Abstract: The disclosure relates to systems and methods for altering perception of virtual or game content in a virtual space based on one or more attribute levels. The perception of some virtual or game content may not be altered. Thus, the depiction of some content is altered while other content is not. A system may alter the depiction of game content based on attributes of an entity and/or based on which entity is to perceive the game content. The different depictions of game content may be provided to the same entity at different times and/or different perceptions of game content may be provided to different entities. Thus, a rich interface may be provided that differentially depicts game content based on attribute levels and/or the entity that is to perceive the game content.

Abstract: An identity authenticator receives a first authentication credential from a first application at a first computing device. The identity authenticator then determines that the first authentication credential is associated with a second authentication credential for the first application at a second computing device based on a stored authentication identity. The identity authenticator then provides a stored execution state for the first application to the first computing device, wherein the stored execution state is associated, based on the stored authentication identity, with at least one of the first authentication credential or the second authentication credential.

Abstract: Various aspects of the subject technology relate to systems, methods, and machine- readable media for adjusting controller settings. The method includes receiving, through a controller associated with a user, controller input for software. The method also includes determining, based on the controller input, a user profile for the user comprising at least a skill level and an input tendency of the user. The method also includes providing suggested adjustments to the controller settings intended to improve performance of the user in relation to the software, the controller settings comprising at least one of controller sensitivity or controller assignments. The method also includes receiving approval of the user to implement the suggested adjustments to the controller settings. The method also includes adjusting the controller settings based on the approval of the user.

Abstract: A UI state crawler system may allow for the crawling of a video game UI that may identify and map UI states of the video game. The UI state crawler system may determine a user interface (UI) state identifier (ID) for a UI state of a UI of a video game based at least in part on a plurality of node IDs corresponding to a plurality of nodes of a hierarchical structure of the UI and determine a UI state map does not include a UI state map node corresponding to the UI state ID. In response to the determining the UI state map does not include the UI state map node corresponding to the UI state ID, the UI state crawler system may generate an updated UI state map including the UI state map node corresponding to the UI state ID.

Abstract: A computer-implemented method for generating a machine-learned model to generate facial position data based on audio data comprising training a conditional variational autoencoder having an encoder and decoder. The training comprises receiving a set of training data items, each training data item comprising a facial position descriptor and an audio descriptor; processing one or more of the training data items using the encoder to obtain distribution parameters; sampling a latent vector from a latent space distribution based on the distribution parameters; processing the latent vector and the audio descriptor using the decoder to obtain a facial position output; calculating a loss value based at least in part on a comparison of the facial position output and the facial position descriptor of at least one of the one or more training data items; and updating parameters of the conditional variational autoencoder based at least in part on the calculated loss value.

Abstract: A system and method optimizes game quality by matching players for an online game to one of several virtual games. This matching process may involve filtering the players who wish to play according to various constraint minimizing criteria, packing the players into one or more virtual games to optimize game quality factors of the virtual games, and then instantiating the virtual games to actual online games played by the players. The game packing process may be iterative and may involve adding a new player into a virtual game. Game quality factor (GQF) values prior to and after the placement of the new player in the virtual game may be compared. The comparison of the GQF values may be used, at least in part to determine whether the new player is to remain in the virtual game. Various criteria may be considered in instantiating a virtual game.

Abstract: Systems and methods are disclosed for calculating dynamic ambient occlusion (AO) values for character models to yield high-quality approximations of global illumination effects. The approach utilizes a dual component machine-learning model that factorizes dynamic AO computation into a non-linear component, in which visibility is determined by approximating spheres and their casted shadows, and a linear component that leverages a skinning-like algorithm for efficiency. The parameters of both components are trained in a regression against ground-truth AO values. The resulting model accommodates lighting interactions with external objects and can be generalized without requiring carefully constructed training data.

Abstract: Systems and methods are provided for enhanced pose generation based on conditional modeling of inverse kinematics. An example method includes accessing an autoencoder trained based on poses, with each pose being defined based on location information of joints, and the autoencoder being trained based on conditional information indicating positions of a subset of the joints. The autoencoder is trained to reconstruct, via a latent variable space, each pose based on the conditional information. Information specifying positions of the subset of the joints is obtained via an interactive user interface and the latent variable space is sampled. An output is generated for inclusion in the interactive user interface based on the sampling and the positions.

Abstract: In some embodiments, the dynamic animation generation system can provide a deep learning framework to produce a large variety of martial arts movements in a controllable manner from unstructured motion capture data. The system can imitate animation layering using neural networks with the aim to overcome challenges when mixing, blending and editing movements from unaligned motion sources. The system can synthesize movements from given reference motions and simple user controls, and generate unseen sequences of locomotion, but also reconstruct signature motions of different fighters. For achieving this task, the dynamic animation generation system can adopt a modular framework that is composed of the motion generator, that maps the trajectories of a number of key joints and root trajectory to the full body motion, and a set of different control modules that map the user inputs to such trajectories.

Abstract: System and methods for using a deep learning framework to customize animation of an in-game character of a video game. The system can be preconfigured with animation rule sets corresponding to various animations. Each animation can be comprised of a series of distinct poses that collectively form the particular animation. The system can provide an animation-editing interface that enables a user of the video game to make modifications to at least one pose or frame of the animation. The system can realistically extrapolate these modifications across some or all portions of the animation. In addition or alternatively, the system can realistically extrapolate the modifications across other types of animations.

