WO2020186934A1

WO2020186934A1 - Method, apparatus, and electronic device for generating animation containing dynamic background

Info

Publication number: WO2020186934A1
Application number: PCT/CN2020/074369
Authority: WO
Inventors: 郭冠军
Original assignee: 北京字节跳动网络技术有限公司
Priority date: 2019-03-20
Filing date: 2020-02-05
Publication date: 2020-09-24
Also published as: CN110047119B; CN110047119A

Abstract

The embodiments of the present disclosure provide a method, apparatus, and electronic device for generating an animation containing a dynamic background, belonging to the technical field of data processing, said method comprising: obtaining a reconstruction model related to a specific region and first element and second element of a target object; on the basis of said reconstruction model, determining a texture feature of the specific region related to input information, and an action of the first element and an action of the second element; while generating a first animation, dynamically selecting, from a plurality of preset animations, an animation matching said first animation to be the background animation of the first animation; on the basis of the first animation and said background animation, generating a final animation related to the input information. The processing solution of the present disclosure increases the authenticity of the generated image.

Description

Animation generating method, device and electronic equipment containing dynamic background

Cross references to related applications

This application claims the priority of a Chinese patent application filed on March 20, 2019, with the application number 201910214896.6 and the title of the invention "animation generating method, device and electronic equipment containing dynamic background", the full text of which is incorporated by reference In this application.

Technical field

The present disclosure relates to the field of data processing technology, and in particular, to an animation generating method, device and electronic device including a dynamic background.

Background technique

With the development of network technology, the application of artificial intelligence technology in network scenarios has been greatly improved. As a specific application requirement, more and more virtual characters are used in the network environment to interact. For example, in the web live broadcast, a virtual anchor is provided to anthropomorphically broadcast the live content and provide necessary guidance for the live broadcast. Thereby enhancing the presence and interactivity of the live broadcast and improving the effect of the web live broadcast.

Expression simulation (for example, mouth movement simulation) technology is a kind of artificial intelligence technology. The current realization of expression simulation is mainly based on text-driven, natural voice-driven and audio-video hybrid modeling methods to drive the facial expressions of characters. For example, the text-driven approach is usually the TTS (Text to Speech, text-to-speech) engine that converts the input text information into the corresponding phoneme sequence, phoneme duration, and corresponding voice waveform, and then select the corresponding model unit in the model library , Through smooth processing and corresponding synchronization algorithm, finally present the voice and facial expression actions corresponding to the input text content.

The emoji simulation in the prior art has a single or even distorted emoji simulation, which is more like a "robot" performing a performance, and the fidelity of the emoji action is still far from the expression of a real person.

Summary of the invention

In view of this, the embodiments of the present disclosure provide a method, device and electronic device for generating an animation including a dynamic background, which at least partially solves the problems existing in the prior art.

In a first aspect, an embodiment of the present disclosure provides a method for generating an animation including a dynamic background, including: obtaining a reconstruction model related to a specific area, a first element, and a second element of a target object, the specific area belonging to the A part of the target object, the first element and the second element are located in the specific area;

Based on the reconstruction model, determine the texture feature of the specific area related to the input information, the action of the first element and the action of the second element, the texture feature of the specific area, the action of the first element And the action of the second element forms a first animation related to the input information;

While generating the first animation, dynamically selecting an animation matching the first animation from a plurality of preset animations as the background animation of the first animation;

Based on the first animation and the background animation, a final animation related to the input information is generated.

According to a specific implementation manner of the embodiments of the present disclosure, before obtaining the reconstruction model related to the specific area, the first element and the second element of the target object, the method further includes:

A plurality of images including the target object are acquired, and based on the plurality of images, a reconstruction model related to the specific area, the first element and the second element of the target object is trained.

According to a specific implementation of the embodiment of the present disclosure, the training of the reconstruction model related to the specific area, the first element and the second element of the target object includes:

Detecting specific areas on the multiple images to obtain a target area;

Performing 3D reconstruction on the target area to obtain a 3D area object;

Acquiring a three-dimensional grid of the 3D area object, where the three-dimensional grid includes preset coordinate values;

Based on the pixel values on different three-dimensional grid coordinates, the texture map of the specific area is determined.

