value of the current preview picture of two adjacent frames of the target camera in the preset time period is smaller than a first threshold value.
In an alternative embodiment of the present application, the variation value includes: and the displacement value of the character area in the current preview picture.
It can be understood that the method mainly generates the corresponding repair area according to the characteristics of the defect area by the generation type artificial intelligence (ARTIFICIAL INTELLIGENCE GENERATED Content, AIGC) technology, thereby achieving the effect of compensating the defect of the original image. Therefore, the sample used for AIGC training should be as static as possible, and may be automatically monitored by the image processing method in addition to the triggering of the stored instructions after the static state is determined by the user. The preset time period and the first threshold value may be set according to experience of a person skilled in the art, and the purpose of the present application is to identify whether an object photographed by the target camera is in a static state within a certain time period, such as a scene of a group photo, a swing photo, etc.
In an alternative embodiment of the application, the method further comprises the steps of: and S5, if the defect area does not exist in the original image, deleting all data in the temporary gallery.
It can be appreciated that the purpose of the present application is to make up for the flaw of the original image, and if the original image acquired by the target camera has no defective area, the preview image previously stored in the temporary gallery can no longer play a training role. In order to save the memory space and keep the content of the temporary gallery simple, all data in the temporary gallery can be deleted immediately when the defect area of the original image is detected to be absent.
In an alternative embodiment of the present application, the S2 further includes: and responding to shooting operation, and acquiring an original image through the target camera if the number of frames of the picture stored in the temporary gallery is greater than or equal to N frames.
It will be appreciated that since it takes time to build the temporary gallery, the photographing operation can be performed only under the condition that the temporary gallery is built. If the number of frames of the picture stored in the current temporary gallery is greater than or equal to N frames, the basic requirement of the temporary gallery is satisfied, and the temporary gallery is established successfully, so that the shooting instruction can be executed in response to the shooting operation input by the user. If the number of frames of the pictures stored in the current temporary gallery is less than N frames, the picture number in the temporary gallery is not satisfied with the requirement of training the subsequent generation of the countermeasure network model, and the temporary gallery is not successfully established. At this time, if a photographing operation input by the user is received, a relevant prompt may be performed through a display, an indicator light, a speaker, or the like.
In an alternative embodiment of the present application, the generating an countermeasure network model includes a feature extractor, a generator, and a arbiter; the feature extractor is used for extracting image features of an input image; the generator is used for generating a regional reconstruction image according to the image features extracted by the feature extractor; the discriminator is used for judging whether the region reconstructed image is true or false according to the region image.
It will be appreciated that training the generation of the countermeasure network by at least N frames of the current preview picture facilitates continuous adjustment of the generator therein to generate a more realistic reconstructed image of the region.
In an alternative embodiment of the present application, the defective area includes at least one of: a defective area of squinting eyes; a defective area where the limbs of the person are blurred.
It can be understood that, in response to the shooting operation, an original image is acquired through the target camera, if conditions such as limb blurring and squint exist in the original image, the user is regarded as unwilling to obtain a shooting effect, wherein a face area of squint and a blurred limb area are defect areas.
In an alternative embodiment of the present application, in training the generating an countermeasure network model by the temporary gallery, the generating an input image of the countermeasure network model includes at least one of: the eye area image of the preview picture stored in the temporary gallery; and the limb area image of the preview picture stored in the temporary gallery.
It can be understood that the training of the temporary gallery to generate the countermeasure network model can be performed after the defect area in the original image is identified, so that the training of the temporary gallery to generate the countermeasure network model can be performed pertinently through the area image, thereby greatly reducing the computational power requirement of the terminal equipment and improving the shooting efficiency.
In an alternative embodiment of the present application, the S3 includes: if the defect area exists in the original image, extracting the image characteristics of the defect area through the characteristic extractor, and generating a corresponding repair area according to the image characteristics through the generator.
In a second aspect, the present application discloses an image generating apparatus based on AIGC, comprising a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory being interconnected, wherein the memory is adapted to store a computer program comprising program instructions, the processor being configured to invoke the program instructions to perform a method according to any of the first aspects.
