WO2023241427A1 - 图像处理方法、装置、设备及存储介质 - Google Patents

图像处理方法、装置、设备及存储介质 Download PDF

Info

Publication number
WO2023241427A1
WO2023241427A1 PCT/CN2023/098807 CN2023098807W WO2023241427A1 WO 2023241427 A1 WO2023241427 A1 WO 2023241427A1 CN 2023098807 W CN2023098807 W CN 2023098807W WO 2023241427 A1 WO2023241427 A1 WO 2023241427A1
Authority
WO
WIPO (PCT)
Prior art keywords
original images
server
image
current screen
original
Prior art date
Application number
PCT/CN2023/098807
Other languages
English (en)
French (fr)
Inventor
马佳欣
刘纯
彭威
王瑞梦
Original Assignee
北京字跳网络技术有限公司
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 北京字跳网络技术有限公司 filed Critical 北京字跳网络技术有限公司
Publication of WO2023241427A1 publication Critical patent/WO2023241427A1/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration
    • G06T5/50Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20212Image combination
    • G06T2207/20221Image fusion; Image merging

Definitions

  • mobile terminals have become one of the indispensable tools for users to carry out entertainment activities. Users can use mobile terminals to perform a variety of image processing. In related technologies, most of the image processing is implemented by running local algorithms on the client. Due to the limitations of the hardware configuration of the mobile terminal, the efficiency of image processing is low, and the accuracy of the processed image is poor. Affect image processing effects.
  • Embodiments of the present disclosure provide an image processing method, device, equipment and storage medium, which send multiple images to the server for fusion processing, which can not only reduce the data processing pressure on the client, but also improve the image fusion effect.
  • an embodiment of the present disclosure provides an image processing method, including:
  • the server Receive the first target image returned by the server, and display the first target image on the current screen; wherein the first target image is an image obtained by the server after fusion processing of the at least two original images.
  • embodiments of the present disclosure also provide an image processing device, including:
  • the original image acquisition module is configured to acquire at least two original images
  • the original image sending module is configured to display the at least two original images on the current screen in a set manner, and send the at least two original images to the server, so that the server can Two original images are fused;
  • the first target image display module is configured to receive the first target image returned by the server and display the first target image on the current screen; wherein the first target image is the server's response to the at least two original images.
  • embodiments of the present disclosure also provide an electronic device, where the electronic device includes:
  • a storage device configured to store one or more programs
  • the one or more processors When the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the image processing method as described in the embodiment of the present disclosure.
  • embodiments of the disclosure further provide a storage medium containing computer-executable instructions, which when executed by a computer processor are used to perform the image processing method as described in embodiments of the disclosure.
  • Figure 2a is a schematic diagram of a user selecting a local image provided by an embodiment of the present disclosure
  • Figure 2c is an example of the original image provided by the embodiment of the present disclosure being displayed on the screen
  • FIG. 4 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.
  • the original image can be the image to be processed.
  • the method of obtaining at least two original images can be: frame grabbing and/or local upload. That is, the at least two original images may be both acquired through frame grabbing, or both may be uploaded locally, or part of the original images may be acquired through frame grabbing and partially uploaded locally.
  • the method of obtaining at least two original images may be: when detecting the first operation triggered by the user, performing at least two consecutive frame capture processes on the current picture to obtain at least two original images; or, when detecting When the user selects at least two original images locally and triggers the second operation, the at least two original images selected by the user are used as the at least two acquired original images.
  • the first operation may be an operation that triggers the terminal device to perform frame capture processing on the current screen. For example, it may be clicking the screen, double-clicking the screen, detecting the user's set gesture or posture, or collecting a message containing a set keyword. Voice signal, etc., or a control button that triggers frame capture is set in the interface, and the user clicks the control button to trigger frame capture.
  • Frame capture can also be called screen capture. By calling the frame capture function, the content displayed on the current screen is captured to obtain the original image.
  • the frame capture processing can also be triggered by a countdown. When the terminal enters the image processing props, it will start to display the countdown number "321" on the interface.
  • a frame capture operation After the countdown is over, a frame capture operation will be performed and "321" will continue to be displayed. Count down the number. After the countdown ends, perform a frame capture operation until the number of captured frames reaches the set value. For example, when a user opens an image processing prop through a terminal device, the terminal device displays the image currently collected by the camera on the current screen in real time, or obtains a video file from a local database or a network database and plays it on the current interface. When the terminal device detects the first operation triggered by the user, it performs at least two consecutive frame capture processes on the content displayed on the current screen to obtain at least two original images.
  • the second operation may be an operation for confirming at least two original images selected by the user.
  • the interface displays a button to add a local image.
  • the terminal displays the locally stored image on the current interface for the user to select.
  • the user detects When at least two original images are selected and the second operation is triggered, the at least two original images selected by the user are used as the at least two original images obtained.
  • Figure 2a is a schematic diagram of the user selecting a local image in this embodiment. As shown in Figure 2a, the user clicks the "+" button, and the terminal displays the locally stored image on the current interface. Assume that the user selects image 1 and image 1. 3, and click the "Confirm” button, then image 1 and image 3 will be used as the final original images obtained.
  • the original image is obtained through frame grabbing or local selection, which can improve the diversity of the original image.
  • the method of obtaining at least two original images may be: during the process of capturing the current picture for at least two consecutive times, if it is detected that the user selects at least two original images locally and triggers the second operation, Then the frame capture processing is terminated, the captured images are deleted, and at least two original images selected by the user are used as the at least two acquired original images.
  • the process of performing at least two consecutive frame capture processes on the current picture can be understood as a period during which frame capture of the current picture has been started but has not been completed. For example, when the terminal has started to capture the current picture but has not completed the frame capture, if it is detected that the user selects at least two original images locally and triggers the second operation, the terminal is controlled to stop capturing the current picture. Frame processing, deleting the captured frame-captured images, and finally using at least two original images selected by the user as the acquired at least two original images. In this embodiment, optionally, the image selected by the user locally can be determined as the acquired original image to meet the user's personalized needs for image processing.
  • S120 Display at least two original images on the current screen according to the setting method, and send the at least two original images to the server, so that the server performs fusion processing on the at least two original images.
  • the setting method can be to display animation or to display still for a set duration.
  • the method of displaying at least two original images on the current screen can be set according to requirements.
  • the method of displaying at least two original images on the current screen according to the setting method may be: obtaining the playback animations corresponding to the at least two original images respectively; and displaying the at least two original images on the current screen according to the playback animation.
  • the playback animation consists of multiple frames, and each frame of the animation image contains the motion information and display information of the original image in the screen.
  • the motion information includes position information and rotation information
  • the display information includes size information and transparency information.
  • the position information can be understood as the position coordinates of the center point of the original image in the current frame.
  • the rotation information can be understood as the angle between the horizontal edge of the original image and the horizontal or vertical direction, or the vertical edge of the original image and the horizontal or vertical direction. angle in the straight direction.
  • the size information can be the length and height of the original image
  • the transparency information can be understood as the display transparency of the original image.
  • the transparency information may be a value between 0 and 1, with 0 representing completely transparent and 1 representing completely opaque.
  • the transparency information of the original image in the animation can be determined based on the overlap of multiple original images. For example, when multiple original images do not overlap, the transparency information of each original image is 1.
  • the transparency of one or more of the original images can be reduced according to the degree of overlap. For example, the corresponding relationship between the overlap degree and the transparency adjustment amount can be established in advance, so that the adjustment amount is determined based on the overlap degree, and the transparency of one or more of the original images is reduced based on the adjustment amount.
  • the motion information and display information of the original image in the animation can be set arbitrarily, or multiple candidate animations can be preset for the user to select.
  • the playback animation corresponding to the two original images can be: the two original images first fly into the current picture from the left and right upper boundaries of the screen, and when the two original images meet in the picture , the two original images move toward the center of the screen. When they move to the center of the screen, the two original images move in opposite directions. The two original images gradually overlap until the two original images complete the overlap, and the animation ends.
  • Figure 2b is an example of the original image displayed on the screen in this embodiment. As shown in Figure 2b, the original image on the left is tilted to the left. The original image on the right is tilted to the right.
  • the at least two original images are displayed on the current screen according to the animation, which can improve the diversity of screen display and improve user experience.
  • the method of displaying at least two original images on the current screen according to the set mode may be: obtaining the set material; still displaying the at least two original images on the current screen according to the first transparency, and displaying the set material according to the first transparency. 2. Transparency is displayed on the current screen.
  • the first transparency is greater than the second transparency, that is, the original image is not completely covered by the set material, and the original image can be seen through the set material.
  • the set material may be a video file, and the video file is composed of a sequence of material pictures, that is, it is composed of multiple material pictures.