Performing feature point detection on the first element on the multiple images;

Divide the detected feature points into a first type feature point and a second type feature point, the first type feature point is used to form a first closed area, and the second type feature point is used to form a second closed area;

A first color is filled in the first closed area, and a second color is filled in the second closed area, and the first color is different from the second color.

Performing feature point detection on the second element on the multiple images;

Based on all the detected feature points, a third closed area is formed;

A third color is filled in the third closed area.

According to a specific implementation manner of an embodiment of the present disclosure, the determining the texture feature of the specific area related to the input information, the action of the first element, and the action of the second element based on the reconstruction model includes :

Predicting the contour of the specific area of the target object, and filling the predicted contour with the texture map determined by the reconstruction model;

The motion parameters obtained after parsing the input information are matched to the first element and the second element to form an action of the first element and the second element.

According to a specific implementation of the embodiment of the present disclosure, the dynamically selecting an animation matching the first animation from a plurality of preset animations as the background animation of the first animation includes:

Analyze the current scene of the input information, dynamically select an animation that matches the current scene from a plurality of preset animations as the background animation.

According to a specific implementation of the embodiment of the present disclosure, the generating a final animation related to the input information based on the first animation and the background animation includes:

Judging whether the background animation is composed of multiple animations of different types;

If it is, smooth the different types of animations.

According to a specific implementation of an embodiment of the present disclosure, the specific area is a face area, the first element is an eye, and the second element is a mouth.

In the second aspect, the embodiments of the present disclosure provide an animation generating device including a dynamic background, including:

The acquiring module is used to acquire a reconstruction model related to a specific area, a first element and a second element of a target object, the specific area belongs to a part of the target object, and the first element and the second element are located in the Within a specific area

The determining module is configured to determine, based on the reconstruction model, the texture feature of the specific area related to the input information, the action of the first element and the action of the second element, the texture feature of the specific area, the The actions of the first element and the actions of the second element form a first animation related to the input information;

The selection module is configured to dynamically select an animation matching the first animation from a plurality of preset animations as the background animation of the first animation while generating the first animation;

A generating module is used to generate a final animation related to the input information based on the first animation and the background animation.

In a third aspect, an embodiment of the present disclosure also provides an electronic device, which includes:

At least one processor; and,

A memory communicatively connected with the at least one processor; wherein,

The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute any of the foregoing first aspect or any implementation of the first aspect Including dynamic background animation generation method.

In a fourth aspect, embodiments of the present disclosure also provide a non-transitory computer-readable storage medium that stores computer instructions that are used to make the computer execute the first aspect or the first aspect described above. An animation generating method including a dynamic background in any implementation manner of one aspect.

In a fifth aspect, the embodiments of the present disclosure also provide a computer program product. The computer program product includes a computing program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When executing, the computer is caused to execute the animation generating method including the dynamic background in the foregoing first aspect or any implementation manner of the first aspect.

The animation generation solution including dynamic background in the embodiment of the present disclosure includes obtaining a reconstruction model related to a specific area, a first element, and a second element of a target object. The specific area belongs to a part of the target object. The first element and the second element are located in the specific area; based on the reconstruction model, the texture feature of the specific area related to the input information, the action of the first element and the action of the second element are determined, so The texture feature of the specific area, the action of the first element, and the action of the second element form a first animation related to the input information; while the first animation is generated, the preset Among the animations, an animation matching the first animation is dynamically selected as a background animation of the first animation; based on the first animation and the background animation, a final animation related to the input information is generated. Through the processing scheme of the present disclosure, it is possible to realistically simulate an animated image matching the input information, which improves the user experience.

Description of the drawings

In order to explain the technical solutions of the embodiments of the present disclosure more clearly, the following will briefly introduce the drawings that need to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained from these drawings without creative work.

FIG. 1 is a schematic diagram of an animation generation process including a dynamic background provided by an embodiment of the disclosure;

FIG. 2 is a schematic diagram of another animation generation process including a dynamic background provided by an embodiment of the present disclosure;

FIG. 3 is a schematic diagram of another animation generation process including a dynamic background provided by an embodiment of the present disclosure;

FIG. 4 is a schematic diagram of another animation generation process including a dynamic background provided by an embodiment of the present disclosure;

FIG. 5 is a schematic structural diagram of an animation generating device including a dynamic background provided by an embodiment of the disclosure;

FIG. 6 is a schematic diagram of an electronic device provided by an embodiment of the disclosure.

detailed description

The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

The following describes the implementation of the present disclosure through specific specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and the features in the embodiments can be combined with each other if there is no conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present disclosure.