In a third aspect, the present application discloses a computer readable storage medium storing a computer program comprising program instructions which, when executed by a processor, cause the processor to perform the method according to any of the first aspects.
The beneficial effects are that: the application discloses an image generation method and device based on AIGC, which finish training of generating an countermeasure network model in a photographing preview stage, so that the generated countermeasure network model can generate a corresponding repair area according to the characteristics of a defect area when the defect area exists in an original image acquired by a target camera, and a repaired target image is obtained. Thereby greatly improving the quality and success rate of the mobile phone snapshot. The application provides more intelligent and convenient photographing experience for users, and ensures that every beautiful moment can be perfectly captured.
In order to make the above objects, features and advantages of the present application more comprehensible, alternative embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of an image generation method based on AIGC provided by the application;
FIG. 2 is a schematic diagram of training principles for generating an countermeasure network model provided by the application;
FIG. 3 is a schematic diagram of the operation of FIG. 2 to generate a repair area against a network model.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In a first aspect, as shown in fig. 1, the present application provides an image generating method based on AIGC, which includes steps S1 to S4. The steps S1, S2, etc. are only step identifiers, and the execution sequence of the method is not necessarily performed in the order from small to large, for example, the step S2 may be performed first and then the step S1 may be performed, which is not limited by the present application.
S1, if the preset condition is met, storing at least N continuous current preview pictures of the target camera into a temporary gallery, wherein N is a positive integer.
In an alternative embodiment of the present application, satisfying the preset condition includes at least one of: receiving a storage instruction triggered by a user; and monitoring that the change value of the current preview picture of two adjacent frames of the target camera in the preset time period is smaller than a first threshold value. Wherein the change value includes: the displacement value of the character region in the current preview screen.
It can be understood that the method mainly generates the corresponding repair area according to the characteristics of the defect area by the generation type artificial intelligence (ARTIFICIAL INTELLIGENCE GENERATED Content, AIGC) technology, thereby achieving the effect of compensating the defect of the original image. Therefore, the sample used for AIGC training should be as static as possible, and may be automatically monitored by the image processing method in addition to the triggering of the stored instructions after the static state is determined by the user. The preset time period and the first threshold value may be set according to experience of a person skilled in the art, and the purpose of the present application is to identify whether an object photographed by the target camera is in a static state within a certain time period, such as a scene of a group photo, a swing photo, etc.
S2, responding to shooting operation, and acquiring an original image through a target camera.
In an alternative embodiment of the present application, S2 further includes: and responding to shooting operation, and acquiring an original image through a target camera if the number of frames of the picture stored in the current temporary gallery is greater than or equal to N frames.
It will be appreciated that since it takes time to build the temporary gallery, the photographing operation can be performed only under the condition that the temporary gallery is built. If the number of frames of the picture stored in the current temporary gallery is greater than or equal to N frames, the basic requirement of the temporary gallery is satisfied, and the temporary gallery is established successfully, so that the shooting instruction can be executed in response to the shooting operation input by the user. If the number of frames of the pictures stored in the current temporary gallery is less than N frames, the picture number in the temporary gallery is not satisfied with the requirement of training the subsequent generation of the countermeasure network model, and the temporary gallery is not successfully established. At this time, if a photographing operation input by the user is received, a relevant prompt may be performed through a display, an indicator light, a speaker, or the like.
And S3, if the defect area in the original image is detected, generating a corresponding repair area aiming at the defect area in the original image through the generated countermeasure network model obtained through temporary gallery training.
In an alternative embodiment of the application, the method further comprises the steps of: and S5, if the defect area does not exist in the original image, deleting all data in the temporary gallery.
It can be appreciated that the purpose of the present application is to make up for the flaw of the original image, and if the original image acquired by the target camera has no defective area, the preview image previously stored in the temporary gallery can no longer play a training role. In order to save the memory space and keep the content of the temporary gallery simple, all data in the temporary gallery can be deleted immediately when the defect area of the original image is detected to be absent.
S4, merging the repair area into the original image to obtain a target image.