  • the material picture can be an image preset by the developer, or a sequence of material pictures used for timing. For example: it can be a sequence of material images in the form of a progress bar, a sequence of material images in the form of a countdown, or a sequence of material images combined with a countdown and a progress bar.
  • At least two original images and the set material are displayed on the current screen at the same time, and the duration for which the at least two original images are still displayed on the current screen is determined by the duration corresponding to the set material.
  • Figure 2c is an example of the original image displayed on the screen in this embodiment. As shown in Figure 2c, two original images are still displayed on the current screen, and the set material is an image sequence generated by a piece of prompt information.
  • the setting material and at least two original images are displayed on the current screen at the same time, which can improve screen display diversity and improve user experience.
  • the process of sending at least two original images to the server so that the server performs fusion processing on the at least two original images may be: sending at least two original images carrying algorithm identifiers to the server so that The server calls the target fusion algorithm according to the algorithm identifier to use the target fusion algorithm to fuse at least two original images.
  • the algorithm identification may consist of information such as algorithm name, algorithm storage address, etc.
  • the target fusion algorithm can be a constructed neural network model, such as: Generative Adversarial Nets (GAN), etc.
  • GAN Generative Adversarial Nets
  • different fusion functions correspond to different fusion algorithms.
  • An image processing prop can set one or more fusion algorithms on the server side, and the user can select the required fusion algorithm.
  • the fusion algorithm may be to fuse at least two facial images into one "baby" image, or to fuse at least two facial images into one virtual facial image, or to fuse at least two differently stylized images.
  • the functions of the fusion algorithm can be set according to needs.
  • the server while sending the at least two original images to the server, it also includes the following steps: calling a local setting algorithm to process any one of the at least two original images to obtain a second target image.
  • S130 Receive the first target image returned by the server, and display the first target image on the current screen.
  • the following steps are also included: if the first target image returned by the server is not received, displaying the second target image on the current screen. Or, if the first target image returned by the server is not received, the setting information is displayed on the current screen.
  • FIG 3 is a schematic structural diagram of an image processing device provided by an embodiment of the present disclosure. As shown in Figure 3, the device includes:
  • the at least two original images selected by the user are used as the at least two acquired original images.
  • the original image acquisition module 310 is also configured to acquire the at least two original images in the following manner:
  • the frame capturing process will be stopped and the captured images will be deleted. And the at least two original images selected by the user are used as the at least two acquired original images.
  • the original image sending module 320 is configured to send the at least two original images to the server for fusion processing in the following manner:
  • At least two original images carrying algorithm identifiers are sent to the server, so that the server calls the target fusion algorithm according to the algorithm identifier to use the target fusion algorithm to fuse the at least two original images.
  • the local setting algorithm is called to process any one of the at least two original images to obtain the second target image; wherein the local setting algorithm corresponds to the target fusion algorithm.
  • the device also includes: a second target image display module, set to:
  • the second target image is displayed on the current screen.
  • the device also includes: an original image display module, set to:
  • the original image display module is configured to display the at least two original images on the current screen according to the animation playback in the following manner:
  • At least two original images are still displayed on the current screen according to the first transparency, and the set material is displayed on the current screen according to the second transparency; wherein the first transparency is greater than the second transparency.
  • the setting information is displayed on the current screen.
  • the image processing device provided by the embodiments of the present disclosure can execute the image processing method provided by any embodiment of the present disclosure, and has functional modules and beneficial effects corresponding to the execution method.
  • FIG. 4 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.
  • Terminal devices in embodiments of the present disclosure may include mobile phones, notebook computers, digital broadcast receivers, personal digital assistants (Personal Digital Assistant, PDA), tablet computers (Portable Android Device, PAD), portable multimedia players (Portable Media Player, PMP), mobile terminals such as vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital televisions (television, TV), desktop computers, etc.
  • PDA Personal Digital Assistant
  • PAD Portable multimedia players
  • PMP portable multimedia players
  • mobile terminals such as vehicle-mounted terminals (such as vehicle-mounted navigation terminals)
  • fixed terminals such as digital televisions (television, TV), desktop computers, etc.
  • the electronic device shown in Figure 4 is only an example.
  • the electronic device 500 may include a processing device (such as a central processing unit, a graphics processor, etc.) 501, which may process data according to a program stored in a read-only memory (Read Only Memory, ROM) 502 or from a storage device 508
  • the program loaded into the random access memory (Random Access Memory, RAM) 503 performs various appropriate actions and processes.
  • RAM Random Access Memory
  • various programs and data required for the operation of the electronic device 500 are also stored.
  • the processing device 501, ROM 502 and RAM 503 are connected to each other via a bus 504.
  • An input/output (I/O) interface 505 is also connected to bus 504.
  • input devices 506 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a Liquid Crystal Display (LCD) , an output device 507 such as a speaker, a vibrator, etc.; a storage device 508 including a magnetic tape, a hard disk, etc.; and a communication device 509.
  • Communication device 509 may allow electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data.
  • FIG. 4 illustrates electronic device 500 with various means, it should be understood that implementation or availability of all illustrated means is not required. More or fewer means may alternatively be implemented or provided.
  • embodiments of the present disclosure include a computer program product including a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the method illustrated in the flowchart.
  • the computer program may be downloaded and installed from the network via communication device 509, or from storage device 508, or from ROM 502.
  • the processing device 501 When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.
  • Embodiments of the present disclosure provide a computer storage medium on which a computer program is stored.
  • the program is executed by a processor, the image processing method provided by the above embodiments is implemented.
  • the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or a combination of the above two.
  • the computer-readable storage medium may be, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or a combination thereof.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code therein. Such propagated data signals may take a variety of forms, including electromagnetic signals, optical signals, or a suitable combination of the above.
  • a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device .
  • Program code contained on a computer-readable medium can be transmitted using any appropriate medium, including: wires, optical cables, radio frequency (Radio Frequency, RF), etc., or appropriate combinations of the above.
  • the client and server can communicate using currently known or future developed network protocols such as HyperText Transfer Protocol (HTTP), and can communicate with digital data in any form or medium (e.g., communications network) interconnection.
  • HTTP HyperText Transfer Protocol
  • Examples of communication networks include local area networks (LAN), wide area networks (WAN), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as currently known or networks for future research and development.
  • the computer-readable medium carries at least one program.
  • the electronic device acquires at least two original images; displays the at least two original images on the current screen in a set manner. screen, and send the at least two original images to the server, so that the server performs fusion processing on the at least two original images; receive the first target image returned by the server, and display the first target image on The current picture; wherein, the first target image is an image obtained by the server after fusing the at least two original images.
  • Programs for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof.
  • Computer program code the above-mentioned programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as "C" language or similar programming languages.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (such as through the Internet using an Internet service provider) .
  • LAN local area network
  • WAN wide area network
  • each block of the block diagram and/or flowchart illustration, and combinations of blocks in the block diagram and/or flowchart illustration can be implemented by special purpose hardware-based systems that perform the specified functions or operations. , or can be implemented using a combination of specialized hardware and computer instructions.
  • the units involved in the embodiments of the present disclosure can be implemented in software or hardware.
  • the name of the unit does not constitute a limitation on the unit itself under certain circumstances.
  • the first acquisition unit can also be described as "the unit that acquires at least two Internet Protocol addresses.”
  • exemplary types of hardware logic components include: Field-Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Parts (ASSP) ), System on Chip (SOC), Complex Programmable Logic Device (CPLD), etc.
  • FPGA Field-Programmable Gate Array
  • ASIC Application Specific Integrated Circuit
  • ASSP Application Specific Standard Parts
  • SOC System on Chip
  • CPLD Complex Programmable Logic Device
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.
  • the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • Machine-readable media may include electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or suitable combinations of the foregoing.
  • machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard drive, random access memory (RAM), Read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any of the above Suitable combination.
  • RAM random access memory
  • ROM Read-only memory
  • EPROM or flash memory erasable programmable read-only memory
  • CD-ROM compact disk read-only memory
  • magnetic storage device or any of the above Suitable combination.
  • an image processing method including:
  • At least two original images are acquired, including:
  • At least two original images are acquired, including:
  • the method further includes:
  • the method further includes:
  • displaying the at least two original images on the current screen in a set manner includes:
  • the at least two original images are displayed on the current screen according to the motion information and the display information; wherein the motion information includes position information and rotation information, and the display information includes size information and transparency information.
  • displaying the at least two original images on the current screen in a set manner includes:
  • the method further includes:
  • the setting information is displayed on the current screen.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Processing Or Creating Images (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

