[go: up one dir, main page]

WO2021139178A1 - Procédé de synthèse d'image et dispositif associé - Google Patents

Procédé de synthèse d'image et dispositif associé Download PDF

Info

Publication number
WO2021139178A1
WO2021139178A1 PCT/CN2020/111878 CN2020111878W WO2021139178A1 WO 2021139178 A1 WO2021139178 A1 WO 2021139178A1 CN 2020111878 W CN2020111878 W CN 2020111878W WO 2021139178 A1 WO2021139178 A1 WO 2021139178A1
Authority
WO
WIPO (PCT)
Prior art keywords
pixel
image
target
blurred
value
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.)
Ceased
Application number
PCT/CN2020/111878
Other languages
English (en)
Chinese (zh)
Inventor
叶明�
雷晨雨
张国辉
宋晨
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Publication of WO2021139178A1 publication Critical patent/WO2021139178A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Definitions

  • This application relates to the field of artificial intelligence and image processing technology, and in particular to an image synthesis method, device, computer equipment, and computer-readable storage medium.
  • the inventor realizes that factors such as privacy issues and data security issues have increased the difficulty of collecting image samples, resulting in insufficient image samples that cannot be collected. How to synthesize more image samples from the collected image samples has become a problem to be solved.
  • the first aspect of the present application provides an image synthesis method, the image synthesis method includes:
  • the target image is synthesized according to the plurality of blurred images, the parameter image, and the target value range.
  • a second aspect of the present application provides an image synthesis device, the image synthesis device includes:
  • the acquisition module is used to acquire standard images
  • the layering module is used to perform fuzzy layering on the standard image to obtain multiple blurred images
  • a generating module configured to generate a parameter image of the standard image based on the pixel coordinates of the standard image
  • a determining module configured to determine the number of images of the plurality of blurred images, and determine a target value range according to the number of images
  • the synthesis module is configured to synthesize a target image according to the plurality of blurred images, the parameter image, and the target value range.
  • a third aspect of the present application provides a computer device that includes a processor, and the processor is configured to execute computer-readable instructions stored in a memory to implement the following steps:
  • the target image is synthesized according to the plurality of blurred images, the parameter image, and the target value range.
  • a fourth aspect of the present application provides a computer-readable storage medium having computer-readable instructions stored on the computer-readable storage medium, and when the computer-readable instructions are executed by a processor, the following steps are implemented:
  • the target image is synthesized according to the plurality of blurred images, the parameter image, and the target value range.
  • This application obtains a standard image; performs fuzzy layering on the standard image to obtain multiple blurred images; generates a parameter image of the standard image based on the pixel coordinates of the standard image; determines the number of images of the multiple blurred images, The target value range is determined according to the number of images; and the target image is synthesized according to the plurality of blurred images, the parameter image, and the target value range.
  • the process of layering the standard image based on the fuzzy algorithm and synthesizing the target image based on the mask (parameter image) ensures the fidelity of the target image.
  • the target image is synthesized through multiple blurred images and parameter images to improve the diversity of the target image. Sex.
  • Fig. 1 is a flowchart of an image synthesis method provided by an embodiment of the present application.
  • Fig. 2 is a structural diagram of an image synthesizing device provided by an embodiment of the present application.
  • Fig. 3 is a schematic diagram of a computer device provided by an embodiment of the present application.
  • the image synthesis method of the present application is applied to one or more computer devices.
  • the computer device is a device that can automatically perform numerical calculation and/or information processing in accordance with pre-set or stored instructions.
  • Its hardware includes, but is not limited to, a microprocessor and an application specific integrated circuit (ASIC) , Programmable Gate Array (Field-Programmable Gate Array, FPGA), Digital Processor (Digital Signal Processor, DSP), embedded equipment, etc.
  • ASIC application specific integrated circuit
  • FPGA Field-Programmable Gate Array
  • DSP Digital Processor
  • embedded equipment etc.
  • This application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, small computers, large computers, including Distributed computing environment for any of the above systems or equipment, etc.
  • This application may be described in the general context of computer-executable instructions executed by a computer, such as a program module.
  • program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types.
  • This application can also be practiced in distributed computing environments. In these distributed computing environments, tasks are performed by remote processing devices connected through a communication network.
  • program modules can be located in local and remote computer storage media including storage devices.
