Abstract: Computer-implemented defined proxemics to manage interpersonal encounters between users in virtual reality (VR) environments. A VR environment is initiated having a VR space in which a user, represented by an avatar, socializes amongst other users respectively represented as other avatars within the VR space. An impenetrable space barrier, having a size defined by predefined criteria, is created to enclose the avatar during movement within the VR space. The size of the impenetrable space barrier, with respect to an allowed interpersonal proximity between the avatar and each specific avatar of the other avatars, is dynamically adjusted during the movement within the VR space according to the predefined criteria and extrapolated data associated with the avatar and the other avatars.

Abstract: A technique for building a bounding volume hierarchy is disclosed. The technique subdividing a candidate box node based on a resolution to generate a plurality of cells of the candidate box node; identifying a plurality of nodes of a triangle set collection that fit within the cells; generating a plurality of candidate splits based on the plurality of nodes; selecting a candidate split based on a selection criterion to obtain a selected candidate split; and generating child box nodes for a box node of a bounding volume hierarchy under construction, based on the selected candidate split.

Abstract: A device including a processor configured to generate, for each of plural query inputs, point information using factors individually extracted from a plurality of pieces of factor data for a corresponding query input and generate pixel information of a pixel position using the point information of points, the plural query inputs being of the points, in a 3D space, on a view direction from a viewpoint toward a pixel position of a two-dimensional (2D) scene.

Abstract: The present disclosure generally relates to techniques and user interfaces for changing the display state of a display, controlling the display state of a display, transitioning between display states of a display, and displaying notifications.

Abstract: The present disclosure relates to a method and apparatus for processing a rotation animation special effect, and a readable storage medium. The method comprises: obtaining an object to be rotated; displaying a rotation parameter configuration window, and associating said object with the rotation parameter configuration window, the rotation parameter configuration window comprising a plurality of configuration items for generating a target rotation animation special effect; and generating a configuration file of the target rotation animation special effect according to configuration information of the plurality of configuration items, the target rotation animation special effect being an animation special effect of rotating said object with a rotation point as the center.

Abstract: Techniques, which may be embodied herein as systems, computing devices, methods, algorithms, software, code, computer readable media, or the like, are described herein for generating heatmap visualizations. A heatmap visualization can be a graphical representation of data where the coordinates of a cell in the visualization can be a key that describes a group of data represented by the cell. The colors of a heatmap may indicate information about the data represented by the cell (e.g., the amount of data in the cell). These cells can be rendered by calculating a per-pixel metric rate for each dataset in the heatmap visualization and mapping a dataset's rate onto pixels within the visualization that correspond to the dataset. After this mapping, the maximum rate within the visualization can be used to determine the visualization's colors and the cells can be rendered by coloring each pixel (e.g. pixel row) in its corresponding color.

Abstract: An example electronic device may include a display module, a memory configured to store computer-executable instructions, and a processor configured to execute the instructions by accessing the memory. The processor may be configured to create a preliminary persona based on first information related to history of a target user, create a first persona from the preliminary persona based on second information related to a time and a space of the target user, apply the first persona to an avatar object in a virtual space and corresponding to the target user, and, when an occurrence of an event related to the target user is detected, create a second persona from the first persona based on the event occurrence and apply the second persona, instead of the first persona, to the avatar object.

Abstract: Devices, systems and processes for an integrated internal and external camera system that enhances the passenger experience in vehicles are described. One example method for enhancing a passenger experiences includes capturing a first set of images of an area around the vehicle using an external camera system, capturing a second set of images of one or more passengers inside the vehicle using an internal camera system, recognizing at least one gesture made by the one or more passengers based on the second set of images, identifying an object or a location external to the vehicle based on the first set of images and the at least one gesture, and displaying information related to the object or the location to the one or more passengers.

Abstract: An embodiment of the present disclosure provides a method for three-dimensional (3D) modeling. The method includes segmenting an image into a region of interest and a region of non-interest, and sending data associated with the region of interest to a server. The method further includes receiving a first 3D model corresponding to the region of interest from the server, the first 3D model being generated by a first neural network at the server; generating a second 3D model corresponding to the region of non-interest by a second neural network, the first neural network having more network parameters than the second neural network; and generating a 3D model corresponding to the image based on the first 3D model and the second 3D model. By using the method of an embodiment of the present disclosure, a processing speed of 3D modeling can be increased, and modeling quality and accuracy can be improved.

Abstract: Embodiments of the present disclosure provide an image processing method and apparatus, an electronic device, and a readable storage medium. The method includes: acquiring an image; detecting a target object in the image; performing, based on a posture of the target object, dancing effect rendering on the target object to generate an animation of the target object dancing; superimposing the animation on the image to obtain a dancing effect animation; and displaying the dancing effect animation. In the embodiment of the present disclosure, the object in the image can be rendered with a dancing effect to generate the animation of the object dancing.