本公开实施例提供了一种图像处理方法、装置、设备及存储介质。该方法包括:获取至少两张原始图像;将所述至少两张原始图像按照设定方式显示于当前画面,并将所述至少两张原始图像发送至服务端,使得所述服务端对所述至少两张原始图像进行融合处理;接收所述服务端返回的第一目标图像,将所述第一目标图像显示于当前画面;其中,所述第一目标图像为所述服务端对所述至少两张原始图像进行融合处理后获得的图像。

Description

图像处理方法、装置、设备及存储介质
本公开要求在2022年6月17日提交中国专利局、申请号为202210693158.6的中国专利申请的优先权,以上申请的全部内容通过引用结合在本公开中。
技术领域
本公开实施例涉及图像处理技术领域,例如涉及一种图像处理方法、装置、设备及存储介质。
背景技术
目前,移动终端已经成为用户进行娱乐活动的不可或缺的工具之一。用户可以采用移动终端进行多种多样的图像处理。相关技术中,在对图像处理过程中,大多数通过运行客户端本地的算法来实现,由于移动终端的硬件配置的限制,使得对图像处理时效率较低,且处理后的图像精度较差,影响图像处理效果。
发明内容
本公开实施例提供一种图像处理方法、装置、设备及存储介质,将多张图像发送至服务端进行融合处理,不仅可以减少客户端的数据处理压力,还可以提高图像的融合效果。
第一方面,本公开实施例提供了一种图像处理方法,包括:
获取至少两张原始图像;
将所述至少两张原始图像按照设定方式显示于当前画面,并将所述至少两张原始图像发送至服务端,使得服务端对所述至少两张原始图像进行融合处理;
接收服务端返回的第一目标图像,将所述第一目标图像显示于当前画面;其中,所述第一目标图像为服务端对所述至少两张原始图像进行融合处理后获得的图像。
第二方面,本公开实施例还提供了一种图像处理装置,包括:
原始图像获取模块,设置为获取至少两张原始图像;
原始图像发送模块,设置为将所述至少两张原始图像按照设定方式显示于当前画面,并将所述至少两张原始图像发送至服务端,使得服务端对所述至少 两张原始图像进行融合处理;
第一目标图像显示模块,设置为接收服务端返回的第一目标图像,将所述第一目标图像显示于当前画面;其中,所述第一目标图像为服务端对所述至少两张原始图像进行融合处理后获得的图像。
第三方面,本公开实施例还提供了一种电子设备,所述电子设备包括:
一个或多个处理器;
存储装置,设置为存储一个或多个程序,
当所述一个或多个程序被所述一个或多个处理器执行,使得所述一个或多个处理器实现如本公开实施例所述的图像处理方法。
第四方面,本公开实施例还提供了一种包含计算机可执行指令的存储介质,所述计算机可执行指令在由计算机处理器执行时用于执行如本公开实施例所述的图像处理方法。
附图说明
贯穿附图中,相同或相似的附图标记表示相同或相似的元素。应当理解附图是示意性的,原件和元素不一定按照比例绘制。
图1是本公开实施例所提供的一种图像处理方法流程示意图;
图2a是本公开实施例所提供的用户选取本地图像的示意图;
图2b是本公开实施例所提供的原始图像在画面中显示的示例图;
图2c是本公开实施例所提供的原始图像在画面中显示的示例图;
图2d是本公开实施例所提供的显示第一目标图像的示例图;
图3是本公开实施例所提供的一种图像处理装置结构示意图;
图4是本公开实施例所提供的一种电子设备的结构示意图。
具体实施方式
下面将参照附图描述本公开的实施例。虽然附图中显示了本公开的某些实施例,然而应当理解的是,本公开可以通过各种形式来实现。应当理解的是,本公开的附图及实施例仅用于示例性作用。
应当理解,本公开的方法实施方式中记载的各个步骤可以按照不同的顺序执行,和/或并行执行。此外,方法实施方式可以包括附加的步骤和/或省略执行 示出的步骤。
本文使用的术语“包括”及其变形是开放性包括,即“包括但不限于”。术语“基于”是“至少部分地基于”。术语“一个实施例”表示“至少一个实施例”;术语“另一实施例”表示“至少一个另外的实施例”;术语“一些实施例”表示“至少一些实施例”。其他术语的相关定义将在下文描述中给出。
需要注意,本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分,并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。
需要注意,本公开中提及的“一个”、“多个”的修饰是示意性的,本领域技术人员应当理解,除非在上下文另有明确指出,否则应该理解为“一个或多个”。
本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的,而并不是用于对这些消息或信息的范围进行限制。
可以理解的是,在使用本公开各实施例公开的技术方案之前,均应当依据相关法律法规通过恰当的方式对本公开所涉及个人信息的类型、使用范围、使用场景等告知用户并获得用户的授权。
例如,在响应于接收到用户的主动请求时,向用户发送提示信息,以明确地提示用户,其请求执行的操作将需要获取和使用到用户的个人信息。从而,使得用户可以根据提示信息来自主地选择是否向执行本公开技术方案的操作的电子设备、应用程序、服务器或存储介质等软件或硬件提供个人信息。
作为一种可选的实现方式,响应于接收到用户的主动请求,向用户发送提示信息的方式例如可以是弹窗的方式,弹窗中可以以文字的方式呈现提示信息。此外,弹窗中还可以承载供用户选择“同意”或者“不同意”向电子设备提供个人信息的选择控件。
可以理解的是,上述通知和获取用户授权过程仅是示意性的,其它满足相关法律法规的方式也可应用于本公开的实现方式中。
可以理解的是,本技术方案所涉及的数据(如包括数据本身、数据的获取或使用)应当遵循相应法律法规及相关规定的要求。
图1为本公开实施例所提供的一种图像处理方法的流程示意图,本公开实施例适用于对多张图像进行融合的情形,该方法可以由图像处理装置来执行,该装置可以通过软件和/或硬件的形式实现,可选的,通过电子设备来实现,该电子设备可以是移动终端、个人计算机(Personal Computer,PC)端或服务器等。
如图1所示,所述方法包括:
S110,获取至少两张原始图像。
其中,原始图像可以是待处理的图像。获取至少两张原始图像的方式可以是:通过抓帧和/或本地上传。即至少两张原始图像可以是均通过抓帧获取,或者均通过本地上传,或者部分通过抓帧获取部分通过本地上传。
可选的,获取至少两张原始图像的方式可以是:当检测到用户触发的第一操作时,对当前画面进行连续至少两次的抓帧处理,获得至少两张原始图像;或,当检测到用户从本地选取至少两张原始图像且触发第二操作时,将用户选取的至少两张原始图像作为获取到的至少两张原始图像。
其中,第一操作可以是触发终端设备对当前画面进行抓帧处理的操作,例如:可以是单击屏幕、双击屏幕、检测用户摆出设定手势或者姿态、采集到包含有设定关键词的语音信号等,或者界面中设置有触发抓帧的控件按钮,用户通过点击该控件按钮以触发抓帧。抓帧还可以称之为截屏,通过调用抓帧函数,对当前画面显示的内容进行抓帧,从而获得原始图像。可选的,抓帧处理的触发方式还可以通过倒计时的方式实现,当终端进入图像处理道具时,开始在界面显示“321”倒数数字,倒数结束后执行一次抓帧操作,继续显示“321”倒数数字,倒数结束后执行一次抓帧操作,直到抓帧数量达到设定值。示例性的,当用户通过终端设备打开一图像处理道具时,终端设备将摄像头当前采集的图像实时的显示在当前画面,或者从本地数据库或者网络数据库中获取视频文件在当前界面进行播放。当终端设备检测到用户触发的第一操作时,对当前画面显示的内容进行连续至少两次的抓帧处理,获得至少两张原始图像。