  • the computer device may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server.
  • the computer device can interact with the user through a keyboard, a mouse, a remote control, a touch panel, or a voice control device.
  • FIG. 1 is a flowchart of an image synthesis method provided in Embodiment 1 of the present application.
  • the image synthesis method is applied to a computer device, and is used to synthesize a locally blurred target image according to a standard image.
  • the image synthesis method specifically includes the following steps. According to different requirements, the order of the steps in the flowchart can be changed, and some of the steps can be omitted.
  • the obtaining a standard image includes:
  • the standard image may include an ID card image, a face image, and the like. Factors such as data security and privacy protection will increase the difficulty of collecting the standard image.
  • a large number of standard images are required as image samples.
  • a target image is synthesized based on a standard image, and the target image can be used as an image sample, thereby expanding the image sample and solving the problem of fewer image samples.
  • the blurring and layering of the standard image includes:
  • Gaussian blur layering is performed on the standard image.
  • the performing motion blur layering on the standard image includes: configuring initial angle parameters and motion degree parameters; and generating a blurred image according to the initial angle parameters and motion degree parameters through a motion blur algorithm.
  • the motion degree parameter is adjusted successively with a preset step length, and a blurred image is generated according to the angle parameter and the motion degree parameter after each adjustment through a motion blur algorithm.
  • the value of the motion degree parameter is 1, and the preset step length is 1.
  • the value of the motion parameter is 1, the first blurred image is generated; when the adjusted motion degree parameter is 2, the second blurred image is generated; when the adjusted motion degree parameter is 3 , Generate the third blurred image, and so on.
  • performing Gaussian blur layering on the standard image includes: configuring an initial filter kernel size and filter kernel coefficients; and generating a blurred image according to the initial filter kernel size and filter kernel coefficients through a Gaussian blur algorithm.
  • the filter core coefficients are adjusted successively with a preset step size, and a blurred image is generated according to the size of the filter core and the filter core coefficients adjusted each time through a motion blur algorithm.
  • the generating the parameter image of the standard image based on the pixel coordinates of the standard image includes:
  • the pixel value of the second pixel point is calculated according to the coordinates of the first pixel point based on the pixel value calculation rule.
  • the size (width, height) of the standard image is consistent with the size (width, height) of the parameter image.
  • the coordinates of the first pixel in the standard image are obtained by the grid sampling point function as (1, 2). It is determined that the pixel with the coordinates (1, 2) in the parameter image is the second pixel.
  • the pixel value calculation rule can be set by the user, or the pixel value calculation rule can be selected from a list of pixel value calculation rules.
  • X and Y are the coordinates of the first pixel point
  • a, b, c, and d are parameters
  • z is the pixel value.
  • a calculation rule can be randomly selected as the pixel value calculation rule, or the pixel value calculation rule can be selected through a preset identifier.
  • the calculating the pixel value of the second pixel point according to the coordinates of the first pixel point based on the pixel value calculation rule includes:
  • the determining the number of images of the plurality of blurred images, and determining the target value range according to the number of images includes:
  • the number of the determined images is N.
  • N can take values of 5, 10, 20, etc.
  • the number of images is N
  • the target value range is determined to be [0, N].
  • the synthesizing a target image according to the plurality of blurred images, the parameter image, and the target value range includes:
  • the target value range is [0, N]
  • the maximum pixel value max and the minimum pixel value min in the parameter image are obtained;
  • the pixel value p of the second pixel is obtained, and the pixel value p is calculated to be mapped to all pixels.
  • the mapping value q obtained from the target value range, q (p-min)/(max-min) ⁇ N.
  • the data type of the mapping value of the second pixel point may be a floating point type.
  • a first target blurred image and a second target blurred image are determined from the plurality of blurred images according to the mapping value of the second pixel.
  • the determining the first target blurred image and the second target blurred image from the plurality of blurred images according to the mapping value of the second pixel point includes:
  • a blurred image whose serial number is consistent with the upper bound integer is determined as the second target blurred image.
  • the sorting of the plurality of blurred images includes:
  • the mapping value is 2.36
  • the upper bound integer of the mapping value is determined to be 3 (that is, an integer greater than or equal to the preset value)
  • the mapping value The lower bound integer of is 2 (that is, the upper bound integer of the mapping value minus 1);
