Cross-modal shape and color manipulation

Abstract

Systems, computer-readable media, and methods herein describe an editing system in which a three-dimensional (3D) object may be edited by editing a 2D sketch or a 2D RGB view of the 3D object. The editing system uses a multi-modal (MM) variational automatic decoder (VAD) (MM-VAD) trained with a shared potential space, enabling editing of a 3D object by editing a 2D sketch of the 3D object. The system determines potential code corresponding to the edited or drawn 2D sketch. The potential code is then used as an input using MM-VAD, thereby generating a 3D object using the potential code. The potential space is divided into a shape potential space and a color potential space. The MM-VAD is trained by using a variational automatic encoder (VAE) and a true value.

Description

[0001] Priority declaration

[0002] This application claims the benefit of priority to U.S. Provisional Application Serial No. 63 / 365,568 filed on May 31, 2022 and U.S. Patent Application Serial No. 17 / 814,391 filed on July 22, 2022, each of which is incorporated herein by reference in its entirety. Technical Field

[0003] Examples herein generally relate to editing the shape and color of a three-dimensional (3D) object by editing a two-dimensional (2D) sketch of the 3D object. Specifically, but not limited to, methods and systems describe using a multimodal (MM) variational autodecoder (VAD) (MM-VAD) utilizing a shared latent space to enable editing of a 3D object by editing a 2D sketch of the 3D object. Background Art

[0004] It is often difficult for people to draw and edit 3D objects. Editing programs that enable users to directly edit 3D objects or color 3D objects are provided, but these programs usually do not enable users to edit 3D objects and color 3D objects without difficulty. BRIEF DESCRIPTION OF THE DRAWINGS

[0005] In the accompanying drawings (which are not necessarily drawn to scale), similar reference numerals may describe similar components in different views. To easily identify the discussion of any particular element or action, the most significant digit or digits in a reference numeral refer to the figure number in which the element is first introduced. Some non-limiting examples are shown in the accompanying drawings, in which:

[0006] Figure 1 is a diagrammatic representation of a networking environment in which the present disclosure may be deployed, according to some examples.

[0007] Figure 2 is a diagrammatic representation of a messaging system having both client-side and server-side functionality according to some examples.

[0008] Figure 3 is a diagrammatic representation of data structures maintained in a database according to some examples.

[0009] Figure 4 is a graphical representation of messages according to some examples.

[0010] Figure 5 is a flow chart of an access restriction process according to some examples.

[0011] Figure 6 A system for cross-modal shape and color manipulation according to some examples is shown.

[0012] Figure 7 A system for cross-modal shape and color manipulation according to some examples is shown.

[0013] Figure 8 A system for training a MM generator according to some examples is shown.

[0014] Fig. 9 A system for cross-modal shape and color manipulation according to some examples is shown.

[0015] Fig.10 Examples of cross-modal shape and color manipulation according to some examples are shown.

[0016] Fig.11 Examples of cross-modal shape and color manipulation according to some examples are shown.

[0017] Fig.12 Examples of cross-modal shape and color manipulation according to some examples are shown.

[0018] Fig.13 Examples of cross-modal shape and color manipulation according to some examples are shown.

[0019] Fig.14 Examples of cross-modal shape and color manipulation according to some examples are shown.

[0020] Fig.15 Examples of cross-modal shape and color manipulation according to some examples are shown.

[0021] Fig.16 Examples of cross-modal shape and color manipulation according to some examples are shown.

[0022] Fig.17 Examples of the effects of occlusion on shape generation according to some examples are shown.

[0023] Fig.18 Shown is a graph comparing an encoder-decoder with MM-VAD according to some examples.

[0024] Fig.19 Examples of cross-modal shape and color manipulation according to some examples are shown.

[0025] Fig. 20 Methods for cross-modal shape and color manipulation according to some examples are shown.

[0026] Fig.21 is a diagrammatic representation of a machine in the form of a computer system according to some examples within which a set of instructions may be executed for causing the machine to perform any one or more of the methodologies discussed herein.

[0027] Fig. 22 is a block diagram illustrating a software architecture in which examples may be implemented.

[0028] Fig.23 is a diagrammatic representation of a processing environment according to some examples. DETAILED DESCRIPTION

[0029] The following description includes the system, method, technology, instruction sequence and computing machine program product of the illustrative example of implementation of the present disclosure. In the following description, for the purpose of illustration, many specific details are set forth in order to provide an understanding of the various examples of the subject of the present invention. However, it is obvious to those skilled in the art that the example of the subject of the present invention can be put into practice without these specific details. Usually, it is not necessary to show in detail known instruction examples, protocols, structures and technologies.

[0030] The examples herein describe computer-readable media, methods, and systems for editing and coloring a 3D shape 608 by editing and coloring a 2D sketch 716 and a 2D red, green, blue (RGB) view 714. The editing module 902 provides a user with an editing program for drawing a 2D sketch 1902. The editing module 902 uses the MM generator 701 to determine a first potential code that can be used to generate a 2D sketch 1902 based on the MM generator 701 using the first potential code as input. Then, the editing module 902 generates a 3D shape 1 1904 and a 2D RGB view 1906 corresponding to the 2D sketch 1902 using the first potential code.

[0031] The user may then edit 3D shape 1 1904 by, for example, adding color to 2D RGB view 1906. Edit module 902 uses MM generator 701 to determine a second latent code that may be used to generate 2D RGB view 1906 with added color 1910 using MM generator 701 with the second latent code as input. Edit module 902 then generates new 3D shape 2 1908 using the second latent code.

[0032] The MM generator 701 enables the editing module 902 to determine changes to the 3D shape 1 1904 based on changes made to the 2D sketch 1902 or the 2D RGB view 1906 and enables the editing module 902 to determine the 3D shape 1 1904 corresponding to the 2D sketch 1902 drawn by the user.

[0033] The challenge is how to construct and train the MM generator 701 so that the 3D shape 1 1904 can be edited with the 2D sketch 1902 and the 2D RGB view 1906. The example is solved by using a separate variational autodecoder (VAD) for each of the modalities of 3D shape 1 1904, 2D sketch 1902 and 2D RGB view 1906, respectively. 607, 712 and 710 to handle the challenge, where a shared latent space is used for all VADs. In addition, a VAD is trained using a paired variational autoencoder (VAE) in conjunction with the ground truth of matching triplets 814 that all correspond to the same object, 3D shape 816, 2D RGB view 818, and 2D sketch 820.

[0034] Networked computing environment

[0035] Figure 1 1 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 a client device 102, each of the multiple instances hosting a number of applications including a messaging client 104 and other applications 106. Each messaging client 104 is communicatively coupled to other instances of the messaging client 104 (e.g., hosted on respective other client devices 102), a messaging server system 108, and a third-party server 110 via a network 112 (e.g., the Internet). The messaging client 104 may also communicate with the locally hosted application 106 using an application program interface (API).

[0036] The messaging clients 104 are able to communicate and exchange data with other messaging clients 104 and messaging server systems 108 via the network 112. The data exchanged between the messaging clients 104 and between the messaging clients 104 and messaging server systems 108 include functions (e.g., commands for activating functions) and payload data (e.g., text, audio, video, or other multimedia data).

[0037] The messaging server system 108 provides server-side functionality to specific messaging clients 104 via the network 112. Although certain functions of the messaging system 100 are described herein as being performed by the messaging client 104 or by the messaging server system 108, the location of certain functions within the messaging client 104 or within the messaging server system 108 may be a design choice. For example, it may be technically preferable to initially deploy certain technologies and functions within the messaging server system 108, but later migrate the technologies and functions to the messaging client 104 where the client device 102 has sufficient processing power.

[0038] The messaging server system 108 supports various services and operations provided to the messaging clients 104. Such operations include sending data to the messaging clients 104, receiving data from the messaging clients 104, and processing data generated by the messaging clients 104. As examples, the data may include message content, client device information, geographic location information, media enhancements and overlays, message content persistence conditions, social network information, and live event information. The data exchange within the messaging system 100 is activated and controlled by functions available via the user interface (UI) of the messaging client 104.

[0039] Turning now specifically to the messaging server system 108, an application program interface (API) server 116 is coupled to the application server 114 and provides a programming interface to the application server 114. The application server 114 is communicatively coupled to a database server 120, which facilitates access to a database 126 that stores data associated with messages processed by the application server 114. Similarly, a web server 128 is coupled to the application server 114 and provides a web-based interface to the application server 114. To this end, the web server 128 processes incoming network requests via the Hypertext Transfer Protocol (HTTP) and several other related protocols.

[0040] The application program interface (API) server 116 receives and sends message data (e.g., commands and message payloads) between the client device 102 and the application server 114. Specifically, the application program interface (API) server 116 provides a set of interfaces (e.g., routines and protocols) that can be called or queried by the messaging client 104 to activate the functions of the application server 114. An application program interface (API) server 116 exposes various functions supported by application server 114, including: account registration; login functionality; sending messages from a particular messaging client 104 to another messaging client 104 via application server 114; sending media files (e.g., images or videos) from a messaging client 104 to messaging server 118 and for possible access by another messaging client 104; setting up a collection of media data (e.g., a story); retrieving a friend list of a user of client device 102; retrieving such a collection; retrieving messages and content; adding and removing entities (e.g., friends) from 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).

[0041] The application server 114 hosts several server applications and subsystems, including, for example, a messaging server 118, an image processing server 122, and a social network server 124. The messaging server 118 implements several message processing technologies and functions, particularly those related to aggregation and other processing of content (e.g., text and multimedia content) included in messages received from multiple instances of the 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., called stories or galleries). These collections are then made available to the messaging client 104. In view of the hardware requirements for other processor and memory intensive processing of data, such processing can also be performed on the server side by the messaging server 118.

[0042] The application server 114 also includes an image processing server 122 that is dedicated to performing various image processing operations, typically on images or videos within the payload of messages sent from or received at the messaging server 118 .

[0043] The social network server 124 supports various social networking functions and services and makes these functions and services available to the messaging server 118. To this end, the social network server 124 maintains and accesses the entity graph 308 (e.g., Figure 3Examples of functions and services supported by social network server 124 include identifying other users with whom a particular user of messaging system 100 has relationships or that the particular user is "following," and also identifying interests and other entities of a particular user.

[0044] Returning to the messaging client 104, features and functionality of external resources (e.g., applications 106 or applet) are available to the user via the interface of the messaging client 104. In this context, "external" refers to the fact that the application 106 or applet is external to the messaging client 104. External resources are typically provided by a third party, but may also be provided by the creator or provider of the messaging client 104. The messaging client 104 receives a user selection of an option for launching or accessing features of such external resources. The external resource may be an application 106 installed on the client device 102 (e.g., a "native application"), or a small-scale version of an application (e.g., a "mini-program") hosted on the client device 102 or located at a remote end of the client device 102 (e.g., on a third-party server 110). The small-scale version of the application includes a subset of the features and functionality of the application (e.g., the full-scale, native version of the application) and is implemented using a markup language document. In one example, a small-scale version of an application (e.g., a "mini program") 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 programs can include scripting languages ​​(e.g., .*js files or .json files) and style sheets (e.g., .*ss files).

