Abstract: Some implementations relate to methods, systems, and computer-readable media for detection and monitoring of available uptime which measures both how accessible a computer system is and how well it is functioning. In some implementations, a computer-implemented method includes determining a number of health check ping responses to a health check ping that are received from a computer system during an allotted timeframe, determining a number of non-error responses measured by the computer system during the allotted timeframe, aggregating the number of health check ping responses and the number of non-error responses to determine a number of partially to fully functioning periods associated with the computer system over a larger time interval, and outputting a system health metric based upon overall functionality of the system over the larger time interval.

Abstract: Some implementations relate to methods, systems, and computer-readable media to generate 3D objects including 3D meshes and 3D cages. A signed distance function (SDF) approximant for a 3D mesh is determined by combining radial basis functions (RBFs) originating on the 3D mesh. A cage for the 3D mesh is generated by positioning cage vertices using the SDF approximant such that the cage overlays the 3D mesh. The generated 3D object includes the 3D mesh and the cage.

Abstract: Various implementations relate to methods, systems and computer readable media to provide cross-device communication with adaptive avatar interaction. According to one aspect, a computer-implemented method includes receiving communication inputs from a first device, determining facial landmarks and head orientation of the first user, and generating an animated 3D avatar based on the inputs. A virtual camera position is adjusted according to the head orientation. The computer-implemented method further receives additional communication inputs from a second device with enhanced features, modifies the avatar accordingly, and provides the enhanced animation to the second device. Various implementations allow for different viewing modes, including picture-in-picture (PIP), side-by-side, and cinematic views, to adapt the experience across multiple devices such as virtual reality (VR) headsets, augmented reality (AR) devices, mobile phones, and desktop computers.

Abstract: An online virtual experiences server generates a first instance of a virtual experience that is associated with a first client device. The server receives a request from the first client device to initiate a video call with a second client device. The video call is displayed as a user interface that includes a first avatar associated with the first client device and a second avatar associated with the second client device. Responsive to the second client device joining the video call, the server generates a second instance of the virtual experience. The first client device and the second client device teleport to the second instance of the virtual experience. The server receives a confirmation from the first client device and the second client device that the video call is hosted by the second instance of the virtual experience. The confirmation includes an identification of eligible participants for the video call.

Abstract: A metaverse application places a first avatar of a first player at a first position and a second avatar of a second player at a second position in a virtual experience. The metaverse application determines a bias direction based on the first position and the second position. The metaverse application determines a bias offset based on the bias direction, the first position, and the second position. The metaverse application a camera position of a virtual camera in the virtual experience based on the bias offset. The metaverse application presents a field of view of a third player in cinematic mode based on the camera position of the virtual camera.

Abstract: A metaverse application receives a first frame of a video. The metaverse application determines facial landmarks of the user in the first frame. The metaverse application generates an animation frame that includes an avatar and a background based on the facial landmarks and the first frame. The metaverse application determines a head orientation of the user in the first frame based on the facial landmarks. The metaverse application maps an orientation of the mobile device to the head orientation of the user. For each additional frame of the video subsequent to the first frame, the metaverse application updates the orientation of the mobile device. The metaverse application generates subsequent animation frames that include the avatar and the background based on the updated orientation of the mobile device in relation to the head orientation.

Abstract: Matchmaking architecture for online game platforms. In some implementations, a computer-implemented method includes receiving a request from a user device for one or more active game instances of a game platform that currently execute on the game platform and which the user device is able to join. The processor determines particular indexes in a data structure based on the request, which are a subset of a stored plurality of indexes that store identifications of a respective subset of active game instances on the platform. Identifications of a set of candidate game instances are obtained from the particular indexes, and a set of eligible game instances is determined based on the identifications and based on eligibility criteria, the set of eligible game instances being available to join. The user device is caused to connect to one of the eligible game instances.

Abstract: Rigid accessory adjustment provides dynamic manipulation of accessories, such as clothing items, headgear, weapons, and ornaments, attached to virtual game three-dimensional (3D) avatars. The rigid accessories maintain a constant shape, allowing players to fine-tune the position, rotation, and scaling of accessories. An accessory adjustment tool is used for fitting or styling of rigid accessories on 3D avatars, including changing position, rotation, and scaling of the rigid accessories. The rigid accessory adjustment include providing an avatar in a 3D virtual environment, providing a rigid accessory for the avatar body, performing at least one adjustment from the group comprising adjusting a position, adjusting a rotation, and adjusting a scale of the rigid accessory relative to the avatar body, and animating the avatar body, wherein the rigid accessory animates in correspondence with the animated avatar body.

Abstract: Various implementations relate to methods, systems, and computer-readable media to generate view consistent textures for three-dimensional (3D) objects. In some implementations, a method includes generating a plurality of depth maps based on a 3D mesh of a 3D object, wherein each of the plurality of depth maps is associated with a respective view of the 3D object. The method further includes receiving a description of a texture and generating two or more views of a texture map for the 3D object with a generative machine-learning (genML) model. The plurality of depth maps and a text prompt based on the description are provided as input to the genML model. Each view of the texture map at least partially covers the 3D mesh. The method further includes combining the two or more views of the texture map based on the 3D mesh to obtain the texture map for the 3D object.

Abstract: Implementations described herein relate to methods, systems, and computer-readable media to render virtual objects on a client device. In some implementations, the method includes obtaining a plurality of virtual objects associated with a virtual experience, for each virtual object of the plurality of virtual objects: determining physical connections of the virtual object to one or more other virtual objects in the virtual experience, and determining logical associations of the virtual object to one or more other virtual objects in the virtual experience, forming streaming sets of virtual objects, wherein for streaming sets that include two or more virtual objects, each virtual object within the streaming set has one or more of a physical connection and a logical association with at least one other virtual object in the streaming set, and rendering virtual objects included in one or more streaming sets in the virtual experience on the client device.