  • the second blurred image whose serial number is consistent with the lower bound integer 2 is determined as the first target blurred image; the serial number is consistent with the upper bound integer 3
  • the third blurred image of is determined as the second target blurred image.
  • the coordinate of the second pixel is (1, 2)
  • the pixel with the coordinate of (1, 2) in the first target blurred image is determined as the third pixel
  • the coordinate in the second target blurred image is The pixel point (1, 2) is determined as the fourth pixel point
  • the pixel point with the coordinate (1, 2) in the target image is determined as the fifth pixel point.
  • the calculating the pixel value of the fifth pixel according to the mapping value of the second pixel, the pixel value of the third pixel, and the pixel value of the fourth pixel includes :
  • the mapping value is 2.36
  • the fractional part (0.36) of the mapping value is determined as the weight of the third pixel
  • 0.64 obtained by 1-0.36
  • the weight of the fourth pixel is determined as the weight of the fourth pixel; to obtain the third pixel
  • the target image After calculating the pixel value of each fifth pixel in the target image, the target image is obtained.
  • the image synthesis method of the first embodiment obtains a standard image; performs fuzzy layering on the standard image to obtain multiple blurred images; generates a parameter image of the standard image based on the pixel coordinates of the standard image; determines the multiple blurred images For the number of images, a target value range is determined according to the number of images; a target image is synthesized according to the plurality of blurred images, the parameter image, and the target value range.
  • the process of layering the standard image based on the fuzzy algorithm and synthesizing the target image based on the mask (parameter image) ensures the fidelity of the target image.
  • the target image is synthesized through multiple blurred images and parameter images to improve the diversity of the target image. Sex.
  • Fig. 2 is a structural diagram of an image synthesizing device provided in the second embodiment of the present application.
  • the image synthesis device 20 is applied to computer equipment.
  • the image synthesis device 20 is used for synthesizing a locally blurred target image according to a standard image.
  • the image synthesis device 20 may include an acquisition module 201, a layering module 202, a generation module 203, a determination module 204, and a synthesis module 205.
  • the obtaining module 201 is used to obtain a standard image.
  • the obtaining a standard image includes:
  • the standard image may include an ID card image, a face image, and the like. Factors such as data security and privacy protection will increase the difficulty of collecting the standard image.
  • a large number of standard images are required as image samples.
  • a target image is synthesized based on a standard image, and the target image can be used as an image sample, thereby expanding the image sample and solving the problem of fewer image samples.
  • the layering module 202 is used to perform fuzzy layering on the standard image to obtain multiple blurred images.
  • the blurring and layering of the standard image includes:
  • Gaussian blur layering is performed on the standard image.
  • the performing motion blur layering on the standard image includes: configuring initial angle parameters and motion degree parameters; and generating a blurred image according to the initial angle parameters and motion degree parameters through a motion blur algorithm.
  • the motion degree parameter is adjusted successively with a preset step length, and a blurred image is generated according to the angle parameter and the motion degree parameter after each adjustment through a motion blur algorithm.
  • the value of the motion degree parameter is 1, and the preset step length is 1.
  • the value of the motion parameter is 1, the first blurred image is generated; when the adjusted motion degree parameter is 2, the second blurred image is generated; when the adjusted motion degree parameter is 3 , Generate the third blurred image, and so on.
  • performing Gaussian blur layering on the standard image includes: configuring an initial filter kernel size and filter kernel coefficients; and generating a blurred image according to the initial filter kernel size and filter kernel coefficients through a Gaussian blur algorithm.
  • the filter core coefficients are adjusted successively with a preset step size, and a blurred image is generated according to the size of the filter core and the filter core coefficients adjusted each time through a motion blur algorithm.
  • the generating module 203 is configured to generate a parameter image of the standard image based on the pixel coordinates of the standard image.
  • the generating the parameter image of the standard image based on the pixel coordinates of the standard image includes:
  • the pixel value of the second pixel point is calculated according to the coordinates of the first pixel point based on the pixel value calculation rule.
  • the size (width, height) of the standard image is consistent with the size (width, height) of the parameter image.
  • the coordinates of the first pixel in the standard image are obtained by the grid sampling point function as (1, 2). It is determined that the pixel with the coordinates (1, 2) in the parameter image is the second pixel.
  • the pixel value calculation rule can be set by the user, or the pixel value calculation rule can be selected from a list of pixel value calculation rules.
  • X and Y are the coordinates of the first pixel point