[0045] In response to receiving a user selection of an option for launching or accessing a feature of an external resource, the messaging client 104 determines whether the selected external resource is a web-based external resource or a locally installed application 106. In some cases, an application 106 locally installed on the client device 102 can be launched independently of and separately from the messaging client 104, for example, by selecting an icon corresponding to the application 106 on a home screen of the client device 102. A small-scale version of such an application can be launched or accessed via the messaging client 104, and in some examples, no portion of the small-scale application can be accessed (or only a limited portion can be accessed) outside of the messaging client 104. The small-scale application can be launched by the messaging client 104 receiving a markup language document associated with the small-scale application from, for example, a third-party server 110 and processing such a document.

[0046] 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 the 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 (for example) a third-party server 110 to obtain a markup language document corresponding to the selected external resource. The messaging client 104 then processes the obtained markup language document to present the web-based external resource within the user interface of the messaging client 104.

[0047] The messaging client 104 may notify the user of the client device 102 or other users (e.g., "friends") associated with such a user of activities occurring in one or more external resources. For example, the messaging client 104 may provide a notification related to the current or recent use of an external resource by one or more members of a user group to a participant in a conversation (e.g., a chat session) in the messaging client 104. One or more users may be invited to join an active external resource or to start an external resource that was recently used but is currently inactive (in the friend group). The external resource may provide the participants in the conversation who each use the corresponding messaging client 104 with the ability to share items, conditions, states, or locations in the external resource with one or more members of the user group entering the chat session. The shared item may be an interactive chat card, and members of the chat may interact using the interactive chat card, such as to start the corresponding external resource, view specific information in the external resource, or bring members of the chat to a specific location or state in the external resource. In a given external resource, a response message may be sent to the user on the messaging client 104. The external resource may selectively include different media items in the response based on the current context of the external resource.

[0048] The messaging client 104 may present a list of available external resources (e.g., applications 106 or applets) to the user to launch or access a given external resource. The list may be presented in a context-sensitive menu. For example, icons representing different ones of the applications 106 (or applets) may vary based on how the user launches the menu (e.g., from a conversational interface or from a non-conversational interface).

[0049] System Architecture

[0050] Figure 21 is a block diagram showing additional details about the 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 that are 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 transient 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 cross-modal shape and color manipulation system 216.

[0051] The transient timer system 202 is responsible for implementing temporary or time-limited access to content by the messaging client 104 and the messaging server 118. The transient timer system 202 includes several timers that selectively enable access (e.g., for presentation and display) to messages and associated content via the messaging client 104 based on duration and display parameters associated with a message or a collection of messages (e.g., a story). Additional details regarding the operation of the transient timer system 202 are provided below.

[0052] The collection management system 204 is responsible for managing collections or collections of media (e.g., collections of text, image 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 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 the concert. The collection management system 204 can also be responsible for publishing an icon that provides notification of the existence of a particular collection to the user interface of the messaging client 104.

[0053] In addition, the collection management system 204 also includes a curation interface 206, which allows a collection manager to manage and curate a specific content collection. For example, the curation interface 206 enables an event organizer to curate a collection of content related to a specific event (e.g., to delete inappropriate content or redundant messages). In addition, the collection management system 204 uses machine vision (or image recognition technology) and content rules to automatically curate content collections. In some examples, compensation can be paid to users for including user-generated content in a collection. In such a case, the collection management system 204 operates to automatically pay such users for using their content.

[0054] The enhancement system 208 provides various functions that enable users to enhance (e.g., annotate or otherwise modify or edit) media content associated with a message. For example, the enhancement system 208 provides functions related to generating and publishing media overlays for messages processed by the messaging system 100. The enhancement system 208 is operable to provide media overlays or enhancements (e.g., image filters) to the messaging client 104 based on the geographic location of the client device 102. In another example, the enhancement system 208 is operable to provide media overlays to the messaging client 104 based on other information such as social network information of the user of the client device 102. The media overlay can include audio and visual content and 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., photos, digital objects) at the client device 102. For example, the media overlay can include text or images that can be overlaid on photos taken by the client device 102. In another example, the media overlay includes a location identification overlay (e.g., Venice Beach), the name of a live event, or a business name overlay (e.g., Beach Cafe). In another example, the enhancement system 208 uses the geographic location of the client device 102 to identify a media overlay that includes the name of the business at the geographic location of the client device 102. The media overlay may include other tags associated with the business. The media overlay may be stored in the database 126 and accessed through the database server 120.

[0055] In some examples, the enhancement system 208 provides a user-based publishing platform that enables a user to select a geographic location on a map and upload content associated with the selected geographic location. The user can also specify an environment in which a particular media overlay should be provided to other users. The enhancement system 208 generates a media overlay that includes the uploaded content and associates the uploaded content with the selected geographic location.

[0056] In other examples, the enhancement system 208 provides a merchant-based publishing platform that enables merchants to select specific media coverage associated with a geographic location via a bidding process. For example, the enhancement system 208 associates the media coverage of the highest bidding merchant with the corresponding geographic location for a predefined amount of time.

[0057] The mapping system 210 provides various geo-location functions and supports the presentation of map-based media content and messages by the messaging client 104. For example, the mapping system 210 enables the display of user icons or avatars (e.g., stored in the profile data 316) on a 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 such friends within the context of the map. For example, a message posted by a user to the messaging system 100 from a particular geographic location can be displayed to a particular user's "friends" on the mapping interface of the messaging client 104 within the context of that particular location on the map. The user can also share his or her location and status information with other users of the messaging system 100 (e.g., using an appropriate status avatar) via the messaging client 104, where the location and status information is similarly displayed to the selected user within the context of the mapping interface of the messaging client 104.

[0058] The gaming system 212 provides various gaming functions within the context of the messaging client 104. The messaging client 104 provides a gaming interface that provides a list of available games that can be launched 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 a particular user to invite other users to participate in playing a particular game by sending an invitation to such other users from the messaging client 104. The messaging client 104 also supports both voice messaging and text messaging within the context of playing games (e.g., chatting), provides leaderboards for games, and also supports providing in-game rewards (e.g., game coins and items).

[0059] The external resource system 214 provides the messaging client 104 with an interface for communicating with a remote server (e.g., a third-party server 110) to launch or access an external resource, i.e., an application or applet. Each third-party server 110 hosts, for example, an application based on a markup language (e.g., HTML5) or a small-scale version of an application (e.g., a game, utility, payment, or ride-sharing application). The messaging client 104 can launch a web-based resource (e.g., an application) by accessing an HTML5 file from a third-party server 110 associated with a web-based resource. In some examples, the application hosted by the third-party server 110 is programmed in JavaScript using a software development kit (SDK) provided by the messaging server 118. The SDK includes an application programming interface (API) with functions that can be called or activated by a web-based application. In some examples, the messaging server 118 includes a JavaScript library that provides access to certain user data of the messaging client 104 to a given external resource. HTML5 is used as an example technology for programming games, but applications and resources programmed based on other technologies can be used.

[0060] In order to integrate the functionality of the SDK into a web-based resource, the SDK is downloaded from the messaging server 118 by the third-party server 110 or received by the third-party server 110 in other ways. 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 the messaging client 104 into the web-based resource.

[0061] The SDK stored on the messaging server 118 effectively provides a bridge between external resources such as applications 106 or applets and the messaging client 104. This provides users with a seamless experience of communicating with other users on the messaging client 104 while retaining the look and feel of the messaging client 104. In order to bridge the communication between the external resources and the messaging client 104, in some examples, the SDK facilitates communication between the third-party server 110 and the messaging client 104. In some examples, the WebViewJavaScriptBridge running on the client device 102 establishes two one-way communication channels between the external resources and the messaging client 104. Messages are sent asynchronously via these communication channels between the external resources and the messaging client 104. Each SDK function activation is sent as a message and a callback. Each SDK function is implemented by constructing a unique callback identifier and sending a message with the callback identifier.

[0062] 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 an HTML5 file corresponding to a web-based external resource to the messaging server 118. The messaging server 118 can add a visual representation (e.g., box art or other graphics) of the web-based external resource in the messaging client 104. Once the user selects the visual representation or instructs the messaging client 104 to access the features of the web-based external resource through the GUI of the messaging client 104, the messaging client 104 obtains the HTML5 file and instantiates the resources required to access the features of the web-based external resource.

[0063] The messaging client 104 presents a graphical user interface (e.g., a login page or title screen) for the external resource. During, before, or after presenting the login page or title screen, the messaging client 104 determines whether the launched external resource has been previously authorized to access the user data of the messaging client 104. In response to determining that the launched external resource has been previously authorized to access the user data of the messaging client 104, the messaging client 104 presents another graphical user interface of the external resource, which includes the functions and features of the external resource. In response to determining that the launched external resource has not been previously authorized to access the user data of the messaging client 104, after a threshold time period (e.g., 3 seconds) of displaying the login page or title screen of the external resource, the messaging client 104 slides a menu for authorizing the external resource to access the user data (e.g., animating the menu to emerge from the bottom of the screen to the middle or other portion of the screen). The menu identifies the type of user data that the external resource will be authorized to use. In response to receiving the user selection of the accept option, the messaging client 104 adds the external resource to the list of authorized external resources and enables the external resource to access the user data from the messaging client 104. In some examples, the external resource is authorized to access the user data by the messaging client 104 according to the OAuth 2 framework.

[0064] The messaging client 104 controls the type of user data shared with the external resource based on the type of external resource that is authorized. For example, an external resource including a full-scale application (e.g., application 106) is provided with access to a first type of user data (e.g., only a two-dimensional avatar of a user with or without different avatar characteristics). As another example, an external resource including a small-scale version of an application (e.g., a web-based version of the application) is provided with access to a second type of user data (e.g., payment information, a two-dimensional avatar of a user, a three-dimensional avatar of a user, and an avatar with various avatar characteristics). Avatar characteristics include different ways to customize the look and feel of an avatar (e.g., different poses, facial features, clothing, etc.).

[0065] The cross-modal shape and color manipulation system 216 provides functions and routines for performing cross-modal shape and color manipulation. The cross-modal shape and color manipulation system 216 provides functions and routines for performing cross-modal shape and color manipulation. Figures 6 to 20 The cross-modal shape and color manipulation system 216 is configured to train the MM encoder 824 and the MM generator 701. The cross-modal shape and color manipulation system 216 provides functionality for a user interface shown on the display 906. According to some examples, the display 906 is a display of the client device 102. According to some examples, the cross-modal shape and color manipulation system 216 operates in conjunction with the client device 102, wherein functionality is divided between the cross-modal shape and color manipulation system 216 and the client device 102.

[0066] Data Architecture

[0067] Figure 3 is a diagram illustrating a data structure 300 that may be stored in a database 126 of a messaging server system 108 according to some examples. Although the contents of the database 126 are illustrated as including several tables, it should be understood that data may be stored in other types of data structures (e.g., as an object-oriented database).

[0068] Database 126 includes message data stored in message table 302. For any particular message, the message data includes at least message sender data, message recipient (or receiver) data, and payload. Figure 4 Additional details regarding information that may be included in a message and included within the message data stored in message table 302 are described.

