Methods, systems, and computer-readable media for image animation

Abstract

A system, method, and computer-readable storage medium for image animation are presented. The method accesses a sequence of image frames from a first computing device, the sequence of image frames including a first image frame and a second image frame, detects a first set of keypoints of the first image frame, sends the first image frame and the first set of keypoints to a second computing device, detects a second set of keypoints of the second image frame, sends the second set of keypoints to the second computing device, and causes an animated image to be displayed on the second computing device.

Description

[0001] Priority requirements

[0002] This application claims the benefit of priority to U.S. Provisional Application No. 63 / 198,143, filed September 30, 2020, the entire contents of which are incorporated herein by reference. Technical Field

[0003] Implementations of this disclosure generally relate to facial animation. More specifically, but not limitingly, this disclosure relates to systems and methods for facial animation in video compression systems. Background Technology

[0004] Image annotation involves generating video sequences such that objects in a target image are animated based on the motion driving the video. Specifically, facial animation involves extracting motion patterns from a driving video containing a sequence of facial expressions and transferring these motion patterns to one or more images of the target face. Attached Figure Description

[0005] In accompanying drawings that are not necessarily drawn to scale, the same numbers may describe similar parts in different views. For ease of identification of any particular element or action being discussed, one or more highest-digit numerals in the drawing reference numerals indicate the drawing number in which the element was first introduced. Some non-limiting examples are shown in the accompanying drawings:

[0006] Figure 1 It is a diagrammatic representation of a networked environment in which the content of this disclosure can be deployed, based on some examples.

[0007] Figure 2 It is a graphical representation of a messaging system with both client-side and server-side functionalities, based on some examples.

[0008] Figure 3 It is a graphical representation of the data structures maintained in the database based on some examples.

[0009] Figure 4 It is a graphical representation based on some example messages.

[0010] Figure 5 This is a flowchart illustrating access restriction processing based on some examples.

[0011] Figure 6 A method for compressing video for transmission according to one embodiment is shown.

[0012] Figure 7It is a graphical representation of a machine in the form of a computer system, based on some examples, in which a set of instructions can be executed to cause the machine to perform any or more of the methods discussed herein.

[0013] Figure 8 It is a block diagram showing a software architecture in which examples can be implemented. Detailed Implementation

[0014] The reference to "one embodiment" or "implementation" in the specification means that a particular feature, structure, or characteristic described in connection with that embodiment is included in at least one embodiment of the subject matter. Therefore, the appearance of the phrase "in one embodiment" or "in an embodiment" in various places throughout the specification does not necessarily refer to the same embodiment.

[0015] For illustrative purposes, specific configurations and details have been set forth to provide a thorough understanding of the subject matter. However, it will be apparent to those skilled in the art that embodiments of the described subject matter can be practiced without the specific details presented herein or in various combinations as described herein. Furthermore, well-known features may be omitted or simplified to avoid obscuring the described embodiments. Various examples may be given throughout this specification. These examples are merely descriptions of particular embodiments. The scope or meaning of the claims is not limited to the examples given.

[0016] The example implementation describes a method for compressing video for transmission over a network. In one example, a video compression system compresses a video generated by a first user and sends the compressed video to a second user. The video compression system sends a first image frame from the video to the second user. The video compression system also calculates keypoints on the first image frame and sends a first set of keypoints to the second user. The video compression system calculates keypoints for all subsequent image frames in the video and sends the remaining keypoints of the subsequent image frames to the second user. The video compression system uses the first set of keypoints and the subsequent keypoints to animate the first image frame on the second user's computing device. In some examples, the keypoints are generated using a first neural network on the first user's computing device. The animation can be generated using a second neural network on the second user's computing device. In some examples, the video compression system is used to transmit video over a low-bandwidth network. The following is combined with... Figure 6 Describe further details about the video compression system.

[0017] Networked computing environment

[0018] Figure 1This is a block diagram illustrating an example messaging system 100 for exchanging data (e.g., messages and associated content) over a network. The messaging system 100 includes multiple instances of client devices 102, each hosting several applications, including a messaging client 104 and other applications 106. Each messaging client 104 is communicatively coupled to a messaging server system 108, a third-party server 116, and other instances of the messaging client 104 (e.g., hosted on corresponding other client devices 102) via a network 112 (e.g., the Internet). The messaging client 104 can also communicate with the local host application 106 using an application programming interface (API).

[0019] Message transceiver client 104 can communicate and exchange data with other message transceiver clients 104 and message transceiver server system 108 via network 112. The data exchanged between message transceiver clients 104 and between message transceiver client 104 and message transceiver server system 108 includes functions (e.g., commands to activate functions) and payload data (e.g., text, audio, video, or other multimedia data).

[0020] The message transceiver server system 108 provides server-side functionality to a specific message transceiver client 104 via network 112. While some functions of the message transceiver system 100 are described herein as being performed by either the message transceiver client 104 or the message transceiver server system 108, the location of certain functions within the message transceiver client 104 or the message transceiver server system 108 can be a design choice. For example, it may be technically preferred that certain technologies and functions are initially deployed within the message transceiver server system 108, but that technology and functions are subsequently migrated to the message transceiver client 104 of the client device 102, which has sufficient processing capabilities.

[0021] The messaging server system 108 supports various services and operations provided to the messaging client 104. Such operations include sending data to and receiving data from the messaging client 104, and processing data generated by the messaging client 104. As an example, this data may include message content, client device information, geolocation information, media enhancements and coverage, message content persistence conditions, social network information, and live event information. Data exchange within the messaging system 100 is activated and controlled through functions available via the user interface (UI) of the messaging client 104.

[0022] Specifically, turning to message transceiver server system 108, application programming interface (API) server 116 is coupled to application server 114 and provides a programming interface to application server 114. Application server 114 is communicatively coupled to database server 120, which provides access to database 126, which stores data associated with messages processed by application server 114. Similarly, web server 128 is coupled to application server 114 and provides a web-based interface to application server 114. To this end, web server 128 processes incoming network requests via Hypertext Transfer Protocol (HTTP) and several other related protocols.

[0023] Application Programming Interface (API) server 116 receives and sends message data (e.g., commands and message payloads) between client device 102 and application server 114. Specifically, API server 116 provides a set of interfaces (e.g., routines and protocols) that message sending and receiving client 104 can invoke or query to activate the functionality of application server 114. Application Programming Interface (API) server 116 exposes various functionalities supported by application server 114, including: account registration; login functionality; sending messages from one messaging client 104 to another messaging client 104 via application server 114; sending media files (e.g., images or videos) from messaging client 104 to messaging server 118 and for possible access by another messaging client 104; setting up media data collections (e.g., stories); retrieving the friend list of the user of client device 102; retrieving such collections; retrieving messages and content; adding and deleting entities (e.g., friends) in an entity graph (e.g., a social graph); locating friends in a social graph; and opening application events (e.g., related to messaging client 104).

[0024] Application server 114 hosts several server applications and subsystems, including, for example, messaging server 118, image processing server 122, and social networking server 124. Messaging server 118 implements several messaging techniques and functions, particularly those related to the aggregation and other processing of content (e.g., text and multimedia content) included in messages received from multiple instances of messaging client 104. As will be described in further detail, text and media content from multiple sources can be aggregated into collections of content (e.g., referred to as stories or galleries). These collections are then made available to messaging client 104. Given the hardware requirements for such processing, additional processor- and memory-intensive data processing can also be performed on the server side by messaging server 118.

[0025] Application server 114 also includes image processing server 122, which is dedicated to performing various image processing operations, typically relative to the image or video within the payload of a message sent from or received at message transceiver server 118.

[0026] Social networking server 124 supports various social networking functions and services, and makes these functions and services available to messaging server 118. To this end, social networking server 124 maintains and accesses entity graph 308 within database 126 (such as...). Figure 3 (As shown). Examples of functions and services supported by the social network server 124 include identifying other users in the messaging system 100 who are related to a particular user or who are being "followed" by that particular user, as well as identifying the interests and other entities of a particular user.

[0027] Returning to messaging client 104, the features and functionality of external resources (e.g., application 106 or applet) are available to the user via the interface of messaging client 104. In this context, "external" refers to the fact that application 106 or applet is outside of messaging client 104. External resources are typically provided by third parties, but may also be provided by the creator or provider of messaging client 104. Message client 104 receives user selections regarding options to initiate or access the features of such external resources. External resources may be application 106 installed on client device 102 (e.g., a "native app"), or a smaller version (e.g., an "app") of an application hosted on client device 102 or located remotely on client device 102 (e.g., on a third-party server 110). A smaller version of an application includes a subset of the application's features and functionality (e.g., a full-scale, native version of the application) and is implemented using markup language documentation. In one example, a smaller version of the application (e.g., a “mini-application”) is a web-based markup language version of the application and is embedded in the messaging client 104. In addition to using markup language documents (e.g., .*ml files), mini-applications may also include scripting languages ​​(e.g., .*js files or .json files) and stylesheets (e.g., .*ss files).

[0028] In response to a user selection of an option to launch or access an external resource, messaging client 104 determines whether the selected external resource is a web-based external resource or a locally installed application 106. In some cases, application 106, locally installed on client device 102, can be launched independently of messaging client 104 and separately from it, for example, by selecting the icon corresponding to application 106 on the home screen of client device 102. A smaller version of such an application can be launched or accessed via messaging client 104, and in some examples, no part of the smaller application can be accessed (or only a limited part can) outside of messaging client 104. A smaller application can be launched by messaging client 104, for example, by receiving and processing markup language documents associated with the smaller application from a third-party server 116.

[0029] In response to determining that the external resource is a locally installed application 106, the messaging client 104 instructs the client device 102 to launch the external resource by executing locally stored code corresponding to the external resource. In response to determining that the external resource is a web-based resource, the messaging client 104 communicates with a third-party server 110 (e.g.) to obtain a markup language document corresponding to the selected external resource. The messaging client 104 then processes the obtained markup language document to render the web-based external resource within the user interface of the messaging client 104.