  • a, b, c, and d are parameters
  • z is the pixel value.
  • a calculation rule may be randomly selected as the pixel value calculation rule, or the pixel value calculation rule may be selected through a preset identifier.
  • the calculating the pixel value of the second pixel point according to the coordinates of the first pixel point based on the pixel value calculation rule includes:
  • the determining module 204 is configured to determine the number of images of the plurality of blurred images, and determine the target value range according to the number of images.
  • the determining the number of images of the plurality of blurred images, and determining the target value range according to the number of images includes:
  • the number of the determined images is N.
  • N can take values of 5, 10, 20, etc.
  • the number of images is N
  • the target value range is determined to be [0, N].
  • the synthesis module 205 is configured to synthesize a target image according to the plurality of blurred images, the parameter image, and the target value range.
  • the synthesizing a target image according to the plurality of blurred images, the parameter image, and the target value range includes:
  • the target value range is [0, N]
  • the maximum pixel value max and the minimum pixel value min in the parameter image are obtained;
  • the pixel value p of the second pixel is obtained, and the pixel value p is calculated to be mapped to all pixels.
  • the mapping value q obtained from the target value range, q (p-min)/(max-min) ⁇ N.
  • the data type of the mapping value of the second pixel point may be a floating point type.
  • a first target blurred image and a second target blurred image are determined from the plurality of blurred images according to the mapping value of the second pixel.
  • the determining the first target blurred image and the second target blurred image from the plurality of blurred images according to the mapping value of the second pixel point includes:
  • a blurred image whose serial number is consistent with the upper bound integer is determined as the second target blurred image.
  • the sorting of the plurality of blurred images includes:
  • the mapping value is 2.36
  • the upper bound integer of the mapping value is determined to be 3 (that is, an integer greater than or equal to the preset value)
  • the mapping value The lower bound integer of is 2 (that is, the upper bound integer of the mapping value minus 1);
  • the second blurred image whose serial number is consistent with the lower bound integer 2 is determined as the first target blurred image; the serial number is consistent with the upper bound integer 3
  • the third blurred image of is determined as the second target blurred image.
  • the coordinate of the second pixel is (1, 2)
  • the pixel with the coordinate of (1, 2) in the first target blurred image is determined as the third pixel
  • the coordinate in the second target blurred image is The pixel point (1, 2) is determined as the fourth pixel point
  • the pixel point with the coordinate (1, 2) in the target image is determined as the fifth pixel point.
  • the calculating the pixel value of the fifth pixel according to the mapping value of the second pixel, the pixel value of the third pixel, and the pixel value of the fourth pixel includes :
  • the mapping value is 2.36
  • the fractional part (0.36) of the mapping value is determined as the weight of the third pixel
  • 0.64 obtained by 1-0.36
  • the weight of the fourth pixel is determined as the weight of the fourth pixel; to obtain the third pixel
  • the target image After calculating the pixel value of each fifth pixel in the target image, the target image is obtained.
  • the image synthesis device 20 of the second embodiment obtains a standard image; performs fuzzy layering on the standard image to obtain multiple blurred images; generates a parameter image of the standard image based on the pixel coordinates of the standard image; determines the multiple For the number of blurred images, a target value range is determined according to the number of images; and a target image is synthesized according to the plurality of blurred images, the parameter image, and the target value range.
  • the process of layering the standard image based on the fuzzy algorithm and synthesizing the target image based on the mask (parameter image) ensures the fidelity of the target image.
  • the target image is synthesized through multiple blurred images and parameter images to improve the diversity of the target image. Sex.
  • This embodiment provides a computer-readable storage medium having computer-readable instructions stored on the computer-readable storage medium.
  • the computer-readable storage medium may be nonvolatile or volatile.
  • the computer-readable instructions when executed by the processor, implement the steps in the above-mentioned image synthesis method embodiment, for example, steps 101-105 shown in Fig. 1:
  • each module in the above-mentioned device embodiment is realized, for example, the modules 201-205 in FIG. 2:
  • the obtaining module 201 is used to obtain a standard image
  • the layering module 202 is configured to perform fuzzy layering on the standard image to obtain multiple blurred images
  • a generating module 203 configured to generate a parameter image of the standard image based on the pixel coordinates of the standard image
  • the determining module 204 is configured to determine the number of images of the plurality of blurred images, and determine the target value range according to the number of images;
  • the synthesis module 205 is configured to synthesize a target image according to the plurality of blurred images, the parameter image, and the target value range.