[0069] The entity table 306 stores entity data and is linked (e.g., by reference) to the entity graph 308 and profile data 316. The entities whose records are maintained within the entity table 302 may include individuals, corporate entities, organizations, objects, places, events, etc. Regardless of the entity type, any entity about which the messaging server system 108 stores data may be an identified entity. Each entity is provided with a unique identifier as well as an entity type identifier (not shown).

[0070] The entity graph 308 stores information about relationships and associations between entities. Such relationships may be social, professional (e.g., working in a common company or organization), interest-based, or activity-based, by way of example only.

[0071] Profile data 316 stores multiple types of profile data about a particular entity. Based on the privacy settings specified by the particular entity, profile data 316 can be selectively used and presented to other users of the messaging system 100. In the case where the entity is a person, profile data 316 includes, for example, a user name, phone number, address, settings (e.g., notification and privacy settings), and an avatar representation (or a collection of such avatar representations) selected by the user. A particular user can then selectively include one or more of these avatar representations within the content of messages transmitted via the messaging system 100 and on a map interface displayed to other users by the messaging client 104. The collection of avatar representations can include a "status avatar" that presents a graphical representation of a status or activity that a user may choose to convey at a particular time.

[0072] Where the entity is a group, profile data 316 for the group may similarly include one or more avatar representations associated with the group, in addition to the group name, members, and various settings for the relevant group (eg, notifications).

[0073] The database 126 also stores enhancement data, such as overlays or filters, in an enhancement table 310. The enhancement data is associated with and applied to videos (data for videos is stored in the video table 304) and images (data for images is stored in the image table 312).

[0074] In one example, a filter is an overlay displayed over an image or video during presentation to a recipient user. The filter can be of various types, including a user-selected filter from a set of filters presented to a sending user by the messaging client 104 when the sending user is composing a message. Other types of filters include geolocation filters (also referred to as geofilters), which can be presented to a sending user based on geographic location. For example, a geolocation filter specific to a nearby or specific location can be presented by the messaging client 104 within a user interface based on geographic location information determined by a global positioning system (GPS) unit of the client device 102.

[0075] Another type of filter is a data filter that can be selectively presented to the sending user by the messaging client 104 based on other input or information collected during the message creation process by the client device 102. Examples of data filters include the current temperature at a particular location, the current speed the sending user is traveling, the battery life of the client device 102, or the current time.

[0076] Other augmented data that may be stored in the image table 312 include augmented reality content items (eg, corresponding to an applied lens or augmented reality experience). The augmented reality content items may be real-time special effects and sounds that may be added to an image or video.

[0077] As described above, the augmented data includes augmented reality content items, overlays, image transformations, AR images, and similar items involving modifications that can be applied to image data (e.g., videos or images). This includes real-time modifications that modify the image when it is captured using the device sensor (e.g., one or more cameras) of the client device 102 and then display the image with the modifications on the screen of the client device 102. This also includes modifications to stored content (e.g., video clips that can be modified in the gallery). For example, in a client device 102 that can access 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 clips. For example, by selecting different augmented reality content items for the content, multiple augmented reality content items that apply different pseudo-random movement models can be applied to the same content. Similarly, real-time video capture can be used with the modifications shown to show how the video image currently captured by the sensor of the client device 102 will modify the captured data. Such data may be displayed only on the screen and not stored in memory, or the content captured by the device sensors may be recorded and stored in memory with or without modification (or both). In some systems, a preview feature may simultaneously show how different augmented reality content items will look in different windows in the display. This may, for example, enable viewing of multiple windows with different pseudo-random animations on the display at the same time.

[0078] Thus, data and various systems using augmented reality content items or other such transformation systems using the data to modify content may involve: detection of objects (e.g., faces, hands, bodies, cats, dogs, surfaces, objects, etc.); tracking such objects in video frames as they leave, enter, and move around the field of view; and modifying or transforming such objects as they are tracked. In various examples, different methods for implementing such transformations may be used. Some examples may involve: generating a three-dimensional mesh model of one or more objects, and using transformations and animated textures of the models within a video to implement the transformations. In other examples, tracking of points on an object may be used to place an image or texture (which may be two-dimensional or three-dimensional) at the tracked location. In yet another example, neural network analysis of video frames may be used to place an image, model, or texture in content (e.g., a frame of an image or video). Thus, augmented reality content items involve both: images, models, and textures used to create transformations in the content, and additional modeling and analysis information required to implement such transformations using object detection, tracking, and placement.

[0079] 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 save it in the memory of the device, or a sensor of the device can be used to generate a video stream. In addition, computer animation models can be used to process any object, such as human faces and body parts, animals, or inanimate objects (e.g., chairs, cars, or other objects).

[0080] In some examples, when a specific modification is selected together with the content to be transformed, the elements to be transformed are identified by a computing device, and then if the elements are present in the frame of the video, they are detected and tracked. The elements of the object are modified according to the modification request, thereby transforming the frame of the video stream. For different types of transformations, the transformation of the frame of the video stream can be performed by different methods. For example, for a frame transformation that mainly refers to a variation of the elements of the object, characteristic points for each element of the object are calculated (for example, using an active shape model (ASM) or other known methods). Then, a grid based on characteristic points is generated for each element of at least one element of the object. The grid is used for the subsequent stages of tracking the elements of the object in the video stream. During the tracking process, the grid mentioned for each element is aligned with the position of each element. Then, additional points are generated on the grid. A first group of first points is generated for each element based on the modification request, and a group of second points is generated for each element based on the group of first points and the modification request. Then, the frame of the video stream can be transformed by modifying the elements of the object based on the group of first points, the group of second points and the grid. In such an approach, the background of the modified object may also be changed or distorted by tracking and modifying the background.

[0081] In some examples, a transformation that changes some areas of an object using elements of an object can be performed by calculating characteristic points of each element of the object and generating a grid based on the calculated characteristic points. Points are generated on the grid, and then various areas are generated based on the points. The elements of the object are then tracked by aligning the area for each element with the position for each element of at least one element, and the properties of the area can be modified based on the modification request, thereby transforming the frame of the video stream. Depending on the specific modification request, the properties of the mentioned area can be transformed in different ways. Such modifications may involve changing the color of the area; removing at least some parts of the area from the frame of the video stream; including one or more new objects into the area based on the modification request; and modifying or distorting the elements of the area or object. In various examples, any combination of such modifications or other similar modifications may be used. For certain models to be animated, some characteristic points may be selected as control points for the entire state space to be used to determine options for model animation.

[0082] In some examples of computer animation models that use face detection to transform image data, faces are detected on an image using a specific face detection algorithm (e.g., Viola-Jones). An active shape model (ASM) algorithm is then applied to the face region of the image to detect facial feature reference points.

[0083] Other methods and algorithms suitable for face detection can be used. For example, in some examples, landmarks are used to locate features, and landmarks represent distinguishable points that are present in most of the images considered. For example, for facial landmarks, the location of the left pupil can be used. If the initial landmarks are not identifiable (for example, if the person is wearing an eye patch), secondary landmarks can be used. Such a landmark identification 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. A similarity transformation (which allows translation, scaling, and rotation) that minimizes the average Euclidean distance between the shape points is used to align one shape with another. The mean shape (meanshape) is the average value of the aligned training shapes.

[0084] In some examples, the landmark search begins with an average shape that aligns with the location and size of the face determined by a global face detector. Such a search then repeats the steps of proposing tentative shapes by template matching the image texture around each point to adjust the location of the shape points, and then conforming the tentative shapes to the global shape model until convergence occurs. In some systems, template matching alone is unreliable, and the shape model pools the results of weak template matches to form a stronger overall classifier. The entire search is repeated at each level in the image pyramid from coarse to fine resolution.

[0085] The transformation system can capture an image or video stream on a client device (e.g., client device 102) and perform complex image manipulations locally on the client device 102 while maintaining an appropriate user experience, computation time, and power consumption. Complex image manipulations can include size and shape changes, emotion transitions (e.g., changing a face from a frown to a smile), state transitions (e.g., aging a subject, reducing apparent age, changing gender), style transitions, application of graphical elements, and any other suitable image or video manipulations enabled by a convolutional neural network that has been configured to execute efficiently on the client device 102.

[0086] In some examples, a computer animation model for transforming image data can be used by a system in which a user can capture an image or video stream of the user (e.g., a selfie) using a client device 102 having a neural network, where the neural network operates 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 within the image or video stream and provides a modification icon associated with the computer animation model for transforming the data image, or the computer animation model can exist in association with an interface described herein. The modification icon includes the following changes, which can be the basis for modifying the face of the user within the image or video stream as part of the modification operation. Once the modification icon is selected, the transformation system initiates a process of transforming the image of the user to reflect the selected modification icon (e.g., generating a smiling face for 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. That is, a user can capture an image or video stream, and once a modification icon is selected, the modified result can be presented to the user in real time or near real time. In addition, the modification can be persistent while the video stream is being captured and the selected modification icon remains toggled. A machine learning neural network can be used to implement such modification.

[0087] The graphical user interface presenting the modifications performed by the transformation system can provide additional interactive options to the user. Such options can be based on the interface for initiating the selection of a particular computer animation model and content capture (e.g., initiated from a content creator user interface). In various examples, the modifications can be persistent after the modification icon is initially selected. The user can switch the modification on or off by tapping or otherwise selecting the face being modified by the transformation system, and store it for later viewing or browsing to other areas of the imaging application. In the case where multiple faces are modified by the transformation system, the user can globally switch the modification on or off by tapping or selecting a single face modified and displayed within the graphical user interface. In some examples, each face in a group of multiple faces can be modified individually, or such modifications can be switched individually by tapping or selecting a single face or a series of individual faces displayed within the graphical user interface.

[0088] The story table 314 stores data related to a collection of messages and associated images, videos, or audio data that are compiled into a collection (e.g., a story or gallery). The creation of a particular collection can be initiated by a particular user (e.g., each user whose record is maintained in the entity table 306). A user can create a "personal story" in the form of a collection of content that has been created and sent / broadcasted by the user. To this end, the user interface of the messaging client 104 may include a user-selectable icon to enable the sending user to add specific content to his or her personal story.

[0089] A collection may also constitute a "live story," which is a collection of content from multiple users created manually, automatically, or using a combination of manual and automatic techniques. For example, a "live story" may constitute a curated stream of user-submitted content from various locations and events. Users whose client devices have location services enabled and who are at a common location event at a particular time may be presented with the option of contributing content to a particular live story, for example, via the user interface of the messaging client 104. Live stories may be identified to the user by the messaging client 104 based on his or her location. The end result is a "live story" told from a community perspective.

[0090] Another type of content collection is called a "location story" that enables users whose client devices 102 are located in a particular geographic location (e.g., on a college or university campus) to contribute to a particular collection. In some embodiments, contributions to location stories may require secondary authentication to verify that the end user belongs to a particular organization or other entity (e.g., is a student on a university campus).

[0091] As mentioned above, the video table 304 stores video data, which in one example is associated with a message whose record is maintained within the message table 302. Similarly, the image table 312 stores image data associated with a message whose message data is stored in the entity table 306. The entity table 306 can associate various enhancements from the enhancement table 310 with the various images and videos stored in the image table 312 and the video table 304.