[0030] The messaging client 104 can notify users of client device 102 or other users (e.g., "friends") associated with such users of one or more external resources. For example, the messaging client 104 can provide participants in a conversation (e.g., a chat session) within the messaging client 104 with notifications related to the current or recent use of external resources by one or more members of a group of users. One or more users can be invited to join a valid external resource or to activate a recently used but currently inactive external resource (within the group of friends). External resources can provide participants in the conversation, each using the corresponding messaging client 104, with the ability to share items, statuses, conditions, or locations within the external resource to the chat session with one or more members of a group of users. Shared items can be interactive chat cards that chat members can use to interact, for example, to activate the corresponding external resource, view specific information within the external resource, or take chat members to a specific location or status within the external resource. Within a given external resource, response messages can be sent to users on the messaging client 104. External resources can selectively include different media items in the response based on the current context of the external resource.

[0031] The messaging client 104 can present a list of available external resources (e.g., application 106 or applet) to the user to launch or access a given external resource. This list can be presented in a context-sensitive menu. For example, the icons representing different applications 106 (or applets) can vary based on how the user launches the menu (e.g., from a conversational interface or a non-conversational interface).

[0032] System Architecture

[0033] Figure 2 This is a block diagram illustrating further details of a messaging system 100 according to some examples. Specifically, the messaging system 100 is shown as including a messaging client 104 and an application server 114. The messaging system 100 includes several subsystems supported on the client side by the messaging client 104 and on the server side by the application server 114. These subsystems include, for example, a short-run timer system 202, a collection management system 204, an enhancement system 208, a map system 210, a game system 212, an external resource system 214, and a video compression system 216.

[0034] The short-lived timer system 202 is responsible for enabling temporary or time-limited access to content by the message sending client 104 and the message sending server 118. The short-lived timer system 202 includes several timers that selectively enable access (e.g., for rendering and displaying) of messages and associated content via the message sending client 104 based on duration and display parameters associated with a message or message set (e.g., a story). Further details regarding the operation of the short-lived timer system 202 are provided below.

[0035] The collection management system 204 is responsible for managing collections or sets of media (e.g., collections of text, images, video, and audio data). Collections of content (e.g., messages, including images, videos, text, and audio) can be organized into "event galleries" or "event stories." Such collections can be made available for a specified time period (e.g., the duration of an event related to the content). For example, content related to a concert can be made available as a "story" for the duration of a concert. The collection management system 204 can also be responsible for publishing icons that notify the user interface of the messaging client 104 of the existence of a specific collection.

[0036] Furthermore, the collection management system 204 includes a curation interface 206 that enables collection managers to manage and curate specific collections of content. For example, curation interface 206 allows event organizers to curate collections of content related to a specific event (e.g., removing inappropriate content or redundant messages). Additionally, the collection management system 204 employs machine vision (or image recognition technology) and content rules to automatically curate content collections. In some examples, users may be compensated for including user-generated content in the collection. In such cases, the collection management system 204 operates to automatically pay such users for using their content.

[0037] Enhancement system 208 provides various functionalities that enable users to enhance (e.g., annotate or otherwise modify or edit) media content associated with a message. For example, enhancement system 208 provides functionalities related to generating and publishing media overlays for messages processed by messaging system 100. Enhancement system 208 can operable to provide media overlays or enhancements (e.g., image filters) to messaging client 104 based on the geolocation of client device 102. In another example, enhancement system 208 can operable to provide media overlays to messaging client 104 based on other information such as the social network information of the user of client device 102. Media overlays can include audio and visual content as well as visual effects. Examples of audio and visual content include pictures, text, logos, animations, and sound effects. Examples of visual effects include color overlays. Audio and visual content or visual effects can be applied to media content items (e.g., photographs) at client device 102. For example, a media overlay can include text or images that can be overlaid on a photograph taken by client device 102. In another example, media overlays include location identifiers (e.g., Venice Beach) overlays, names of live events, or business names (e.g., Beach Cafe) overlays. In yet another example, enhancement system 208 uses the geolocation of client device 102 to identify media overlays that include the name of a business at the geolocation of client device 102. Media overlays may include additional tags associated with the business. Media overlays may be stored in database 126 and accessed via database server 120.

[0038] In some examples, enhancement system 208 provides a user-based publishing platform that allows users to select geolocations on a map and upload content associated with those geolocations. Users can also specify which media coverage should be provided to other users. Enhancement system 208 generates media coverage that includes the uploaded content and associates it with the selected geolocation.

[0039] In other examples, enhancement system 208 provides a merchant-based publishing platform that enables merchants to select specific media coverage associated with geolocation via bidding. For example, enhancement system 208 associates the media coverage of the highest-bidding merchant with a corresponding geolocation for a predefined amount of time.

[0040] Map system 210 provides various geolocation functions and supports the presentation of map-based media content and messages by messaging client 104. For example, map system 210 can display (e.g., stored in profile data 316) user icons or avatars on the map to indicate the current or past locations of the user's "friends," as well as media content (e.g., a collection of messages including photos and videos) generated by these friends within the map's context. For example, on the map interface of messaging client 104, messages posted by a user from a specific geolocation to messaging system 100 can be displayed to the specific user's "friends" within the context of that specific location on the map. The user can also share his or her location and status information with other users of messaging system 100 (e.g., using appropriate status avatars) via messaging client 104, where the location and status information is displayed to selected users within the context of the map interface of messaging client 104.

[0041] The game system 212 provides various game functions within the context of the messaging client 104. The messaging client 104 provides a game interface that displays a list of available games, which can be started by a user within the context of the messaging client 104 and played with other users of the messaging system 100. The messaging system 100 also enables specific users to invite other users to participate in specific games by sending invitations from the messaging client 104. The messaging client 104 also supports both voice and text messaging (e.g., chat) within the context of playing games, provides leaderboards for games, and also supports providing in-game rewards (e.g., coins and items).

[0042] External resource system 214 provides an interface for messaging client 104 to communicate with remote servers (e.g., third-party server 110) to launch or access external resources (i.e., applications or applets). Each third-party server 110, for example, hosts applications or applets based on markup languages ​​(e.g., HTML5) or smaller versions of applications (e.g., game applications, utility applications, payment applications, or ride-sharing applications). Messaging client 104 can launch web-based resources (e.g., applications) by accessing HTML5 files from the third-party server 110 associated with the web-based resource. In some examples, the application hosted by third-party server 110 is programmed in JavaScript using a software development kit (SDK) provided by messaging server 118. The SDK includes an application programming interface (API) with functionality that can be invoked or activated by the web-based application. In some examples, messaging server 118 includes a JavaScript library that provides access to a given external resource for some user data of messaging client 104. HTML5 is used as an example technology for programming games, but applications and resources programmed based on other technologies can be used.

[0043] To integrate the SDK's functionality into the web-based resource, the SDK is downloaded by third-party server 110 from message server 118, or otherwise received by third-party server 110. Once downloaded or received, the SDK is included as part of the application code of the web-based external resource. The code of the web-based resource can then call or activate certain functions of the SDK to integrate the features of message client 104 into the web-based resource.

[0044] The SDK stored on message transceiver server 118 effectively provides a bridge between external resources (e.g., application 106 or a mini-application) and message transceiver client 104. This provides users with a seamless experience communicating with other users on message transceiver client 104 while preserving the look and feel of message transceiver client 104. To bridge communication between external resources and message transceiver client 104, in some examples, the SDK facilitates communication between third-party server 110 and message transceiver client 104. In some examples, a WebViewJavaScriptBridge running on client device 102 establishes two unidirectional communication channels between external resources and message transceiver client 104. Messages are sent asynchronously between external resources and message transceiver client 104 via these communication channels. Each SDK function call is sent as a message and a callback. Each SDK function is implemented by constructing a unique callback identifier and sending a message with that callback identifier.

[0045] By using the SDK, not all information from the messaging client 104 is shared with the third-party server 110. The SDK limits which information is shared based on the needs of the external resource. In some examples, each third-party server 110 provides the messaging server 118 with an HTML5 file corresponding to the web-based external resource. The messaging server 118 can add a visual representation (such as a box design or other graphics) of the web-based external resource in the messaging client 104. Once the user selects a visual representation or instructs the messaging client 104 via its GUI to access a feature of the web-based external resource, the messaging client 104 obtains the HTML5 file and instantiates the resources required to access the feature of the web-based external resource.

[0046] The messaging client 104 presents a graphical user interface (GUI) for an external resource (e.g., a login page or title screen). During, before, or after presenting the login page or title screen, the messaging client 104 determines whether the initiated external resource has previously been authorized to access the messaging client 104's user data. In response to determining that the initiated external resource has previously been authorized to access the messaging client 104's user data, the messaging client 104 presents another GUI for the external resource, including its functionality and characteristics. In response to determining that the initiated external resource has not previously been authorized to access the messaging client 104's user data, after a threshold time period (e.g., 3 seconds) of displaying the external resource's login page or title screen, the messaging client 104 slides up a menu (e.g., animates the menu to appear from the bottom of the screen to the middle or other part of the screen) to authorize the external resource to access user data. This menu identifies the type of user data that the external resource will be authorized to use. In response to receiving a user's selection of the accept option, messaging client 104 adds the external resource to the list of authorized external resources and allows the external resource to access user data from messaging client 104. In some examples, the external resource is authorized by messaging client 104 to access user data according to the OAuth 2 framework.