  • FIG. 3 is a schematic diagram of the computer equipment provided in the fourth embodiment of the application.
  • the computer device 30 includes a memory 301, a processor 302, and computer-readable instructions stored in the memory 301 and running on the processor 302, such as an image synthesis program.
  • the processor 302 executes the computer-readable instructions, the steps in the embodiment of the image synthesis method described above are implemented, for example, steps 101-105 shown in FIG. 1:
  • each module in the above-mentioned device embodiment is realized, for example, the modules 201-205 in FIG. 2:
  • the obtaining module 201 is used to obtain a standard image
  • the layering module 202 is configured to perform fuzzy layering on the standard image to obtain multiple blurred images
  • a generating module 203 configured to generate a parameter image of the standard image based on the pixel coordinates of the standard image
  • the determining module 204 is configured to determine the number of images of the plurality of blurred images, and determine the target value range according to the number of images;
  • the synthesis module 205 is configured to synthesize a target image according to the plurality of blurred images, the parameter image, and the target value range.
  • the computer-readable instructions may be divided into one or more modules, and the one or more modules are stored in the memory 301 and executed by the processor 302 to complete the method.
  • the one or more modules may be a series of computer-readable instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer-readable instructions in the computer device 30.
  • the computer-readable instructions may be divided into the acquisition module 201, the layering module 202, the generating module 203, the determining module 204, and the synthesizing module 205 in FIG. 2.
  • the specific functions of each module refer to the second embodiment.
  • the computer device 30 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server.
  • a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server.
  • the schematic diagram 3 is only an example of the computer device 30, and does not constitute a limitation on the computer device 30. It may include more or less components than those shown in the figure, or combine certain components, or different components.
  • the computer device 30 may also include input and output devices, network access devices, buses, and so on.
  • the so-called processor 302 may be a central processing unit (Central Processing Unit, CPU), other general processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
  • the general-purpose processor can be a microprocessor or the processor 302 can also be any conventional processor, etc.
  • the processor 302 is the control center of the computer device 30, which uses various interfaces and lines to connect the entire computer device 30 Various parts.
  • the memory 301 may be used to store the computer-readable instructions, and the processor 302 executes or executes the computer-readable instructions or modules stored in the memory 301 and calls the data stored in the memory 301 to implement all the instructions.
  • the various functions of the computer device 30 are described.
  • the memory 301 may mainly include a storage program area and a storage data area, where the storage program area may store an operating system, an application program required by at least one function (such as a sound playback function, an image playback function, etc.); the storage data area may Data and the like created in accordance with the use of the computer device 30 are stored.
  • the memory 301 may include a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a Secure Digital (SD) card, a flash memory card (Flash Card), at least one disk storage device, flash memory Devices, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), or other non-volatile/volatile storage devices.
  • the integrated module of the computer device 30 may be stored in a computer-readable storage medium.
  • the computer-readable storage medium may be non-volatile or volatile. Based on this understanding, this application implements all or part of the processes in the above-mentioned embodiments and methods, and can also be completed by instructing relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium.
  • the computer-readable instruction when executed by the processor, it can implement the steps of the foregoing method embodiments.
  • the computer-readable instructions may be in the form of source code, object code, executable file, or some intermediate forms, etc.
  • the computer-readable storage medium may include: any entity or device capable of carrying the computer-readable instructions, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, read only memory (ROM), random access memory ( RAM).
  • modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • the functional modules in the various embodiments of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module.
  • the above-mentioned integrated modules can be implemented in the form of hardware, or in the form of hardware plus software functional modules.
  • the above-mentioned integrated modules implemented in the form of software functional modules may be stored in a computer-readable storage medium.
  • the above-mentioned software function module is stored in a storage medium, and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform the image synthesis described in the various embodiments of this application. Part of the method.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Image Processing (AREA)