[0092] Data communication architecture

[0093] Figure 4is a schematic diagram illustrating the structure of a message 400 according to some examples, the message 400 being generated by a messaging client 104 for transmission to another messaging client 104 or a messaging server 118. The content of a particular message 400 is used to populate a message table 302 stored in a database 126 accessible by a messaging server 118. Similarly, the content of the message 400 is stored in memory as an "in-transit" or "in-flight" data repository of a client device 102 or application server 114. The message 400 is illustrated as including the following example components.

[0094] Message identifier 402 : a unique identifier that identifies the message 400 .

[0095] Message text payload 404 : Text to be generated by a user via the user interface of the client device 102 and included in the message 400 .

[0096] Message image payload 406 : Image data captured by a camera component of the client device 102 or retrieved from a memory component of the client device 102 and included in the message 400 . Image data for a sent or received message 400 may be stored in the image table 312 .

[0097] Message video payload 408 : Video data captured by the camera component or retrieved from the memory component of the client device 102 and included in the message 400 . The video data for a message 400 that has been sent or received may be stored in the video table 304 .

[0098] Message audio payload 410 : audio data captured by a microphone or retrieved from a memory component of the client device 102 and included in the message 400 .

[0099] Message enhancement data 412 : Enhancement data (eg, 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 the message 400 . The enhancement data for a sent or received message 400 may be stored in the enhancement table 310 .

[0100] Message duration parameter 414: A parameter value indicating the amount of time in seconds that the content of a message (eg, message image payload 406, message video payload 408, message audio payload 410) will be presented to or made accessible to a user via messaging client 104.

[0101] Message geolocation parameters 416: Geolocation data (e.g., latitude and longitude coordinates) associated with the content payload of the message. 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 a message image payload 406, or a specific video within a message video payload 408).

[0102] Message story identifier 418: An identifier value that identifies one or more content collections (e.g., a "story" identified in story table 314) associated with a particular content item in message image payload 406 of message 400. For example, an identifier value may be used to associate multiple images within message image payload 406 with each of multiple content collections.

[0103] Message tags 420: Each message 400 may be tagged with a plurality of tags, each of which indicates the subject of the content included in the message payload. For example, where a particular image included in the message image payload 406 depicts an animal (e.g., a lion), a tag value indicating the relevant animal may be included within the message tags 420. The tag values ​​may be manually generated based on user input, or may be automatically generated using, for example, image recognition.

[0104] • Message sender identifier 422: An identifier (eg, a messaging system identifier, an email address, or a device identifier) ​​that indicates the user of the client device 102 on which the message 400 was generated and from which the message 400 was sent.

[0105] • Message recipient identifier 424: An identifier (eg, a messaging system identifier, an email address, or a device identifier) ​​that indicates the user of the client device 102 to which the message 400 is addressed.

[0106] The content (e.g., value) of each component of message 400 may be a pointer to a location in a table in which the content data value is stored. For example, the image value in message image payload 406 may be a pointer to a location in image table 312 (or the address of a location in image table 312). Similarly, the value in message video payload 408 may point to data stored in video table 304, the value stored in message enhancement 412 may point to data stored in enhancement table 310, the value stored in message story identifier 418 may point to data stored in story table 314, and the values ​​stored in message sender identifier 422 and message recipient identifier 424 may point to user records stored in entity table 306.

[0107] Time-based access restriction architecture

[0108] Figure 5is a schematic diagram illustrating an access restriction process 500 according to which access to content (e.g., ephemeral message 502 and associated multimedia data payload) or a collection of content (e.g., ephemeral message group 504) can be time-restricted (e.g., made ephemeral).

[0109] The ephemeral message 502 is shown to be associated with a message duration parameter 506, the value of which determines the amount of time that the messaging client 104 will display the ephemeral message 502 to the receiving user of the ephemeral message 502. In one example, the receiving user can view the ephemeral message 502 for up to 10 seconds, depending on the amount of time specified by the sending user using the message duration parameter 506.

[0110] The message duration parameter 506 and the message recipient identifier 424 are shown as inputs to a message timer 510, which is responsible for determining the amount of time that the transient message 502 is shown to a particular receiving user identified by the message recipient identifier 424. In particular, the transient message 502 is shown to the associated receiving user only for a period of time determined by the value of the message duration parameter 506. The message timer 510 is shown as providing an output to a more general transient timer system 202, which is responsible for the overall timing of displaying content (e.g., the transient message 502) to the receiving user.

[0111] exist Figure 5 1. Ephemeral message 502 is shown as being included within an ephemeral message group 504 (e.g., a collection of messages in a personal story or event story). Ephemeral message group 504 has an associated group duration parameter 508, the value of which determines the duration for which ephemeral message group 504 is presented and accessible to users of messaging system 100. For example, group duration parameter 508 may be the duration of a concert, wherein ephemeral message group 504 is a collection of content about the concert. Alternatively, a user (an owning user or a curator user) may specify the value of group duration parameter 508 when performing setup and creation of ephemeral message group 504.

[0112] In addition, each ephemeral message 502 within the ephemeral message group 504 has an associated group participation parameter 512, the value of which determines the duration for which the ephemeral message 502 is accessible within the context of the ephemeral message group 504. Thus, a particular ephemeral message group 504 may "expire" and become inaccessible within the context of the ephemeral message group 504 before the ephemeral 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 recipient identifier 424 each provide inputs to a group timer 514, which is operable to first determine whether a particular ephemeral message 502 of the ephemeral message group 504 is to be displayed to a particular receiving user, and if so, how long to display it. Note that the identity of the particular receiving user is also known to the ephemeral message group 504 due to the message recipient identifier 424.

[0113] Thus, the group timer 514 operatively controls the overall lifespan of the associated ephemeral message group 504 and the individual ephemeral messages 502 included in 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 may still determine the duration for which a particular ephemeral message 502 is displayed to a receiving user. Thus, the message duration parameter 506 determines the duration for which a particular ephemeral message 502 is displayed to a receiving user, regardless of whether the receiving user is viewing the ephemeral message 502 within or outside the context of the ephemeral message group 504.

[0114] The transient timer system 202 may also be operable to remove a particular transient message 502 from a transient message group 504 based on a determination that an associated group participation parameter 512 has been exceeded. For example, where a sending user has established a group participation parameter 512 of 24 hours from posting, the transient timer system 202 will remove the associated transient message 502 from the transient message group 504 after the designated 24 hours. The transient timer system 202 also operates to remove a transient message group 504 when the group participation parameter 512 for each transient message 502 within the transient message group 504 has expired, or when the transient message group 504 itself has expired according to the group duration parameter 508.

[0115] In some use cases, the creator of a particular ephemeral message group 504 may 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, a new ephemeral message 502 with a new group participation parameter 512 added to the ephemeral message group 504 effectively extends the life of the ephemeral message group 504 to a value equal to the group participation parameter 512.

[0116] In response to the transient timer system 202 determining that the transient message group 504 has expired (e.g., is no longer accessible), the transient timer system 202 communicates with the messaging system 100 (and, for example, in particular, the messaging client 104) to cause the indicia (e.g., icon) associated with the relevant transient message group 504 to no longer be displayed within the user interface of the messaging client 104. Similarly, when the transient timer system 202 determines that the message duration parameter 506 for a particular transient message 502 has expired, the transient timer system 202 causes the messaging client 104 to no longer display the indicia (e.g., icon or text identification) associated with the transient message 502.

[0117] Cross-modal shape and color manipulation

[0118] Figure 6 A system 600 for cross-modal shape and color manipulation according to some examples is shown. The system 600 obtains a value z from a latent space (Z) 602 and uses z as an input to a multimodal (MM) generator 604 to generate 606, 610, 612 a three-dimensional (3D) shape 608, a 2D RGB view 616, and a two-dimensional (2D) sketch 614, respectively. The 3D shape 608, the 2D RGB view 616, and the 2D sketch 614 represent the same object, in this case, an airplane. The system 600 trains the MM generator 604 with triples or pairs of true values ​​of the 3D shape 608, the 2D RGB view 616, and the 2D sketch 614, where the latent space 602 is shared between independent MM variational autodecoders (VADs) including the MM generator 604. In some examples, the 2D RGB view 616 is referred to as a 2D color view.

[0119] Figure 7 A system 700 for cross-modal shape and color manipulation according to some examples is shown. MM generator 701 is Figure 6 An example of the MM generator 604. 730, 728, G R 710 and G S712 is a variational auto-decoder (VAD). VAD shares the latent space Z 602. The latent space Z 602 is composed of the latent space Z for color (C) C 704 and the latent space Z for shape (S) S 704. Each potential code z 703∈Z 602 is given by equation (1): where z S 702 is with z S 702∈Z S The shape of the latent code is , and where z C 704 is with z C 704∈Z C The color potential code of Represents the bitwise concatenation operator. P 706 is The system 700 generates the 3D coordinates of or three real coordinates based on equation (2): The output is 730.

[0120] Formula (2): Those skilled in the art will recognize that other representations besides SDF may be used such as voxels, grids, point clouds, etc. The output of 730. System 700 generates based on equation (3) Output of 728.

[0121] Formula (3): Color. Terminology 722 Instructions The kth layer of 730 is fed to 728 as input. The system 700 combines the SDF 720 with the 3D color 718 to generate a 3D shape 608. 607 generates or renders a 3D shape 608. The system 700 indicates the training module 810 or the editing module 902. The system 700 generates the 3D shape 608 based on equation (4).

[0122] Formula (4): According to some examples, 730 and 728 are multilayer perceptrons (MLPs) or feedforward fully connected neural networks with eight and three layers, respectively. According to some examples, and is a fully connected neural network with a fixed number of layers. Different architectures can be used 730, 728, and Such as the use of different numbers of layers or convolutional layers, upsampling layers, downsampling layers, cross-connected layers, etc. The system 700 determines a 2D sketch 716 based on equation (5). The system 700 determines a 2D RGB view 714 based on equation (6). According to some examples, the 2D RGB view 714 is referred to as a 2D color view.

[0123] Formula (5): Sketch 716, where shape code z S 702 and view (v) 708 are 712 is the input, and the 2D sketch 716 is the output. Formula (6): RGB view 714, where the color code z C 704 and v 708 are 710 is the input, and the 2D RGB view 714 is the output. The system 700 is trained with different views 708 associated with the true value or training data. 712 and 610 , such that the view 708 value is associated with the orientation of the 2D RGB view 616 or the orientation of the 2D sketch 614 .

[0124] Figure 8 A system 800 for training the MM generator 701 according to some examples is shown. According to some examples, the MM encoder 824 is similar to the MM generator 701, where the MM encoder 824 is a variational autoencoder (VAE) with four components as encoders instead of decoders. The MM encoder 824 generates a z-shaped image from the 3D shape 816, the 2D RGB view 818, and the 2D sketch 820. S 702 and z C 704 is composed of z 703. In some examples, v 708 is generated by MM encoder 824.

[0125] The training module 810 uses one of the 3D shape 816, 2D RGB view 818, or 2D sketch 820 of the matched triplet 814 as input to an MM encoder 824 with parameters or weights 822. The output of the MM encoder 824 is z 703 and optionally v 708.

[0126] z 703 and optionally v 708 are input to the MM generator 701 to generate a 3D shape 804, a 2D RGB view 806 or a 2D sketch 808 as output 802. The generated 3D shape 804, 2D RGB view 806 or 2D sketch 808 is then compared with the matching triples 814 used as input to the MM encoder 824.