It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be obvious that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and/or function described herein are only illustrative. Based on the present disclosure, those skilled in the art should understand that one aspect described herein can be implemented independently of any other aspects, and two or more of these aspects can be combined in various ways. For example, any number of aspects set forth herein can be used to implement devices and/or methods of practice. In addition, structures and/or functionalities other than one or more of the aspects set forth herein may be used to implement this device and/or practice this method.

It should also be noted that the illustrations provided in the following embodiments merely illustrate the basic idea of the present disclosure in a schematic manner. The figures only show the components related to the present disclosure rather than the number, shape, and shape of the components in actual implementation. For size drawing, the type, quantity, and ratio of each component can be changed at will during actual implementation, and the component layout type may also be more complicated.

In addition, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that the described aspects may be practiced without these specific details.

The embodiment of the present disclosure provides a method for generating an animation including a dynamic background. The method for generating an animation containing a dynamic background provided in this embodiment can be executed by a computing device, which can be implemented as software, or as a combination of software and hardware, and the computing device can be integrated in a server, terminal device, etc. .

Referring to FIG. 1, an animation generating method including a dynamic background provided by an embodiment of the present disclosure includes the following steps S101-S104:

S101. Acquire a reconstruction model related to a specific area, a first element, and a second element of a target object, where the specific area belongs to a part of the target object, and the first element and the second element are located in the specific area .

The actions and expressions of the target object are the content to be simulated and predicted by the solution of the present disclosure. As an example, the target object can be a real person who can broadcast on the Internet, or other objects with information dissemination functions, such as TV programs. Hosts, news program announcers, teachers who give lectures, etc.

The target object is usually a person with a communication function. Since this type of person usually has a certain reputation, when there is a large amount of content that the target object needs to broadcast including voice and/or video actions, it usually costs more. At the same time, for live broadcast programs, the target object usually cannot appear in multiple live broadcast rooms (or multiple live channels) at the same time. At this time, if you want to present an effect such as "Anchor Clone", it is usually difficult to achieve this effect through live broadcast by real people.

For this reason, it is necessary to pre-train the reconstruction model, which can predict the image and actions of the target object based on the input information, thereby generating actions and expressions that match the input information. For example, for a piece of news that needs to be broadcast, the target audience can broadcast the news in the form of a news broadcaster.

In order to be able to predict the actions and expressions of the target object, it is usually necessary to imitate more components on the target object (for example, eyes, ears, eyebrows, nose, mouth, etc.). However, components with more predictions will affect the efficiency of predictions and consume more resources. For this reason, the solution of the present disclosure only selects the component elements that are most relevant to the identification of the target object: the specific area, the first element and the second element. As an example, the specific area is the face area of the target object, the first element is the eyes of the target object, and the second element is the mouth of the target object.

S102. Based on the reconstruction model, determine the texture feature of the specific region, the action of the first element and the action of the second element related to the input information, the texture feature of the specific region, the first element The action of and the action of the second element form a first animation related to the input information.

Based on the reconstruction model, the various actions and expressions of the target object in the video can be predicted through video animation. Specifically, the fidelity image can be used to generate a video file containing the actions and expressions of the target object. The fidelity image can be used as all frames or key frames of the video file, and the fidelity image contains information that matches the input information. A collection of multiple images for one or more predicted actions.

The input information can be in multiple ways. For example, the input information can be that the target object needs to play a piece of text or a piece of audio content at the same time during the animation display process, that is, the input information can be in the form of text or audio. Based on different input information, the target object can produce different animations. After data analysis, the input information is transformed into parameters matching the texture map and the shape constraint map, and the reconstruction model obtained after training is used to finally complete the guarantee by calling the texture map and the shape constraint map Image generation.

In the stage of prediction, the texture map of the specific area of the target object and the shape constraints of the first element and the second element can be given, and the trained reconstruction model can be used to predict the image of the two-dimensional anchor image. Through the continuous first element, The shape constraint of the second element and the fixed texture of the specific area are used as input to predict the continuous animation image of the target object.