[0047] The messaging client 104 controls the type of user data shared with external resources based on the type of authorized external resource. For example, it provides access to a first type of user data (e.g., a two-dimensional avatar of a user, with or without different avatar characteristics) to external resources including full-scale applications (e.g., application 106). As another example, it provides access to a second type of user data (e.g., payment information, a user's two-dimensional avatar, a user's three-dimensional avatar, and avatars with various avatar characteristics) to external resources including smaller versions of the application (e.g., a web-based version of the application). Avatar characteristics include different ways of customizing the appearance and feel of the avatar (e.g., different poses, facial features, clothing, etc.).

[0048] The video compression system 216 compresses the video generated on the first device and sends the compressed video to the second device. The video compression system 216 sends a first image frame from the video to the second device, and subsequently sends keyframes of all image frames to the second device. The video compression system 216 uses the keyframes of all image frames to animate the first image frame on the graphical user interface of the second device.

[0049] Data Architecture

[0050] Figure 3 This is a schematic diagram illustrating a data structure 300 that can be stored in a database 126 of a message transceiver server system 108, according to certain examples. Although the contents of the database 126 are shown as including several tables, it will be understood that the data can be stored in other types of data structures (e.g., as an object-oriented database).

[0051] Database 126 includes message data stored in message table 302. For any given message, this message data includes at least message sender data, message receiver (or recipient) data, and a payload. See below for reference. Figure 4 Further details are provided regarding information that can be included in the message and in the message data stored in message table 302.

[0052] Entity table 306 stores entity data and (for example, links to entity diagram 308 and profile data 316). Entities for which records are maintained within entity table 306 may include individuals, company entities, organizations, objects, locations, events, etc. Regardless of entity type, any entity whose data is stored in message transceiver server system 108 can be an identifiable entity. Each entity is assigned a unique identifier and an entity type identifier (not shown).

[0053] Entity graph 308 stores information about the relationships and associations between entities. As an example only, such relationships can be social relationships based on interests or activities, or professional relationships (e.g., working in a common company or organization).

[0054] Profile data 316 stores various types of profile data about a specific entity. Based on privacy settings specified by the specific entity, profile data 316 can be selectively used and presented to other users of messaging system 100. In the case of an individual, profile data 316 includes, for example, a username, phone number, address, settings (e.g., notification and privacy settings), and an avatar representation (or a set of such avatar representations) selected by the user. A specific user can then selectively include one or more of these avatar representations in the content of messages transmitted via messaging system 100 and in a map interface displayed to other users by messaging client 104. The set of avatar representations may include “status avatars,” which present a graphical representation of a user’s chosen state or activity at a specific time.

[0055] In the case that the entity is a group, in addition to the group name, members and various settings of the associated group (e.g., notifications), the group profile data 316 may similarly include one or more avatars associated with the group.

[0056] Database 126 also stores enhancement data, such as overlays or filters, in enhancement table 310. The enhancement data is associated with and applied to videos (video data is stored in video table 304) and images (image data is stored in image table 312).

[0057] In one example, a filter is an overlay displayed as an image or video during presentation to the receiving user. Filters can be of various types, including filters selected by the user from a set of filters presented to the sending user by the messaging client 104 when the sending user is composing a message. Other types of filters include geolocation filters (also known as geographic filters), which can be presented to the sending user based on geographic location. For example, a geolocation filter specific to a nearby or particular location can be presented by the messaging client 104 within the user interface based on geolocation information determined by the Global Positioning System (GPS) unit of the client device 102.

[0058] Another type of filter is a data filter, which can be selectively presented to the sending user by the messaging client 104 based on other inputs or information collected by the client device 102 during the message creation process. Examples of data filters include the current temperature at a specific location, the current speed of the sending user, the battery life of the client device 102, or the current time.

[0059] Other augmented data that can be stored in image table 312 includes augmented reality content items (e.g., corresponding to applied lenses or augmented reality experiences). Augmented reality content items can be real-time special effects and sounds that can be added to images or videos.

[0060] As described above, augmented data includes augmented reality content items, overlays, image transformations, AR images, and similar terms refer to modifications that can be applied to image data (e.g., video or images). This includes real-time modifications, which modify images as they are captured using the device sensors (e.g., one or more cameras) of client device 102 and then display the modified images on the screen of client device 102. This also includes modifications to stored content, such as modifications to video clips in a gallery that can be modified. For example, in client device 102, which has access to multiple augmented reality content items, a user can use a single video clip with multiple augmented reality content items to see how different augmented reality content items will modify the stored clip. For example, by selecting different augmented reality content items for the content, multiple augmented reality content items with different pseudo-random motion models can be applied to the same content. Similarly, real-time video capture can be used with the illustrated modifications to show how the video image currently captured by the sensors of client device 102 will modify the captured data. Such data can be simply displayed on the screen without being stored in memory, or content captured by the device's sensors can be recorded and stored in memory with or without modification (or both). In some systems, preview functionality can simultaneously show how different augmented reality content items will look in different windows on the display. For example, this allows viewing multiple windows with different pseudo-random animations on the display at the same time.

[0061] Therefore, various systems using augmented reality content items, or other such transformation systems that use the data to modify content, and the data itself, can involve the detection of objects (e.g., faces, hands, bodies, cats, dogs, surfaces, objects, etc.) in video frames, the tracking of these objects as they leave, enter, and move around within the field of view, and the modification or transformation of these objects while tracking them. In various examples, different methods can be used to implement such transformations. Some examples may involve generating 3D mesh models of one or more objects, and using transformations and animated textures of the models within the video to implement the transformations. In other examples, tracking points on objects can be used to place images or textures (which can be two-dimensional or three-dimensional) at the tracked locations. In further examples, neural network analysis of video frames can be used to place images, models, or textures within content (e.g., images or video frames). Therefore, augmented reality content items refer both to the images, models, and textures used to create transformations within content, and to the additional modeling and analysis information required to achieve such transformations through object detection, tracking, and placement.

[0062] Real-time video processing can be performed using any type of video data (e.g., video streams, video files, etc.) stored in the memory of any type of computerized system. For example, a user can load a video file and store it in the device's memory, or a video stream can be generated using the device's sensors. Furthermore, computer-animated models can be used to process any object, such as a human face and parts of the human body, animals, or inanimate objects (such as chairs, cars, or other objects).

[0063] In some examples, when a specific modification is selected along with the content to be transformed, the element to be transformed is identified by the computing device and then detected and tracked if the element to be transformed exists in a frame of the video. The elements of the object are modified according to the modification request, thereby transforming the frames of the video stream. For different kinds of transformations, the transformation of the video stream frames can be performed using different methods. For example, for a transformation of frames that primarily refers to changing the form of elements of an object, feature points of each element of the object are calculated (e.g., using an Active Shape Model (ASM) or other known methods). Then, a feature point-based mesh is generated for each of at least one element of the object. This mesh is used for subsequent stages of tracking the elements of the object in the video stream. During tracking, the mesh for each mentioned element is aligned with the position of each element. Then, additional points are generated on the mesh. A first set of first points is generated for each element based on the modification request, and a second set of points is generated for each element based on the first set of points and the modification request. The frames of the video stream can then be transformed by modifying the elements of the object based on the first set of points, the second set of points, and the mesh. In this method, the background of the modified object can also be changed or deformed by tracking and modifying the background.

[0064] In some examples, transformations that alter some regions of an object using its elements can be performed by calculating feature points for each element of the object and generating a mesh based on those calculated feature points. Points are generated on the mesh, and various regions are then generated based on these points. The elements of the object are then tracked by aligning the region of each element with the position of at least one of the elements, and the properties of the regions can be modified based on modification requests, thereby transforming frames of the video stream. Depending on the specific modification request, the properties of the mentioned regions can be transformed in different ways. Such modifications can involve: changing the color of the region; removing at least some portions of the region from the frames of the video stream; including one or more new objects in the region based on the modification request; and modifying or deforming the elements of the region or object. In various examples, any combination of such modifications or other similar modifications can be used. For certain models to be animated, some feature points can be selected as control points to determine the entire state space for options used in model animation.

[0065] In some examples of computer animation models that use face detection to transform image data, a specific face detection algorithm (e.g., Viola-Jones) is used to detect faces in the image. The Active Shape Model (ASM) algorithm is then applied to the facial regions of the image to detect facial feature reference points.

[0066] Other methods and algorithms suitable for face detection can be used. For example, in some examples, landmarks are used to locate features that represent distinguishable points present in most of the images considered. For example, for a face landmark, the location of the left pupil could be used. If the initial landmark is not recognizable (e.g., if the person is wearing an eye patch), secondary landmarks can be used. Such a landmark recognition process can be used for any such object. In some examples, a set of landmarks forms a shape. The shape can be represented as a vector using the coordinates of the points in the shape. One shape is aligned with another shape through a similarity transformation (allowing translation, scaling, and rotation) that minimizes the average Euclidean distance between the points of the shapes. The average shape is the average of the aligned training shapes.

[0067] In some examples, a landmark search begins with an average shape aligned with the position and size of a face determined by a global face detector. This search then repeats the following steps: proposing provisional shapes by adjusting the positions of shape points using template matching of the image texture around each point, and then conforming the provisional shapes to a global shape model until convergence occurs. In some systems, individual template matching is unreliable, and the shape model pools the results of weak template matching to form a stronger overall classifier. The entire search is repeated at each level of the image pyramid, from coarse to fine resolution.

[0068] The transformation system can capture image or video streams on a client device (e.g., client device 102) and perform complex image manipulations locally on client device 102 while maintaining an appropriate user experience, computation time, and power consumption. Complex image manipulations can include size and shape changes, emotion shifts (e.g., changing a face from frowning to smiling), state shifts (e.g., aging an object, reducing its apparent age, or changing its gender), style shifts, application of graphical elements, and any other suitable image or video manipulations implemented by a convolutional neural network that has been configured to execute efficiently on client device 102.