其中,第二操作可以是用于确认用户选取的至少两张原始图像的操作。本实施例中,当用户通过终端设备打开一图像处理道具时,界面显示有添加本地图像的按钮,用户点击该按钮后,终端将本地存储的图像显示于当前界面供用户选择,当检测到用户从中选取至少两张原始图像且触发第二操作时,将用户选取的至少两张原始图像作为获取到的至少两张原始图像。示例性的,图2a是本实施例中用户选取本地图像的示意图,如图2a所示,用户点击“+”按钮,终端将本地存储的图像显示于当前界面,假设用户选择了图像1和图像3,并点击了“确认”按钮,则将图像1和图像3作为最终获取到的原始图像。本实施例中,通过抓帧方式或者本地选取的方式获取原始图像,可以提高原始图像的多样性。
可选的,获取至少两张原始图像的方式可以是:在对当前画面进行连续至少两次的抓帧处理的过程中,若检测到用户从本地选取至少两张原始图像且触发第二操作,则终止抓帧处理,将已抓帧获取的图像删除,并将用户选取的至少两张原始图像作为获取到的至少两张原始图像。
其中,对当前画面进行连续至少两次的抓帧处理的过程可以理解为已经开始对当前画面进行抓帧但未完成抓帧的时段。示例性的,在终端已经开始对当前画面进行抓帧但未完成抓帧的过程中,若检测到用户从本地选取至少两张原始图像且触发第二操作,则控制终端停止度当前画面进行抓帧处理,并将已抓帧获取的图像删除,最后将用户选取的至少两张原始图像作为获取到的至少两张原始图像。本实施例中,可选的,可以将用户从本地选取的图像确定为获取到的原始图像,以满足用户对图像处理的个性化需求。
S120,将至少两张原始图像按照设定方式显示于当前画面,并将至少两张原始图像发送至服务端,使得服务端对至少两张原始图像进行融合处理。
其中,设定方式可以是以播放动画的方式显示或者静止显示设定时长,至少两张原始图像显示于当前画面的方式可以根据需求设置。
可选的,将至少两张原始图像按照设定方式显示于当前画面的方式可以是:获取至少两张原始图像分别对应的播放动画;按照播放动画将至少两张原始图像显示于当前画面。
其中,播放动画由多帧组成,每帧动画图像包含原始图像在画面中的运动信息和显示信息。其中,运动信息包括位置信息和旋转信息,显示信息包括尺寸信息和透明度信息。位置信息可以理解为原始图像的中心点在当前帧中的位置坐标,旋转信息可以理解为原始图像的横边与水平方向或者竖直方向的夹角,或者原始图像的竖边与水平方向或者竖直方向的夹角。尺寸信息可以是原始图像的长和高,透明度信息可以理解为原始图像的显示透明度。
本实施例中,透明度信息可以是0-1之间的值,0表示完全透明,1表示完全不透明。对于播放动画中原始图像的透明度信息,可以根据多张原始图像的重叠度来确定。示例性的,当多张原始图像未发生重叠时,各原始图像的透明度信息均为1,当多张原始图像发生重叠时,可以根据重叠度调低其中一张或者多张原始图像的透明度。例如,可以预先建立重叠度和透明度调整量的对应关系,从而根据重叠度确定调整量,基于该调整量调低其中一张或者多张原始图像的透明度。
本实施例中,播放动画中原始图像的运动信息和显示信息可以任意设置,或者预先设置多个候选动画供用户选择。示例性的,以两张原始图像为例,两张原始图像对应的播放动画可以是:两张原始图像先分别从屏幕的左右上边界飞入当前画面,当两张原始图像在画面中相遇后,两张原始图像向画面中心移动,当移动到画面中心后,两张原始图像沿相向方向移动,两张原始图像逐渐重叠,直到两张原始图像完成重叠时,动画结束。示例性的,图2b是本实施例中原始图像在画面中显示的示例图,如图2b所示,左侧的原始图像向左倾斜, 右侧的原始图像向右倾斜。本实施例中,按照播放动画将所述至少两张原始图像显示于当前画面,可以提高画面显示多样性,提高用户体验。
可选的,将至少两张原始图像按照设定方式显示于当前画面的方式可以是:获取设定素材;将至少两张原始图像按照第一透明度静止显示于当前画面,将设定素材按照第二透明度显示于当前画面。
其中,第一透明度大于第二透明度,即原始图像未被设定素材完全覆盖,透过设定素材可以看到原始图像。设定素材可以是一段视频文件,该段视频文件由素材图序列构成,即由多个素材图构成。素材图可以是开发人员预先设置的图像,可以是用于计时的素材图序列。例如:可以是进度条形式的素材图序列,或者倒计时形式的素材图序列,或者倒计时与进度条相结合的素材图序列。本实施例中,至少两张原始图像和设定素材同时显示于当前画面,则至少两张原始图像静止显示于当前画面的时长由设定素材对应的时长确定。示例性的,图2c是本实施例中原始图像在画面中显示的示例图,如图2c所示,两张原始图像静止显示于当前画面,设定素材为由一段提示信息生成的图像序列。本实施例中,将设定素材和至少两张原始图像同时显示于当前画面,可以提高画面显示多样性,提高用户体验。
本实施例中,将至少两张原始图像发送至服务端,使得服务端对至少两张原始图像进行融合处理的过程可以是:将携带有算法标识的至少两张原始图像发送至服务端,使得服务端根据算法标识调用目标融合算法,以采用目标融合算法对至少两张原始图像进行融合处理。
其中,算法标识可以由算法名称、算法存储地址等信息组成。目标融合算法可以是构建的神经网络模型,例如:生成对抗网络模型(Generative Adversarial Nets,GAN)等。本实施例中,不同融合功能对应不同的融合算法,一种图像处理道具可以在服务端设置一个或者多个融合算法,由用户选择所需的融合算法。示例性的,融合算法可以是将至少两张面部图像融合为一张“宝宝”图像,或者,将至少两张面部图像融合为一张虚拟面部图像,或者将至少两张不同风格化的图像融合为一张新的风格化图像等,融合算法的功能可以根据需求设置。
本实施例中,客户端将至少两张原始图像发送至服务端后,由于网络状况的影响且目标融合算法运行需要时间,服务端返回第一目标图像的时间不确定,在发送原始图像与接收到第一目标图像间的时间段内,可以将至少两张原始图像按照设定方式显示于当前画面。即将至少两张原始图像按照设定方式显示于当前画面与将至少两张原始图像发送至服务端同时执行。本实施例中,将至少两张原始图像发送至服务端的进行处理融合处理的过程中,通过将至少两张原始图像按照设定方式显示于当前画面,对服务端的目标融合算法预留出处理时 间,提高了界面交互的灵活性。
本实施例中,将所述至少两张原始图像发送至服务端的同时,还包括如下步骤:调用本地设定算法对至少两张原始图像中的任意一张图像进行处理,获得第二目标图像。
示例性的,在获取到至少两张原始图像后,并行调用服务端的目标融合算法和本地客户端的本地设定算法对至少两张原始图像进行处理,从而获得目标融合算法输出的第一目标图像和本地设定算法输出的第二目标图像。本实施例中,若服务端能够将第一目标图像及时的返回至客户端,则客户端显示第一目标图像,若服务端无法将第一目标图像及时的返回至客户端,则客户端显示第二目标图像。并行调用服务端的目标融合算法和本地客户端的本地设定算法对至少两张原始图像进行处理,兼顾了服务端的高精度计算能力以及客户端的处理效率。
其中,本地设定算法和目标融合算法相对应。本地设定算法可以是构建的神经网络模型,例如:生成对抗网络模型(Generative Adversarial Nets,GAN)等。本地设定算法和目标融合算法相对应可以理解为:本地设定算法和目标融合算法的功能相同,且本地设定算法与目标融合算法相比,精度较低且占用系统资源较少。示例性的,假设服务端到的目标融合算法可以是将至少两张面部图像融合为一张“宝宝”图像,则本地设定算法可以是将一张原始图像转换为“宝宝”图像。本实施例中,调用本地设定算法对所述至少两张原始图像中的任意一张图像进行处理和将至少两张原始图像发送至服务端处理同步执行。本实施例中,当客户端在设定时长内未接收到服务端返回的第一目标图像时,将本地设定算法输出的第二目标图像显示于当前画面,可以防止当前画面无图像显示的情况,提高用户体验。
S130,接收服务端返回的第一目标图像,将第一目标图像显示于当前画面。
其中,所述第一目标图像为服务端对所述至少两张原始图像进行融合处理后获得的图像。本实施例中,当接收到服务端返回的第一目标图像之后,可以将第一目标图像显示于当前画面中。
其中,将第一目标图像显示于当前画面的方式可以是:单独将第一目标图像显示于当前画面,或者将第一目标图像和至少两张原始图像同时显示于当前画面。本实施例中,可以将第一目标图像全屏显示于当前画面,或者以小于屏幕尺寸的方式显示于当前画面。示例性的,图2d是本实施例中显示第一目标图像的示例图,如图2d所示,将第一目标图像和至少两张原始图像同时显示于当前画面。
可选的,在将至少两张原始图像按照设定方式显示于当前画面之后,还包括如下步骤:若未接收到服务端返回的第一目标图像,则将第二目标图像显示于当前画面。或者,若未接收到服务端返回的第一目标图像,则将设定信息显示于当前画面。
其中,设定信息可以是表征未接收到服务端返回的第一目标图像的信息,例如:“处理失败”等。本实施例中,当客户端在设定时长内未接收到服务端返回的第一目标图像时,将设定信息显示于当前画面,可以防止当前画面无内容显示的情况,且可以起到提示用户的作用,从而提高用户体验。
本公开实施例的技术方案,获取至少两张原始图像;将至少两张原始图像按照设定方式显示于当前画面,并将至少两张原始图像发送至服务端,使得服务端对至少两张原始图像进行融合处理;接收服务端返回的第一目标图像,将第一目标图像显示于当前画面;其中,第一目标图像为服务端对至少两张原始图像进行融合处理后获得的图像。本公开实施例提供的图像处理方法,将至少两张原始图像发送至服务端进行融合处理,不仅可以减少客户端的数据处理压力,还可以提高图像的融合效果。
图3为本公开实施例所提供的一种图像处理装置结构示意图,如图3所示,装置包括:
原始图像获取模块310,设置为获取至少两张原始图像;
原始图像发送模块320,设置为将至少两张原始图像按照设定方式显示于当前画面,并将至少两张原始图像发送至服务端,使得所述服务端对至少两张原始图像进行融合处理;
第一目标图像显示模块330,设置为接收所述服务端返回的第一目标图像,将第一目标图像显示于当前画面;其中,第一目标图像为所述服务端对至少两张原始图像进行融合处理后获得的图像。
可选的,原始图像获取模块310,设置为通过以下方式获取所述至少两张原始图像:
当检测到用户触发的第一操作时,对当前画面进行连续至少两次的抓帧处理,获得至少两张原始图像;或,
当检测到用户从本地选取至少两张原始图像且触发第二操作时,将用户选取的至少两张原始图像作为获取到的至少两张原始图像。
可选的,原始图像获取模块310,还设置为通过以下方式获取所述至少两张原始图像:
在对当前画面进行连续至少两次的抓帧处理的过程中,若检测到用户从本地选取至少两张原始图像且触发第二操作,则停止抓帧处理,将已抓帧获取的图像删除,并将用户选取的至少两张原始图像作为获取到的至少两张原始图像。
可选的,原始图像发送模块320,设置为通过以下方式将所述至少两张原始图像发送给服务端进行融合处理:
将携带有算法标识的至少两张原始图像发送至服务端,使得服务端根据算法标识调用目标融合算法,以采用目标融合算法对至少两张原始图像进行融合处理。
可选的,该装置还包括:第二目标图像获取模块,设置为:
调用本地设定算法对至少两张原始图像中的任意一张图像进行处理,获得第二目标图像;其中,本地设定算法和目标融合算法相对应。
可选的,该装置还包括:第二目标图像显示模块,设置为:
若未接收到服务端返回的第一目标图像,则将第二目标图像显示于当前画面。
可选的,该装置还包括:原始图像显示模块,设置为:
获取至少两张原始图像分别对应的播放动画;
按照播放动画将至少两张原始图像显示于当前画面。
可选的,原始图像显示模块,设置为通过以下方式按照播放动画将所述至少两张原始图像显示于当前画面:
按照运动信息和显示信息将至少两张原始图像显示于当前画面;其中,运动信息包括位置信息和旋转信息,显示信息包括尺寸信息和透明度信息。
可选的,原始图像显示模块,还设置为通过以下方式将所述至少两张原始图像按照设定方式显示于当前画面:
获取设定素材;
将至少两张原始图像按照第一透明度静止显示于当前画面,将设定素材按照第二透明度显示于当前画面;其中,第一透明度大于第二透明度。
可选的,该装置还包括:设定信息显示模块,设置为:
若未接收到服务端返回的第一目标图像,则将设定信息显示于当前画面。
本公开实施例所提供的图像处理装置可执行本公开任意实施例所提供的图像处理方法,具备执行方法相应的功能模块和有益效果。
值得注意的是,上述装置所包括的各个单元和模块只是按照功能逻辑进行划分的,但并不局限于上述的划分,只要能够实现相应的功能即可;另外,各功能单元的名称也只是为了便于相互区分。
图4为本公开实施例所提供的一种电子设备的结构示意图。下面参考图4,其示出了适于用来实现本公开实施例的电子设备(例如图4中的终端设备或服务器)500的结构示意图。本公开实施例中的终端设备可以包括诸如移动电话、笔记本电脑、数字广播接收器、个人数字助理(Personal Digital Assistant,PDA)、平板电脑(Portable Android Device,PAD)、便携式多媒体播放器(Portable Media Player,PMP)、车载终端(例如车载导航终端)等的移动终端以及诸如数字电视(television,TV)、台式计算机等的固定终端。图4示出的电子设备仅仅是一个示例。
如图4所示,电子设备500可以包括处理装置(例如中央处理器、图形处理器等)501,其可以根据存储在只读存储器(Read Only Memory,ROM)502中的程序或者从存储装置508加载到随机访问存储器(Random Access Memory,RAM)503中的程序而执行各种适当的动作和处理。在RAM 503中,还存储有电子设备500操作所需的各种程序和数据。处理装置501、ROM 502以及RAM 503通过总线504彼此相连。输入/输出(Input/Output,I/O)接口505也连接至总线504。
通常,以下装置可以连接至I/O接口505:包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置506;包括例如液晶显示器(Liquid Crystal Display,LCD)、扬声器、振动器等的输出装置507;包括例如磁带、硬盘等的存储装置508;以及通信装置509。通信装置509可以允许电子设备500与其他设备进行无线或有线通信以交换数据。虽然图4示出了具有各种装置的电子设备500,但是应理解的是,并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。
在一实施例中,根据本公开的实施例,上文参考流程图描述的过程可以被实现为计算机软件程序。例如,本公开的实施例包括一种计算机程序产品,其包括承载在非暂态计算机可读介质上的计算机程序,该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中,该计算机程序可以通过通信装置509从网络上被下载和安装,或者从存储装置508被安装,或者从ROM 502被安装。在该计算机程序被处理装置501执行时,执行本公开实施例的方法中限定的上述功能。
本公开实施例提供的电子设备与上述实施例提供的图像处理方法属于同一发明构思,未在本实施例中详尽描述的技术细节可参见上述实施例,并且本实施例与上述实施例具有相同的有益效果。
本公开实施例提供了一种计算机存储介质,其上存储有计算机程序,该程序被处理器执行时实现上述实施例所提供的图像处理方法。
需要说明的是,本公开上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的组合。计算机可读存储介质例如可以是电、磁、光、电磁、红外线、或半导体的系统、装置或器件,或者以上的组合。计算机可读存储介质的示例可以包括:具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(Electronic Programable Read Only Memory,EPROM)或闪存(FLASH)、光纤、便携式紧凑磁盘只读存储器(Compact Disc-Read Only Memory,CD-ROM)、光存储器件、磁存储器件、或者上述的合适的组合。在本公开中,计算机可读存储介质可以是包含或存储程序的有形介质,该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开中,计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号,其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式,包括电磁信号、光信号或上述的合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质,该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输,包括:电线、光缆、射频(Radio Frequency,RF)等,或者上述的合适的组合。
在一些实施方式中,客户端、服务器可以利用诸如超文本传输协议(HyperText Transfer Protocol,HTTP)之类的当前已知或未来研发的网络协议进行通信,并且可以与任意形式或介质的数字数据通信(例如,通信网络)互连。通信网络的示例包括局域网(Local Area Network,LAN),广域网(Wide Area Network,WAN),网际网(例如,互联网)以及端对端网络(例如,ad hoc端对端网络),以及当前已知或未来研发的网络。
上述计算机可读介质可以是上述电子设备中所包含的;也可以是单独存在,而未装配入该电子设备中。
上述计算机可读介质承载有至少一个程序,当上述至少一个程序被该电子设备执行时,使得该电子设备:获取至少两张原始图像;将所述至少两张原始图像按照设定方式显示于当前画面,并将所述至少两张原始图像发送至服务端,使得服务端对所述至少两张原始图像进行融合处理;接收服务端返回的第一目标图像,将所述第一目标图像显示于当前画面;其中,所述第一目标图像为服务端对所述至少两张原始图像进行融合处理后获得的图像。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的 计算机程序代码,上述程序设计语言包括面向对象的程序设计语言诸如Java、Smalltalk、C++,还包括常规的过程式程序设计语言诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中,远程计算机可以通过任意种类的网络包括局域网(LAN)或广域网(WAN)连接到用户计算机,或者,可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图,图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上,流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分,该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意,在有些作为替换的实现中,方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如,两个接连地表示的方框实际上可以基本并行地执行,它们有时也可以按相反的顺序执行,这依所涉及的功能而定。也要注意的是,框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合,可以用执行规定的功能或操作的专用的基于硬件的系统来实现,或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施例中所涉及到的单元可以通过软件的方式实现,也可以通过硬件的方式来实现。其中,单元的名称在某种情况下并不构成对该单元本身的限定,例如,第一获取单元还可以被描述为“获取至少两个网际协议地址的单元”。
本文中以上描述的功能可以至少部分地由至少一个硬件逻辑部件来执行。例如,可以使用的示范类型的硬件逻辑部件包括:现场可编程门阵列(Field-Programmable Gate Array,FPGA)、专用集成电路(Application Specific Integrated Circuit,ASIC)、专用标准产品(Application Specific Standard Parts,ASSP)、片上系统(System on Chip,SOC)、复杂可编程逻辑设备(Complex Programmable Logic Device,CPLD)等。
在本公开的上下文中,机器可读介质可以是有形的介质,其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备,或者上述内容的合适组合。机器可读存储介质的示例可包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、 只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的合适组合。
根据本公开的一个或多个实施例,提供了一种图像处理方法,包括:
获取至少两张原始图像;
将所述至少两张原始图像按照设定方式显示于当前画面,并将所述至少两张原始图像发送至服务端,使得所述服务端对所述至少两张原始图像进行融合处理;
接收所述服务端返回的第一目标图像,将所述第一目标图像显示于当前画面;其中,所述第一目标图像为所述服务端对所述至少两张原始图像进行融合处理后获得的图像。
在一实施例中,获取至少两张原始图像,包括:
当检测到用户触发的第一操作时,对当前画面进行连续至少两次的抓帧处理,获得至少两张原始图像;或,
当检测到用户从本地选取至少两张原始图像且触发第二操作时,将用户选取的至少两张原始图像作为获取到的至少两张原始图像。
在一实施例中,获取至少两张原始图像,包括:
在对当前画面进行连续至少两次的抓帧处理的过程中,若检测到用户从本地选取至少两张原始图像且触发第二操作,则停止抓帧处理,将已抓帧获取的图像删除,并将用户选取的至少两张原始图像作为获取到的至少两张原始图像。
在一实施例中,将所述至少两张原始图像发送至服务端,使得服务端对所述至少两张原始图像进行融合处理,包括:
将携带有算法标识的所述至少两张原始图像发送至服务端,使得服务端根据所述算法标识调用目标融合算法,以采用所述目标融合算法对所述至少两张原始图像进行融合处理。
在一实施例中,在获取至少两张原始图像之后,还包括:
调用本地设定算法对所述至少两张原始图像中的任意一张图像进行处理,获得第二目标图像;其中,所述本地设定算法和所述目标融合算法相对应。
在一实施例中,在将所述至少两张原始图像按照设定方式显示于当前画面之后,还包括:
若未接收到服务端返回的第一目标图像,则将所述第二目标图像显示于当 前画面。
在一实施例中,将所述至少两张原始图像按照设定方式显示于当前画面,包括:
获取所述至少两张原始图像分别对应的播放动画;
按照所述播放动画将所述至少两张原始图像显示于当前画面。
在一实施例中,所述播放动画包括原始图像在画面中的运动信息和显示信息;按照所述播放动画将所述至少两张原始图像显示于当前画面,包括:
按照所述运动信息和所述显示信息将所述至少两张原始图像显示于当前画面;其中,所述运动信息包括位置信息和旋转信息,所述显示信息包括尺寸信息和透明度信息。
在一实施例中,将所述至少两张原始图像按照设定方式显示于当前画面,包括:
获取设定素材;
将所述至少两张原始图像按照第一透明度静止显示于当前画面,将所述设定素材按照第二透明度显示于当前画面;其中,所述第一透明度大于所述第二透明度。
在一实施例中,在将所述至少两张原始图像按照设定方式显示于当前画面之后,还包括:
若未接收到服务端返回的第一目标图像,则将设定信息显示于当前画面。
此外,虽然采用特定次序描绘了各操作,但是这不应当理解为要求这些操作以所示出的特定次序或以顺序次序执行来执行。在一定环境下,多任务和并行处理可能是有利的。

Claims (13)

  1. 一种图像处理方法,包括:
    获取至少两张原始图像;
    将所述至少两张原始图像按照设定方式显示于当前画面,并将所述至少两张原始图像发送至服务端,使得所述服务端对所述至少两张原始图像进行融合处理;
    接收所述服务端返回的第一目标图像,将所述第一目标图像显示于当前画面;其中,所述第一目标图像为所述服务端对所述至少两张原始图像进行融合处理后获得的图像。
  2. 根据权利要求1所述的方法,其中,所述获取至少两张原始图像,包括:
    当检测到用户触发的第一操作时,对当前画面进行连续至少两次的抓帧处理,获得至少两张原始图像;或,
    当检测到用户从本地选取至少两张原始图像且触发第二操作时,将用户选取的至少两张原始图像作为获取到的至少两张原始图像。
  3. 根据权利要求2所述的方法,其中,所述获取至少两张原始图像,包括:
    在对当前画面进行连续至少两次的抓帧处理的过程中,响应于检测到用户从本地选取至少两张原始图像且触发第二操作,停止抓帧处理,将已抓帧获取的图像删除,并将用户选取的至少两张原始图像作为获取到的至少两张原始图像。
  4. 根据权利要求1所述的方法,其中,所述将所述至少两张原始图像发送至服务端,使得所述服务端对所述至少两张原始图像进行融合处理,包括:
    将携带有算法标识的所述至少两张原始图像发送至服务端,使得所述服务端根据所述算法标识调用目标融合算法,以采用所述目标融合算法对所述至少两张原始图像进行融合处理。
  5. 根据权利要求4所述的方法,在将所述至少两张原始图像发送至服务端的同时,所述方法还包括:
    调用本地设定算法对所述至少两张原始图像中的任意一张图像进行处理,获得第二目标图像;其中,所述本地设定算法和所述目标融合算法相对应。
  6. 根据权利要求5所述的方法,在将所述至少两张原始图像按照设定方式显示于当前画面之后,所述方法还包括:
    响应于未接收到所述服务端返回的第一目标图像,将所述第二目标图像显示于当前画面。
  7. 根据权利要求1所述的方法,其中,所述将所述至少两张原始图像按照设定方式显示于当前画面,包括:
    获取所述至少两张原始图像分别对应的播放动画;
    按照所述播放动画将所述至少两张原始图像显示于当前画面。
  8. 根据权利要求7所述的方法,其中,所述播放动画包括原始图像在画面中的运动信息和显示信息;所述按照所述播放动画将所述至少两张原始图像显示于当前画面,包括:
    按照所述运动信息和所述显示信息将所述至少两张原始图像显示于当前画面;其中,所述运动信息包括位置信息和旋转信息,所述显示信息包括尺寸信息和透明度信息。
  9. 根据权利要求1所述的方法,其中,所述将所述至少两张原始图像按照设定方式显示于当前画面,包括:
    获取设定素材;
    将所述至少两张原始图像按照第一透明度静止显示于当前画面,将所述设定素材按照第二透明度显示于当前画面;其中,所述第一透明度大于所述第二透明度。
  10. 根据权利要求1所述的方法,在将所述至少两张原始图像按照设定方式显示于当前画面之后,所述方法还包括:
    响应于未接收到所述服务端返回的第一目标图像,将设定信息显示于当前画面。
  11. 一种图像处理装置,包括:
    原始图像获取模块,设置为获取至少两张原始图像;
    原始图像发送模块,设置为将所述至少两张原始图像按照设定方式显示于当前画面,并将所述至少两张原始图像发送至服务端,使得所述服务端对所述至少两张原始图像进行融合处理;
    第一目标图像显示模块,设置为接收所述服务端返回的第一目标图像,将所述第一目标图像显示于当前画面;其中,所述第一目标图像为所述服务端对所述至少两张原始图像进行融合处理后获得的图像。
  12. 一种电子设备,所述电子设备包括:
    一个或多个处理器;
    存储装置,设置为存储一个或多个程序,
    当所述一个或多个程序被所述一个或多个处理器执行,使得所述一个或多个处理器实现如权利要求1-10中任一所述的图像处理方法。
  13. 一种包含计算机可执行指令的存储介质,所述计算机可执行指令在由计算机处理器执行时用于执行如权利要求1-10中任一所述的图像处理方法。
PCT/CN2023/098807 2022-06-17 2023-06-07 图像处理方法、装置、设备及存储介质 WO2023241427A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210693158.6 2022-06-17
CN202210693158.6A CN115082368A (zh) 2022-06-17 2022-06-17 图像处理方法、装置、设备及存储介质

Publications (1)

Publication Number Publication Date
WO2023241427A1 true WO2023241427A1 (zh) 2023-12-21

Family

ID=83252856

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/098807 WO2023241427A1 (zh) 2022-06-17 2023-06-07 图像处理方法、装置、设备及存储介质

Country Status (2)

Country Link
CN (1) CN115082368A (zh)
WO (1) WO2023241427A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115082368A (zh) * 2022-06-17 2022-09-20 北京字跳网络技术有限公司 图像处理方法、装置、设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8472684B1 (en) * 2010-06-09 2013-06-25 Icad, Inc. Systems and methods for generating fused medical images from multi-parametric, magnetic resonance image data
CN110503703A (zh) * 2019-08-27 2019-11-26 北京百度网讯科技有限公司 用于生成图像的方法和装置
CN111724407A (zh) * 2020-05-25 2020-09-29 北京市商汤科技开发有限公司 图像处理方法和相关产品
CN112116684A (zh) * 2020-08-05 2020-12-22 中国科学院信息工程研究所 图像处理方法、装置、设备及计算机可读存储介质
CN115082368A (zh) * 2022-06-17 2022-09-20 北京字跳网络技术有限公司 图像处理方法、装置、设备及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8472684B1 (en) * 2010-06-09 2013-06-25 Icad, Inc. Systems and methods for generating fused medical images from multi-parametric, magnetic resonance image data
CN110503703A (zh) * 2019-08-27 2019-11-26 北京百度网讯科技有限公司 用于生成图像的方法和装置
CN111724407A (zh) * 2020-05-25 2020-09-29 北京市商汤科技开发有限公司 图像处理方法和相关产品
CN112116684A (zh) * 2020-08-05 2020-12-22 中国科学院信息工程研究所 图像处理方法、装置、设备及计算机可读存储介质
CN115082368A (zh) * 2022-06-17 2022-09-20 北京字跳网络技术有限公司 图像处理方法、装置、设备及存储介质

Also Published As

Publication number Publication date
CN115082368A (zh) 2022-09-20

Similar Documents

Publication Publication Date Title
CN113489937B (zh) 视频共享方法、装置、设备及介质
EP4262214A1 (en) Screen projection method and apparatus, and electronic device and storage medium
US20230291980A1 (en) Method and apparatus for video generation and displaying, device, and medium
US20230024650A1 (en) Method and apparatus for selecting menu items, readable medium and electronic device
WO2023169305A1 (zh) 特效视频生成方法、装置、电子设备及存储介质
EP4344224A1 (en) Live-streaming interaction method and apparatus, and readable medium and electronic device
WO2021218318A1 (zh) 视频传输方法、电子设备和计算机可读介质
WO2023231915A1 (zh) 消息处理方法、装置、设备及存储介质
EP4344236A1 (en) Video processing method and apparatus, electronic device and storage medium
WO2023241427A1 (zh) 图像处理方法、装置、设备及存储介质
WO2022078066A1 (zh) 视频处理方法、系统、终端和存储介质
WO2022171024A1 (zh) 图像显示方法、装置、设备及介质
US11818491B2 (en) Image special effect configuration method, image recognition method, apparatus and electronic device
WO2024022403A1 (zh) 任务的处理方法、装置、设备及存储介质
WO2020220782A1 (zh) 信息分享方法、装置、设备和介质
WO2023221941A1 (zh) 图像处理方法、装置、设备及存储介质
WO2024027819A1 (zh) 图像处理方法、装置、设备及存储介质
WO2024041637A1 (zh) 特效图生成方法、装置、设备及存储介质
WO2024022179A1 (zh) 媒体内容的显示方法、装置、电子设备和存储介质
WO2024037556A1 (zh) 图像处理方法、装置、设备及存储介质
WO2024037491A1 (zh) 媒体内容处理方法、装置、设备及存储介质
US20240073488A1 (en) Live video processing method and apparatus, device and medium
EP4274237A1 (en) Information display method and apparatus, and device and medium
CN116320654A (zh) 消息显示处理方法、装置、设备及介质
EP4142297A1 (en) Method, apparatus and device for configuring video special effect, and storage medium

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: 23822996

Country of ref document: EP

Kind code of ref document: A1