S103: While generating the first animation, dynamically select an animation matching the first animation from a plurality of preset animations as a background animation of the first animation.

In order to improve the realism of the generated screen, the background animation related to the target object is recorded in advance. The background animation can be a variety of different types of background animation, for example, it can be serious, lively, happy, sad, and other different styles of animation. The background animation has a certain length so that it can be called easily.

When calling the background animation, it is necessary to analyze the current scene of the input information. Based on the results of the analysis, dynamically select the animation that matches the current scene from the preset multiple animations as the background animation. For example, if the analysis knows that the current input information is excited, then the excited background animation is called. When a change in the scene of the input information is detected, even if the currently called background animation has not been played, it will switch to call the background animation matching the changed scene. After the currently called background animation is played, if it is found that the current scene of the input information has not changed, the current background animation will continue to be played in a loop.

S104: Generate a final animation related to the input information based on the first animation and the background animation.

By superimposing the predicted first animation and the background animation, the final animation related to the input information is generated. The final animation can be stored or disseminated in the form of video files.

In the process of generating the final animation, there may be situations where the background animation is switched. For this, it can be determined whether the background animation is composed of multiple different types of animation splicing, and if so, smooth processing is performed on the different types of animation. Make the transition between different types of animation as background animation more natural.

The reconstruction model is obtained through neural network training. For this reason, before obtaining the reconstruction model related to the specific area, the first element and the second element of the target object, it is also necessary to collect multiple images containing the target object. Images, training a reconstruction model related to the specific area, the first element and the second element of the target object.

Referring to FIG. 2, training a reconstruction model related to a specific region, first element, and second element of the target object can be performed through a specific implementation manner according to an embodiment of the present disclosure, which can include:

S201: Detect specific areas on the multiple images to obtain a target area.

Multiple images can be used for target matching to obtain a target area. As an example, the target area may be a face area. In this case, face areas existing on multiple images can be detected by means of face detection.

S202: Perform 3D reconstruction on the target area to obtain a 3D area object.

After acquiring multiple images related to the target object, the constituent objects on the target object can be selected to model the target object. Various methods can be used for 3D modeling of the target area. For example, a depth value can be added on the basis of the two-dimensional pixel values of the multiple image planes, and the depth value can be obtained based on the brightness values of the multiple images.

S203: Acquire a three-dimensional grid of the 3D area object, where the three-dimensional grid includes preset coordinate values.

The 3D area object uses a three-dimensional grid to describe its specific location. For this purpose, specific coordinate values are set for the three-dimensional grid. For example, the three-dimensional grid can be described by setting two-dimensional plane coordinates and spatial height coordinates.

S204: Determine a texture map of the specific region based on pixel values on different three-dimensional grid coordinates.

The pixel values on different three-dimensional grid coordinates can be connected together to form a grid plane, which forms a texture map of a specific area.

In addition to training the target area, it is also necessary to train the first element. Referring to FIG. 3, according to a specific implementation of an embodiment of the present disclosure, the training is related to the specific area of the target object, the first element and Refactored models related to the second element, including:

S301: Perform feature point detection on the first element on the multiple images.

Perform feature setting on the first element to obtain feature points related to the first element. Taking the eye as an example, the contour and pupil of the eye can be used as feature objects, and feature points related to the contour and pupil of the eye can be obtained through feature detection.

S302. Divide the detected feature points into a first type feature point and a second type feature point, the first type feature point is used to form a first closed area, and the second type feature point is used to form a second closed area. area.

The first element is composed of at least two components (for example, pupil and sclera). Based on the different parts to which the feature points belong, the detected feature points are divided into first type feature points and second type feature points, for example, the first Type feature points are feature points related to the pupil, and the second type feature points are feature points related to the sclera. By forming the first type feature points and the second type feature points into a closed curve, the first closed area and the second closed area can be formed respectively.

S303: Fill a first color in the first closed area, and a second color in the second closed area, where the first color is different from the second color.

For example, you can fill blue in the first closed area and white in the second closed area. By filling different first and second colors in different closed areas, the image of the predicted target object can be more improved. lifelike.