Abstract: Some implementations relate to a computer-implemented method that includes identifying candidate content items from a set of eligible content items. The computer-implemented method further includes assigning a corresponding rank to each of the candidate content items using an objective function that mitigates a popularity bias among the candidate content items. The computer-implemented method further includes determining an impression-distribution mix of the ranked candidate content items. The computer-implemented method further includes causing one or more of the ranked candidate content items to be displayed based on the impression-distribution mix.

Abstract: Some implementations relate to methods, systems and computer readable media to provide an aerodynamic force model for real-time distributed physics simulation. According to one aspect, a computer-implemented method includes receiving a description of a mechanism that includes physically coupled geometric assemblies within a virtual experience, with each geometric assembly defining a surface mesh. The description includes motion data of the mechanism. The method further includes, for each geometric assembly, identifying exposed surface areas of the surface mesh. The method further includes evaluating an aerodynamic force model based on the exposed surface areas and the motion data of the mechanism, where the aerodynamic force model includes a pressure coefficient that varies based on an angle of attack and based on windward and leeward facing surfaces. The method further includes integrating the aerodynamic force models into a physics simulation to refine the motion data of the mechanism.

Abstract: Various implementations relate to methods, systems and computer readable media to provide body tracking from monocular video. According to one aspect, a computer-implemented method includes obtaining a video including a set of video frames depicting movement of a human subject; extracting 2D images of the human subject from the video frames; providing the 2D images as input to a pre-trained neural network model. The method further includes determining a pose of the subject based on the 2D images. The method further includes generating a 3D pose estimation of upper body joint positions of the human subject. The method further includes determining confidence scores, and selecting a set of keypoints of the upper body joints of the human subject based on the confidence scores. The method further includes animating a 3D avatar using at least the selected set of keypoints, and displaying the animated 3D avatar in a user interface.

Abstract: Implementations described herein relate to methods, systems, and computer-readable media to recommend content items. In some implementations, a method includes identifying candidate content items for recommendation to a user and assigning respective ranks to the candidate content items, wherein the respective ranks are personalized to the user. The method further includes selecting, based on the respective ranks, one or more candidate content items from the candidate content items. The method further includes providing the selected one or more candidate content items to a client device for display in a user interface.

Abstract: Some implementations relate to methods, systems, and computer-readable media for digital advertising. In some implementations, a computer-implemented method includes presenting virtual items at a virtual user engagement station. The virtual user engagement station may include a threshold radius for activation of a change in configuration. Upon an avatar crossing the threshold radius, the avatar may be allowed to temporarily wear or interact with the presented virtual items, display different virtual items, and/or purchase virtual items.

Abstract: A metaverse application generates a first abuse score for the audio stream associated with a first user based on rules that analyze user signals, wherein the user signals include one or more selected from the group of one or more second users muting the first user, a history of past moderation actions associated with the first user, one or more third users blocking the first user, and combinations thereof. The metaverse application includes an audio-classifier model that obtains a second abuse score for an audio stream associated with the first user, wherein the audio stream is provided as input to the audio-classifier model. The metaverse application determines that the first user is committing abuse based on one or more selected from the group of the first abuse score, the second abuse score, and combinations thereof exceeding a threshold score value. Responsive to determining that the first user is committing abuse, the metaverse application performs a remedial action.

Abstract: Some implementations relate to providing adaptive, distributed simulation of fluids with rigid body coupling. According to one aspect, a method simulates, with a coarse resolution on one or more server devices, a global flow field for a fluid within a virtual environment. The method determines regions within the grid to obtain additional detail for, based on the presence of one or more rigid objects within the virtual environment. For each region, the computer-implemented method: assigns client device(s) to the region; sends fluid simulation data pertaining to the region to the client devices; and receives refined fluid simulation data for the region from the client devices. The method replaces the fluid simulation data in the global fluid simulation pertaining to the regions with the refined fluid simulation data for the regions. The method then updates the global flow field for the fluid in real time based on the simulation data.

Abstract: Real-time extraction of human poses from video data for animation of avatars. In some implementations, a computer-implemented method includes obtaining an input video including a plurality of video frames in a sequence that depict movement of a person based on a plurality of poses of the person in the input video. Keypoints of the person are detected in the video frames of the input video data, and a sequence of 3D body poses are determined that correspond to the plurality of poses of the person in the video frames of the input video. Determining the 3D body poses includes using a spatial-temporal transformer to determine joint angles of the keypoints, where the spatial-temporal transformer separately encodes inputs in spatial dimensions within each video frame and a temporal dimension across the video frames.

Abstract: A metaverse application receives a user-provided audio stream associated with a user. The metaverse application obtains portions of one or more audio streams. The metaverse application divides the user-provided audio stream into a plurality of portions, wherein each portion corresponds to a particular time window of the audio stream. The metaverse application providing the plurality of portions of the user-provided audio stream as input to an audio machine-learning model. The audio machine-learning model outputs, based on the portions of the user-provided audio stream, a determination of abuse in a particular portion of the plurality of portions. The metaverse application performs a remedial action responsive to the determination of abuse in the particular portion.

Abstract: Implementations described herein relate to methods, systems, and computer-readable media to localize dynamic content. In some implementations, a computer-implemented method includes receiving visual content associated with a game from a first client locale, the visual content including text being represented at the first client locale by a first language, converting the text to generate translated text in at least a second language associated with a second client locale, and storing the translated text in a database in association with the visual content.