[0069] In some examples, a computer animation model for transforming image data can be used by a system in which a user can use a client device 102 with a neural network to capture an image or video stream of the user (e.g., a selfie), the neural network operating as part of a messaging client 104 operating on the client device 102. A transformation system operating within the messaging client 104 determines the presence of a face in the image or video stream and provides a modification icon associated with the computer animation model to transform the image data, or the computer animation model can be presented as associated with the interface described herein. The modification icon includes changes that can be based on modifying the user's face in the image or video stream as part of a modification operation. Once a modification icon is selected, the transformation system initiates a process to transform the user's image to reflect the selected modification icon (e.g., generating a smiley face on the user). Once the image or video stream is captured and the specified modification is selected, the modified image or video stream can be presented in a graphical user interface displayed on the client device 102. The transformation system can implement a complex convolutional neural network on a portion of the image or video stream to generate and apply the selected modification. In other words, once an edit icon is selected, the user can capture an image or video stream and see the changes displayed in real-time or near real-time. Furthermore, while a video stream is being captured, the edits can be persistent, and the selected edit icon continues to be toggled. Machine-trained neural networks can be used to achieve such edits.

[0070] A graphical user interface (GUI) presenting modifications performed by a transformation system can provide users with additional interactive options. Such options can be based on an interface used to initiate content capture and select a specific computer animation model (e.g., initiated from a content creator GUI). In various examples, modifications can be persistent after an initial selection of the modification icon. Users can turn modifications on or off by tapping or otherwise selecting a face modified by the transformation system and save it for later viewing or browsing to other areas of the imaging application. In cases where multiple faces are modified by the transformation system, users can globally turn modifications on or off by tapping or selecting a single face modified and displayed within the GUI. In some examples, individual faces within a set of multiple faces can be modified individually, or such modifications can be toggled individually, by tapping or selecting a single face or a series of faces displayed within the GUI.

[0071] Story table 314 stores data about collections of messages and associated image, video, or audio data, compiled into collections (e.g., stories or galleries). The creation of a specific collection can be initiated by a specific user (e.g., each user whose records are stored in entity table 306). A user can create a "personal story" in the form of a collection of content that has already been created and sent / broadcast by that user. For this purpose, the user interface of messaging client 104 may include user-selectable icons that allow the sending user to add specific content to his or her personal story.

[0072] The collection can also constitute a "live story" as a collection of content from multiple users, created manually, automatically, or using a combination of manual and automatic techniques. For example, a "live story" can constitute a curated stream of user-submitted content from different locations and events. Users whose client devices have location services enabled and are at a common location event at a specific time can be presented with the option to contribute content to a specific live story, for example, through the user interface of messaging client 104. The messaging client 104 can identify live stories to users based on their location. The end result is a "live story" told from a collective perspective.

[0073] Another type of content collection is called a "location story," which allows users whose client devices 102 are located in a specific geographic location (e.g., on a college or university campus) to contribute to a specific collection. In some examples, contributing to a location story may require secondary authentication to verify that the end user belongs to a specific organization or other entity (e.g., a student on a university campus).

[0074] As mentioned above, video table 304 stores video data, which, in one example, is associated with a message whose record is stored in message table 302. Similarly, image table 312 stores image data, which is associated with a message whose message data is stored in entity table 306. Entity table 306 can associate various enhancements from enhancement table 310 with various images and videos stored in image table 312 and video table 304.

[0075] Data communication architecture

[0076] Figure 4This is a schematic diagram illustrating the structure of message 400 according to some examples. Message 400 is generated by message transceiver client 104 for transmission to another message transceiver client 104 or message transceiver server 118. The content of a particular message 400 is used to populate message table 302 stored in database 126, which is accessible by message transceiver server 118. Similarly, the content of message 400 is stored in memory as "in transit" or "in flight" data of client device 102 or application server 114. Message 400 is shown to include the following example components:

[0077] • Message Identifier 402: A unique identifier that identifies message 400.

[0078] • Message text payload 404: The text to be generated by the user via the user interface of the client device 102 and included in message 400.

[0079] • Message image payload 406: Image data captured by the camera component of the client device 102 or retrieved from the memory component of the client device 102 and included in the message 400. The image data of the sent or received message 400 may be stored in the image table 312.

[0080] • Message video payload 408: Video data captured by the camera device component or retrieved from the memory component of the client device 102 and included in the message 400. The video data of the sent or received message 400 can be stored in the video table 304.

[0081] • Message audio payload 410: Audio data captured by the microphone or retrieved from the memory component of the client device 102 and included in message 400.

[0082] • Message enhancement data 412: Enhancement data (e.g., filters, stickers, or other annotations or enhancements) representing enhancements to be applied to the message image payload 406, message video payload 408, or message audio payload 410 of message 400. Enhancement data for sent or received messages 400 can be stored in enhancement table 310.

[0083] • Message duration parameter 414: A parameter value that indicates the amount of time, in seconds, during which the content of the message (e.g., message image payload 406, message video payload 408, message audio payload 410) will be presented to the user or made accessible to the user via the message sending and receiving client 104.

[0084] • Message geolocation parameter 416: Geolocation data (e.g., latitude and longitude coordinates) associated with the message's content payload. Multiple message geolocation parameter 416 values ​​may be included in the payload, each of which is associated with a content item included in the content (e.g., a specific image within the message image payload 406 or a specific video within the message video payload 408).

[0085] • Message Story Identifier 418: An identifier value that identifies one or more content sets (e.g., “Stories” identified in Story Table 314), wherein a specific content item in the message image payload 406 of message 400 is associated with one or more content sets. For example, the identifier value can be used to associate multiple images within the message image payload 406 with multiple content sets, respectively.

[0086] • Message Tag 420: Each message 400 can be labeled with multiple tags, each tag indicating the subject of the content included in the message payload. For example, if a specific image in the message image payload 406 depicts an animal (e.g., a lion), a tag value indicating the relevant animal can be included in the message tag 420. The tag values ​​can be generated manually based on user input or automatically using, for example, image recognition.

[0087] • Message sender identifier 422: An identifier (e.g., message sending system identifier, email address, or device identifier) ​​indicating the user of the client device 102 on which message 400 is generated and from which message 400 is sent.

[0088] • Message receiver identifier 424: An identifier (e.g., message sending and receiving system identifier, email address, or device identifier) ​​indicating the user of the client device 102 to which message 400 is addressed.

[0089] The content (e.g., values) of each component of message 400 can be pointers to locations in tables where content data values ​​are stored. For example, image values ​​in message image payload 406 can be pointers (or addresses) to locations within image table 312. Similarly, values ​​in message video payload 408 can point to data stored in video table 304, values ​​in message enhancement 412 can point to data stored in enhancement table 310, values ​​in message story identifier 418 can point to data stored in story table 314, and values ​​in message sender identifier 422 and message receiver identifier 424 can point to user records stored in entity table 306.

[0090] Time-based access restriction architecture

[0091] Figure 5 This is a schematic diagram illustrating an access restriction process 500, according to which access to content (e.g., a short message 502 and a multimedia payload of associated data) or a collection of content (e.g., a short message group 504) can be time-restricted (e.g., so that it is short).

[0092] A brief message 502 is shown to be associated with a message duration parameter 506, the value of which determines the amount of time the message sending and receiving client 104 will display the brief message 502 to the receiving user. In one example, depending on the amount of time specified by the sending user using the message duration parameter 506, the receiving user can view the brief message 502 for a maximum of 10 seconds.

[0093] The message duration parameter 506 and the message receiver identifier 424 are shown as inputs to a message timer 510, which is responsible for determining the amount of time for which the brief message 502 is shown to a specific receiving user identified by the message receiver identifier 424. Specifically, the brief message 502 is shown to the relevant receiving user only within the time period determined by the value of the message duration parameter 506. The message timer 510 is shown as providing an output to a more generalized brief timer system 202, which is responsible for the overall timing of displaying content (e.g., the brief message 502) to the receiving user.

[0094] Figure 5 The transient message 502 shown is included within a transient message group 504 (e.g., a collection of messages in a personal story or event story). The transient message group 504 has an associated group duration parameter 508, the value of which determines the duration for which the transient message group 504 is presented and accessible to a user of the messaging system 100. For example, the group duration parameter 508 could be the duration of a concert, where the transient message group 504 is a collection of content related to that concert. Alternatively, when setting up and creating the transient message group 504, the user (owner user or curator user) can specify the value of the group duration parameter 508.

[0095] Additionally, each short message 502 within a short message group 504 has an associated group participation parameter 512, the value of which determines the duration for which the short message 502 will be accessible within the context of the short message group 504. Therefore, a particular short message group 504 can "expire" and become inaccessible within its context before the short message group 504 itself expires according to the group duration parameter 508. The group duration parameter 508, the group participation parameter 512, and the message receiver identifier 424 each provide input to a group timer 514, which is operable to first determine whether a particular short message 502 of the short message group 504 will be displayed to a specific receiving user, and if so, determine for how long. Note that the short message group 504 also knows the identity of the specific receiving user due to the message receiver identifier 424.

[0096] Therefore, the group timer 514 operatively controls the associated ephemeral message group 504 and the total lifetime of the individual ephemeral messages 502 included within the ephemeral message group 504. In one example, each ephemeral message 502 within the ephemeral message group 504 remains viewable and accessible for a period of time specified by the group duration parameter 508. In another example, within the context of the ephemeral message group 504, a particular ephemeral message 502 may expire based on the group participation parameter 512. Note that even within the context of the ephemeral message group 504, the message duration parameter 506 can still determine the duration for which a particular ephemeral message 502 is displayed to the receiving user. Therefore, the message duration parameter 506 determines the duration for which a particular ephemeral message 502 is displayed to the receiving user, regardless of whether the receiving user views the ephemeral message 502 within or outside the context of the ephemeral message group 504.