For the second element with only one component, a simple processing method can be used to improve the efficiency of data processing. Referring to FIG. 4, according to a specific implementation of the embodiment of the present disclosure, the training of a reconstruction model related to a specific area, a first element, and a second element of the target object includes:

S401: Perform feature point detection on the second element on the multiple images.

The feature setting of the second element can detect the feature points related to the second element. Taking the mouth as an example, the entire mouth can be used as a feature object, and the feature points related to the mouth can be obtained through feature detection.

S402: Form a third closed area based on all the detected feature points.

After all the feature points of the second element are obtained, a closed area can be formed by connecting all the feature points together, and then a third closed area can be obtained.

S403, filling a third color in the third closed area.

After the third closed area is obtained, the third closed area can be filled with a color matching the second element. Taking the mouth as an example, the third closed area can be filled with red that matches the mouth.

In the process of actually predicting the target object, the contour of the specific area of the target object is predicted, and the texture map determined by the reconstruction model is filled in the predicted contour, thereby obtaining the contour of the specific area of the target object Figure (e.g., face contour map).

The motion parameters obtained after parsing the input information are matched to the first element and the second element, and the actions of the first element and the second element are formed. Specifically, the input information may be in multiple ways, for example, the input information may be in the form of text or audio. The input information is transformed into a first analysis result after data analysis. The first analysis result includes parameters matching the texture map and the shape constraint map of the first element and the second element. The reconstruction model obtained after training is used to pass The texture map and the shape constraint map are called to finally complete the generation of the target object prediction action.

The first analysis result contains the motion amplitude parameters for the first element and the second element on the target object. Take the mouth as an example. When the mouth is fully opened, the motion amplitude can be quantified as 1. When the mouth is fully closed, the motion amplitude It can be quantified as 0. By quantifying the value between 0 and 1, the intermediate state of the mouth between fully opened and fully closed can be described.

Corresponding to the above method embodiment, referring to FIG. 5, an embodiment of the present disclosure also discloses an animation generating device 50 containing a dynamic background, including:

The obtaining module 501 is configured to obtain a reconstruction model related to a specific area, a first element, and a second element of a target object, the specific area belongs to a part of the target object, and the first element and the second element are located in the target object. Said within a specific area.

In order to be able to predict the actions and expressions of the target object, it is usually necessary to imitate more components on the target object (for example, eyes, ears, eyebrows, nose, mouth, etc.). However, the more predictive components will affect the efficiency of the forecast and consume more resources. For this reason, the solution of the present disclosure only selects the component elements that are most relevant to the identification of the target object: the specific area, the first element and the second element. As an example, the specific area is the face area of the target object, the first element is the eyes of the target object, and the second element is the mouth of the target object.

The determining module 502 is configured to determine, based on the reconstruction model, the texture feature of the specific area, the action of the first element and the action of the second element related to the input information, the texture feature of the specific area, the The action of the first element and the action of the second element form a first animation related to the input information.

The input information can be in a variety of ways. For example, the input information can be in the form of text or audio. After data analysis, the input information is transformed into parameters matching the texture map and the shape constraint map, and the reconstruction model obtained after training is used to finally complete the guarantee by calling the texture map and the shape constraint map Image generation.

In the stage of prediction, the texture map of the specific area of the target object and the shape constraints of the first element and the second element can be given, and the trained reconstruction model can be used to predict the image of the two-dimensional anchor image through the continuous first element, The shape constraint of the second element and the fixed texture of the specific area are used as input to predict the continuous animation image of the target object.

The selection module 503 is configured to dynamically select an animation matching the first animation from a plurality of preset animations as the background animation of the first animation while generating the first animation.

When calling the background animation, it is necessary to analyze the current scene of the input information, and based on the analysis result, dynamically select an animation that matches the current scene from a plurality of preset animations as the background animation. For example, if the analysis knows that the current input information is excited, then the excited background animation is called. When a change in the scene of the input information is detected, even if the currently called background animation has not been played, it will switch to call the background animation matching the changed scene. After the currently called background animation is played, if it is found that the current scene of the input information has not changed, the current background animation will continue to be played in a loop.

The generating module 504 is configured to generate a final animation related to the input information based on the first animation and the background animation.