It can be appreciated that the application discloses an image generation method based on AIGC, which completes training of generating an countermeasure network model in a photographing preview stage, so that the generated countermeasure network model can generate a corresponding repair area according to the characteristics of the defect area when the defect area exists in an original image acquired by a target camera, thereby obtaining a repaired target image. Thereby greatly improving the quality and success rate of the mobile phone snapshot. The application provides more intelligent and convenient photographing experience for users, and ensures that every beautiful moment can be perfectly captured.
In an alternative embodiment of the application, as shown in FIG. 2, generating an countermeasure network model includes a feature extractor 101, a generator 102, and a arbiter 103; the feature extractor 101 is configured to extract image features of an input image; the generator 102 is used for generating a region reconstructed image according to the image features extracted by the feature extractor; the discriminator 103 is used for judging whether the region reconstructed image is true or false according to the region image.
It will be appreciated that training the generation of the countermeasure network by at least N frames of the current preview picture facilitates continuous adjustment of the generator therein to generate a more realistic reconstructed image of the region.
The generating countermeasure network generates the countermeasure network for the self-mapping supervision cycle, and the total loss is as follows:;
Wherein, Function corresponding to generator,/>As a function of the arbiter,/>To combat losses,/>For self-mapping check loss,/>The lost weights are checked for self-mapping.
Generating a countering loss for the countering network from the mapping supervision loop includes:
;
Wherein, Representing image features of the input image extracted by the feature extractor,/>An area image representing an image feature contained in the input image extracted by the second extractor,/>Representing a desire;
the self-mapping check loss of the self-mapping supervision loop generation countermeasure network satisfies the following equation:
。
in an alternative embodiment of the application, the defect area comprises at least one of: a defective area of squinting eyes; a defective area where the limbs of the person are blurred.
It can be understood that, in response to the shooting operation, an original image is acquired through the target camera, if conditions such as limb blurring and squint exist in the original image, the user is regarded as unwilling to obtain a shooting effect, wherein a face area of squint and a blurred limb area are defect areas.
In an alternative embodiment of the application, in generating the countermeasure network model by temporary gallery training, generating the input image of the countermeasure network model includes at least one of: an eye region image of the preview picture stored in the temporary gallery; the limb area image of the preview screen stored in the temporary gallery.
It can be understood that the training of the temporary gallery to generate the countermeasure network model can be performed after the defect area in the original image is identified, so that the training of the temporary gallery to generate the countermeasure network model can be performed pertinently through the area image, thereby greatly reducing the computational power requirement of the terminal equipment and improving the shooting efficiency.
Taking the case of recognizing the defect area of face squint in the original image as an example, as shown in fig. 2, a training process is shown, firstly extracting an eye area image of a preview picture in a temporary gallery; extracting image features of each eye region image, such as an eye angle, an eye line contour, an eye tail, etc., by the feature extractor 101, so that the generator 102 generates an eye region image in an open eye state as a region reconstruction image according to the image features; and finally judging whether the region reconstructed image is true or false according to the eye region image by a discriminator.
In an alternative embodiment of the present application, S3 includes: if the defect area exists in the original image, the image characteristics of the defect area are extracted through the characteristic extractor, and then the corresponding repair area is generated according to the image characteristics through the generator.
As shown in fig. 3, after identifying that a defective area exists in the original image, the defective area is extracted to the feature extractor 101 to extract image features, so that the generator 102 generates a corresponding repair area according to the image features, and finally fuses the repair area and the original image, so as to obtain a target image expected by a user.
In a second aspect, the present application provides an image generation apparatus based on AIGC. The AIGC-based image generation device includes one or more processors; one or more input devices, one or more output devices, and memory. The processor, the input device, the output device and the memory are connected through a bus. The memory is for storing a computer program comprising program instructions and the processor is for executing the program instructions stored by the memory. Wherein the processor is configured to invoke the program instructions to perform the operations of any of the methods of the first aspect:
It should be appreciated that in embodiments of the present invention, the Processor may be a central processing unit (Central Processing Unit, CPU), which may also be other general purpose Processor, digital signal Processor (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), off-the-shelf Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The input devices may include a touch pad, a fingerprint sensor (for collecting fingerprint information of a user and direction information of a fingerprint), a microphone, etc., and the output devices may include a display (LCD, etc.), a speaker, etc.