[0127] For example, if the training module 810 uses the 3D shape 816 as input to the MM encoder 824 to generate z 703, and then uses z 703 as input to the MM generator 701 to generate the 3D shape 804, the 3D shape 804 is compared to the 3D shape 816 to determine the loss, which is then back-propagated through the MM generator 701, z 703 and / or the MM encoder 824 to adjust the weights 812, the values ​​of z 703 and / or the weights 822, respectively, where typically only one set of weights 812, 822 is adjusted at a time, while the other weights 812, 822 are frozen or remain unchanged.

[0128] In some examples, the matched triplet 814 is referred to as a true value. In some examples, the matched triplet 814 is constructed from an available database of objects. The 3D shape 816 is represented by an SDF, which is a representation of sampled 3D points of an object with a signed distance from the object surface. 3D points greater than a threshold from the object surface are assigned a background color, such as white, and 3D points not greater than the threshold are assigned the color of the nearest surface point. For the 2D sketch 820 and the 2D RGB view 818, the contour is used to generate the 2D sketch 820 and the 2D RGB view 818 from the object of the 3D shape 816. In some examples, the color of the 2D RGB view 818 is randomly assigned by the fragments of the object. Weights 822, weights 812, z 703 and v 708 are referred to as model parameters.

[0129] The training module 810 trains the model parameters based on maximizing the evidence lower bound (ELBO) given by equation (7). where φ is the parameter of the MM encoder 824, θ is the parameter of the MM generator 701, x is the observed variable, KL is the Kullback-Leibler divergence, z is the latent variable, p is the distribution, and E is the expectation. φ (z|x) approximates the posterior distribution p(z|x).

[0130] Item-KL(q φ (z|x)||p(z)) reduces the relative entropy between the posterior distribution and the underlying prior distribution p(z). is the reconstruction loss determined by the training module 810 based on comparing one of the matching triplets 814 with one of the outputs 802 , where the goal is to make the output 802 as close as possible to the input of one of the matching triplets 814 .

[0131] The training module 810 determines the term q based on equation (8): φ (z|x i ). Formula (8): in is a product with average value μi and standard deviation∑ i Gaussian distribution, and where x i is one of the matching triplets 814. The training module 810 uses a reparameterization technique to back-propagate the gradient of equation (7) through z 703 during training. The reparameterization technique adds an ∈ term to the φ term, which represents the statistical part of z 703, and where ∈ remains unchanged.

[0132] The training module 810 estimates the parameter φ of the MM encoder 824 by maximizing equation (9) based on equation (7), while the parameter θ of the MM generator 701 is frozen. Equation (9):

[0133] The training module 810 learns three modes x, w and y, where Based on equation (10), it is maximized. For example, x can be a 3D shape 816, w can be a 2D RGB view 818, and y can be a 2D sketch 820. Equation (10): where the symbols have the same meaning as in equation (7), where the additional modalities are w and y, and where the latent space z is now shared by the three modalities. In addition, assuming that the three modalities x, w, and y are independently conditioned on the latent variable z, and where θ(x), θ(w), and θ(y) are parameters of the weights 812 of different generators such as the MM generator 701, then For example, θ(x) is The weight of 730, θ(w) is 610, and θ(y) is Weights 812 include all weights of MM generator 701.

[0134] The training module 810 is based on φ={μ i ,∑ i} to learn the approximate posterior distribution q of z 703 φ The parameters φ of (x|x, w, y) are obtained by freezing the θ parameters of the MM generator 701 while maximizing the ELBO according to equation (11). Equation (11): in Given by equation (10). In some examples, the training module 810 is extended to learn more or less than three modalities simultaneously.

[0135] Training module 810 uses As training The objective function of 607, is a measure of the loss between the 3D shape 816 input to the MM encoder 824 and the 3D shape 804 output from the MM generator 701. The training module 810 uses As training The objective function of 712, is a measure of the cross entropy loss between the 2D sketch 820 input to the MM encoder 824 and the 2D sketch 808 output from the MM generator 701. The training module 810 uses As training The objective function of 710, It is given by formula (12).

[0136] Formula (12): where z i is the target image R i (2D RGB view 806) is a concatenation of the shape and color codes, where N is the image R i , J is the total number of levels in the Laplacian pyramid, which defaults to three, and L j (x) is the jth level in the Laplacian pyramid of image x. The objective function used by the training module 810 is given by equation (13), which is equation (10) with the following substitutions: x=C, which represents the 3D shape 608; w=S, which represents the 2D sketch 716; and y=R, which represents the 2D RGB view 714.

[0137] Formula (13): Wherein, the KL term regularizes the posterior distribution z 703, and the second term is decomposed into three components given by equation (14).

[0138] Formula (14): It is equal to Since the 3D shape 804 modality C contains all the information of the latent variable z, q φ (z|C, S, R) = q φ (z|C). In some examples, an optimizer is used with β1=0.9 and β2=0.999 to train the MM encoder 824 and the MM generator 701 based on equation (13).

[0139] Fig. 9A system 900 for cross-modal shape and color manipulation according to some examples is shown. An editing module 902 enables a user to edit a modality of a 2D sketch 908, a 2D RGB view 910, or a 3D shape 912, and then determine a corresponding change to another modality. For example, a user can edit a 3D shape 912 by changing a 2D sketch 908. The editing module 902 determines a corresponding change to the 3D shape 912 based on the change to the 2D sketch 908.

[0140] The editing module 902 is configured to obtain the potential code z0 and use the potential code z0 as z 703 input to the MM generator 701 to generate one or more of the 3D shape 804, the 2D RGB view 806 and the 2D sketch 808. For example, the editing module 902 generates the 3D shape 804 based on equation (4), generates the 2D sketch 808 based on equation (5), and generates one or more 2D RGB views 714 based on equation (6).

[0141] Then, the user edits the 2D sketch 808 or the 2D RGB view 714. Then, the editing module 902 determines the updated potential code based on equation (15): Formula (15): Where the modality (M) is S for the 2D sketch 908 or R for the 2D RGB view 910, e M is a 2D edit of S or R, and is the loss determined by the editing module 902 based on equation (16). Equation (16): Where γ and β are parameters for controlling the loss intensity. Then, the editing module 902 obtains the determined By using As input to the MM generator 701, a new 3D shape 912 and optionally a 2D RGB view 910 and / or a 2D sketch 908 are determined. In some examples, the editing module 902 iterates to find And based on With e M The difference between is less than the first threshold or does not exceed the first threshold and / or is less than a second threshold or does not exceed a second threshold to determine will be used as potential code for 2D sketch 908 .

[0142] In addition, the user may draw a 2D sketch 908 or a 2D RGB view 910, and the editing module 902 then finds the 2D sketch 908 or the 2D RGB view 910, x based on equation (17). M The corresponding potential code To generate a 3D shape 912.

[0143] Formula (17): in It can be determined based on equation (16). In some examples, the editing module 902 iterates to find And based on With x M The difference between is less than the first threshold or does not exceed the first threshold and / or is less than a second threshold or does not exceed a second threshold to determine will be used as potential code for 2D sketch 908 .

[0144] In some examples, the editing module 902 generates and use equation (4) to generate multiple 3D shapes 912. For example, the editing module 902 can determine the value based on equation (15) or equation (17). Edit module 902 can then generate a new where each y is a number with an increment added to one or more dimensions of The editing module 902 then generates 3D shapes 804 for each of the y's and presents them on a display 906. According to some embodiments, the display 906 is a display of the client device 102. In this way, the user can be provided with 3D shapes 804 that approximate the shape of the image in the latent space Z 602. Generated 3D shape 804 .

[0145] In addition, based on several 2D images representing 3D shapes such as armchairs or airplanes, the editing module 902 learns to transform the prior distribution z of the latent space into Mapping function h to the new distribution ω (z). Formula (18): h ω (z) = new distribution. ω The new distribution of (z) is consistent with the target data distribution of the 3D shape depicted by several 2D images such as 2D sketch 908 and / or 2D RGB view 910 Alignment. The editing module 902 is based on the h ω (z) instead of z 703, the 2D sketch 908 is generated by equation (5), and based on the h ω (z) instead of z 703 in equation (6) to generate a 2D RGB view 910. The editing module 902 is based on equation (19): Learn the mapping function h ω (z), where M is S (Formula (5)) or R (Formula (6)), and the mapping function h ω (z) is when the weights 812 are frozen and the output of the MM generator 701 is fed to the discriminator In some examples, the latent space z 703 is the first latent space, and the mapping function h ω (z) is mapped to the second latent space. The mapping function h ω (z) Mapping multiple 2D sketches 908 to the same region of the second latent space such that h ω (z) Codes are close to each other in the second latent space.

[0146] Fig.10 An example 1000 of cross-modal shape and color manipulation according to some examples is shown. Fig.10 , editing module 902 generates 3D shape 1008 and 2D sketch 1002 using potential code z0 as z703. 2D sketch includes engine 1006, and the user deletes 1004 engine 1006 using an editing program provided by editing module 902. 3D shape 1008 generated 1012 by editing module 902 based on z0 includes engine 1010. After the user deletes 1004 engine 1006, 2D sketch 1014 does not have engine 1016. In some examples, editing module 902 determines based on equation (13): Then, a 3D shape 1018 is generated based on equation (4). In some examples, when an additional 2D sketch 1002 of the aircraft is presented, the editing module 902 learns a mapping function h based on equation (17): ω (z), and based on formula (13), h is used for z ω (z) to determine Then, the editing module 902 generates a 3D shape 1018 based on equation (4), where z is given by h ω (z) Alternative, where the engine is deleted 1020. The editing module 902 enables the user to edit the 3D shape 1008 by editing the 2D sketch 1002.

[0147] Fig.11 An example 1100 of cross-modal shape and color manipulation according to some examples is shown. Fig.11 , editing module 902 generates 3D shape 1108 and 2D RGB view 1102 using latent code z0 as z703. 2D RGB view 1102 adds color 1104 from the user edit. The body of 3D shape 1108 generated by editing module 902 using z0 is not colored 1106. After the user adds the added color 1104, editing module 902 uses equation (13) to determine A 3D shape 1112 is then generated 1110 based on equation (4), where the 3D shape 1112 is colored 1114 based on the added color 1104. In some examples, when the additional 2D RGB view 1102 of the aircraft is presented, the editing module 902 learns the mapping function h based on equation (16): ω (z), and based on formula (15), h is used for z ω (z) to determine Then, the editing module 902 generates 1110 a 3D shape 1112 based on equation (4), where z is given by h ω (z) Replacement. The editing module 902 enables the user to edit the 3D shape 1108 by editing the 2D RGB view 1102. In some examples, the editing module 902 generates a new 2D RGB view such that it is based on or ω (z) coloring, and rendering the new 2D RGB view in 3D shape 1112.

[0148] Fig.12 An example 1200 of cross-modal shape and color manipulation according to some examples is shown. The user generates a 3D shape from an RGB view 1214 as follows. The user draws a 2D RGB view 1202, and the editing module 902 determines z to generate the 2D RGB view 1202 based on equation (15). Then, the editing module 902 generates 1204 a 3D shape 1206 based on z and equation (4). The user generates a 3D shape from a 2D sketch 1216 as follows. The user draws a 2D sketch 1208, and the editing module 902 determines z to generate the 2D sketch 1208 based on equation (15). Then, the editing module 902 generates 1210 a 3D shape 1212 based on z and equation (4).