Abstract: Disclosed are issue tracking systems, troubleshooting techniques, and user interfaces for troubleshooting, which are associated with a user of a software application triggering the recording of a session. During the session, the user may narrate suggestions or problems for the application while they interact with the application in real-time, and a recording engine of the application may record various types of session data, such as the user's interaction, narration, telemetry data, call stack data, and so forth. The session data is automatically submitted to an issue tracking system to process a support ticket. The issue tracking system may provide a user interface enabling a developer to review a support ticket and any associated session data to quickly determine the relevant portion of the application data (e.g., underlying program code) that needs to be modified. The issue tracking system may also process session data to identify related tickets or recurring issues.

Abstract: A method, device, and computer-readable storage medium for generating shadows in an image of a scene. The method includes: generating a shadow map to determine pixels in shadow; for each pixel in shadow, performing a sampling of neighboring pixels; for each pixel in shadow, computing an average brightness of the sampling to generate a shadow mapped shadow value; determining a set of close shadow edge pixels, which are shadow edge pixels that correspond to locations on an object that are below a threshold distance to an occluding object; for each pixel in the set of close shadow edge pixels, performing ray tracing to determine a ray traced shadow value; and outputting shadow values for pixels in shadow, wherein the output is based on the ray traced shadow value for the close shadow edge pixels, and the output is based on the shadow mapped shadow value for other shadow pixels.

Abstract: A change tracking and analytics system and method receives software code blocks from one or more repositories of software related to a software project, such as a new video game. Changes associated with software code blocks, such as relative to previous versions of the software code blocks, may be determined and logged. Additionally, various analytics, such as metrics associated with complexity, divergence from a master version of software code blocks, and/or any cascading effects of the software code blocks may be generated and stored in association with the software code blocks. The change information and analytics may then be used to generate any variety of reports indicating complexity, divergence, or the like over time, information related to software code blocks, and/or information related to behavior of software teams. The change information may also be used to make changes to allocated resources, such as quality assurance resources and/or software engineering resources.

Abstract: A system may perform head pose neutralization on an input mesh to produce a neutral mesh and/or determine blend shapes for the neutral mesh. The system may generate a neutral mesh based on an input mesh and a reference mesh and then generate a blend shape associated with the neutral mesh based at least in part on one or more reference neutral meshes and one or more corresponding reference blend shapes.

Abstract: Systems and methods are disclosed for universal body movement translation and character rendering. Motion data from a source character can be translated and used to direct movement of a target character model in a way that respects the anatomical differences between the two characters. The movement of biomechanical parts in the source character can be converted into normalized values based on defined constraints associated with the source character, and those normalized values can be used to inform the animation of movement of biomechanical parts in a target character based on defined constraints associated with the target character.

Abstract: An autoplayer system and method enables one or more automated player(s) (autoplayers) that can be used to populate and/or fill a multiplayer online game. The autoplayers may emulate a human player in playing the online game. By filling the online game, the autoplayers may enhance the enjoyment of the human players in playing the online game. Additionally, autoplayer(s) may be used to replace players who drop out of the online game during gameplay of the online game, so that the remaining players can experience a sufficiently filled online game that continues in a similar manner as when the online game was initiated. Autoplayer(s) can also be used to test an online game, such as with a relatively large number of players, prior to deployment for players to play. New features that have been added to an online game can also be tested using autoplayers.

Abstract: A computer-implemented method of generating speech audio in a video game is provided. The method includes inputting, into a synthesizer module, input data that represents speech content. Source acoustic features for the speech content in the voice of a source speaker are generated and are input, along with a speaker embedding associated with a player of the video game into an acoustic feature encoder of a voice convertor. One or more acoustic feature encodings are generated as output of the acoustic feature encoder, which are inputted into an acoustic feature decoder of the voice convertor to generate target acoustic features. The target acoustic features are processed with one or more modules, to generate speech audio in the voice of the player.

Abstract: This specification provides a computer-implemented method, the method comprising obtaining a machine-learning model. The machine-learning model is being trained with expert data comprising a plurality of training examples. Each training example comprises: (i) game state data representing a state of a video game environment, and (ii) scored action data representing an action and a score for that action if performed by a video game entity of the video game environment subsequent to the state of the video game environment. An action is performed by the video game entity based on a prediction for the action generated by the machine-learning model. The method further comprises determining whether the action performed by the video game entity was optimal. In response to determining that the action performed by the video game entity was suboptimal, a healed training example is generated.

Abstract: Embodiments of an automated fraud detection system are disclosed that can detect user accounts that are engaging in unauthorized activities within a game application. The fraud detection system can provide an automated system that identifies parasitic accounts. The fraud detection system may identify patterns using machine learning based on characteristics, such as gameplay and transaction characteristics, associated with the parasitic user accounts. The fraud detection system may generate a model that can be applied to existing accounts within the game in order to automatically identify users that are engaging in unauthorized activities. The fraud detection system may automatically identify these parasitic accounts and implement appropriate actions to prevent the accounts from impacting legitimate users within the game application.

Abstract: A computer-implemented method is provided of finding one or more data items that match one or more defined criteria in a dataset. The method comprises identifying data snippets of the dataset using a set of one or more attention rules; categorizing the identified data snippets using fuzzy matching by assigning them to buckets such that each bucket contains data snippets that are similar to another according to a similarity measure; classifying buckets containing data snippets having more than a threshold number of the true positive data items as true positive buckets and remaining buckets as false positive buckets; calculating culling rules based on the true positive buckets and the false positive buckets, and using the culling rules to remove the false positive data items from the true positive buckets.