In the process of generating the final animation, there may be situations where the background animation is switched. For this, it can be determined whether the background animation is composed of multiple different types of animation splicing, and if so, smooth processing is performed on the different types of animation. Make the transition between different types of animation more natural.

The device shown in FIG. 5 can correspondingly execute the content in the foregoing method embodiment. For parts that are not described in detail in this embodiment, refer to the content recorded in the foregoing method embodiment, which will not be repeated here.

Referring to FIG. 6, an embodiment of the present disclosure also provides an electronic device 60, which includes:

At least one processor; and,

A memory communicatively connected with the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute the animation generation method including the dynamic background in the foregoing method embodiment.

The embodiments of the present disclosure also provide a non-transitory computer-readable storage medium that stores computer instructions, and the computer instructions are used to make the computer execute the foregoing method embodiments.

The embodiments of the present disclosure also provide a computer program product, the computer program product includes a calculation program stored on a non-transitory computer-readable storage medium, the computer program includes program instructions, when the program instructions are executed by a computer, The computer executes the animation generation method including the dynamic background in the foregoing method embodiment.

Reference is now made to FIG. 6, which shows a schematic structural diagram of an electronic device 60 suitable for implementing embodiments of the present disclosure. Electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle-mounted terminals (for example, Mobile terminals such as car navigation terminals) and fixed terminals such as digital TVs, desktop computers, etc. The electronic device shown in FIG. 6 is only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present disclosure.

As shown in FIG. 6, the electronic device 60 may include a processing device (such as a central processing unit, a graphics processor, etc.) 601, which may be loaded into a random access device according to a program stored in a read-only memory (ROM) 602 or from a storage device 608. The program in the memory (RAM) 603 executes various appropriate actions and processing. The RAM 603 also stores various programs and data required for the operation of the electronic device 60. The processing device 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also connected to the bus 604.

Generally, the following devices can be connected to the I/O interface 605: including input devices 606 such as touch screen, touch panel, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; including, for example, liquid crystal display (LCD), speakers, An output device 607 such as a vibrator; a storage device 608 such as a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 60 to perform wireless or wired communication with other devices to exchange data. Although the figure shows the electronic device 60 having various devices, it should be understood that it is not required to implement or have all the illustrated devices. It may alternatively be implemented or provided with more or fewer devices.

In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

It should be noted that the above-mentioned computer-readable medium in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electric, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, 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 suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as a part of a carrier wave, and a computer-readable program code is carried therein. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium. The computer-readable signal medium may send, propagate, or transmit the program for use by or in combination with the instruction execution system, apparatus, or device . The program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wire, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above.

The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist alone without being assembled into the electronic device.

The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains at least two Internet protocol addresses; and sends to the node evaluation device including the at least two A node evaluation request for an Internet Protocol address, wherein the node evaluation device selects an Internet Protocol address from the at least two Internet Protocol addresses and returns it; receives the Internet Protocol address returned by the node evaluation device; wherein, the obtained The Internet Protocol address indicates the edge node in the content distribution network.

Alternatively, the aforementioned computer-readable medium carries one or more programs, and when the aforementioned one or more programs are executed by the electronic device, the electronic device: receives a node evaluation request including at least two Internet Protocol addresses; Among the at least two Internet Protocol addresses, select an Internet Protocol address; return the selected Internet Protocol address; wherein, the received Internet Protocol address indicates an edge node in the content distribution network.

The computer program code used to perform the operations of the present disclosure may be written in one or more programming languages or a combination thereof. The above-mentioned programming languages include object-oriented programming languages—such as Java, Smalltalk, C++, and also conventional Procedural programming language-such as "C" language or similar programming language. The program code can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server. In the case of a remote computer, the remote computer can 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 it can be connected to an external computer (for example, using an Internet service provider to pass Internet connection).

The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions, and operations of the system, method, and computer program product according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram can represent a module, program segment, or part of code, and the module, program segment, or part of code contains one or more for realizing the specified logical function Executable instructions. It should also be noted that, in some alternative implementations, the functions marked in the block may also occur in a different order from the order marked in the drawings. For example, two blocks shown in succession can actually be executed substantially in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations Or it can be realized by a combination of dedicated hardware and computer instructions.