Abstract: A method including receiving a three-dimensional scan of a coating that coats an object. The coating and the object, in combination, have a shape. The method also includes flattening the three-dimensional scan to generate flattened data. Flattening includes conforming scan data in the three-dimensional scan to zone data for zones of a layout. The zones represents sections of the shape cut along boundaries in the shape. Each of the zones represents a corresponding thickness of the coating in a corresponding section of the sections. The method also includes vectorizing the flattened data into a vector data structure. The method also includes generating a prediction whether one or more zones of the zones are out of an engineering tolerance for the coating. Generating the prediction is performed by a machine learning model that takes, as input, the vector data structure and produces, as output, the prediction.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for generating a placement of a camera. In some implementations, maintaining monitoring information of a property; generating a virtual model of a property; determining an initial placement location for a virtual camera in the virtual model; obtaining image data generated in the virtual model from the virtual camera placed at the initial placement location; analyzing the image data; determining, using the analysis of the image data, whether to identify an updated placement location; and providing the placement location for a physical camera at the property to a device using a result of the determination whether to identify the updated placement location.

Abstract: An artificial intelligence framework is described that incorporates a number of neural networks and a number of transformers for converting a two-dimensional image into three-dimensional semantic information. Neural networks convert one or more images into a set of image feature maps, depth information associated with the one or more images, and query proposals based on the depth information. A first transformer implements a cross-attention mechanism to process the set of image feature maps in accordance with the query proposals. The output of the first transformer is combined with a mask token to generate initial voxel features of the scene. A second transformer implements a self-attention mechanism to convert the initial voxel features into refined voxel features, which are up-sampled and processed by a lightweight neural network to generate the three-dimensional semantic information, which may be used by, e.g., an autonomous vehicle for various advanced driver assistance system (ADAS) functions.

Abstract: A display in a commercial passenger vehicle can an option to be locked or unlock to enhance security. An example system for securing an in-vehicle entertainment (IVE) display in a commercial passenger vehicle comprises a mobile device and a computer. The mobile device comprises a first processor configured to secure a display located in the commercial passenger vehicle, where the first processor is configured to: obtain a payload; generate a first digitally signed payload as a first output of a first mathematical computation performed on the payload with a secret key; and send a first message comprising the first digitally signed payload and a lock command to instruct the display to lock the display. The computer is communicably coupled with the display and comprises a second processor configured to send a first instruction to cause the display to lock in response to a reception of the lock command.

Abstract: Apparatuses, systems, and techniques to generate labels of objects depicted with in an image. In at least one embodiment, one or more object labels are generated in association with an image frame based, at least in part, on one or more prior frames and one or more subsequent frames.

Abstract: Various implementations disclosed herein include devices, systems, and methods that progressively capture data representing an actual appearance of a user for creating a 3D avatar of the user. Image sensors at a user's electronic device may capture images (or other sensor data) of different portions of a user's body over time. Images and other sensor data that is captured initially or at a given time may not represent all of the user's body. Thus, in some implementations, the progressively captured data provides representations of additional portions of the user's 3D avatar over time.

Abstract: Provided is an information processing apparatus including an information acquisition unit that acquires information regarding a length of a moving image template and information regarding a length of a material moving image to be fitted into the moving image template and a change processing unit that changes reproduction management information regarding the moving image template in order to adjust the length of the moving image template in accordance with the length of the material moving image.

Abstract: Some examples of the disclosure are directed to a virtual motion capture application configured to operate on a first electronic device. In some examples, the virtual motion capture application is configured to present, via the first electronic device, a user interface element containing an animation timeline and a virtual platter including a virtual object in a computer-generated environment. In some examples, the user interface element includes a plurality of options and tools for generating pose-centered motion for the virtual object in the computer-generated environment. In some examples, the virtual motion capture application is configured to exchange data corresponding to the virtual object with a content creation application running on a second electronic device. In some examples, the second electronic device may display a motion creation user interface associated with the content creation application while the first electronic device presents the computer-generated environment.

Abstract: The present disclosure discloses the use of machine learning to address the process of motion synthesis and generation of intermediate poses for virtual entities. A transformer-based model can be used to generate intermediate poses for an animation based on a set of key frames.

Abstract: Apparatuses, systems, and techniques to generate an image. In at least one embodiment, neural networks receive an inputted one or more images, generate feature and depth information, and a neural network uses said information to generate one or more images. In at least one embodiment, a processor comprises one or more circuits to use one or more first neural networks to generate one or more first images from a viewpoint outside of an object based, at least in part, on depth information generated using one or more second neural networks and feature information generated by one or more third neural networks. In at least one embodiment, Using a point cloud and a viewpoint as inputs, a third neural network generates an image of vehicle from said viewpoint while parking.