[0097] The short-lived timer system 202 can also operatively remove a specific short-lived message 502 from the short-lived message group 504 based on determining that the specific short-lived message 502 has exceeded its associated group participation parameter 512. For example, when the sending user has established a group participation parameter 512 for 24 hours from the date of publication, the short-lived timer system 202 will remove the relevant short-lived message 502 from the short-lived message group 504 after the specified 24 hours. The short-lived timer system 202 also operates to remove the short-lived message group 504 when the group participation parameter 512 for each short-lived message 502 within the short-lived message group 504 has expired, or when the short-lived message group 504 itself has expired according to the group duration parameter 508.

[0098] In certain use cases, the creator of a specific ephemeral message group 504 can specify an indefinite group duration parameter 508. In this case, the expiration of the group participation parameter 512 for the last remaining ephemeral message 502 within the ephemeral message group 504 will determine when the ephemeral message group 504 itself expires. In this case, adding a new ephemeral message 502 with a new group participation parameter 512 to the ephemeral message group 504 effectively extends the lifetime of the ephemeral message group 504 to a value equal to the group participation parameter 512.

[0099] In response to the short-lived timer system 202 determining that a short-lived message group 504 has expired (e.g., is no longer accessible), the short-lived timer system 202 communicates with the messaging system 100 (and, in particular, the messaging client 104) to cause the markers (e.g., icons) associated with the relevant short-lived message group 504 to no longer be displayed in the user interface of the messaging client 104. Similarly, when the short-lived timer system 202 determines that the message duration parameter 506 for a particular short-lived message 502 has expired, the short-lived timer system 202 causes the messaging client 104 to no longer display the markers (e.g., icons or text identifiers) associated with the short-lived message 502.

[0100] Figure 6 This is an example method 600 for compressing video for transmission, based on some example implementations. Although the described flowcharts may show the operations as a sequential process, many operations may be performed in parallel or simultaneously. Furthermore, the order of operations may be rearranged. A process terminates when its operations are completed. A process may correspond to a method, program, algorithm, etc. The operations of a method may be performed wholly or partially, may be performed in combination with some or all operations from other methods, and may be performed by any number of different systems (e.g., the systems described herein) or any part thereof (e.g., a processor included in any system).

[0101] In operation 602, video compression system 216 accesses a sequence of image frames from the first computing device. The sequence of image frames includes a first image frame and a second image frame. In some examples, the sequence of image frames (e.g., video) is generated by a camera system coupled to the first computing device. The video may be a video call between a first user operating the first computing device and a second user operating a second computing device. The video may depict the face of the first user of the first computing device.

[0102] In operation 604, the video compression system 216 uses a motion estimation machine learning model to detect a first set of keypoints in the first image frame. In some examples, the motion estimation machine learning model comprises two neural networks: a keypoint detector neural network and a dense motion neural network. For example, the keypoint detector neural network and the dense motion neural network could be convolutional neural networks.

[0103] Machine learning is the field of research that enables computers to learn without being explicitly programmed. Machine learning explores the study and construction of algorithms (also referred to herein as tools) that can learn from existing data and make predictions about new data. Such machine learning tools operate by building models based on example training data (e.g., user login attempt features and known challenge response labels) to make data-driven predictions or decisions represented as outputs or evaluations. While the example implementations are about some machine learning tools presented, the principles presented herein can be applied to other machine learning tools. In some example implementations, different machine learning tools can be used. For example, logistic regression (LR), Naive Bayes, random forest (RF), neural network (NN), matrix factorization, and support vector machine (SVM) tools can be used to predict a days to pending amount for a given attribute.

[0104] Machine learning algorithms use features to analyze data to generate evaluations. A feature is a unique, measurable attribute of an observed phenomenon. The concept of a feature is related to the concept of explanatory variables used in statistical techniques such as linear regression. Selecting informative, discriminative, and independent features is important for the efficient operation of MLPs in pattern recognition, classification, and regression. Features can be of different types, such as numeric features, strings, and graphs.

[0105] Machine learning algorithms use training data to discover correlations between identified features that influence outcomes or evaluations. In some example implementations, the training data includes labeled data, which is known data on one or more identified features and one or more outcomes (e.g., number of days to be determined).

[0106] Once the training data is pieced together and processed, machine learning techniques can be used to build machine learning training modules. Machine learning techniques train a model to accurately predict data fed into the model (e.g., what a user said in a given utterance; whether a noun is a person, place, or thing; what the weather will be like tomorrow). During the learning phase, the model is developed and optimized against the training dataset to correctly predict the output for a given input. Typically, the learning phase can be supervised, semi-supervised, or unsupervised; indicating the degree of descent corresponding to providing “correct” outputs for the training inputs. In the supervised learning phase, all outputs are provided to the model, and the model is designed to develop general rules or algorithms that map inputs to outputs. In contrast, in the unsupervised learning phase, no expected outputs are provided for the inputs, allowing the model to develop its own rules to discover relationships within the training dataset. In the semi-supervised learning phase, an incompletely labeled training set is provided, where some outputs are known and some are unknown for the training dataset.

[0107] The model can be run for several epochs (e.g., iterations) against a training dataset, where the training dataset is repeatedly fed into the model to improve its results. For example, in a supervised learning phase, the model is developed to predict the output for a given set of inputs, and the model is evaluated over several epochs to more reliably provide the output specified to correspond to a given input for a maximum number of inputs in the training dataset. In another example, for an unsupervised learning phase, the model is developed to cluster a dataset into n groups, and the model is evaluated over several epochs on how consistently the model places a given input into a given group and how reliably the model produces n desired clusters across each epoch.

[0108] Once a period has been run, the model is evaluated and the values ​​of the model's variables are adjusted to attempt to improve the model iteratively. In various aspects, the evaluation is biased towards false negatives, false positives, or uniformly biased relative to the model's overall accuracy. Depending on the machine learning technique used, these values ​​can be adjusted in several ways. For example, in genetic or evolutionary algorithms, the values ​​of the model most successful in predicting the desired output are used to develop values ​​for the model to use in subsequent periods; this may include random variations / mutations to provide additional data points. Those skilled in the art will be familiar with several other machine learning algorithms that can be applied to this disclosure, including linear regression, random forests, decision tree learning, neural networks, deep neural networks, etc.

[0109] Each model develops a rule or algorithm over several epochs by changing the values ​​of one or more variables that influence the input to more closely map to the desired outcome. However, perfect accuracy and precision may not be achievable due to the potentially variable and, preferably, very large, training datasets. Therefore, the multiple epochs constituting the learning phase can be set to a given number of trials or a fixed time / computational budget, or the multiple epochs constituting the learning phase can terminate before reaching that number / budget, provided the accuracy of a given model is sufficiently high or low, or has reached an accuracy plateau. For example, if the training phase is designed to run for n epochs and produce a model with at least 95% accuracy, and such a model is produced before the nth epoch, the learning phase can end early and the produced model that meets the final target accuracy threshold can be used. Similarly, if a given model is not accurate enough to meet a stochastic chance threshold (e.g., the model is only 55% accurate in determining the true / false output for a given input), the learning phase for that model can terminate early, but other models in the learning phase can continue training. Similarly, when a given model consistently provides similar accuracy or variability in its results across multiple periods—having reached a performance plateau—the learning phase of the given model can terminate before reaching the number of periods / computational budget.

[0110] Once the learning phase is complete, the model is finalized. In some example implementations, the finalized model is evaluated against test criteria. In a first example, a test dataset including known outputs corresponding to its inputs is fed into the final model to determine its accuracy when processing data that has not yet been trained on. In a second example, the false positive rate or false negative rate can be used to evaluate the finalized model. In a third example, delineation between data clusters is used to select the model that produces the clearest boundaries for the clusters of its data.

[0111] The goal of motion estimation machine learning models is to predict the dimensions of frames D∈R from the driving video of dimension H×W. 3×H×W (For example, a sequence of image frames) to the source frame S∈R 3×H×W A dense motion field (e.g., the first image frame). This dense motion field is later used to align the feature maps computed from the source frame S with the object poses in frame D of the driving video. The dense motion field is generated by the function T. S←D :R 2 →R 2 To model this, the function maps each pixel position in D to its corresponding position in S. S←D This is called backward optical flow. The video compression system 216 uses backward optical flow because it can use bilinear sampling to achieve back-warping in a differentiable manner.

[0112] In some examples, the video compression system 216 assumes an abstract reference frame R and independently estimates two transformations: from R to S(T). S←R ) and from R to D(T D←R In the first step, the video compression system 216 approximates the two transformations from a set of sparse trajectories obtained by using keypoints learned in a self-supervised manner. The positions of the keypoints in D and S are predicted by the encoder-decoder network, respectively. The keypoint representation acts as a bottleneck leading to the compact motion representation.

[0113] In some examples, the video compression system 216 uses local affine transformations to model motion around each keypoint. Compared to using only keypoint displacements, local affine transformations allow the video compression system 216 to model a larger family of transformations. The video compression system 216 also uses Taylor expansion to represent the transformation from R to D (T) using a set of keypoint locations and affine transformations. D←R Therefore, the keypoint detector network outputs the keypoint locations and the parameters of each affine transformation.

[0114] The video compression system 216 uses a dense motion neural network to combine local approximations to obtain the final dense motion field. In addition to the dense motion field, the dense motion neural network outputs a masking mask that indicates which parts of the image D can be reconstructed from the distortion of the source image, and which parts should be repaired (e.g., inferred from the context). For example, repair includes preserving damaged, degraded, or missing parts of the image.