The memory may include read only memory and random access memory and provide instructions and data to the processor. A portion of the memory may also include non-volatile random access memory. For example, the memory may also store information of the device type.
In a specific implementation, the processor, the input device, and the output device described in the embodiments of the present invention may perform an implementation manner described in any method of the first aspect, or may perform an implementation manner of the terminal device described in the embodiments of the present invention, which is not described herein again.
In a third aspect, the present invention provides a computer readable storage medium storing a computer program comprising program instructions which when executed by a processor implement the steps of any of the methods of the first aspect.
The computer readable storage medium may be an internal storage unit of the terminal device of any of the foregoing embodiments, for example, a hard disk or a memory of the terminal device. The computer-readable storage medium may be an external storage device of the terminal device, for example, a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD), or the like, which are provided in the terminal device. Further, the computer-readable storage medium may further include both an internal storage unit and an external storage device of the terminal device. The computer-readable storage medium is used for storing the computer program and other programs and data required by the terminal device. The above-described computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In several embodiments provided in the present application, it should be understood that the disclosed terminal device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the above-described division of units is merely a logical function division, and there may be another division manner in actual implementation, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices, or elements, or may be an electrical, mechanical, or other form of connection.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment of the present invention.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units described above, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method in the various embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above description is only of alternative embodiments of the application and of illustrations of the technical principles applied. It will be appreciated by persons skilled in the art that the scope of the application referred to in the present application is not limited to the specific combinations of the technical features described above, but also covers other technical features formed by any combination of the technical features described above or their equivalents without departing from the inventive concept described above. Such as the above-mentioned features and the technical features disclosed in the present application (but not limited to) having similar functions are replaced with each other.
The above description is only of alternative embodiments of the present application and is not intended to limit the present application, and various modifications and variations will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (10)
1. A AIGC-based image generation method, comprising the steps of:
s1, if a preset condition is met, storing at least N continuous current preview pictures of a target camera to a temporary gallery, wherein N is a positive integer;
S2, responding to shooting operation, and acquiring an original image through the target camera;
s3, if the defect area in the original image is detected, generating a corresponding repair area aiming at the defect area in the original image through a generated countermeasure network model obtained through the temporary gallery training;
S4, merging the repair area into the original image to obtain a target image.
2. The AIGC-based image generation method of claim 1, wherein,
The meeting of the preset condition comprises at least one of the following:
receiving a storage instruction triggered by a user;
And monitoring that the change value of the current preview picture of two adjacent frames of the target camera in the preset time period is smaller than a first threshold value.
3. The AIGC-based image generation method of claim 2, wherein,
The change value includes: and the displacement value of the character area in the current preview picture.
4. The AIGC-based image generation method of claim 1, wherein,
The method also comprises the following steps: and S5, if the defect area does not exist in the original image, deleting all data in the temporary gallery.
5. The method for generating a AIGC-based image of claim 4,
The S2 further includes: and responding to shooting operation, and acquiring an original image through the target camera if the number of frames of the picture stored in the temporary gallery is greater than or equal to N frames.
6. The AIGC-based image generation method of claim 1, wherein,
The generation of the countermeasure network model comprises a feature extractor, a generator and a discriminator; the feature extractor is used for extracting image features of an input image; the generator is used for generating a regional reconstruction image according to the image features extracted by the feature extractor; the discriminator is used for judging whether the region reconstructed image is true or false according to the region image.
7. The AIGC-based image generation method of claim 6, wherein,
The defective area includes at least one of:
A defective area of squinting eyes;
A defective area where the limbs of the person are blurred.
8. The method of generating AIGC based image of claim 7,
In training the generating an countermeasure network model by the temporary gallery, the generating an input image of the countermeasure network model includes at least one of:
The eye area image of the preview picture stored in the temporary gallery;
and the limb area image of the preview picture stored in the temporary gallery.