[0149] Fig.13 An example 1300 of cross-modal shape and color manipulation according to some examples is shown. A user edits the row of the front 2D sketch 1310 within the dashed rectangle, and the editing module 902 generates a row of the back 3D shape 1316, which indicates the changes made to the front 3D shape 1312 by the user's edits. The edits can be seen by comparing the front 2D sketch 1310 with the back 2D sketch 1314. In the example of columns A 1302 and B 1304, the user removes the engine 1318, and in the columns of examples C 1306 and D 1308, the user adds the engine 1320. In example B 1304, the editing module 902 generates the back 3D shape 1316 with the new engine on the tail of the airplane, indicating that there are no airplanes without engines or only a few airplanes without engines in the latent space Z 602.

[0150] Fig.14An example 1400 of cross-modal shape and color manipulation according to some examples is shown. A user edits the rows of the front 2D sketch 1410 within the dashed rectangle, and the editing module 902 generates rows of the back 3D shapes 1416, which indicate the changes made to the corresponding front 3D shapes 1412 by the user's edits. The edits can be seen by comparing the rows of the front 2D sketch 1410 to the rows of the back 2D sketch 1414. In the examples of columns A 1402, B 1404, and C 1406, the user removed the curve 1418, and in the examples of columns D 1408, E 1422, and F 1424, the user added the curve 1420.

[0151] Fig.15An example 1500 of cross-modal shape and color manipulation according to some examples is shown. Column A 1502 is before any color is added by the user. Columns B 1504, C 1506, D 1508, and E 1510 have edits where color is added to the 2D RGB view 1520 at coloring 1512, 1514, 1516, and 1518, respectively, and color is added to the 2D RGB view 1524 at coloring 1528, 1530, 1532, and 1534, respectively. Row 3D shapes 1522 show shapes generated by the editing module 902 based on the potential code z of the corresponding shapes of the rows of the 2D RGB view 1520. Row 3D shapes 1526 show shapes generated by the editing module 902 based on the potential code z of the corresponding shapes of the rows of the 2D RGB view 1520. The changes to the 3D shapes 1522, 1526 can be discerned by comparing them to the 3D shapes 1522, 1526 of column A 1502. For example, the user adds coloring 1512 to the 2D RGB view 1520 in column B 1504. The editing module 902 generates the 3D shape 1522 in column B 1504 based on the latent code z that generates the 2D RGB view 1520 of column B. By comparing the 3D shape 1522 in column A 1502 to the 3D shape 1522 in column B, it can be discerned that the fuselage of the aircraft has been colored with the color used by the user at coloring 1512. The coloring 1514 on the right wing of the aircraft in column C 1506 of the row 2D RGB view 1520 changes the color of both wings of the aircraft as shown in column C 1506 of the row 3D shape 1522. Similarly, colorization 1516 and colorization 1518 both change the color of the two wings of the airplane in the airplane generated by editing module 902 in column D 1508 and column E 1510, respectively, of row 3D shape 1522. Similarly, colorization 1528, 1530, 1532, and 1534 on the seat of the chair in 2D RGB view 1524 causes 3D shape 1526 generated by editing module 902 to have changed colors on both the seat 1538 and the backrest 1536. This may be because latent space Z 602 does not have many examples for chairs with different colors for the seat and backrest.

[0152] Fig.16An example 1600 of cross-modal shape and color manipulation according to some examples is shown. A 2D RGB view 1608 is provided to the user by the editing module 902. A 3D shape 1610 is generated by the editing module 902 based on the latent space Z 602 and the 2D RGB view 1608, with edits of colors 1612, 1615, 1616, 1618, 1620, and 1622 as described herein. In column A 1602, the user colors the bottom of the seat of the chair in the overall stripe color 1612, and the resulting 3D shape 1610 in column A 1602 is the color of the entire chair that has been colored in color 1612.

[0153] In column B 1604, the user has colored the seat bottom 1614 and the legs of the chair 1616. The resulting 3D shape 1610 in column B 1604 is the color of the chair in all colors 1616 except for the seat bottom which has color 1614.

[0154] In column C 1606, the user colors a stroke of color 1618 across the back and both armrests of the chair, colors the legs of the chair 1620, and colors the seat bottom 1622 with the same color as coloring 1618. The resulting 3D shape 1610 in column C 1606 has the seat bottom, back and armrests colored 1618, 1622, and the legs colored 1620.

[0155] Fig.17 An example 1700 of the effect of occlusion on shape generation according to some examples is shown. The rows show different occlusion percentages of a 2D sketch 1708, with rectangles 1716 indicating the occluded portions of the 2D sketch 1708. In row A 1702, the 2D sketch 1708 is not occluded. In row B 1704, approximately 40% of the 2D sketch 1708 is occluded. In row C 1706, approximately 60% of the 2D sketch 1708 is occluded. As described herein, column 3D Shape 1 1710 is generated by the editing module 902 based on the latent space Z602 from the unoccluded portion of the 2D sketch 1708 into a 3D Shape 1 1710. The columns labeled 3D shape 2 1712 are identical to 3D shape 1 1710, where the editing module 902 performs a second generation of determining the latent code z based on determining the latent codes for the columns labeled 2D sketch 1708 and the columns labeled 3D shape 1 1710. Encoder-decoder (Enc-dec) 1714 indicates a conventional method for generating an encoder and decoder for a 3D shape.

[0156] Fig.18A graph 1800 comparing an encoder-decoder to an MM-VAD according to some examples is shown. The vertical axis is chamber distance 1802, where lower values ​​are better. Chamber distance 1802 measures the loss between a 2D sketch 1708 of row A 1702 with 3D shape 1 1710, 3D shape 2 1712, and Enc-Dec 1714 at different occlusion ratios 1804. MM-VAD 1808 outperforms encoder-decoder 1806 with lower chamber distance 1802 values.

[0157] Fig.19 An example 1900 of cross-modal shape and color manipulation according to some examples is shown. The editing module 902 provides an editor for a user to draw a 2D sketch 1902. As described herein, the editing module 902 generates a 3D shape 1 1904 and a 2D RGB view 1906 from the 2D sketch 1902 based on the latent space Z 602. The user colors the 2D RGB view 1906 with colors 1910. As described herein, the editing module 902 generates a 3D shape 2 1908 based on the latent space Z 602 and the 2D RGB view 1906 with colors 1910.

[0158] Fig. 20 A method 2000 for cross-modal shape and color manipulation according to some examples is shown. At operation 2002, the method 2000 begins by accessing a 2D sketch. For example, the editing module 902 may access the 2D sketch 1902 drawn by a user. The method 2000 continues at operation 2004, where a potential code corresponding to the 2D sketch is determined based on a first VAD. For example, the editing module 902 determines a value of z 703 based on equation (17), and when the value is input to the MM generator 701, the potential code corresponding to the 2D sketch is determined based on the first VAD. At 712, a 2D sketch 808 is generated that is close to the 2D sketch 1902 drawn by the user. The method 2000 continues at operation 2006, where a 3D shape is generated based on the potential code with the potential code as input based on the second VAD. For example, the editing module 902 uses the MM generator 701 in At 607 , the 3D shape 912 is generated with the latent code as input. The method 2000 continues at operation 2008 , where the 3D shape is displayed on a display of the computing device. For example, the editing module 902 may display the 3D shape 1 1904 on the display 906 .

[0159] Machine Architecture

[0160] Fig.21It is a diagrammatic representation of a machine 2100 within which instructions 2110 (e.g., software, programs, applications, applet, app, or other executable code) may be executed for causing the machine 2100 to perform any one or more of the methods discussed herein. For example, the instructions 2110 may cause the machine 2100 to perform any one or more of the methods described herein. The instructions 2110 transform a general-purpose, unprogrammed machine 2100 into a specific machine 2100 that is programmed to perform the functions described and shown in the manner described. The machine 2100 may operate as a standalone device or may be coupled (e.g., networked) to other machines. In a networked deployment, the machine 2100 may 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. The machine 2100 may include, but is not limited to, a server computer, a client computer, a personal computer (PC), a tablet computer, a laptop computer, a netbook, a set-top box (STB), a personal digital assistant (PDA), an entertainment media system, a cellular phone, a smart phone, a mobile device, a wearable device (e.g., a smart watch), a smart home device (e.g., a smart appliance), other smart devices, a web appliance, a network router, a network switch, a network bridge, or any machine capable of sequentially or otherwise executing instructions 2110 specifying actions to be taken by the machine 2100. In addition, although only a single machine 2100 is shown, the term "machine" should also be considered to include a collection of machines that individually or jointly execute instructions 2110 to perform any one or more of the methods discussed herein. For example, the machine 2100 may include any of the client device 102 or a number of server devices that form part of the messaging server system 108. In some examples, the machine 2100 may also include both a client system and a server system, wherein certain operations of a particular method or algorithm are performed on the server side, and certain operations of the particular method or algorithm are performed on the client side.

[0161] The machine 2100 may include a processor 2104, a memory 2106, and an input / output I / O component 2102 that may be configured to communicate with each other via a bus 2140. In an example, the processor 2104 (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, a processor 2108 that executes instructions 2110 and a processor 2112. The term "processor" is intended to include multi-core processors, which may include two or more independent processors (sometimes referred to as "cores") that may execute instructions simultaneously. Although Fig.21 Multiple processors 2104 are shown, but the machine 2100 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.

[0162] The memory 2106 includes a main memory 2114, a static memory 2116, and a storage unit 2118, which can be accessed by the processor 2104 via the bus 2140. The main memory 2106, the static memory 2116, and the storage unit 2118 store instructions 2110 that embody any one or more of the methods or functions described herein. The instructions 2110 may also reside, completely or partially, in the main memory 2114, in the static memory 2116, in the machine-readable medium 2120 in the storage unit 2118, in at least one of the processors 2104 (e.g., in a cache memory of a processor), or in any suitable combination thereof during execution thereof by the machine 2100.

[0163] I / O components 2102 may include various components for receiving input, providing output, generating output, sending information, exchanging information, capturing measurements, etc. The specific I / O components 2102 included in a particular machine will depend on the type of machine. For example, a portable machine such as a mobile phone may include a touch input device or other such input mechanism, while a headless server machine will most likely not include such a touch input device. It should be appreciated that I / O components 2102 may include Fig.212102. In various examples, the I / O components 2102 may include a user output component 2126 and a user input component 2128. The user output component 2126 may include a visual component (e.g., a display such as a plasma display panel (PDP), a light emitting diode (LED) display, a liquid crystal display (LCD), a projector, or a cathode ray tube (CRT)), an acoustic component (e.g., a speaker), a tactile component (e.g., a vibration motor, a resistance mechanism), other signal generators, etc. The user input component 2128 may include an alphanumeric input component (e.g., a keyboard, a touch screen configured to receive alphanumeric input, an optical keyboard, or other alphanumeric input component), a point-based input component (e.g., a mouse, a touch pad, a trackball, a joystick, a motion sensor, or other pointing instrument), a tactile input component (e.g., a physical button, a touch screen or other tactile input component that provides the location and force of a touch or touch gesture), an audio input component (e.g., a microphone), etc.