The units involved in the embodiments described in the present disclosure may be implemented in a software manner, or may be implemented in a hardware manner. Wherein, the name of the unit does not constitute a limitation on the unit itself under certain circumstances. For example, the first obtaining unit can also be described as "a unit for obtaining at least two Internet Protocol addresses."

It should be understood that each part of the present disclosure can be implemented by hardware, software, firmware or a combination thereof.

The above are only specific implementations of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present disclosure. All should be covered within the protection scope of this disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

A method for generating animation containing dynamic background, characterized in that it comprises:

Acquiring a reconstruction model related to a specific area, a first element, and a second element of a target object, the specific area belongs to a part of the target object, and the first element and the second element are located in the specific area;

Based on the reconstruction model, determine the texture feature of the specific area related to the input information, the action of the first element and the action of the second element, the texture feature of the specific area, the action of the first element And the action of the second element forms a first animation related to the input information;

While generating the first animation, dynamically selecting an animation matching the first animation from a plurality of preset animations as the background animation of the first animation;

Based on the first animation and the background animation, a final animation related to the input information is generated.
The method according to claim 1, wherein before obtaining the reconstruction model related to the specific area, the first element and the second element of the target object, the method further comprises:

A plurality of images including the target object are acquired, and based on the plurality of images, a reconstruction model related to the specific area, the first element and the second element of the target object is trained.
The method according to claim 2, wherein the training a reconstruction model related to the specific area, the first element and the second element of the target object comprises:

Detecting specific areas on the multiple images to obtain a target area;

Performing 3D reconstruction on the target area to obtain a 3D area object;

Acquiring a three-dimensional grid of the 3D area object, where the three-dimensional grid includes preset coordinate values;

Based on the pixel values on different three-dimensional grid coordinates, the texture map of the specific area is determined.
The method according to claim 2, wherein the training a reconstruction model related to the specific area, the first element and the second element of the target object comprises:

Performing feature point detection on the first element on the multiple images;

Divide the detected feature points into a first type feature point and a second type feature point, the first type feature point is used to form a first closed area, and the second type feature point is used to form a second closed area;

A first color is filled in the first closed area, and a second color is filled in the second closed area, and the first color is different from the second color.
The method according to claim 2, wherein the training a reconstruction model related to the specific area, the first element and the second element of the target object comprises:

Performing feature point detection on the second element on the multiple images;

Based on all the detected feature points, a third closed area is formed;

A third color is filled in the third closed area.
The method according to claim 3, wherein the determining the texture feature of the specific area related to the input information, the action of the first element and the action of the second element based on the reconstruction model, include:

Predicting the contour of the specific area of the target object, and filling the predicted contour with the texture map determined by the reconstruction model;

The motion parameters obtained after parsing the input information are matched to the first element and the second element to form an action of the first element and the second element.
The method according to claim 1, wherein the dynamically selecting an animation matching the first animation from a plurality of preset animations as the background animation of the first animation comprises:

Analyze the current scene of the input information, dynamically select an animation that matches the current scene from a plurality of preset animations as the background animation.
The method according to claim 1, wherein the generating a final animation related to the input information based on the first animation and the background animation comprises:

Judging whether the background animation is composed of multiple animations of different types;

If it is, smooth the different types of animations.
The method according to claim 1, wherein:

The specific area is a face area, the first element is an eye, and the second element is a mouth.
An animation generating device containing a dynamic background, characterized in that it comprises:

The acquiring module is used to acquire a reconstruction model related to a specific area, a first element and a second element of a target object, the specific area belongs to a part of the target object, and the first element and the second element are located in the Within a specific area

The determining module is configured to determine, based on the reconstruction model, the texture feature of the specific area related to the input information, the action of the first element and the action of the second element, the texture feature of the specific area, the The actions of the first element and the actions of the second element form a first animation related to the input information;

The selection module is configured to dynamically select an animation matching the first animation from a plurality of preset animations as the background animation of the first animation while generating the first animation;

A generating module is used to generate a final animation related to the input information based on the first animation and the background animation.
An electronic device, characterized in that, the electronic device includes:

At least one processor; and,

A memory communicatively connected with the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute any of the preceding claims 1-9. Including dynamic background animation generation method.
A non-transitory computer-readable storage medium that stores

Computer instructions, which are used to make the computer execute the animation generating method including dynamic background according to any one of claims 1-9.