9. The AIGC-based image generation method of claim 8, wherein,
The step S3 comprises the following steps: if the defect area exists in the original image, extracting the image characteristics of the defect area through the characteristic extractor, and generating a corresponding repair area according to the image characteristics through the generator.
10. A AIGC-based image generation device is characterized in that,
Comprising a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory being interconnected, wherein the memory is adapted to store a computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the method according to any of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410592132.1A CN118175238A (en) | 2024-05-14 | 2024-05-14 | Image generation method and device based on AIGC |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410592132.1A CN118175238A (en) | 2024-05-14 | 2024-05-14 | Image generation method and device based on AIGC |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118175238A true CN118175238A (en) | 2024-06-11 |
Family
ID=91350755
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410592132.1A Pending CN118175238A (en) | 2024-05-14 | 2024-05-14 | Image generation method and device based on AIGC |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118175238A (en) |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006050782A1 (en) * | 2004-11-10 | 2006-05-18 | Fotonation Vision Limited | A digital image acquisition system having means for determining a camera motion blur function |
| CN102665002A (en) * | 2012-04-18 | 2012-09-12 | 广东步步高电子工业有限公司 | Mobile communication equipment with dual photographic stabilizing function and method thereof |
| CN104281996A (en) * | 2013-07-09 | 2015-01-14 | 聚晶半导体股份有限公司 | Image denoising method and image denoising device |
| CN105472240A (en) * | 2015-11-18 | 2016-04-06 | 努比亚技术有限公司 | Method and device for image acquisition |
| CN107302666A (en) * | 2017-08-29 | 2017-10-27 | 广东欧珀移动通信有限公司 | Photographic method, mobile terminal and computer-readable recording medium |
| CN108769521A (en) * | 2018-06-05 | 2018-11-06 | Oppo广东移动通信有限公司 | A kind of photographic method, mobile terminal and computer readable storage medium |
| CN109348135A (en) * | 2018-11-21 | 2019-02-15 | Oppo广东移动通信有限公司 | Photographic method, device, storage medium and terminal device |
| CN109377448A (en) * | 2018-05-20 | 2019-02-22 | 北京工业大学 | A kind of facial image restorative procedure based on generation confrontation network |
| CN109951635A (en) * | 2019-03-18 | 2019-06-28 | Oppo广东移动通信有限公司 | It takes pictures processing method, device, mobile terminal and storage medium |
| CN110222628A (en) * | 2019-06-03 | 2019-09-10 | 电子科技大学 | A kind of face restorative procedure based on production confrontation network |
| CN110661970A (en) * | 2019-09-03 | 2020-01-07 | RealMe重庆移动通信有限公司 | Photographing method and device, storage medium and electronic equipment |
| CN111553854A (en) * | 2020-04-21 | 2020-08-18 | 维沃移动通信有限公司 | Image processing method and electronic equipment |
| CN112785507A (en) * | 2019-11-07 | 2021-05-11 | 上海耕岩智能科技有限公司 | Image processing method and device, storage medium and terminal |
| CN116091326A (en) * | 2021-11-02 | 2023-05-09 | 慧伊创新科技(北京)有限公司 | Face image shielding repair algorithm based on deep learning and application research thereof |
| CN116109505A (en) * | 2023-01-12 | 2023-05-12 | 无锡闻泰信息技术有限公司 | Image deblurring method and device, electronic equipment and storage medium |
| US20230281972A1 (en) * | 2022-05-13 | 2023-09-07 | Nanjing University Of Aeronautics And Astronautics | Few-shot defect detection method based on metric learning |
-
2024
- 2024-05-14 CN CN202410592132.1A patent/CN118175238A/en active Pending
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006050782A1 (en) * | 2004-11-10 | 2006-05-18 | Fotonation Vision Limited | A digital image acquisition system having means for determining a camera motion blur function |
| CN102665002A (en) * | 2012-04-18 | 2012-09-12 | 广东步步高电子工业有限公司 | Mobile communication equipment with dual photographic stabilizing function and method thereof |
| CN104281996A (en) * | 2013-07-09 | 2015-01-14 | 聚晶半导体股份有限公司 | Image denoising method and image denoising device |