[0115] In some examples, the keypoint detector neural network is deployed on a mobile device (e.g., a first computing device). For instance, the video compression system 216 must significantly reduce the size of the keypoint detector neural network and train the smaller-sized network to produce reasonable results. In this case, the video compression system 216 adds an additional distillation loss to the output of the keypoint detector neural network. More specifically, for keypoints {g} predicted by the smaller-sized network... t}, t=1...K and keypoints {G} predicted by the original larger keypoint detector neural network. t}, t=1...K, the video compression system 216 adds additional distillation losses, which can be calculated by the following formula:

[0116]

[0117] In operation 606, the video compression system 216 transmits a first image frame and a first set of keypoints to a second computing device via a network (e.g., the Internet). The transmission of the first image frame and the first set of keypoints can be in real-time or near real-time. In operation 608, the video compression system 216 uses a motion estimation machine learning model to detect a second set of keypoints in a second image frame. In operation 610, the video compression system 216 transmits the second set of keypoints to the second computing device via a network. The transmission of the second set of keypoints can be in real-time or near real-time. In some examples, the motion estimation machine learning model is configured to generate a motion estimation difference between the first set of keypoints and the second set of keypoints.

[0118] In operation 612, the video compression system 216 displays an animated image on a second computing device. This animated image is generated using an image-generating neural network trained to analyze a first set of keypoints and a second set of keypoints to generate an animated first image frame. The animated image can be presented on a graphical user interface of the second computing device. The image-generating neural network renders an image of a source object (e.g., the first image frame) moving as provided in the driving video (e.g., a sequence of image frames). The video compression system 216 uses an image-generating neural network G that distorts the source image based on a obtained dense motion field and repairs occluded portions of the source image. In some examples, the image-generating neural network takes the first image frame, the first set of keypoints, and the second set of keypoints as input and outputs an animated image.

[0119] Fully unsupervised methods provide tools for performing real motion transfer. Therefore, in some implementations, to improve head pose matching and facial expression matching, the video compression system 216 uses a combination of supervised and self-supervised feature points within the frame. More specifically, the video compression system 216 supervises the following key points: two for the center of the eyes and two for the corners of the mouth, leaving the identification of the remaining six key points to the network.

[0120] A sequence of image frames can be transmitted in real time or near real time between a first computing device and a second computing device via a network. In some examples, video can be transmitted via a low-bandwidth connection (e.g., below 25 megabits per second (Mbps)). In another example, some portions of the video can be transmitted via a medium or high-bandwidth connection (e.g., above 25 Mbps), while other portions of the video can be transmitted via a low-bandwidth connection. The video compression system 216 can first measure the network speed before compressing the video. For example, after detecting that the network speed is below a threshold speed (e.g., 25 Mbps), the video compression system 216 can perform the operation of method 600.

[0121] In some examples, the video compression system 216 sends individual source image frames instead of a sequence of image frames as the first image frame. The source image frames may be images stored on a first computing device. The source image frames may be sent to a second computing device and animated based on a first set of keypoints and a second set of keypoints generated from the sequence of image frames.

[0122] In some implementations, the video compression system 216 uses a training video dataset to train a motion estimation machine learning model and an image generation neural network. The video compression system 216 may augment the training video dataset with synthetic image pairs. In some examples, image-to-image transformation methods are used to generate synthetic image pairs. For example, the video compression system 216 trains an image-to-image neural network (e.g., an image2image neural network) that generates images of smiling faces with visible teeth from facial images with neutral expressions where teeth are not visible. This neural network can be used to generate a large dataset of {neutral, smiling} pairs. Each pair can be considered as a synthetic video comprising two frames. Furthermore, since the region with teeth constitutes a small portion of a frame, the reconstruction error is relatively small. However, this region is important for human perception, and small visual artifacts in this region are easily noticed. Therefore, the video compression system 216 increases the weight of the reconstruction loss in this particular region.

[0123] For example, suppose D is the baseline truth frame and This is the generated frame. The tooth mask M can be represented by the following formula:

[0124]

[0125] Where "λ" > 1 represents the weight of the tooth region, and p is the coordinate of a specific pixel. Therefore, the reweighted reconstruction loss of the video compression system 216 is expressed by the following formula:

[0126]

[0127] Where, N k It is the k-th part of the perceptual loss, and M is appropriately reduced.

[0128] In some implementations, the video compression system 216 adds Adaptive Instance Normalization (AdaIN) applied via a mask. The video compression system 216 trains an additional tooth encoder along with the rest of the pipeline. For example, the tooth encoder acquires images of cropped and resized teeth and generates style vectors for them. The video compression system 216 adds AdaIN blocks to each resolution of the generator's decoder and modifies the upsampling blocks (e.g., upsampling is a method of training on an imbalanced dataset that includes randomly copying observations from the minority class to augment their signals to balance the dataset) so that they also predict 1-channel masks instead of just features. This mask specifies the predicted mask γ. (h，w) and β (h，w) The region of features applied to the corresponding AdaIN block. Since the AdaIN block should only affect the mouth region, the mask allows features outside the mouth region to remain unchanged. For example, the predicted mask is calculated using the following formula:

[0129] γ (h,w) =1-m (h,w) +m (h,w) *γ (h,w)

[0130] β (h,w) =m (h,w) *β (h,w)

[0131] Machine architecture

[0132] Figure 7This is a schematic representation of machine 700, within which instructions 710 (e.g., software, programs, applications, applets, or other executable code) can be executed to cause machine 700 to perform any or more of the methods discussed herein. For example, instructions 710 can cause machine 700 to perform any or more of the methods described herein. Instructions 710 transform a general, non-programmable machine 700 into a specific machine 700 programmed to perform the described and illustrated functions in the described manner. Machine 700 can operate as a standalone device or can be coupled (e.g., networked) to other machines. In a networked deployment, machine 700 can operate as a server machine or a client machine in a server-client network environment, or as a peer machine in a peer-to-peer (or distributed) network environment. Machine 700 may include, but is not limited to: server computers, client computers, personal computers (PCs), tablet computers, laptop computers, netbooks, set-top boxes (STBs), personal digital assistants (PDAs), entertainment media systems, cellular phones, smartphones, mobile devices, wearable devices (e.g., smartwatches), smart home devices (e.g., smart appliances), other smart devices, web devices, network routers, network switches, network bridges, or any machine capable of sequentially or otherwise executing instructions 710 specifying actions to be taken by machine 700. Furthermore, although only a single machine 700 is shown, the term "machine" should also be considered as a collection of machines that individually or jointly execute instructions 710 to perform any one or more of the methods discussed herein. For example, machine 700 may include client device 102 or any of several server devices forming part of message transceiver server system 108. In some examples, machine 700 may also include both client and server systems, wherein certain operations of a particular method or algorithm are performed on the server side and certain operations of a particular method or algorithm are performed on the client side.

[0133] Machine 700 may include a processor 704, a memory 706, and an input / output (I / O) unit 702 that can be configured to communicate with each other via a bus 740. In the example, processor 704 (e.g., a central processing unit (CPU), a reduced instruction set computing (RISC) processor, a complex instruction set computing (CISC) processor, a graphics processing unit (GPU), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a radio frequency integrated circuit (RFIC), another processor, or any suitable combination thereof) may include, for example, processors 708 and 712 that execute instruction 710. The term "processor" is intended to include multi-core processors, which may include two or more independent processors (sometimes referred to as "cores") capable of executing instructions simultaneously. Although Figure 7 Multiple processors 704 are shown, but machine 700 may include a single processor with a single core, a single processor with multiple cores (e.g., a multi-core processor), multiple processors with a single core, multiple processors with multiple cores, or any combination thereof.

[0134] Memory 706 includes main memory 714, static memory 716, and memory cells 718 that are accessible to processor 704 via bus 740. Main memory 706, static memory 716, and memory cells 718 store instructions 710 that implement any one or more of the methods or functions described herein. Instructions 710 may also reside wholly or partially in main memory 714, in static memory 716, in machine-readable medium 720 within memory cells 718, within at least one processor in processor 704 (e.g., within the processor's cache memory), or in any suitable combination thereof, during execution by machine 700.

[0135] I / O component 702 may include a wide variety of components for receiving input, providing output, generating output, sending information, exchanging information, capturing measurement results, etc. The specific I / O component 702 included in a particular machine will depend on the type of machine. For example, portable machines such as mobile phones may include touch input devices or other such input mechanisms, while headless server machines are unlikely to include such touch input devices. It will be understood that I / O component 702 may include... Figure 7 Many other components are not shown. In various examples, I / O component 702 may include user output component 726 and user input component 728. User output component 726 may include visual components (e.g., displays such as plasma display panels (PDPs), light-emitting diode (LED) displays, liquid crystal displays (LCDs), projectors, or cathode ray tube (CRT) displays), acoustic components (e.g., speakers), haptic components (e.g., vibration motors, resistance mechanisms), other signal generators, etc. User input component 728 may include alphanumeric input components (e.g., keyboards, touchscreens configured to receive alphanumeric input, photoelectric keyboards, or other alphanumeric input components), point-based input components (e.g., mice, touchpads, trackballs, joysticks, motion sensors, or other pointing instruments), haptic input components (e.g., physical buttons, touchscreens that provide position and force for touch or touch gestures, or other haptic input components), audio input components (e.g., microphones), etc.

[0136] In other examples, I / O component 702 may include biometric component 730, motion component 732, environmental component 734, or positioning component 736, as well as various other components. For example, biometric component 730 includes components for detecting expressions (e.g., hand gestures, facial expressions, voice expressions, body posture, or eye tracking), measuring biosignals (e.g., blood pressure, heart rate, body temperature, sweating, or brain waves), and identifying a person (e.g., voice recognition, retinal recognition, facial recognition, fingerprint recognition, or EEG-based recognition). Motion component 732 includes accelerometer components (e.g., accelerometers), gravity sensor components, and rotation sensor components (e.g., gyroscopes).