Abstract

La présente demande se rapporte au domaine technique du traitement des images en vision par ordinateur, et concerne un procédé de synthèse d'image et un dispositif associé. Le procédé de synthèse d'image consiste à acquérir une image standard ; à réaliser une division hiérarchique floue sur l'image standard pour obtenir une pluralité d'images floues ; sur la base de coordonnées de pixel de l'image standard, générer une image paramétrique de l'image standard ; déterminer la quantité d'images de la pluralité d'images floues et, sur la base de la quantité d'images, déterminer une plage cible ; et sur la base de la pluralité d'images floues, de l'image paramétrique et de la plage cible, synthétiser une image cible. Dans la présente invention, une image cible floue locale est synthétisée sur la base d'une image standard, ce qui améliore la diversité et la fidélité d'images synthétisées.
PCT/CN2020/111878 2020-07-28 2020-08-27 Procédé de synthèse d'image et dispositif associé Ceased WO2021139178A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010740642.0A CN111861963B (zh) 2020-07-28 2020-07-28 图像合成方法及相关设备
CN202010740642.0 2020-07-28

Publications (1)

Publication Number Publication Date
WO2021139178A1 true WO2021139178A1 (fr) 2021-07-15

Family

ID=72948495

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/111878 Ceased WO2021139178A1 (fr) 2020-07-28 2020-08-27 Procédé de synthèse d'image et dispositif associé

Country Status (2)

Country Link
CN (1) CN111861963B (fr)
WO (1) WO2021139178A1 (fr)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114140811A (zh) * 2021-11-04 2022-03-04 北京中交兴路信息科技有限公司 一种证件样本生成方法、装置、电子设备和存储介质
CN114329539A (zh) * 2021-12-24 2022-04-12 杭州海康机器人技术有限公司 加密图像的方法、校验图像的方法、装置及系统
CN115439343A (zh) * 2022-06-17 2022-12-06 北京罗克维尔斯科技有限公司 圆角区域的模糊处理方法、装置、电子设备和介质
CN115797395A (zh) * 2022-11-03 2023-03-14 网易（杭州）网络有限公司 运动模糊图像的生成方法、装置、电子设备和存储介质
CN118646959A (zh) * 2024-08-13 2024-09-13 浙江大华技术股份有限公司 一种图像调整方法、装置、监控系统和存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6181829B1 (en) * 1998-01-21 2001-01-30 Xerox Corporation Method and system for classifying and processing of pixels of image data
CN102148930A (zh) * 2010-02-05 2011-08-10 佳能株式会社 摄像设备和图像处理方法
CN108073909A (zh) * 2017-12-29 2018-05-25 深圳云天励飞技术有限公司 合成模糊人脸图像的方法和装置、计算机装置及存储介质
CN110992395A (zh) * 2019-11-01 2020-04-10 北京达佳互联信息技术有限公司 图像训练样本的生成方法及装置、运动跟踪方法及装置