[0164] In other examples, the I / O component 2102 may include a biometric component 2130, a motion component 2132, an environmental component 2134, or a positioning component 2136, as well as various other components. For example, the biometric component 2130 includes components for detecting expressions (e.g., hand expressions, facial expressions, voice expressions, body postures, or eye tracking), measuring biosignals (e.g., blood pressure, heart rate, body temperature, sweat, or brain waves), identifying people (e.g., voice recognition, retinal recognition, facial recognition, fingerprint recognition, or EEG-based recognition), etc. The motion component 2132 includes an acceleration sensor component (e.g., an accelerometer), a gravity sensor component, and a rotation sensor component (e.g., a gyroscope).

[0165] Environmental components 2134 include, for example, one or more cameras (with still image / photo and video capabilities), lighting sensor components (e.g., photometers), temperature sensor components (e.g., one or more thermometers that detect ambient temperature), humidity sensor components, pressure sensor components (e.g., barometers), acoustic sensor components (e.g., one or more microphones that detect background noise), proximity sensor components (e.g., infrared sensors that detect nearby objects), gas sensors (e.g., gas detection sensors that detect concentrations of hazardous gases for safety or measure pollutants in the atmosphere), or other components that can provide indications, measurements, or signals corresponding to the surrounding physical environment.

[0166] With respect to cameras, client device 102 may have a camera system including, for example, a front-facing camera on a front surface of client device 102 and a rear-facing camera on a rear surface of client device 102. The front-facing camera may, for example, be used to capture still images and videos (e.g., “selfies”) of a user of client device 102, which may then be enhanced with the enhancement data (e.g., filters) described above. For example, the rear-facing camera may be used to capture still images and videos in a more conventional camera mode, where the images are similarly enhanced with the enhancement data. In addition to the front-facing camera and the rear-facing camera, client device 102 may also include a 360° camera for capturing 360° photos and videos.

[0167] Additionally, 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 triple, quad, or quintuple rear camera configurations on the front and back sides of the client device 102. For example, these multiple camera systems may include a wide-angle camera, an ultra-wide-angle camera, a telephoto camera, a macro camera, and a depth sensor.

[0168] The positioning component 2136 includes a position sensor component (for example, a GPS receiver component), an altitude sensor component (for example, an altimeter or barometer that detects air pressure, and the altitude can be obtained based on the air pressure), an orientation sensor component (for example, a magnetometer), etc.

[0169] A variety of technologies can be used to achieve communication. The I / O component 2102 also includes a communication component 2138 that is operable to couple the machine 2100 to the network 2122 or device 2124 via a corresponding coupling or connection. For example, the communication component 2138 may include a network interface component or other suitable device that interfaces with the network 2122. In other examples, the communication component 2138 may include a wired communication component, a wireless communication component, a cellular communication component, a near field communication (NFC) component, Parts (e.g. Low power consumption), Device 2124 may be another machine or any of a variety of peripheral devices (eg, a peripheral device coupled via USB).

[0170] In addition, the communication component 2138 can detect the identifier or include a component that can be operated to detect the identifier. For example, the communication component 2138 can 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 bar codes such as universal product code (UPC) bar codes, multi-dimensional bar codes such as Quick Response (QR) codes, Aztec codes, Data Matrix, Dataglyph, MaxiCode, PDF417, Ultra Code, UCC RSS-2D bar codes, and other optical codes) or an acoustic detection component (e.g., a microphone for identifying a tagged audio signal). In addition, various information can be obtained via the communication component 2138, such as location via Internet Protocol (IP) geolocation, ... Signal triangulation to derive location, location via detection of NFC beacon signals that can indicate a specific location, etc.

[0171] Various memories (e.g., main memory 2114, static memory 2116, and memory of processor 2104) and storage unit 2118 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. When executed by processor 2104, these instructions (e.g., instructions 2110) cause various operations to implement the disclosed examples.

[0172] The instructions 2110 may be sent or received over the network 2122 using a transmission medium via a network interface device (e.g., a network interface component included in the communication component 2138) and using any of a number of well-known transmission protocols (e.g., Hypertext Transfer Protocol (HTTP)). Similarly, the instructions 2110 may be sent or received via a coupling (e.g., a peer-to-peer coupling) with the device 2124 using a transmission medium.

[0173] Software Architecture

[0174] Fig. 222200 is a block diagram illustrating a software architecture 2204 that may be installed on any one or more of the devices described herein. The software architecture 2204 is supported by hardware, such as a machine 2202 including a processor 2220, a memory 2226, and an I / O component 2238. In this example, the software architecture 2204 may be conceptualized as a stack of layers, each of which provides specific functionality. The software architecture 2204 includes layers such as an operating system 2212, a library 2210, a framework 2208, and an application 2206. In operation, the application 2206 invokes an API call 2250 through the software stack and receives a message 2252 in response to the API call 2250.

[0175] The operating system 2212 manages hardware resources and provides public services. The operating system 2212 includes, for example, a kernel 2214, a service 2216, and a driver 2222. The kernel 2214 serves as an abstraction layer between the hardware and other software layers. For example, the kernel 2214 provides functions such as memory management, processor management (e.g., scheduling), component management, networking, and security settings. The service 2216 can provide other public services for other software layers. The driver 2222 is responsible for controlling the underlying hardware or interfacing with the underlying hardware. For example, the driver 2222 may include a display driver, a camera driver, or Low-power drivers, Flash drivers, Serial communication drivers (e.g., USB drivers), Drivers, audio drivers, power management drivers, etc.

[0176] The library 2210 provides a common low-level infrastructure used by the application 2206. The library 2210 may include a system library 2218 (e.g., a C standard library) that provides functions such as memory allocation functions, string manipulation functions, mathematical functions, etc. In addition, the library 2210 may include an API library 2224, such as a media library (e.g., a library for supporting the presentation 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 codec, Joint Photographic Experts Group (JPEG or JPG), or Portable Network Graphics (PNG)), a graphics library (e.g., an OpenGL framework for presenting in two dimensions (2D) and three dimensions (3D) in graphics content on a display), a database library (e.g., SQLite providing various relational database functions), a web library (e.g., WebKit providing web browsing functions), etc. The library 2210 may also include various other libraries 2228 to provide many other APIs to the application 2206 .

[0177] The framework 2208 provides a common high-level infrastructure used by the applications 2206. For example, the framework 2208 provides various graphical user interface (GUI) functions, high-level resource management, and high-level positioning services. The framework 2208 can provide a wide range of other APIs that can be used by the applications 2206, some of which can be specific to a particular operating system or platform.

[0178] In an example, applications 2206 may include a home application 2236, a contacts application 2230, a browser application 2232, a book reader application 2234, a location application 2242, a media application 2244, a messaging application 2246, a game application 2248, and a variety of other applications such as third-party applications 2240. A cross-modal shape and color manipulation application 2241 generates an image, such as a combination of Fig. 9 and the images described herein. Additionally, cross-modal shape and color manipulation application 2241 provides one or more of the functions or services provided by cross-modal shape and color manipulation system 216. Application 2206 is a program that performs the functions defined in the program. Various programming languages ​​can be used to create one or more of the variously structured applications 2206, such as an object-oriented programming language (e.g., Objective-C, Java, or C++) or a procedural programming language (e.g., C or assembly language). In a specific example, third-party application 2240 (e.g., a third-party application created by an entity other than the vendor of a particular platform using ANDROID TM or IOS TM Software Development Kit (SDK) can be used to develop applications on platforms such as IOS TM ANDROID TM , Mobile software running on the mobile operating system of the phone or other mobile operating systems. In this example, the third-party application 2240 can activate the API call 2250 provided by the operating system 2212 to facilitate the functions described in this article.

[0179] Processing components

[0180] Now go to Fig.23 , which shows a diagrammatic representation of a processing environment 2300 that includes a processor 2302, a processor 2306, and a processor 2308 (eg, a GPU, a CPU, or a combination thereof).

[0181] Processor 2302 is shown coupled to power source 2304 and is shown to include modules (permanently configured or temporarily instantiated), namely training component 2310, production component 2312, and communication component 2314. Training component 2310 trains neural networks, such as MM encoder 824 and MM generator 701. Production component 2312 implements the functionality of an interface for a user to use the trained MM generator 701, such as editing module 902. For example, the interface is Fig.11 906. The communication component 2312 may be tied back to the messaging server system 108 to retrieve the trained MM encoder 824 and / or the trained MM generator 701 and to provide additional functionality.

[0182] Glossary

[0183] "Module" refers to any logic, component, module, or mechanism. A module may constitute a software module (e.g., code contained on a machine-readable medium or in a transmission signal) or a hardware module. A "hardware module" is a tangible unit that is capable of performing certain operations and may be configured or arranged in some physical manner. In various example embodiments, one or more computer systems (e.g., a stand-alone computer system, a client computer system, or a server computer system) or one or more hardware modules of a computer system (e.g., a processor or a group of processors) may be configured by software (e.g., an application or an application portion) as a hardware module that operates to perform certain operations as described herein.

[0184] "Carrier signal" refers to any intangible medium that can store, encode or carry instructions for execution by a machine and includes digital or analog communications signals or other intangible media to facilitate the transmission of such instructions. Instructions may be sent or received over a network using a transmission medium via a network interface device.

[0185] "Client Device" refers to any machine that interfaces with a communications network to obtain resources from one or more server systems or other client devices. A client device may be, but is not limited to, a mobile phone, a desktop computer, a laptop computer, a portable digital assistant (PDA), a smart phone, a tablet computer, an ultrabook, a netbook, a notebook computer, a multiprocessor system, a microprocessor-based or programmable consumer electronics product, a game console, a set-top box, or any other communications device that a user may use to access a network.

[0186] "Communications network" means one or more parts of a network, which may be an ad hoc network, an intranet, an extranet, a virtual private network (VPN), a local area network (LAN), a wireless LAN (WLAN), a wide area network (WAN), a wireless WAN (WWAN), a metropolitan area network (MAN), the Internet, a part of the Internet, a part of the public switched telephone network (PSTN), a plain old telephone service (POTS) network, a cellular telephone network, a wireless network, A network, other type of network, or a combination of two or more such networks. For example, the network or a portion of the 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 type of cellular or wireless coupling. In this example, the coupling may implement any of various types of data transmission technologies, such as single carrier radio transmission technology (1xRTT), evolution data optimized (EVDO) technology, general packet radio service (GPRS) technology, enhanced data rates for GSM evolution (EDGE) technology, the third generation partnership project (3GPP) including 3G, fourth generation wireless (4G) network, universal mobile telecommunications system (UMTS), high speed packet access (HSPA), world wide interoperability for microwave access (WiMAX), long term evolution (LTE) standards, other data transmission technologies defined by various standard setting organizations, other long distance protocols, or other data transmission technologies.