[0137] The environmental component 734 includes, for example: one or more camera devices (with still image / photograph and video capabilities), an illumination sensor component (e.g., a photometer), a temperature sensor component (e.g., one or more thermometers that detect ambient temperature), a humidity sensor component, a pressure sensor component (e.g., a barometer), an acoustic sensor component (e.g., one or more microphones that detect background noise), a proximity sensor component (e.g., an infrared sensor that detects nearby objects), a gas sensor (e.g., a gas detection sensor that detects the concentration of hazardous gases for safety purposes or measures pollutants in the atmosphere), or other components that can provide indications, measurements, or signals corresponding to the surrounding physical environment.

[0138] Regarding the camera device, client device 102 may have a camera device system including, for example, a front-facing camera on the front surface of client device 102 and a rear-facing camera on the rear surface of client device 102. The front-facing camera may be used, for example, to capture still images and videos (e.g., "selfies") of the user of client device 102, which can then be enhanced using the aforementioned enhancement data (e.g., filters). For example, the rear-facing camera may be used to capture still images and videos in a more conventional camera device mode, which are similarly enhanced using the enhancement data. In addition to the front and rear-facing cameras, client device 102 may also include a 360° camera for capturing 360° photos and videos.

[0139] Furthermore, the camera system of the client device 102 may include dual rear cameras (e.g., a main camera and a depth-sensing camera), or even include triple, quadruple, or quintuple rear camera configurations on the front and rear sides of the client device 102. For example, these multi-camera systems may include wide-angle cameras, ultra-wide-angle cameras, telephoto cameras, macro cameras, and depth sensors.

[0140] The positioning component 736 includes a position sensor component (e.g., a GPS receiver component), an altitude sensor component (e.g., an altimeter or barometer that detects air pressure to obtain altitude), an orientation sensor component (e.g., a magnetometer), etc.

[0141] A wide variety of technologies can be used to implement communication. I / O component 702 also includes a communication component 738, operable to couple machine 700 to network 722 or device 724 via a suitable coupling or connection. For example, communication component 738 may include a network interface component or another suitable device to interface with network 722. In other examples, communication component 738 may include wired communication components, wireless communication components, cellular communication components, near field communication (NFC) components, etc. Components (e.g.) (low power consumption) Components and other communication components that provide communication in other forms. Device 724 can be any peripheral device from other machines or various peripheral devices (e.g., a peripheral device coupled via USB).

[0142] Furthermore, the communication component 738 can detect identifiers or include components operable to detect identifiers. For example, the communication component 738 may include a radio frequency identification (RFID) tag reader component, an NFC smart tag detection component, an optical reader component (e.g., an optical sensor for detecting one-dimensional barcodes such as Universal Product Code (UPC) barcodes, multi-dimensional barcodes such as Quick Response (QR) codes, Aztec codes, Data Matrix, Dataglyph, MaxiCode, PDF417, UltraCode, UCC RSS-2D barcodes, and other optical codes) or an acoustic detection component (e.g., a microphone for identifying audio signals from the tag). Additionally, various information can be derived via the communication component 738, such as location via Internet Protocol (IP) geolocation, etc. The location of signal triangulation, the location of NFC beacon signals that can be detected to indicate a specific location, etc.

[0143] Various memories (e.g., main memory 714, static memory 716, and the memory of processor 704) and storage units 718 may store one or more sets of instructions and data structures (e.g., software) implemented or used by any one or more of the methods or functions described herein. These instructions (e.g., instruction 710) cause various operations to implement the disclosed examples when executed by processor 704.

[0144] Instructions 710 can be sent or received over network 722 via a network interface device (e.g., a network interface component included in communication component 738), using a transmission medium and employing any of several known transmission protocols (e.g., Hypertext Transfer Protocol (HTTP)). Similarly, instructions 710 can be sent or received via a transmission medium through a coupling (e.g., peer-to-peer coupling) to device 724.

[0145] Software Architecture

[0146] Figure 8 This is a block diagram 800 illustrating a software architecture 804 that can be installed on any or more devices described herein. The software architecture 804 is supported by hardware such as a machine 802 including a processor 820, memory 826, and I / O components 838. In this example, the software architecture 804 can be conceptualized as a stack of layers, where each layer provides specific functionality. The software architecture 804 includes layers such as an operating system 812, libraries 810, frameworks 808, and applications 806. Operationally, application 806 activates API calls 850 via the software stack and receives messages 852 in response to API calls 850.

[0147] Operating system 812 manages hardware resources and provides public services. Operating system 812 includes, for example, a kernel 814, services 816, and drivers 822. The kernel 814 acts as an abstraction layer between the hardware layer and other software layers. For example, the kernel 814 provides memory management, processor management (e.g., scheduling), component management, network and security settings, and other functions. Services 816 can provide other public services to other software layers. Drivers 822 are responsible for controlling or interfacing with the underlying hardware. For example, drivers 822 may include display drivers, camera drivers, etc. or Low-power drivers, flash drives, serial communication drivers (e.g., USB drives), Drivers, audio drivers, power management drivers, etc.

[0148] Library 810 provides common low-level infrastructure used by application 806. Library 810 may include system libraries 818 (e.g., the C standard library), which provide functions such as memory allocation, string manipulation, and mathematical functions. Additionally, library 810 may include API libraries 824, such as media libraries (e.g., libraries supporting the rendering and manipulation of various media formats, such as Moving Picture Experts Group-4 (MPEG4), Advanced Video Coding (H.264 or AVC), Moving Picture Experts Group Layer-3 (MP3), Advanced Audio Coding (AAC), Adaptive Multi-Rate (AMR) audio codecs, Joint Picture Experts Group (JPEG or JPG) or Portable Web Graphics (PNG)), graphics libraries (e.g., the OpenGL framework for rendering graphic content on a display in two-dimensional (2D) and three-dimensional (3D) formats), database libraries (e.g., SQLite, providing various relational database functions), web libraries (e.g., WebKit, providing web browsing functionality), etc. Library 810 may also include a wide variety of other libraries 828 to provide many other APIs to application 806.

[0149] Framework 808 provides common high-level infrastructure for use by application 806. For example, framework 808 provides various graphical user interface (GUI) functions, advanced resource management, and advanced location services. Framework 808 can provide a wide range of other APIs that can be used by application 806, some of which may be specific to a particular operating system or platform.

[0150] In the example, application 806 may include a home application 836, a contacts application 830, a browser application 832, a book reader application 834, a location application 842, a media application 844, a messaging application 846, a game application 848, and a wide variety of other applications such as third-party application 840. Application 806 is a program that performs the functions defined in the program. One or more applications 806 can be created using various programming languages, such as object-oriented programming languages ​​(e.g., Objective-C, Java, or C++) or procedural programming languages ​​(e.g., C or assembly language). In a particular example, third-party application 840 (e.g., an entity other than the vendor of a particular platform using Android) TM or iOS TM Applications developed using a Software Development Kit (SDK) can be used on platforms such as iOS. TM ANDROID TM , Mobile software running on the phone's mobile operating system or other mobile operating systems. In this example, a third-party application 840 can activate API calls 850 provided by the operating system 812 to facilitate the functionality described herein.

[0151] Glossary

[0152] "Carrier signal" refers to any intangible medium capable of storing, encoding, or carrying instructions to be executed by a machine, and includes digital or analog communication signals or other intangible media to facilitate the communication of such instructions. Instructions can be sent or received over a network using a transmission medium via a network interface device.

[0153] "Client device" refers to any machine that interfaces with a communication network to obtain resources from one or more server systems or other client devices. Client devices can be, but are not limited to, mobile phones, desktop computers, laptop computers, portable digital assistants (PDAs), smartphones, tablet computers, ultrabooks, netbooks, laptop computers, multiprocessor systems, microprocessor-based or programmable consumer electronics, game consoles, set-top boxes, or any other communication device that a user can use to access the network.

[0154] "Communication network" refers to one or more parts of a network, which can be an ad hoc network, intranet, extranet, virtual private network (VPN), local area network (LAN), wireless LAN (WLAN), wide area network (WAN), wireless WAN (WWAN), metropolitan area network (MAN), the Internet, a part of the Internet, a part of the Public Switched Telephone Network (PSTN), a POTS (Plain Old-Style Telephone Service) network, a cellular telephone network, a wireless network, etc. A network, other types of networks, or a combination of two or more such networks. For example, a network or part of a network may include a wireless network or a cellular network, and the coupling may be a Code Division Multiple Access (CDMA) connection, a Global System for Mobile Communications (GSM) connection, or other types of cellular or wireless coupling. In this example, the coupling can implement any data transmission technology of various types, such as Single Carrier Radio Transmission (1xRTT), Evolved Data Optimization (EVDO), General Packet Radio Service (GPRS), Enhanced Data Rate Evolution of GSM (EDGE), the 3rd Generation Partnership Project (3GPP) including 3G, fourth-generation wireless (4G) networks, Universal Mobile Telecommunications System (UMTS), High-Speed ​​Packet Access (HSPA), Global Microwave Access Interoperability (WiMAX), Long Term Evolution (LTE) standards, other data transmission technologies defined by various standards setting organizations, other long-distance protocols, or other data transmission technologies.