| CN105472240A (en) * | 2015-11-18 | 2016-04-06 | 努比亚技术有限公司 | Method and device for image acquisition |
| CN107302666A (en) * | 2017-08-29 | 2017-10-27 | 广东欧珀移动通信有限公司 | Photographic method, mobile terminal and computer-readable recording medium |
| CN109377448A (en) * | 2018-05-20 | 2019-02-22 | 北京工业大学 | A kind of facial image restorative procedure based on generation confrontation network |
| CN108769521A (en) * | 2018-06-05 | 2018-11-06 | Oppo广东移动通信有限公司 | A kind of photographic method, mobile terminal and computer readable storage medium |
| CN109348135A (en) * | 2018-11-21 | 2019-02-15 | Oppo广东移动通信有限公司 | Photographic method, device, storage medium and terminal device |
| CN109951635A (en) * | 2019-03-18 | 2019-06-28 | Oppo广东移动通信有限公司 | It takes pictures processing method, device, mobile terminal and storage medium |
| CN110222628A (en) * | 2019-06-03 | 2019-09-10 | 电子科技大学 | A kind of face restorative procedure based on production confrontation network |
| CN110661970A (en) * | 2019-09-03 | 2020-01-07 | RealMe重庆移动通信有限公司 | Photographing method and device, storage medium and electronic equipment |
| CN112785507A (en) * | 2019-11-07 | 2021-05-11 | 上海耕岩智能科技有限公司 | Image processing method and device, storage medium and terminal |
| CN111553854A (en) * | 2020-04-21 | 2020-08-18 | 维沃移动通信有限公司 | Image processing method and electronic equipment |
| CN116091326A (en) * | 2021-11-02 | 2023-05-09 | 慧伊创新科技(北京)有限公司 | Face image shielding repair algorithm based on deep learning and application research thereof |
| US20230281972A1 (en) * | 2022-05-13 | 2023-09-07 | Nanjing University Of Aeronautics And Astronautics | Few-shot defect detection method based on metric learning |
| CN116109505A (en) * | 2023-01-12 | 2023-05-12 | 无锡闻泰信息技术有限公司 | Image deblurring method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10949952B2 (en) | Performing detail enhancement on a target in a denoised image | |
| CN108898567B (en) | Image noise reduction method, device and system | |
| CN108805047B (en) | Living body detection method and device, electronic equipment and computer readable medium | |
| CN108875333B (en) | Terminal unlocking method, terminal and computer readable storage medium | |
| CN108810413B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| CN112102204B (en) | Image enhancement method and device and electronic equipment | |
| CN108805265B (en) | Neural network model processing method and device, image processing method and mobile terminal | |
| CN113992850B (en) | ISP-based image processing method and device, storage medium and image pickup apparatus | |
| CN107040726B (en) | Double-camera synchronous exposure method and system | |
| CN111985281B (en) | Image generation model generation method and device and image generation method and device | |
| CN110443766B (en) | Image processing method and device, electronic equipment and readable storage medium | |
| CN110956679B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| CN108513069B (en) | Image processing method, image processing device, storage medium and electronic equipment | |
| CN115633262B (en) | Image processing method and electronic device | |
| CN108322648B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| CN112802033A (en) | Image processing method and device, computer readable storage medium and electronic device | |
| CN110365897B (en) | Image correction method and device, electronic equipment and computer readable storage medium | |
| CN109523456B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| CN112215069A (en) | Method, device and equipment for detecting living body and assisting living body detection | |
| CN113658065B (en) | Image noise reduction method and device, computer readable medium and electronic equipment | |
| CN108259769B (en) | Image processing method, image processing device, storage medium and electronic equipment | |
| CN108462831B (en) | Image processing method, image processing device, storage medium and electronic equipment | |
| CN108259767B (en) | Image processing method, image processing device, storage medium and electronic equipment | |
| CN108289176B (en) | Photographing question searching method, question searching device and terminal equipment | |
| CN109120856B (en) | Camera shooting method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |