WO2023226851A1 - 三维效果形象的生成方法、装置、电子设备及存储介质 - Google Patents

三维效果形象的生成方法、装置、电子设备及存储介质 Download PDF

Info

Publication number
WO2023226851A1
WO2023226851A1 PCT/CN2023/094792 CN2023094792W WO2023226851A1 WO 2023226851 A1 WO2023226851 A1 WO 2023226851A1 CN 2023094792 W CN2023094792 W CN 2023094792W WO 2023226851 A1 WO2023226851 A1 WO 2023226851A1
Authority
WO
WIPO (PCT)
Prior art keywords
virtual image
image
target material
layers
occlusion relationship
Prior art date
Application number
PCT/CN2023/094792
Other languages
English (en)
French (fr)
Inventor
曾伟宏
王旭
Original Assignee
北京字节跳动网络技术有限公司
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 北京字节跳动网络技术有限公司 filed Critical 北京字节跳动网络技术有限公司
Publication of WO2023226851A1 publication Critical patent/WO2023226851A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T15/00—3D [Three Dimensional] image rendering

Definitions

  • the present disclosure relates to the field of computer technology, for example, to methods, devices, electronic devices and storage media for generating three-dimensional effect images.
  • the shortcomings of related technologies at least include: in some personalized image rendering scenarios, it takes a long time to create and render the three-dimensional data of the image, and the real-time performance is poor.
  • the present disclosure provides a method, device, electronic device and storage medium for generating a three-dimensional effect image, which can generate an image with a three-dimensional effect in real time without creating three-dimensional data of the image.
  • the present disclosure provides a method for generating a three-dimensional effect image, including:
  • the target material wherein the target material is divided into at least two layers;
  • the target material and the virtual image are rendered according to the occlusion relationship to generate a virtual image with a three-dimensional effect.
  • the present disclosure also provides a device for generating a three-dimensional effect image, including:
  • the material acquisition module is configured to acquire target material; wherein the target material is divided into at least two layers;
  • an occlusion relationship determination module configured to determine the occlusion relationship between the at least two layers and the virtual image
  • a rendering module is configured to render the target material and the virtual image according to the occlusion relationship, and generate a virtual image with a three-dimensional effect.
  • the present disclosure also provides an electronic device, which includes:
  • processors one or more processors
  • 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 above-mentioned method for generating a three-dimensional effect image.
  • the present disclosure also provides a storage medium containing computer-executable instructions, which when executed by a computer processor are used to perform the above-mentioned method for generating a three-dimensional effect image.
  • the present disclosure also provides a computer program product, including a computer program carried on a non-transitory computer-readable medium, and the computer program includes program code for executing the above-mentioned method for generating a three-dimensional effect image.
  • Figure 1 is a schematic flowchart of a method for generating a three-dimensional effect image provided by an embodiment of the present disclosure
  • Figure 2 is a schematic diagram of determining the occlusion relationship in a method for generating a three-dimensional effect image provided by an embodiment of the present disclosure
  • Figure 3 is a schematic diagram of determining the occlusion relationship in another method for generating a three-dimensional effect image provided by an embodiment of the present disclosure
  • Figure 4 is a schematic flowchart of determining the occlusion relationship in a method for generating a three-dimensional effect image provided by an embodiment of the present disclosure
  • Figure 5 is a schematic flowchart of another method for generating a three-dimensional effect image provided by an embodiment of the present disclosure
  • Figure 6 is a schematic diagram of the process of presenting a virtual image with a naked-eye three-dimensional (3D) effect in the interface in a method for generating a three-dimensional effect image provided by an embodiment of the present disclosure
  • Figure 7 is a schematic structural diagram of a device for generating a three-dimensional effect image provided by an embodiment of the present disclosure
  • FIG. 8 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.
  • the term “include” and its variations are open inclusive, that is, “includes.”
  • the term “based on” is “to Based in part on “.
  • the term “one embodiment” means “at least one embodiment”; the term “another embodiment” means “at least one additional embodiment”; the term “some embodiments” means “at least some embodiments” .Relevant definitions of other terms will be given in the description below.
  • a prompt message is sent to the user to clearly remind the user that the operation requested will require the acquisition and use of the user's personal information. Therefore, users can autonomously choose whether to provide personal information to software or hardware such as electronic devices, applications, servers or storage media that perform the operations of the technical solution of the present disclosure based on the prompt information.
  • the method of sending prompt information to the user may be, for example, a pop-up window, and the prompt information may be presented in the form of text in the pop-up window.
  • the pop-up window can also contain a selection control for the user to choose "agree” or "disagree” to provide personal information to the electronic device.
  • FIG. 1 is a schematic flowchart of a method for generating a three-dimensional effect image provided by an embodiment of the present disclosure.
  • the embodiments of the present disclosure are suitable for generating a virtual image with a 3D effect, for example, for generating a virtual image with a naked-eye 3D effect in real time.
  • the method can be executed by a device for generating a three-dimensional effect image, which can be implemented in the form of software and/or hardware.
  • the device can be configured in an electronic device, such as a mobile phone or a computer.
  • the method for generating a three-dimensional effect image may include:
  • At least one two-dimensional image material can be designed in advance, and each material can be divided into at least two layers during the design process.
  • the target material can be determined based on at least one of the following methods: in response to a selection instruction input by the user, determining the target material from the multiple pre-designed materials; in response to a sorting condition input by the user (such as material theme, update date, usage popularity, etc.), sort multiple materials, and determine the top-ranked material as the target material; use the default material among multiple materials as the target material, etc.
  • a sorting condition input by the user (such as material theme, update date, usage popularity, etc.), sort multiple materials, and determine the top-ranked material as the target material; use the default material among multiple materials as the target material, etc.
  • other methods of determining target materials can also be applied here, and are not exhaustive here.
  • the target material After determining the target material, it can be determined whether the target material has been downloaded locally. If the target material has been downloaded locally, the target material can be obtained locally; if the target material has not been downloaded locally, it can be downloaded to obtain the target material.
  • the method of generating a virtual image may include at least one of the following: in response to a one-click generation instruction input by the user, generating an avatar consisting of multiple random parts; in response to an image editing instruction input by the user, Generate a virtual image composed of multiple parts corresponding to the image editing instructions; generate a virtual image similar to the real object based on the characteristics of the real object.
  • the virtual image can be a two-dimensional image, or a quasi-three-dimensional image with a three-dimensional display effect can be generated by placing multiple two-dimensional parts at different depths.
  • the above-mentioned creation of a virtual image according to editing instructions and the generation of a virtual image similar to the real image can be regarded as personalized image generation scenarios.
  • the generation scenario of personalized images can be understood as the virtual image is not generated in advance, but needs to be generated immediately before rendering.
  • the generation of a two-dimensional virtual image or a quasi-three-dimensional virtual image in this embodiment can reduce the time consumption of image generation and facilitate the realization of rapid and real-time image creation. render.
  • the occlusion relationship between at least two layers and the avatar may include: some layers are on the upper layer of the avatar, and some layers are on the lower layer of the avatar.
  • the layer can block the virtual object, so that the effect of the avatar behind the layer can be visually presented; when the layer is on the lower layer of the virtual object, the virtual object can block the layer, This allows you to visually present the effect of the avatar in front of the layer.
  • a visual depth relationship can be constructed, which can produce a naked-eye 3D effect after rendering the virtual object according to the occlusion relationship.
  • Determining the occlusion relationship between at least two layers and the virtual image may include at least one of the following: determining the occlusion relationship between at least two layers and the virtual object in response to an occlusion relationship determination instruction input by the user; and performing actions based on the avatar. , determine the occlusion relationship between at least two layers and the virtual image in real time; determine the occlusion relationship between at least two layers and the avatar according to the preset occlusion relationship identifiers of at least two layers.
  • the instruction for determining the occlusion relationship may include an upper-lower order of at least two layers and the virtual object, and the upper-lower occlusion relationship of at least two layers and the virtual object may be determined based on the upper-lower order.
  • the virtual object can perform corresponding actions in response to the driving instructions. For example, the virtual object can poke its head to the left in response to the "left probe" instruction input by the user.
  • the occlusion relationship between at least two layers and the virtual image can be determined in real time based on the executed actions.
  • FIG. 2 is a schematic diagram of determining the occlusion relationship in a method for generating a three-dimensional effect image provided by an embodiment of the present disclosure.
  • the target material is a window material, which can be divided into two left and right layers.
  • the left and right layers contain the left window sash and the right window sash respectively.
  • the layer containing the left sash can be below the avatar, and the layer containing the right sash can be above the avatar; when the avatar pokes its head to the right or left, the layer containing the right sash can be The layer can be below the avatar, and the layer containing the left sash can be above the avatar.
  • the process of determining the occlusion relationship based on the execution actions of the virtual object can be understood as a process of rendering and determining the occlusion relationship. That is, while rendering the action of the virtual object, the occlusion relationship of at least two layers in the target material can be determined based on the action, and rendering of the target material and the virtual object based on the occlusion relationship can be performed.
  • determining the occlusion relationship between at least two layers and the virtual object in real time during the virtual object's execution of actions a variety of naked-eye 3D effects can be presented and the user experience can be improved.
  • an occlusion relationship indicator is set for each layer in response to dividing the material into at least two layers.
  • the preset occlusion relationship identifier may include, for example, a background identifier and a foreground identifier; and the layer corresponding to the background identifier may be a layer below the avatar, and the layer corresponding to the foreground identifier may be a layer above the avatar.
  • the object relationship between at least two layers and the virtual object can be determined based on the preset occlusion relationship identifier.
  • FIG. 3 is a schematic diagram of determining the occlusion relationship in another method for generating a three-dimensional effect image provided by an embodiment of the present disclosure.
  • the target material is a mirror material, which can be divided into two upper and lower layers.
  • the preset occlusion relationship identifiers of the upper and lower layers can be respectively the background identifier and the foreground identifier.
  • At least two layers and the avatar can be rendered according to the occlusion relationship between the at least two layers and the avatar, and a visual depth relationship between the virtual object and different parts of the target material can be constructed, thereby making the virtual object With naked-eye 3D effect.
  • This process eliminates the need to create three-dimensional figures of the image According to reports, through low-cost two-dimensional images, supplemented by some preset materials, naked-eye 3D visual effects can be achieved, and images with three-dimensional effects can be generated in real time.
  • the target material contains a border; the target material and the avatar are rendered according to the occlusion relationship, including: rendering the avatar in front of part of the border.
  • the target materials may include mirrors, televisions, windows, railings, walls, and other materials containing borders.
  • the technical solution of the embodiment of the present disclosure includes obtaining the target material; the target material can be divided into at least two layers; determining the occlusion relationship between the at least two layers and the virtual image; rendering the target material and the virtual image according to the occlusion relationship, Generate avatars with three-dimensional effects.
  • determining the occlusion relationship between at least two layers in the target material and the virtual object, and rendering the target material and the virtual object according to the occlusion relationship an image with a naked-eye three-dimensional effect can be presented. This process does not require the creation of three-dimensional data of the image, and can meet the needs of real-time generation of images with three-dimensional effects.
  • the embodiments of the present disclosure can be combined with multiple solutions of the three-dimensional effect image generation method provided in the above embodiments.
  • the method for generating a three-dimensional effect image provided in this embodiment describes the steps for determining the occlusion relationship.
  • the virtual image can perform corresponding actions, thereby improving the interactivity of the virtual image and making it more playable.
  • the occlusion relationship between at least two layers and the virtual object can be determined in real time, thereby achieving diverse naked-eye 3D effects and improving user experience.
  • FIG. 4 is a schematic flowchart of determining the occlusion relationship in a method for generating a three-dimensional effect image provided by an embodiment of the present disclosure.
  • the process of determining the occlusion relationship in this embodiment may include:
  • S410 Collect video data of the target object according to the input video collection instruction.
  • the video data of the target object can be collected through a video collection device (such as one or more cameras).
  • a video collection device such as one or more cameras.
  • the object when there is only one object within the collection range of the video collection device, the object can be used as the target object; when the collection range contains multiple objects, the focus instruction input by the user can be used, or other methods such as automatic focus can be used. , focus on the target object from multiple objects.
  • S420 Analyze the video data to obtain the real-time actions of the target object.
  • Open source action recognition models can be used to analyze video data to obtain the real-time actions of the target object. Alternatively, you can first identify multiple feature points of the target object through an open source feature point recognition model, and determine the real-time actions of the target object by tracking the location of the feature points. In addition, other methods of obtaining real-time movements of target objects through video analysis can also be applied here, and are not exhaustive here.
  • Driving instructions can be generated based on real-time actions, and the generated virtual image can be driven through the driving instructions, so that the virtual image performs corresponding actions.
  • the corresponding actions may include actions that are the same as the real-time actions of the target object, or may include actions that are the same as the real-time actions and add certain special effects, etc.
  • the virtual image can be a two-dimensional image or a quasi-three-dimensional image
  • the virtual image can be driven through an open source two-dimensional driving algorithm.
  • the interactivity of the virtual image can be improved and the playability is high.
  • the real-time facial expressions of the target object in addition to parsing the real-time actions of the target object and synchronously migrating them to the avatar, the real-time facial expressions of the target object can also be parsed, and the avatar can be driven based on the real-time facial expressions to cause the avatar to perform Corresponding expressions can improve interactivity and user experience.
  • the process of driving the virtual image to perform the same action in real time can be considered as the process of rendering the action of the virtual object.
  • the occlusion relationship between at least two layers and the virtual image can be determined in real time based on the actions performed by the virtual image.
  • the target material and virtual objects can be rendered according to the occlusion relationship. That is to say, this process can be considered as a process of rendering and determining the occlusion relationship.
  • the technical solution of the embodiment of the present disclosure describes the steps for determining the occlusion relationship.
  • the virtual image can perform corresponding actions, thereby improving the interactivity of the virtual image and making it more playable.
  • the occlusion relationship between at least two layers and the virtual object can be determined in real time, thereby achieving diverse naked-eye 3D effects and improving user experience.
  • the three-dimensional effect image generation method provided by the embodiments of the present disclosure belongs to the same concept as the three-dimensional effect image generation method provided by the above-mentioned embodiments.
  • Technical details that are not described in detail in this embodiment can be found in the above-mentioned embodiments, and the same technical features This embodiment has the same effect as the above-mentioned embodiment.
  • the embodiments of the present disclosure can be combined with multiple solutions of the three-dimensional effect image generation method provided in the above embodiments.
  • the method for generating a three-dimensional effect image provided in this embodiment can create a virtual image of thousands of people and faces by analyzing the attributes of multiple parts of the target object.
  • the real image of the target object can be presented in the interface; after the avatar is generated, a virtual image exclusive to the real image can be presented through transition effects.
  • the generation of personalized images can improve the user experience.
  • Figure 5 is a schematic flowchart of another method for generating a three-dimensional effect image provided by an embodiment of the present disclosure. picture. As shown in Figure 5, the method for generating a three-dimensional effect image provided by this embodiment includes:
  • S512 Collect image data of the target object according to the input image collection instruction.
  • image data of the target object can be collected through an image collection device (such as one or more cameras).
  • the method of determining the target object may refer to the method of collecting video data of the target object.
  • the sequence can be determined based on the business scenario. For example, the user can first select the target material on the material selection interface, and then jump to the shooting interface containing the target material to capture the image data of the target object. For another example, the user can first capture the image data in the shooting interface, and then add the target material to the image data.
  • the target material and image data can be directly rendered into the interface to present the true image of the target object.
  • S530 Analyze the image data to obtain attributes of multiple parts of the target object.
  • Image data can be analyzed through traditional image analysis algorithms or machine learning algorithms to obtain the attributes of multiple parts of the target object. For example, when the target object is a human object, the type, color and other attributes of the human object's eyes, nose, mouth, eyebrows, beard, hair and other parts can be analyzed.
  • S540 Select the corresponding virtual part from the preset library according to the attributes of each part, and generate an avatar based on the multiple virtual parts.
  • Transition effects can refer to the special effects played in the interface when different scenes change.
  • transition effects can include emitting particles from the center of the interface to the surroundings, flying particles from one side of the interface to the other, etc., where the particles can refer to light, stars, petals, etc.
  • the default transition effect can be used as the preset transition effect, or the transition effect selected by the user can be used as the preset transition effect.
  • the original rendering target material and image data interface is converted into a rendering interface.
  • the interface that dyes the target material and the virtual image can show the effect of transformation from the real image to the virtual image, which can enhance the fun and improve the user experience.
  • S550 and S560 do not have a strict timing relationship.
  • the preset transition effects can be executed first and converted into an interface for rendering the target material and the avatar; and then based on the avatar's The action determines the occlusion relationship between at least two layers and the virtual image in real time and renders it, realizing the process of rendering and determining the occlusion relationship at the same time.
  • the technical solutions of the embodiments of the present disclosure can create virtual images of thousands of people with thousands of faces by analyzing the attributes of multiple parts of the target object. Moreover, before generating the avatar, the real image of the target object can be presented in the interface; after the avatar is generated, a virtual image exclusive to the real image can be presented through transition effects. The generation of personalized images can improve the user experience.
  • the three-dimensional effect image generation method provided by the embodiments of the present disclosure belongs to the same concept as the three-dimensional effect image generation method provided by the above-mentioned embodiments. Technical details that are not described in detail in this embodiment can be found in the above-mentioned embodiments, and the same technical features This embodiment has the same effect as the above-mentioned embodiment.
  • the embodiments of the present disclosure can be combined with multiple solutions of the three-dimensional effect image generation method provided in the above embodiments.
  • the method for generating a three-dimensional effect image exemplifies the process of presenting a virtual image with a naked-eye 3D effect in the interface.
  • the image acquisition instruction and the video acquisition instruction can be the same instruction.
  • the virtual object can also be driven according to the action of the target object.
  • the virtual image can display a naked-eye 3D effect.
  • FIG. 6 is a schematic diagram of the process of presenting a virtual image with a naked-eye 3D effect in an interface in a method for generating a three-dimensional effect image provided by an embodiment of the present disclosure.
  • the target material may be the magic mirror material shown in FIG. 3 .
  • the process of presenting a virtual image with a naked-eye 3D effect in the interface may include:
  • the image data can be analyzed to obtain the attributes of multiple parts of the character object; and based on the attributes of each part, the corresponding virtual part is selected from the preset library, and an avatar is generated based on the multiple virtual parts.
  • the original shooting interface that renders magic mirror materials and image data can be converted into an interface that renders magic mirror materials and avatars (which can be called an avatar interface).
  • the virtual image can be placed before the upper layer and after the lower layer of the magic mirror material.
  • video data of human objects can be collected, and the video data can be analyzed to obtain the real-time actions of the human objects; the virtual image can be driven based on the real-time actions to make the virtual image perform corresponding actions.
  • the virtual image interface can present a naked-eye 3D effect, visually as if the image is coming out of the mirror, which is very lively and interesting.
  • the technical solutions of the embodiments of the present disclosure exemplarily describe the process of presenting a virtual image with a naked-eye 3D effect in the interface.
  • the image acquisition instruction and the video acquisition instruction can be the same instruction.
  • the virtual object can also be driven according to the action of the target object.
  • the virtual image can display a naked-eye 3D effect.
  • the three-dimensional effect image generation method provided by the embodiments of the present disclosure belongs to the same concept as the three-dimensional effect image generation method provided by the above-mentioned embodiments.
  • Technical details that are not described in detail in this embodiment can be found in the above-mentioned embodiments, and the same technical features This embodiment has the same effect as the above-mentioned embodiment.
  • FIG. 7 is a schematic structural diagram of a device for generating a three-dimensional effect image provided by an embodiment of the present disclosure.
  • the embodiments of the present disclosure are suitable for generating a virtual image with a 3D effect, for example, for generating a virtual image with a naked-eye 3D effect in real time.
  • the device for generating a three-dimensional effect image may include:
  • the material acquisition module 710 is configured to acquire the target material; wherein the target material is divided into at least two layers; the occlusion relationship determination module 720 is configured to determine the occlusion relationship between the at least two layers and the virtual image; the rendering module 730 is configured to The target material and the virtual image are rendered according to the occlusion relationship to generate a virtual image with a three-dimensional effect.
  • the occlusion relationship determination module 720 can be set to:
  • the occlusion relationship between at least two layers and the virtual image is determined in real time.
  • the device for generating a three-dimensional effect image may also include:
  • Driver module can be set to:
  • the video data of the target object is collected; the video data is analyzed to obtain the real-time actions of the target object; the virtual image is driven according to the real-time actions to make the virtual image perform corresponding actions.
  • the occlusion relationship determination module 720 can also be set to:
  • the device for generating a three-dimensional effect image may also include:
  • the avatar generation module can generate avatars based on the following methods:
  • the image data of the target object is collected; the image data is analyzed to obtain the attributes of multiple parts of the target object; according to the attributes of each part, the corresponding virtual part is selected from the preset library, and the corresponding virtual part is selected according to the multiple parts Virtual parts generate virtual images.
  • rendering module 730 may be configured to:
  • the target material and image data are rendered; in response to executing the preset transition special effects, the target material and the avatar are rendered according to the occlusion relationship.
  • the target material includes a border; the rendering module 730 may be configured to render the avatar in front of part of the border.
  • the device for generating a three-dimensional effect image provided by an embodiment of the present disclosure can execute the method for generating a three-dimensional effect image provided by any embodiment of the present disclosure, and has functional modules and effects corresponding to the execution method.
  • the multiple units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned divisions, as long as they can achieve the corresponding functions; in addition, the names of the multiple functional units are only for the convenience of distinguishing each other. , are not used to limit the protection scope of the embodiments 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 Mobile terminals such as Player, PMP), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital televisions (Television, TV), desktop computers, and the like.
  • the electronic device 800 shown in FIG. 8 is only an example and should not bring any limitations to the functions and usage scope of the embodiments of the present disclosure.
  • the electronic device 800 may include a processing device (such as a central processing unit, a graphics processor, etc.) 801, which may process data according to a program stored in a read-only memory (Read-Only Memory, ROM) 802 or from a storage device. 808 loads the program in the random access memory (Random Access Memory, RAM) 803 to perform various appropriate actions and processes. In the RAM 803, various programs and data required for the operation of the electronic device 800 are also stored.
  • the processing device 801, ROM 802 and RAM 803 are connected to each other via a bus 804.
  • An input/output (I/O) interface 805 is also connected to bus 804.
  • the following devices can be connected to the I/O interface 805: input devices 806 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 807 such as a speaker, a vibrator, etc.; a storage device 808 including a magnetic tape, a hard disk, etc.; and a communication device 809.
  • the communication device 809 may allow the electronic device 800 to communicate wirelessly or wiredly with other devices to exchange data.
  • Figure 8 shows the Electronic device 800 has various means and is not required to implement or have all illustrated means. 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 809, or from storage device 808, or from ROM 802.
  • the processing device 801 When the computer program is executed by the processing device 801, the above functions defined in the three-dimensional effect image generation method of the embodiment of the present disclosure are performed.
  • the electronic device provided by the embodiments of the present disclosure and the method for generating a three-dimensional effect image provided by the above embodiments belong to the same concept.
  • Technical details that are not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same characteristics as the above embodiments. Same effect.
  • 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 method for generating a three-dimensional effect image provided in 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 any combination of the above two.
  • the computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof.
  • Examples of computer-readable storage media may include: an electrical connection having one or more wires, a portable computer disk, a hard drive, RAM, ROM, Erasable Programmable Read-Only Memory (EPROM), or Flash memory (FLASH), optical fiber, portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device.
  • 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 many forms, including electromagnetic signals, optical signals, or any 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 embodied on a computer-readable medium can be transmitted using any appropriate medium, including: wire, optical cable, radio frequency (Radio Frequency, RF), etc., or any suitable combination of the above.
  • the client and server can communicate using any currently known or future developed network protocol such as Hyper Text Transfer Protocol (HTTP), and can communicate with digital data in any form or medium.
  • HTTP Hyper Text Transfer Protocol
  • Data communications e.g., communications network
  • Examples of communication networks include local area networks (LAN), wide area networks (WAN), the Internet (eg, the Internet), and end-to-end networks (eg, ad hoc end-to-end networks), as well as any current network for knowledge or future research and development.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; it may also exist independently without being assembled into the electronic device.
  • the computer-readable medium carries one or more programs.
  • the electronic device obtains the target material; wherein the target material is divided into at least two layers; determines at least The occlusion relationship between the two layers and the virtual image; the target material and the virtual image are rendered according to the occlusion relationship to generate a virtual image with a three-dimensional effect.
  • Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional Procedural programming language—such as "C" or a similar programming language.
  • 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 computer through any kind of network, including a LAN or WAN, or may be connected to an external computer (eg, through the Internet using an Internet service provider).
  • each block in the flowchart or block diagram may represent a module, segment, or portion of code that contains one or more logic functions that implement the specified executable instructions.
  • the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown one after another may actually execute substantially in parallel, or they may sometimes execute in the reverse order, depending on the functionality involved.
  • 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. Among them, the name of a unit or module does not constitute a limitation on the unit or module itself.
  • exemplary types of hardware logic components include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (Application Specific Integrated Circuit) Integrated Circuit (ASIC), Application Specific Standard Parts (ASSP), System on Chip (SOC), Complex Programming 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 Programming 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 any suitable combination of the foregoing. Examples of machine-readable storage media would include an electrical connection based on one or more wires, a portable computer disk, a hard drive, RAM, ROM, EPROM or flash memory, optical fiber, CD-ROM, optical storage device, magnetic storage device, or Any suitable combination of the above.
  • Example 1 provides a method for generating a three-dimensional effect image, which method includes:
  • the target material wherein the target material is divided into at least two layers;
  • the target material and the virtual image are rendered according to the occlusion relationship to generate a virtual image with a three-dimensional effect.
  • Example 2 provides a method for generating a three-dimensional effect image, which also includes:
  • determining the occlusion relationship between the at least two layers and the avatar includes:
  • the occlusion relationship between the at least two layers and the virtual image is determined in real time.
  • Example 3 provides a method for generating a three-dimensional effect image, which also includes:
  • the avatar performs actions based on:
  • the virtual image is driven according to the real-time action, so that the virtual image performs a corresponding action.
  • Example 4 provides a method for generating a three-dimensional effect image, which also includes:
  • determining the occlusion relationship between the at least two layers and the avatar includes:
  • the occlusion relationship between the at least two layers and the avatar is determined according to the preset occlusion relationship identifiers of the at least two layers.
  • Example 5 provides a method for generating a three-dimensional effect image, which also includes:
  • the virtual image is generated based on the following methods:
  • image data of the target object is collected
  • the corresponding virtual part is selected from the preset library, and the virtual image is generated based on the plurality of virtual parts.
  • Example 6 provides a method for generating a three-dimensional effect image, which also includes:
  • before generating the avatar it further includes: rendering the target material and the image data;
  • the rendering of the target material and the virtual image according to the occlusion relationship includes:
  • the target material and the avatar are rendered according to the occlusion relationship.
  • Example 7 provides a method for generating a three-dimensional effect image, which also includes:
  • the target material includes a border
  • Rendering the target material and the virtual image according to the occlusion relationship includes: rendering the virtual image in front of part of the frame.
  • Example 8 provides a device for generating a three-dimensional effect image, which device includes:
  • the material acquisition module is configured to acquire target material; wherein the target material is divided into at least two layers;
  • an occlusion relationship determination module configured to determine the occlusion relationship between the at least two layers and the virtual image
  • a rendering module is configured to render the target material and the virtual image according to the occlusion relationship, and generate a virtual image with a three-dimensional effect.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Graphics (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Processing Or Creating Images (AREA)

Abstract

本公开提供了三维效果形象的生成方法、装置、电子设备及存储介质。该三维效果形象的生成方法包括：获取目标素材；其中，所述目标素材分为至少两个图层；确定所述至少两个图层与虚拟形象的遮挡关系；根据所述遮挡关系对所述目标素材与所述虚拟形象进行渲染，生成具有三维效果的虚拟形象。

Description

三维效果形象的生成方法、装置、电子设备及存储介质
本申请要求在2022年05月25日提交中国专利局、申请号为202210579466.6的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本公开涉及计算机技术领域，例如涉及三维效果形象的生成方法、装置、电子设备及存储介质。
背景技术
相关技术中，为使界面中渲染的形象具有三维效果，通常需要先创建该形象的三维数据。相关技术的不足之处至少包括：在一些个性化形象渲染场景下，创建形象的三维数据并渲染需较长的耗时，实时性较差。
发明内容
本公开提供了三维效果形象的生成方法、装置、电子设备及存储介质，无需创建形象的三维数据，可实时生成具有三维效果的形象。
第一方面，本公开提供了一种三维效果形象的生成方法，包括：
获取目标素材；其中，所述目标素材分为至少两个图层；
确定所述至少两个图层与虚拟形象的遮挡关系；
根据所述遮挡关系对所述目标素材与所述虚拟形象进行渲染，生成具有三维效果的虚拟形象。
第二方面，本公开还提供了一种三维效果形象的生成装置，包括：
素材获取模块，设置为获取目标素材；其中，所述目标素材分为至少两个图层；
遮挡关系确定模块，设置为确定所述至少两个图层与虚拟形象的遮挡关系；
渲染模块，设置为根据所述遮挡关系对所述目标素材与所述虚拟形象进行渲染，生成具有三维效果的虚拟形象。
第三方面，本公开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上述的三维效果形象的生成方法。
第四方面，本公开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上述的三维效果形象的生成方法。
第五方面，本公开还提供了一种计算机程序产品，包括承载在非暂态计算机可读介质上的计算机程序，所述计算机程序包含用于执行上述的三维效果形象的生成方法的程序代码。
附图说明
图1为本公开实施例所提供的一种三维效果形象的生成方法的流程示意图；
图2为本公开实施例所提供的一种三维效果形象的生成方法中确定遮挡关系的示意图；
图3为本公开实施例所提供的另一种三维效果形象的生成方法中确定遮挡关系的示意图；
图4为本公开实施例所提供的一种三维效果形象的生成方法中确定遮挡关系的流程示意图；
图5为本公开实施例所提供的另一种三维效果形象的生成方法的流程示意图；
图6为本公开实施例所提供的一种三维效果形象的生成方法中界面中呈现裸眼三维(3 Dimension，3D)效果的虚拟形象的过程示意图；
图7为本公开实施例所提供的一种三维效果形象的生成装置的结构示意图；
图8为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
下面将参照附图更详细地描述本公开的实施例。虽然附图中显示了本公开的一些实施例，然而本公开可以通过多种形式来实现，提供这些实施例是为了理解本公开。本公开的附图及实施例仅用于示例性作用。
本公开的方法实施方式中记载的多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。本公开的范围在此方面不受限制。
本文使用的术语“包括”及其变形是开放性包括，即“包括”。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。
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。
本公开中提及的“一个”、“多个”的修饰是示意性而非限制性的，本领域技术人员应当理解，除非在上下文另有指出，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。
在使用本公开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。
上述通知和获取用户授权过程仅是示意性的，不对本公开的实现方式构成限定，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。
图1为本公开实施例所提供的一种三维效果形象的生成方法的流程示意图。本公开实施例适用于生成具有3D效果的虚拟形象的情形，例如适用于实时生成裸眼3D效果的虚拟形象的情形。该方法可以由三维效果形象的生成装置来执行，该装置可以通过软件和/或硬件的形式实现，该装置可配置于电子设备中，例如配置于手机、电脑中。
如图1所示，本实施例提供的三维效果形象的生成方法，可以包括：
S110、获取目标素材；其中，目标素材分为至少两个图层。
本公开实施例中，可预先设计至少一个二维图像素材，且每个素材在设计过程中可被划分为至少两个图层。
当预先设计的素材为一个时，该素材可作为目标素材。当预先设计的素材为多个时，可基于下述至少一种方式确定目标素材：响应于用户输入的选取指令，从预先设计的多个素材中确定目标素材；响应于用户输入的排序条件(例如素材主题、更新日期、使用热度等条件)，对多个素材进行排序，并将排序靠前的素材确定为目标素材；将多个素材中的默认素材作为目标素材等。此外，其他确定目标素材的方式也可应用于此，在此不做穷举。
在确定目标素材后，可判断目标素材是否已下载至本地，若目标素材已下载至本地则可以从本地获取目标素材；若目标素材未下载至本地则可以对其进行下载，以获取目标素材。
S120、确定至少两个图层与虚拟形象的遮挡关系。
本公开实施例中，虚拟形象的生成方式可以包括下述至少一种：响应于用户输入的一键生成指令，生成由随机的多个部位构成的虚拟形象；响应于用户输入的形象编辑指令，生成由与形象编辑指令对应的多个部位构成的虚拟形象；根据真实对象特征，生成与真实对象相似的虚拟形象。其中，虚拟形象可以为二维形象，也可以为将多个二维部位放在不同的深度生成具有三维显示效果的类三维形象。
上述的根据编辑指令制作虚拟形象，以及生成与真实形象相似的虚拟形象，都可以看成是个性化形象的生成场景。个性化形象的生成场景可理解为，虚拟形象并非预先生成的，而是需要在渲染前即时生成的。在这些场景下，相较于相关技术中需要生成形象的三维数据，本实施例中生成二维虚拟形象或类三维虚拟形象，可以减少形象生成的耗时，有利于实现快速地、实时地形象渲染。
至少两个图层与虚拟形象的遮挡关系，可以包括：部分图层在虚拟形象的上层，部分图层在虚拟形象的下层。当图层在虚拟形象的上层时，图层可以遮挡虚拟对象，从而可以在视觉上呈现虚拟形象在该图层后面的效果；当图层在虚拟对象的下层时，虚拟对象可以遮挡图层，从而可以在视觉上呈现虚拟形象在该图层前面的效果。通过使部分图层在虚拟对象上层，部分图层在虚拟对象下层，可以构建一个视觉上的深度关系，可在根据遮挡关系渲染虚拟对象后产生裸眼3D的效果。
确定至少两个图层与虚拟形象的遮挡关系，可以包括下述至少一项：响应于用户输入的遮挡关系确定指令，确定至少两个图层与虚拟对象的遮挡关系；根据虚拟形象执行的动作，实时确定至少两个图层与虚拟形象的遮挡关系；根据至少两个图层的预设遮挡关系标识，确定至少两个图层与虚拟形象的遮挡关系。
遮挡关系确定指令可以包括至少两个图层与虚拟对象的上下层顺序，根据该上下层顺序可确定至少两个图层与虚拟对象的上下层遮挡关系。
虚拟对象可响应于驱动指令执行相应动作，例如虚拟对象可响应于用户输入的“左探头”指令，将头部向左探出。在虚拟对象动态化执行动作过程中，可实时根据执行的动作确定至少两个图层与虚拟形象的遮挡关系。
示例性的，图2为本公开实施例所提供的一种三维效果形象的生成方法中确定遮挡关系的示意图。参见图2，目标素材为窗户素材，该素材可以分为左右两个图层，该左右两个图层分别包含左窗扇和右窗扇。当虚拟形象将头向左探出时，包含左窗扇的图层可在虚拟形象下层，包含右窗扇的图层可在虚拟形象上层；当虚拟形象将头右左探出时，包含右窗扇的图层可在虚拟形象下层，包含左窗扇的图层可在虚拟形象上层。
可以将根据虚拟对象的执行动作确定遮挡关系的过程，理解为边渲染、边确定遮挡关系的过程。即，可以边对虚拟对象的动作进行渲染，边根据动作确定目标素材中至少两个图层的遮挡关系，并执行根据遮挡关系渲染目标素材和虚拟对象。通过在虚拟对象执行动作过程中，实时确定至少两个图层与虚拟对象的遮挡关系，可呈现多样化的裸眼3D效果，提升用户体验。
在预先设计素材的过程中，还响应于将素材划分为至少两个图层，为每个图层设置遮挡关系标识。该预设遮挡关系标识，例如可以包括背景标识和前景标识；且背景标识对应的图层可以为在虚拟形象的下层的图层，前景标识对应的图层可以为在虚拟形象上层的图层。相应的，可根据该预设遮挡关系标识确定至少两个图层与虚拟对象的对象关系。
示例性的，图3为本公开实施例所提供的另一种三维效果形象的生成方法中确定遮挡关系的示意图。参见图3，目标素材为镜子素材，该素材可以分为上下两个图层，该上下两个图层的预设遮挡关系标识可分别为背景标识和前景标识。当渲染虚拟形象时，可以将虚拟形象放置在上图层之前、下图层之后。通过使虚拟形象遮挡上图层中的部分镜框，可以呈现从镜子中探出的裸眼3D效果。
本实施例中，通过基于多样化方式确定遮挡关系，能够更为灵活地渲染具有裸眼3D效果的形象，提高用户体验。
S130、根据遮挡关系对目标素材与虚拟形象进行渲染，生成具有三维效果的虚拟形象。
本公开实施例中，可根据至少两个图层与虚拟形象的遮挡关系渲染至少两个图层以及虚拟形象，可以构建虚拟对象与目标素材不同部分的视觉上的深度关系，从而可以使虚拟对象具备裸眼3D的效果。该过程无需创建形象的三维数 据，通过低成本的二维形象，辅以一些预设的素材，就可达到裸眼3D的视觉效果，可实时生成具有三维效果的形象。
在一些实现方式中，目标素材中包含边框；根据遮挡关系对目标素材与虚拟形象进行渲染，包括：将虚拟形象渲染在边框的部分边框前。在这些实施例中，目标素材可以包括镜子、电视、窗户、栏杆墙等包含边框的素材。通过将虚拟形象渲染在部分边框之前，能够使虚拟形象遮挡部分边框，可呈现从虚拟形象镜子中探出、从电视屏幕中探出、从窗户中探出、从两栏杆之间探出等裸眼3D效果，玩法丰富，可提高用户体验。
本公开实施例的技术方案，包括获取目标素材；该目标素材可分为至少两个图层；确定至少两个图层与虚拟形象的遮挡关系；根据遮挡关系对目标素材与虚拟形象进行渲染，生成具有三维效果的虚拟形象。通过确定目标素材中至少两个图层与虚拟对象的遮挡关系，根据遮挡关系渲染目标素材和虚拟对象，可呈现具有裸眼三维效果的形象。该过程无需创建形象的三维数据，可满足具有三维效果的形象实时生成的需求。
本公开实施例与上述实施例中所提供的三维效果形象的生成方法中多个方案可以结合。本实施例所提供的三维效果形象的生成方法，对遮挡关系的确定步骤进行了描述。通过采集目标对象的动作，并同步迁移到虚拟形象上，可以使虚拟形象执行相应动作，从而可提高虚拟形象的交互性，可玩性较高。进而，可在虚拟对象执行动作过程中，实时确定至少两个图层与虚拟对象的遮挡关系，可实现多样化的裸眼3D效果，提升用户体验。
图4为本公开实施例所提供的一种三维效果形象的生成方法中确定遮挡关系的流程示意图。参见图4，本实施例中确定遮挡关系的流程，可以包括：
S410、根据输入的视频采集指令，采集目标对象的视频数据。
当接收到用户输入的视频采集指令时，可以通过视频采集装置(例如一个或多个摄像头)采集目标对象的视频数据。其中，当视频采集装置的采集范围内仅有一个对象时，可以将该对象作为目标对象；当该采集范围内包含多个对象时，可根据用户输入的对焦指令，或采用自动对焦等其他方式，从多个对象中聚焦到目标对象。
S420、对视频数据进行解析，得到目标对象的实时动作。
可以采用开源的动作识别模型对视频数据进行解析，以得到目标对象的实时动作。或者，可以先通过开源的特征点识别模型识别目标对象的多个特征点，通过跟踪特征点位置来确定目标对象的实时动作。此外，其他通过视频解析获得目标对象实时动作的方式也可应用与此，在此不做穷举。
S430、根据实时动作驱动虚拟形象，以使虚拟形象执行相应的动作。
可以根据实时动作生成驱动指令，通过驱动指令对已生成的虚拟形象进行驱动，以使虚拟形象执行相应的动作。其中，相应的动作可以包括与目标对象的实时动作相同的动作，也可包括将与实时动作相同的动作添加一定特效后的动作等。
由于虚拟形象可以为二维形象或类三维形象，可以通过开源的二维驱动算法对虚拟形象进行驱动。通过基于目标对象的实时动作驱动虚拟形象，可提高虚拟形象交互性，可玩性较高。
在一些实施方式中，除了解析目标对象的实时动作并将其同步迁移至虚拟形象外，还可对目标对象的实时面部表情进行解析，并可根据实时面部表情驱动虚拟形象，以使虚拟形象执行相应的表情，可提高交互性，提高用户体验。
S440、根据虚拟形象执行的动作，实时确定至少两个图层与虚拟形象的遮挡关系。
实时驱动虚拟形象执行相同动作的过程，可认为是对虚拟对象的动作进行渲染的过程。在实时驱动虚拟形象执行动作过程中，可根据虚拟形象执行的动作实时确定至少两个图层与虚拟图像的遮挡关系。进而，可根据遮挡关系渲染目标素材和虚拟对象。即该过程可认为是边渲染、边确定遮挡关系的过程。通过在虚拟对象执行动作过程中，实时确定至少两个图层与虚拟对象的遮挡关系，可呈现多样化的裸眼3D效果，提升用户体验。
本公开实施例的技术方案，对遮挡关系的确定步骤进行了描述。通过采集目标对象的动作，并同步迁移到虚拟形象上，可以使虚拟形象执行相应动作，从而可提高虚拟形象的交互性，可玩性较高。进而，可在虚拟对象执行动作过程中，实时确定至少两个图层与虚拟对象的遮挡关系，可实现多样化的裸眼3D效果，提升用户体验。本公开实施例提供的三维效果形象的生成方法与上述实施例提供的三维效果形象的生成方法属于同一构思，未在本实施例中详尽描述的技术细节可参见上述实施例，并且相同的技术特征在本实施例与上述实施例中具有相同的效果。
本公开实施例与上述实施例中所提供的三维效果形象的生成方法中多个方案可以结合。本实施例所提供的三维效果形象的生成方法，可通过对目标对象中多个部位的属性分析，创建千人千面的虚拟形象。并且，在生成虚拟形象前，可在界面中呈现目标对象的真实形象；在生成虚拟形象后，可通过转场特效呈现与真实形象专属的虚拟形象，个性化形象的生成可提高用户体验。
图5为本公开实施例所提供的另一种三维效果形象的生成方法的流程示意 图。如图5所示，本实施例提供的三维效果形象的生成方法，包括：
S511、获取目标素材；其中，目标素材分为至少两个图层。
S512、根据输入的图像采集指令，采集目标对象的图像数据。
当接收到用户输入的图像采集指令时，可以通过图像采集装置(例如一个或多个摄像头)采集目标对象的图像数据。其中，确定目标对象的方式可参考采集目标对象的视频数据时的方式。
S520、将目标素材与图像数据进行渲染。
获取目标素材和采集图像数据的步骤并无严格的时序关系，可根据业务场景进行先后时序的确定。例如，用户可先在素材选取界面选取目标素材，再跳转至包含目标素材的拍摄界面，以拍摄目标对象的图像数据。又如，用户可先在拍摄界面拍摄图像数据后，再在图像数据上添加目标素材。
在获取目标素材与图像数据后，可以将目标素材和图像数据直接渲染至界面中，以对目标对象的真实形象进行呈现。
S530、对图像数据进行解析，得到目标对象中多个部位属性。
可以通过传统的图像分析算法或机器学习算法对图像数据进行解析，得到目标对象中多个部位的属性。示例性的，当目标对象为人物对象时，可以对人物对象的眼睛、鼻子、嘴巴、眉毛、胡子、头发等部位的类型、颜色等属性进行解析。
S540、根据每个部位属性，从预设库中选择对应的虚拟部位，并根据多个虚拟部位生成虚拟形象。
在确定目标对象中多个部位属性后，可以从预设库中选择相同属性的多个虚拟部位，并根据多个虚拟部位生成二维形象或类三维形象。通过根据目标对象的多个部位属性生成虚拟形象，可确定与目标对象相似的专属虚拟形象，能够提高用户体验。
S550、确定至少两个图层与虚拟形象的遮挡关系。
S560、响应于执行预设转场特效，根据遮挡关系对目标素材与虚拟形象进行渲染。
转场特效可以指不同场景转换时界面中播放的特效。示例性的，转场特效可以包括从界面中心向四周发射粒子，从界面一侧到另一侧飞过粒子等，其中粒子可以指光线、星星、花瓣等。其中，可将默认的转场特效作为预设转场特效，也可将用户选取的转场特效作为预设转场特效。
通过播放预设转场特效，将原来渲染目标素材和图像数据的界面转换为渲 染目标素材和虚拟形象的界面，可呈现由真实形象到虚拟形象变身的效果，可增强趣味性，提高用户体验。
S550和S560并非具有严格的时序关系。例如，在根据虚拟形象执行动作实时确定遮挡关系的场景下，也可以在确定出虚拟形象后，先执行预设转场特效，转换为渲染目标素材和虚拟形象的界面；再边根据虚拟形象的动作实时确定至少两个图层与虚拟形象的遮挡关系并渲染，实现边渲染、边确定遮挡关系的过程。
本公开实施例的技术方案，可通过对目标对象中多个部位的属性分析，创建千人千面的虚拟形象。并且，在生成虚拟形象前，可在界面中呈现目标对象的真实形象；在生成虚拟形象后，可通过转场特效呈现与真实形象专属的虚拟形象，个性化形象的生成可提高用户体验。本公开实施例提供的三维效果形象的生成方法与上述实施例提供的三维效果形象的生成方法属于同一构思，未在本实施例中详尽描述的技术细节可参见上述实施例，并且相同的技术特征在本实施例与上述实施例中具有相同的效果。
本公开实施例与上述实施例中所提供的三维效果形象的生成方法中多个方案可以结合。本实施例所提供的三维效果形象的生成方法，对界面中呈现裸眼3D效果的虚拟形象的过程进行了示例性描述。本实施例中，图像采集指令和视频采集指令可以相同指令，基于该指令生成虚拟图像后，还可以根据目标对象动作来驱动虚拟对象。在驱动过程中，当虚拟形象驱动至一些特定情况时，可使虚拟形象呈现裸眼3D效果。
示例性的，图6为本公开实施例所提供的一种三维效果形象的生成方法中界面中呈现裸眼3D效果的虚拟形象的过程示意图，其中目标素材可以为图3所示的魔镜素材。参见图6，界面中呈现裸眼3D效果的虚拟形象的过程，可以包括：
首先，可根据用户输入的图像采集指令(同视频采集指令)，跳转至魔镜素材的拍摄界面中。在该拍摄界面中，可采集人物对象的图像数据，并对魔镜素材与图像数据进行渲染，以呈现人物照镜子的视觉效果。
接着，可以对图像数据进行解析，得到人物对象中多个部位属性；并根据每个部位属性，从预设库中选择对应的虚拟部位，并根据多个虚拟部位生成虚拟形象。
然后，可通过炫酷的预设转场特效，将原来渲染魔镜素材和图像数据的拍摄界面转换为渲染魔镜素材和虚拟形象的界面(可称为虚拟形象界面)。其中，虚拟形象可被放置在魔镜素材的上图层之前、下图层之后。
最后，可采集人物对象的视频数据，并对视频数据进行解析，得到人物对象的实时动作；根据实时动作驱动虚拟形象，以使虚拟形象执行相应的动作。
在实时驱动虚拟形象过程中，当虚拟形象遮挡部分镜子边框时，虚拟形象界面中能够呈现裸眼3D的效果，视觉上仿佛形象从镜中钻出来一样，非常生动有趣。
本公开实施例的技术方案，对界面中呈现裸眼3D效果的虚拟形象的过程进行了示例性描述。本实施例中，图像采集指令和视频采集指令可以相同指令，基于该指令生成虚拟图像后，还可以根据目标对象动作来驱动虚拟对象。在驱动过程中，当虚拟形象驱动至一些特定情况时，可使虚拟形象呈现裸眼3D效果。本公开实施例提供的三维效果形象的生成方法与上述实施例提供的三维效果形象的生成方法属于同一构思，未在本实施例中详尽描述的技术细节可参见上述实施例，并且相同的技术特征在本实施例与上述实施例中具有相同的效果。
图7为本公开实施例所提供的一种三维效果形象的生成装置的结构示意图。本公开实施例适用于生成具有3D效果的虚拟形象的情形，例如适用于实时生成裸眼3D效果的虚拟形象的情形。
如图7所示，本公开实施例提供的三维效果形象的生成装置，可以包括：
素材获取模块710，设置为获取目标素材；其中，目标素材分为至少两个图层；遮挡关系确定模块720，设置为确定至少两个图层与虚拟形象的遮挡关系；渲染模块730，设置为根据遮挡关系对目标素材与虚拟形象进行渲染，生成具有三维效果的虚拟形象。
在一些实现方式中，遮挡关系确定模块720，可以设置为：
根据虚拟形象执行的动作，实时确定至少两个图层与虚拟形象的遮挡关系。
在一些实现方式中，三维效果形象的生成装置，还可以包括：
驱动模块，可以设置为：
根据输入的视频采集指令，采集目标对象的视频数据；对视频数据进行解析，得到目标对象的实时动作；根据实时动作驱动虚拟形象，以使虚拟形象执行相应的动作。
在一些实现方式中，遮挡关系确定模块720，还可以设置为：
根据至少两个图层的预设遮挡关系标识，确定至少两个图层与虚拟形象的遮挡关系。
在一些实现方式中，三维效果形象的生成装置，还可以包括：
虚拟形象生成模块，可以基于下述方式生成虚拟形象：
根据输入的图像采集指令，采集目标对象的图像数据；对图像数据进行解析，得到目标对象中多个部位属性；根据每个部位属性，从预设库中选择对应的虚拟部位，并根据多个虚拟部位生成虚拟形象。
在一些实现方式中，渲染模块730可以设置为：
在生成虚拟形象之前，将目标素材与图像数据进行渲染；响应于执行预设转场特效，根据遮挡关系对目标素材与虚拟形象进行渲染。
在一些实现方式中，目标素材中包含边框；渲染模块730可以设置为：将虚拟形象渲染在边框的部分边框前。
本公开实施例所提供的三维效果形象的生成装置，可执行本公开任意实施例所提供的三维效果形象的生成方法，具备执行方法相应的功能模块和效果。
上述装置所包括的多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，多个功能单元的名称也只是为了便于相互区分，并不用于限制本公开实施例的保护范围。
下面参考图8，其示出了适于用来实现本公开实施例的电子设备(例如图8中的终端设备或服务器)800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)等等的移动终端以及诸如数字电视(Television，TV)、台式计算机等等的固定终端。图8示出的电子设备800仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
如图8所示，电子设备800可以包括处理装置(例如中央处理器、图形处理器等)801，其可以根据存储在只读存储器(Read-Only Memory，ROM)802中的程序或者从存储装置808加载到随机访问存储器(Random Access Memory，RAM)803中的程序而执行多种适当的动作和处理。在RAM 803中，还存储有电子设备800操作所需的多种程序和数据。处理装置801、ROM 802以及RAM 803通过总线804彼此相连。输入/输出(Input/Output，I/O)接口805也连接至总线804。
通常，以下装置可以连接至I/O接口805：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806；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807；包括例如磁带、硬盘等的存储装置808；以及通信装置809。通信装置809可以允许电子设备800与其他设备进行无线或有线通信以交换数据。虽然图8示出了具 有多种装置的电子设备800，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。
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809从网络上被下载和安装，或者从存储装置808被安装，或者从ROM802被安装。在该计算机程序被处理装置801执行时，执行本公开实施例的三维效果形象的生成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三维效果形象的生成方法属于同一构思，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三维效果形象的生成方法。
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任意组合。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，或者任意以上的组合。计算机可读存储介质的的例子可以包括：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、RAM、ROM、可擦式可编程只读存储器(Erasable Programmable 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、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何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、光信号或上述的任意合适的组合。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)等等，或者上述的任意合适的组合。
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(Hyper Text Transfer Protocol，HTTP)之类的任何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)，以及任何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一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：获取目标素材；其中，目标素材分为至少两个图层；确定至少两个图层与虚拟形象的遮挡关系；根据遮挡关系对目标素材与虚拟形象进行渲染，生成具有三维效果的虚拟形象。
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LAN或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，图示了按照本公开多种实施例的系统、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、模块的名称在一种情况下并不构成对该单元、模块本身的限定。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如，非限制性地，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 Programming Logic Device，CPLD)等等。
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，或者上述内容的任何合适组合。机器可读存储介质的示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、RAM、ROM、EPROM或快闪存储器、光纤、CD-ROM、光学储存设备、磁储存设备、或上述内容的任何合适组合。
根据本公开的一个或多个实施例，【示例一】提供了一种三维效果形象的生成方法，该方法包括：
获取目标素材；其中，所述目标素材分为至少两个图层；
确定所述至少两个图层与虚拟形象的遮挡关系；
根据所述遮挡关系对所述目标素材与所述虚拟形象进行渲染，生成具有三维效果的虚拟形象。
根据本公开的一个或多个实施例，【示例二】提供了一种三维效果形象的生成方法，还包括：
在一些实现方式中，所述确定所述至少两个图层与虚拟形象的遮挡关系，包括：
根据所述虚拟形象执行的动作，实时确定所述至少两个图层与所述虚拟形象的遮挡关系。
根据本公开的一个或多个实施例，【示例三】提供了一种三维效果形象的生成方法，还包括：
在一些实现方式中，所述虚拟形象基于下述方式执行动作：
根据输入的视频采集指令，采集目标对象的视频数据；
对所述视频数据进行解析，得到所述目标对象的实时动作；
根据所述实时动作驱动所述虚拟形象，以使所述虚拟形象执行相应的动作。
根据本公开的一个或多个实施例，【示例四】提供了一种三维效果形象的生成方法，还包括：
在一些实现方式中，所述确定所述至少两个图层与虚拟形象的遮挡关系，包括：
根据所述至少两个图层的预设遮挡关系标识，确定所述至少两个图层与虚拟形象的遮挡关系。
根据本公开的一个或多个实施例，【示例五】提供了一种三维效果形象的生成方法，还包括：
在一些实现方式中，所述虚拟形象基于下述方式生成：
根据输入的图像采集指令，采集目标对象的图像数据；
对所述图像数据进行解析，得到所述目标对象中多个部位属性；
根据每个部位属性，从预设库中选择对应的虚拟部位，并根据多个虚拟部位生成所述虚拟形象。
根据本公开的一个或多个实施例，【示例六】提供了一种三维效果形象的生成方法，还包括：
在一些实现方式中，在所述生成所述虚拟形象之前，还包括：将所述目标素材与所述图像数据进行渲染；
所述根据所述遮挡关系对所述目标素材与所述虚拟形象进行渲染，包括：
响应于执行预设转场特效，根据所述遮挡关系对所述目标素材与所述虚拟形象进行渲染。
根据本公开的一个或多个实施例，【示例七】提供了一种三维效果形象的生成方法，还包括：
在一些实现方式中，所述目标素材中包含边框；
所述根据所述遮挡关系对所述目标素材与所述虚拟形象进行渲染，包括：将所述虚拟形象渲染在所述边框的部分边框前。
根据本公开的一个或多个实施例，【示例八】提供了一种三维效果形象的生成装置，该装置包括：
素材获取模块，设置为获取目标素材；其中，所述目标素材分为至少两个图层；
遮挡关系确定模块，设置为确定所述至少两个图层与虚拟形象的遮挡关系；
渲染模块，设置为根据所述遮挡关系对所述目标素材与所述虚拟形象进行渲染，生成具有三维效果的虚拟形象。
此外，虽然采用特定次序描绘了多个操作，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。同样地，虽然在上面论述中包含了多个实现细节，但是这些不应当被解释为对本公开的范围的限制。在单独的实施例的上下文中描述的一些特征还可以组合地实现在单个实施例中。相反地，在单个实施例的上下文中描述的多种特征也可以单独地或以任何合适的子组合的方式实现在多个实施例中。

Claims (11)

  1. 一种三维效果形象的生成方法，包括：
    获取目标素材；其中，所述目标素材分为至少两个图层；
    确定所述至少两个图层与虚拟形象的遮挡关系；
    根据所述遮挡关系对所述目标素材与所述虚拟形象进行渲染，生成具有三维效果的虚拟形象。
  2. 根据权利要求1所述的方法，其中，所述确定所述至少两个图层与虚拟形象的遮挡关系，包括：
    根据所述虚拟形象执行的动作，实时确定所述至少两个图层与所述虚拟形象的遮挡关系。
  3. 根据权利要求2所述的方法，其中，所述虚拟形象基于下述方式执行动作：
    根据输入的视频采集指令，采集目标对象的视频数据；
    对所述视频数据进行解析，得到所述目标对象的实时动作；
    根据所述实时动作驱动所述虚拟形象，以使所述虚拟形象执行相应的动作。
  4. 根据权利要求1所述的方法，其中，所述确定所述至少两个图层与虚拟形象的遮挡关系，包括：
    根据所述至少两个图层的预设遮挡关系标识，确定所述至少两个图层与所述虚拟形象的遮挡关系。
  5. 根据权利要求1所述的方法，其中，所述虚拟形象基于下述方式生成：
    根据输入的图像采集指令，采集目标对象的图像数据；
    对所述图像数据进行解析，得到所述目标对象中多个部位属性；
    根据每个部位属性，从预设库中选择对应的虚拟部位，并根据多个虚拟部位生成所述虚拟形象。
  6. 根据权利要求5所述的方法，在所述生成所述虚拟形象之前，还包括：将所述目标素材与所述图像数据进行渲染；
    所述根据所述遮挡关系对所述目标素材与所述虚拟形象进行渲染，包括：
    响应于执行预设转场特效，根据所述遮挡关系对所述目标素材与所述虚拟形象进行渲染。
  7. 根据权利要求1-6中任一所述的方法，其中，所述目标素材中包含边框；
    所述根据所述遮挡关系对所述目标素材与所述虚拟形象进行渲染，包括：
    将所述虚拟形象渲染在所述边框的部分边框前。
  8. 一种三维效果形象的生成装置，包括：
    素材获取模块，设置为获取目标素材；其中，所述目标素材分为至少两个图层；
    遮挡关系确定模块，设置为确定所述至少两个图层与虚拟形象的遮挡关系；
    渲染模块，设置为根据所述遮挡关系对所述目标素材与所述虚拟形象进行渲染，生成具有三维效果的虚拟形象。
  9. 一种电子设备，包括：
    至少一个处理器；
    存储装置，设置为存储至少一个程序；
    当所述至少一个程序被所述至少一个处理器执行，使得所述至少一个处理器实现如权利要求1-7中任一所述的三维效果形象的生成方法。
  10. 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1-7中任一所述的三维效果形象的生成方法。
  11. 一种计算机程序产品，包括承载在非暂态计算机可读介质上的计算机程序，所述计算机程序包含用于执行如权利要求1-7中任一所述的三维效果形象的生成方法的程序代码。
PCT/CN2023/094792 2022-05-25 2023-05-17 三维效果形象的生成方法、装置、电子设备及存储介质 WO2023226851A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210579466.6A CN117173305A (zh) 2022-05-25 2022-05-25 三维效果形象的生成方法、装置、电子设备及存储介质
CN202210579466.6 2022-05-25

Publications (1)

Publication Number Publication Date
WO2023226851A1 true WO2023226851A1 (zh) 2023-11-30

Family

ID=88918445

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/094792 WO2023226851A1 (zh) 2022-05-25 2023-05-17 三维效果形象的生成方法、装置、电子设备及存储介质

Country Status (2)

Country Link
CN (1) CN117173305A (zh)
WO (1) WO2023226851A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108830940A (zh) * 2018-06-19 2018-11-16 广东虚拟现实科技有限公司 遮挡关系处理方法、装置、终端设备及存储介质
CN112270735A (zh) * 2020-10-27 2021-01-26 北京达佳互联信息技术有限公司 虚拟形象模型生成方法、装置、电子设备及存储介质
CN113240692A (zh) * 2021-06-30 2021-08-10 北京市商汤科技开发有限公司 一种图像处理方法、装置、设备以及存储介质
CN113923297A (zh) * 2020-06-24 2022-01-11 中兴通讯股份有限公司 影像显示方法及装置、计算机可读存储介质、电子装置
CN115937379A (zh) * 2021-08-16 2023-04-07 北京字跳网络技术有限公司 一种特效生成方法、装置、电子设备及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108830940A (zh) * 2018-06-19 2018-11-16 广东虚拟现实科技有限公司 遮挡关系处理方法、装置、终端设备及存储介质
CN113923297A (zh) * 2020-06-24 2022-01-11 中兴通讯股份有限公司 影像显示方法及装置、计算机可读存储介质、电子装置
CN112270735A (zh) * 2020-10-27 2021-01-26 北京达佳互联信息技术有限公司 虚拟形象模型生成方法、装置、电子设备及存储介质
CN113240692A (zh) * 2021-06-30 2021-08-10 北京市商汤科技开发有限公司 一种图像处理方法、装置、设备以及存储介质
CN115937379A (zh) * 2021-08-16 2023-04-07 北京字跳网络技术有限公司 一种特效生成方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN117173305A (zh) 2023-12-05

Similar Documents

Publication Publication Date Title
US11895426B2 (en) Method and apparatus for capturing video, electronic device and computer-readable storage medium
WO2022121557A1 (zh) 一种直播互动方法、装置、设备及介质
WO2021082760A1 (zh) 虚拟形象的生成方法、装置、终端及存储介质
WO2020083021A1 (zh) 视频录制方法、视频播放方法、装置、设备及存储介质
WO2018010682A1 (zh) 直播方法、直播数据流展示方法和终端
WO2022105862A1 (zh) 视频生成及显示方法、装置、设备、介质
EP4047490A1 (en) Video-based interaction realization method and apparatus, device and medium
CN112199016B (zh) 图像处理方法、装置、电子设备及计算机可读存储介质
WO2023179346A1 (zh) 特效图像处理方法、装置、电子设备及存储介质
WO2022105846A1 (zh) 虚拟对象显示方法及装置、电子设备、介质
US20230182028A1 (en) Game live broadcast interaction method and apparatus
CN109600559B (zh) 一种视频特效添加方法、装置、终端设备及存储介质
CN114463470A (zh) 虚拟空间浏览方法、装置、电子设备和可读存储介质
WO2023226814A1 (zh) 视频处理方法、装置、电子设备及存储介质
WO2023143299A1 (zh) 消息展示方法、装置、设备及存储介质
WO2023232056A1 (zh) 图像处理方法、装置、存储介质及电子设备
WO2023134419A1 (zh) 信息交互方法、装置、设备及存储介质
WO2023151525A1 (zh) 生成特效视频的方法、装置、电子设备及存储介质
CN112055252A (zh) 多屏互动方法、装置、计算机可读介质及电子设备
WO2023273697A1 (zh) 图像处理方法、模型训练方法、装置、电子设备及介质
KR20230128063A (ko) 햅틱 피드백을 갖는 실시간 비디오 통신 인터페이스
EP4315005A1 (en) Interface with haptic and audio feedback response
WO2023140786A2 (zh) 特效视频处理方法、装置、电子设备及存储介质
WO2024027819A1 (zh) 图像处理方法、装置、设备及存储介质
WO2024051540A1 (zh) 特效处理方法、装置、电子设备及存储介质

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: 23810924

Country of ref document: EP

Kind code of ref document: A1