[0187] "Component" refers to a logic, device or physical entity with boundaries defined by function or subroutine calls, branch points, APIs or other technical definitions that provide partitioning or modularization for specific processing or control functions. Components can be combined with other components via their interfaces to perform machine processes. Components can be packaged functional hardware units designed for use with other components, and part of a program that generally performs specific functions in related functions. Components can constitute software components (e.g., codes implemented on machine-readable media) or hardware components. "Hardware components" are tangible units that can perform certain operations and can be configured or arranged in a certain physical manner. In various examples, one or more computer systems (e.g., independent 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., applications or application parts) to operate to perform certain operations described herein. Hardware components can also be implemented mechanically, electronically, or any suitable combination thereof. For example, a hardware component may include a dedicated circuit or logic that is permanently configured to perform certain operations. A hardware component may be a dedicated processor, such as a field programmable gate array (FPGA) or an application-specific integrated circuit (ASIC). The hardware component may also include a programmable logic or circuit that is temporarily configured to perform certain operations by software. For example, the 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 component of a machine) that is uniquely customized to perform the configured function, and is no longer a general-purpose processor. It will be understood that the decision to mechanically implement the hardware component in a dedicated and permanently configured circuit or in a temporarily configured (e.g., configured by software) circuit can be driven for cost and time considerations. Therefore, the phrase "hardware component" (or "hardware-implemented component") should be understood to include a tangible entity, that is, an entity that is physically constructed, permanently configured (e.g., hardwired) or temporarily configured (e.g., programmed) to operate in some way or perform certain operations described herein. Considering an example in which a hardware component is temporarily configured (e.g., programmed), it is not necessary to configure or instantiate each of the hardware components at any time. For example, in the case where a hardware component includes a general-purpose processor that is configured by software and becomes a special-purpose processor, the general-purpose processor can be configured to different special-purpose processors (e.g., including different hardware components) at different times. The software configures one or more specific processors accordingly, for example, to constitute a specific hardware component at one time and to constitute different hardware components at different times. Hardware components can provide information to other hardware components and receive information from other hardware components. Therefore, the described hardware components can be considered to be communicatively coupled.In the case of multiple hardware components being present at the same time, communication can be achieved by signal transmission (e.g., by appropriate circuits and buses) between or among two or more hardware components in the hardware components. In examples where multiple hardware components are configured or instantiated at different times, communication between such hardware components can be achieved, for example, by storing information in a memory structure that multiple hardware components can access and retrieving information in the memory structure. For example, a hardware component can perform an operation, and the output of the operation is stored in a memory device coupled to it in communication. Then, other hardware components can access the memory device at a subsequent time to retrieve and process the stored output. The hardware component can also initiate communication with an input device or an output device, and can operate on resources (e.g., a collection of information). The various operations of the example methods described herein can be performed at least in part by a temporary configuration (e.g., by software) or one or more processors that are permanently configured to perform related operations. Whether it is temporarily configured or permanently configured, such a processor can constitute a processor-implemented component that operates to perform one or more operations or functions described herein. As used herein, "processor-implemented components" refer to hardware components implemented using one or more processors. Similarly, the method described herein can be implemented at least in part by a processor, wherein one or more specific processors are examples of hardware. For example, at least some of the operation of the method can be performed by one or more processors or the components implemented by the processor. In addition, one or more processors can also operate to support the execution of related operations in a "cloud computing" environment or as a "software as a service" (SaaS) operation. For example, at least some of the operations in the operation can be performed by a computer group (as an example of a machine including a processor), wherein these operations can be accessed via a network (e.g., the Internet) and via one or more appropriate interfaces (e.g., API). The execution of some operations in the operation can be distributed between processors, not only resident in a single machine, but deployed across multiple machines. In some examples, a processor or a component implemented by a processor can be located in a single geographic location (e.g., in a home environment, an office environment, or a server cluster). In other examples, a processor or a component implemented by a processor can be distributed across multiple geographic locations.

[0188] "Computer-readable storage media" refers to both machine storage media and transmission media. Therefore, these terms include both storage devices / media and carrier / modulated data signals. The terms "machine-readable medium", "computer-readable medium" and "device-readable medium" mean the same thing and can be used interchangeably in this disclosure.

[0189] "Ephemeral messages" are messages that are accessible for a limited duration. Ephemeral messages can be text, images, videos, etc. The access time for ephemeral messages can be set by the sender of the message. Alternatively, the access time can be a default setting or a setting specified by the recipient. Regardless of the setting technique, the message is transient.

[0190] "Machine storage media" refers to a single or multiple storage devices and media (e.g., centralized or distributed databases, and associated caches and servers) that store executable instructions, routines, and data. Thus, the 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 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), FPGA, and flash memory devices; magnetic disks, such as internal hard disks and removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks. The terms "machine storage media," "device storage media," and "computer storage media" mean the same thing and may be used interchangeably in this disclosure. The terms "machine storage media," "computer storage media," and "device storage media" expressly exclude carrier waves, modulated data signals, and other such media, at least some of which are covered under the term "signal media."

[0191] “Non-transitory computer-readable storage medium” refers to a tangible medium capable of storing, encoding, or carrying instructions for execution by a machine.

[0192] "Signal medium" refers to any intangible medium that is 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 software or data. The term "signal medium" should be deemed to include any form of modulated data signals, carrier waves, etc. The term "modulated data signal" refers to a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. The terms "transmission medium" and "signal medium" mean the same thing and may be used interchangeably in this disclosure.

Claims

1. A method comprising: Access two-dimensional (2D) sketches; determining, by one or more processors, a latent code corresponding to the 2D sketch based on a first variational autodecoder (VAD); generating a three-dimensional (3D) shape from the latent code based on a second VAD with the latent code as input; as well as The 3D shape is displayed on a display of a computing device.

2. The method according to claim 1, wherein: The 2D sketch is a first 2D sketch, and wherein determining the potential code further comprises: generating a second 2D sketch based on the first VAD with the latent code as input; determining a loss between the first 2D sketch and the second 2D sketch; and In response to the loss being less than a threshold, a determination is made to use the potential code for the first 2D sketch.

3. The method according to claim 2, wherein: The latent codes include color latent codes and shape latent codes.

4. The method according to claim 3, wherein: The second 2D sketch is generated using only the shape latent code, and the 3D shape is generated using both the color latent code and the shape latent code.

5. The method according to claim 3, wherein: The second VAD includes a third VAD and a fourth VAD, and wherein generating the 3D shape further comprises: generating a three-dimensional (3D) color based on the third VAD with the color latent code as input; generating a signed distance field (SDF) based on the fourth VAD with the shape latent code as input; and The 3D color and the SDF are combined to generate the 3D shape.

6. The method according to claim 2, wherein: The threshold is a first threshold, the loss is a first loss, and wherein the method further comprises: determining a loss between a previous potential code and the potential code; and wherein, in response to the loss, further comprising: Responsive to the first loss being less than the first threshold and the second loss being less than a second threshold, determining to use the potential code for the first 2D sketch.

7. The method according to any one of claims 1 to 5, wherein: The potential code is a first potential code, the 2D sketch is a first 2D sketch, and wherein the method further comprises: displaying the first 2D sketch on the display based on the first VAD with the first latent code as input; determining that the first 2D sketch has been edited; and A second latent code corresponding to the edited 2D sketch is determined based on the first VAD.

8. The method according to claim 7, wherein: The 3D shape is a first 3D shape, and wherein the method further comprises: generating a second 3D shape from the second latent code based on the second VAD with the second latent code as input; and The second 3D shape is displayed on a display of the computing device.

9. The method according to any one of claims 1 to 5, further comprising: generating a 2D color view based on a third VAD with the latent code and the view as input; as well as The 2D color view is displayed on a display of the computing device.

10. The method according to claim 9, wherein: The 2D color view is a first 2D color view, the potential code is a first potential code, the 2D sketch is a first 2D sketch, the 3D shape is a first 3D shape, and wherein the method further comprises: determining that the first 2D color view includes editing; determining a second latent code corresponding to the edited 2D color view based on the third VAD; generating a second 2D color view based on the third VAD with the second latent code as input; generating a second 2D sketch based on the first VAD with the second latent code as input; generating a second 3D shape based on the second VAD with the second latent code as input; and The second 2D color view, the second 2D sketch, and the second 3D shape are displayed on a display of the computing device.

11. The method according to claim 10, wherein: The editing of the first 2D color view is editing that changes the color of the first 2D color view.

12. The method according to any one of claims 1 to 5, wherein: The 2D sketch is a first 2D sketch, and wherein determining the potential code further comprises: determining the plurality of potential codes based on a loss between the 2D sketch and a plurality of 2D sketches generated from the plurality of potential codes; generating a plurality of 3D shapes based on the second VAD with the plurality of latent codes as input; displaying the plurality of 3D shapes on a display of the computing device; and In response to selection of a 3D shape from the plurality of 3D shapes, it is determined that a corresponding potential code from the plurality of potential codes that was used as input to generate the selected 3D shape is the potential code.

13. The method according to any one of claims 1 to 5, wherein: The potential code is a first potential code, and wherein the method further comprises: Generate a second latent code based on the first variational autoencoder (VAE) taking the ground-truth 2D sketch as input; generating a third 2D sketch based on the first VAD with the second latent code as input; and The weights of the first VAD and the first VAE are adjusted based on a difference between the third 2D sketch and the ground-truth 2D sketch.

14. The method according to claim 13, wherein: The 3D shape is a first 3D shape, and wherein the method further comprises: generating a third latent code based on a second VAE with the ground-truth 3D shape as input, wherein the ground-truth 3D shape and the ground-truth 2D sketch are a matching pair; generating a second 3D shape based on the second VAD with the third latent code as input; and The weights of the second VAD and the second VAE are adjusted based on a difference between the second 3D shape and the true 3D shape.

15. The method according to any one of claims 1 to 5, wherein: The first VAD and the second VAD are fully connected neural networks having three to eight layers, and wherein the first VAD and the second VAD are trained based on matching pairs of 2D sketches and corresponding 3D shapes.

16. The method according to any one of claims 1 to 5, further comprising: The first VAD and the second VAD are trained to learn a mapping between a latent space including the latent code and a second latent space, wherein latent codes of multiple 2D sketches depicting the same 3D shape are mapped to the same region of the second latent space.

17. A non-transitory computer-readable storage medium comprising instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising: Access two-dimensional (2D) sketches; determining a latent code corresponding to the 2D sketch based on a first variational autodecoder (VAD); generating a 3D shape from the latent code based on a second VAD with the latent code as input; as well as The 3D shape is displayed on a display of a computing device.

18. The computer-readable storage medium of claim 17, wherein: The operations also include: Access two-dimensional (2D) sketches; determining a latent code corresponding to the 2D sketch based on a first variational autodecoder (VAD); generating a 3D shape from the latent code based on a second VAD with the latent code as input; and The 3D shape is displayed on a display of a computing device.

19. A system comprising: processor; as well as a memory storing instructions that, when executed by the processor, configure the system to perform operations comprising: Access two-dimensional (2D) sketches; determining a latent code corresponding to the 2D sketch based on a first variational autodecoder (VAD); generating a 3D shape from the latent code based on a second VAD with the latent code as input; and The 3D shape is displayed on a display of a computing device.

20. The system of claim 19, wherein: The operations also include: Access two-dimensional (2D) sketches; determining a latent code corresponding to the 2D sketch based on a first variational autodecoder (VAD); generating a 3D shape from the latent code based on a second VAD with the latent code as input; and The 3D shape is displayed on a display of a computing device.

Images