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006011539A (ja) * 2004-06-22 2006-01-12 Namco Ltd プログラム、情報記憶媒体、及び画像生成システム
TWI462054B (zh) * 2012-05-15 2014-11-21 Nat Univ Chung Cheng Estimation Method of Image Vagueness and Evaluation Method of Image Quality

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6181829B1 (en) * 1998-01-21 2001-01-30 Xerox Corporation Method and system for classifying and processing of pixels of image data
CN102148930A (zh) * 2010-02-05 2011-08-10 佳能株式会社 摄像设备和图像处理方法
CN108073909A (zh) * 2017-12-29 2018-05-25 深圳云天励飞技术有限公司 合成模糊人脸图像的方法和装置、计算机装置及存储介质
CN110992395A (zh) * 2019-11-01 2020-04-10 北京达佳互联信息技术有限公司 图像训练样本的生成方法及装置、运动跟踪方法及装置

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114140811A (zh) * 2021-11-04 2022-03-04 北京中交兴路信息科技有限公司 一种证件样本生成方法、装置、电子设备和存储介质
CN114329539A (zh) * 2021-12-24 2022-04-12 杭州海康机器人技术有限公司 加密图像的方法、校验图像的方法、装置及系统
CN115439343A (zh) * 2022-06-17 2022-12-06 北京罗克维尔斯科技有限公司 圆角区域的模糊处理方法、装置、电子设备和介质
CN115797395A (zh) * 2022-11-03 2023-03-14 网易（杭州）网络有限公司 运动模糊图像的生成方法、装置、电子设备和存储介质
CN118646959A (zh) * 2024-08-13 2024-09-13 浙江大华技术股份有限公司 一种图像调整方法、装置、监控系统和存储介质

Also Published As

Publication number Publication date
CN111861963A (zh) 2020-10-30
CN111861963B (zh) 2023-08-01

Similar Documents

Publication Publication Date Title
WO2021139178A1 (fr) Procédé de synthèse d'image et dispositif associé
CN112560980A (zh) 目标检测模型的训练方法、装置及终端设备
CN110660066A (zh) 网络的训练方法、图像处理方法、网络、终端设备及介质
WO2021164269A1 (fr) Procédé et appareil d'acquisition de carte de disparité basés sur un mécanisme d'attention
CN111290684B (zh) 图像显示方法、图像显示装置及终端设备
US12373928B2 (en) Image correction method and computing device utilizing method
CN108830787A (zh) 图像变形的方法、装置及电子设备
CN114372931A (zh) 一种目标对象虚化方法、装置、存储介质及电子设备
CN111754435A (zh) 图像处理方法、装置、终端设备及计算机可读存储介质
CN112419342B (zh) 图像处理方法、装置、电子设备和计算机可读介质
CN113887507A (zh) 人脸图像处理方法、装置、电子设备及存储介质
CN113610958A (zh) 一种基于风格迁移的3d图像构建方法、装置及终端
CN111340722B (zh) 图像处理方法、处理装置、终端设备及可读存储介质
WO2022001648A1 (fr) Procédé et appareil de traitement d'images, ainsi que dispositif et support
CN114493988A (zh) 一种图像虚化方法、图像虚化装置及终端设备
CN113407537B (zh) 数据处理方法、装置及电子设备
CN111784607B (zh) 图像色调映射方法、装置、终端设备及存储介质
CN111210500B (zh) 一种三维点云处理方法及装置
CN114677319A (zh) 干细胞分布确定方法、装置、电子设备及存储介质
CN111754411A (zh) 图像降噪方法、图像降噪装置及终端设备
CN116977539A (zh) 图像处理方法、装置、计算机设备、存储介质和程序产品
CN110619668A (zh) 一种图像抽象方法、装置及终端设备
CN117634751B (zh) 数据要素评估方法、装置、计算机设备以及存储介质
CN112105051B (zh) 热力图生成方法及电子设备
CN114782862B (zh) 一种平面检测方法、设备、介质及程序产品

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20912126

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20912126

Country of ref document: EP

Kind code of ref document: A1