[0155] A “component” refers to a device, physical entity, or logic having boundaries defined by functional or subroutine calls, branch points, APIs, or other technologies that provide partitioning or modularity for a particular processing or control function. A component can be combined with other components via its interface to perform machine processing. A component can be an encapsulated functional hardware unit designed for use with other components and can be part of a program that typically performs a specific function within a related function. A component can constitute a software component (e.g., code implemented on a machine-readable medium) or a hardware component. A “hardware component” is a tangible unit capable of performing certain operations and can be configured or arranged in some physical manner. In various examples, one or more computer systems (e.g., standalone computer systems, client computer systems, or server computer systems) or one or more hardware components (e.g., processors or processor groups) of a computer system can be configured by software (e.g., an application or application portion) to perform certain operations described herein. Hardware components can also be implemented mechanically, electronically, or in any suitable combination thereof. For example, a hardware component can include a dedicated circuit system or logic permanently configured to perform certain operations. Hardware components can be dedicated processors, such as field-programmable gate arrays (FPGAs) or application-specific integrated circuits (ASICs). Hardware components can also include programmable logic or circuit systems temporarily configured by software to perform certain operations. For example, a hardware component may include software executed by a general-purpose processor or other programmable processor. Once configured by such software, the hardware component becomes a specific machine (or a specific part of a machine) uniquely tailored to perform the configured function, and no longer a general-purpose processor. It will be understood that the implementation of hardware components may be determined, for cost and time considerations, whether mechanically implemented in dedicated and permanently configured circuitry or in temporarily configured (e.g., software-configured) circuitry. Accordingly, the phrase “hardware component” (or “hardware-implemented component”) should be understood to include tangible entities, i.e., entities physically constructed, permanently configured (e.g., hardwired), or temporarily configured (e.g., programmed) to operate or perform certain operations described herein. Consider the example of hardware components being temporarily configured (e.g., programmed), without requiring each hardware component in the hardware component to be configured or instantiated at any given time. For example, in cases where the hardware components include a general-purpose processor that can be configured by software to become a dedicated processor, this general-purpose processor can be configured as different dedicated processors (e.g., including different hardware components) at different times. The software accordingly configures one or more specific processors to constitute a specific hardware component, for example, at one moment and as different hardware components at different times. Hardware components can provide information to and receive information from other hardware components. Therefore, the described hardware components can be considered communicatively coupled.In the presence of multiple hardware components, communication can be achieved through signal transmission between or among two or more hardware components (e.g., via appropriate circuitry and buses). In examples where multiple hardware components are configured or instantiated at different times, such communication between hardware components can be achieved, for example, by storing information in a memory structure accessed by the multiple hardware components and retrieving information from that memory structure. For example, a hardware component can perform an operation and store the output of that operation in a memory device communicatively coupled to it. Other hardware components can then access the memory device at a subsequent time to retrieve the stored output and process it. Hardware components can also initiate communication with input or output devices and can operate on resources (e.g., information collection). The various operations of the example methods described herein can be performed at least in part by one or more processors that are temporarily configured (e.g., by software) or permanently configured to perform the relevant operations. Whether temporarily or permanently configured, such processors can constitute processor-implemented components that operate to perform one or more operations or functions described herein. As used herein, "processor-implemented component" refers to a hardware component implemented using one or more processors. Similarly, the methods described herein can be implemented at least in part by processors, where a particular processor or one or more processors are examples of hardware. For example, at least some operations of the methods can be performed by one or more processors 602 or processor-implemented components. Furthermore, the one or more processors can also be configured to support the execution of related operations in a “cloud computing” environment or to operate as “Software as a Service” (SaaS). For example, at least some operations can be performed by a group of computers (as an example of a machine including processors), where these operations are accessible via a network (e.g., the Internet) and via one or more appropriate interfaces (e.g., APIs). The execution of some operations can be distributed among processors, not residing within a single machine, but deployed across multiple machines. In some examples, the processor or processor-implemented component can be located in a single geographic location (e.g., in a home environment, office environment, or server cluster). In other examples, the processor or processor-implemented component can be distributed across several geographic locations.

[0156] "Computer-readable storage medium" refers to both machine-readable storage media and transmission media. Therefore, these terms encompass both storage devices / media and carrier / modulated data signals. The terms "machine-readable medium," "computer-readable medium," and "device-readable medium" refer to the same thing and may be used interchangeably in this disclosure.

[0157] A "brief message" is a message that is accessible for a limited period of time. Brief messages can be text, images, videos, etc. The access time for a brief message can be set by the message sender. Alternatively, the access time can be a default setting or a setting specified by the recipient. Regardless of the setting method, the message is temporary.

[0158] "Machine storage medium" refers to one or more storage devices and media (e.g., centralized or distributed databases, and associated caches and servers) that store executable instructions, routines, and data. Therefore, this term should be considered to include, but is not limited to, solid-state memory and optical and magnetic media, including memory internal or external to the processor. Specific examples of machine storage media, computer storage media, and / or device storage media include: non-volatile memory, including, for example, semiconductor memory devices such as erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), FPGAs, and flash memory devices; disks, such as internal hard disks and removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks. The terms "machine storage medium," "device storage medium," and "computer storage medium" refer to the same thing and are used interchangeably in this disclosure. The terms "machine storage medium," "computer storage medium," and "device storage medium" expressly exclude carrier waves, modulated data signals, and other such media, at least some of which are covered by the term "signal medium."

[0159] "Non-transitory computer-readable storage medium" refers to a tangible medium capable of storing, encoding, or carrying instructions that can be executed by a machine.

[0160] "Signal medium" means any intangible medium capable of storing, encoding, or carrying instructions executable by a machine, and includes digital or analog communication signals or other intangible media that facilitate the communication of software or data. The term "signal medium" should be considered to include any form of modulated data signal, carrier wave, etc. The term "modulated data signal" means a signal whose characteristics are set or altered in a manner that encodes information in the signal. The terms "transmission medium" and "signal medium" refer to the same thing and may be used interchangeably in this disclosure.

Claims

1. A method for image animation, comprising: A sequence of image frames accessed from a first computing device, the sequence of image frames including a first image frame and a second image frame; The first set of key points in the first image frame is detected using a motion estimation machine learning model. The first image frame and the first set of key points are sent to the second computing device via the network; The motion estimation machine learning model is used to detect a second set of key points in the second image frame; The second set of key points is sent to the second computing device via the network; Based on the first set of key points and the second set of key points, a dense motion field from the sequence of image frames to the first image frame is predicted, and a masking mask for the sequence of image frames is generated. as well as An animated image is displayed on the second computing device. The animated image is generated using an image generation neural network that is trained to distort the first image frame based on the dense motion field and the occlusion mask to generate the animated image.

2. The method according to claim 1, wherein, The motion estimation machine learning model includes a keypoint detector neural network and a dense motion neural network.

3. The method according to claim 2, wherein, The keypoint detector neural network is trained to identify keypoints in the center of the eye pair and keypoints at the corners of the mouth.

4. The method according to claim 2, wherein, The keypoint detector neural network and the dense motion neural network are configured to generate motion estimation differences between the first set of keypoints and the second set of keypoints.

5. The method according to claim 4, wherein, The animated image includes an animated first image frame, wherein the image generation neural network is configured to generate the animated first image frame by applying motion estimation differences between a first set of key points and a second set of key points.

6. The method according to claim 1, wherein, The network in question is a low-bandwidth network.

7. The method according to claim 1, wherein, The first image frame, the first set of key points, and the second set of key points are sent in real time.

8. The method according to claim 1, wherein, The motion estimation machine learning model operates on the first computing device.

9. The method according to claim 1, wherein, The image generation neural network operates on the second computing device, and wherein the image generation neural network is trained to analyze the first image frame, the first set of key points, and the second set of key points.

10. A computing system for image animation, the computing system comprising: One or more processors; as well as A memory that stores instructions, which, when executed by the one or more processors, cause the one or more processors to perform operations, the operations including: A sequence of image frames accessed from a first computing device, the sequence of image frames including a first image frame and a second image frame; The first set of key points in the first image frame is detected using a motion estimation machine learning model. The first image frame and the first set of key points are sent to the second computing device via the network; The motion estimation machine learning model is used to detect a second set of key points in the second image frame; The second set of key points is sent to the second computing device via the network; Based on the first set of key points and the second set of key points, a dense motion field from the sequence of image frames to the first image frame is predicted, and a masking mask for the sequence of image frames is generated; and An animated image is displayed on the second computing device. The animated image is generated using an image generation neural network that is trained to distort the first image frame based on the dense motion field and the occlusion mask to generate the animated image.

11. The computing system according to claim 10, wherein, The motion estimation machine learning model includes a keypoint detector neural network and a dense motion neural network.

12. The computing system according to claim 11, wherein, The keypoint detector neural network is trained to identify keypoints in the center of the eye pair and keypoints at the corners of the mouth.

13. The computing system according to claim 11, wherein, The keypoint detector neural network and the dense motion neural network are configured to generate motion estimation differences between the first set of keypoints and the second set of keypoints.

14. The computing system according to claim 13, wherein, The animated image includes an animated first image frame, wherein the image generation neural network is configured to generate the animated first image frame by applying motion estimation differences between a first set of key points and a second set of key points.

15. The computing system according to claim 10, wherein, The network in question is a low-bandwidth network.

16. The computing system according to claim 10, wherein, The first image frame, the first set of key points, and the second set of key points are sent in real time.

17. The computing system according to claim 10, wherein, The motion estimation machine learning model operates on the first computing device.

18. The computing system according to claim 10, wherein, The image generation neural network operates on the second computing device.

19. A non-transitory computer-readable storage medium storing instructions that, when executed by one or more processors of a machine, cause the non-transitory computer-readable storage medium to perform operations, the operations including: A sequence of image frames accessed from a first computing device, the sequence of image frames including a first image frame and a second image frame; The first set of key points in the first image frame is detected using a motion estimation machine learning model. The first image frame and the first set of key points are sent to the second computing device via the network; The motion estimation machine learning model is used to detect a second set of key points in the second image frame; The second set of key points is sent to the second computing device via the network; Based on the first set of key points and the second set of key points, a dense motion field from the sequence of image frames to the first image frame is predicted, and a masking mask for the sequence of image frames is generated. as well as An animated image is displayed on the second computing device. The animated image is generated using an image generation neural network that is trained to distort the first image frame based on the dense motion field and the occlusion mask to generate the animated image.

20. The non-transitory computer-readable storage medium according to claim 19, wherein, The network in question is a low-bandwidth network.

Images