Abstract: This disclosure describes a method including determining one or more object clusters from a plurality of frames of the video content. At least one of the one or more object clusters is an object cluster with movement through the plurality of frames. The method includes extracting the determined one or more object clusters from the plurality of frames to generate a set of frames having extracted one or more object clusters and outputting the set of frames having extracted one or more object clusters. This disclosure describes a method including receiving the set of frames having the extracted one or more object clusters, rendering one or more of the set of frames in a live camera feed of a device, and generating video content based on the rendered one or more set of frames and a user interacting with the extracted one or more object clusters.

Abstract: There are provided a system and method of optimization of operating a Convolutional Neural Network (CNN), the method including: for each given layer of the CNN, obtaining at least one input feature map, retrieving an index of one or more filters in the given layer; generating one or more output feature maps corresponding to the one or more filters, including: for each given block, querying the index to find a number of selected filters meeting a predetermined criterion related to respective inner products between the selected filters and the given block, applying the selected filters on the given block to obtain a number of output values for a given output position in a number of output feature maps corresponding to the number of selected filters, and filling in the given output position in the rest of output feature maps with a value of zero, thereby reducing the computational cost of operating the CNN.

Abstract: Provided is a method and a device for creating and displaying a multilayer augmented reality image. The device may include a photographing circuit configured to capture images of a real environment and an image processor configured to create an AR content, extract at least one object from the captured images of the real environment, display the captured images of real environment as a first layer, display the created AR content as a second layer and overlay the second layer on the first layer, and display the extracted object as an object image layer and overlay the object image layer on the second layer.

Abstract: Described herein are devices, systems and methods to utilize non-volatile memory to save and retrieve data that is used to accelerate the load and resume of GPU accelerated applications. Non-volatile memory and GPU logic are configured to enable the GPU to directly access the non-volatile memory to enable data to be read without requiring the data to traverse the CPU and CPU memory. This data access path creates a faster method for loading data into GPU local memory.

Abstract: The disclosed embodiment generate a 3D representation of a 2D scene depicted to two dimensional video. The 3D representation includes individual 3D media elements representing objects included in the 2D scene. 3D void segments within the 2D scene are identified based on an aggregation of the individual 3D media elements. The 3D void segments are prioritized for insertion of additional 3D media elements within the 3D void spaces based on a variety of factors including lighting present at the 3D void segment, a distance of the 3D void segment from a center of the 2D scene, a size of the 3D void segment, and a time duration the 3D void segment is present in the 2D scene. A new 3D media element in these selected for insertion into the 2D scene based on the priorities of the 3D void segments.

Abstract: Methods and systems for packaging a product offering of product items associated with a merchant account. A product packaging model is associated with a kit of product items having a selected packaging option. During assembly, one or more images of the kit are captured and image features are detected and compared to parameters specified in the product packaging model. An error notification is output if a deviation is detected between the detected image features and the parameters prescribed by the product packaging model.

Abstract: A method for performing object occlusion is disclosed. The method includes capturing an image of a physical item, determining a location and an orientation of a first virtual item with an augmented reality registration function; generating an augmented reality image, wherein the augmented reality image comprises a rendering of the first virtual item in the image using a first rendering function to depict the location and orientation of the first virtual item in the image and a rendering of a second virtual item in the image with a second rendering function; displaying the augmented reality image, wherein occlusion of the first virtual item by the physical item is shown in the augmented reality image based on occlusion of the first virtual item by the second virtual item wherein the first virtual item depicts a next step in the step-by-step instructions for the assembly.

Abstract: Image processing is carried out by accepting an array of voxels that include data representing a physical property of a 3-dimensional object, segmenting the array of voxels into a plurality of regional subarrays of voxels that respectively satisfy predetermined criteria, transforming the subarrays into respective triangular meshes, the meshes having triangles that surround the subarrays and intercept the outer voxels of the subarrays, and rendering the triangular meshes on a display

Abstract: Methods, systems, articles of manufacture and apparatus to generate digital scenes are disclosed. An example apparatus to generate labelled models includes a map builder to generate a three-dimensional (3D) model of an input image, a grouping classifier to identify a first zone of the 3D model corresponding to a first type of grouping classification, a human model builder to generate a quantity of placeholder human models corresponding to the first zone, a coordinate engine to assign the quantity of placeholder human models to respective coordinate locations of the first zone, the respective coordinate locations assigned based on the first type of grouping classification, a model characteristics modifier to assign characteristics associated with an aspect type to respective ones of the quantity of placeholder human models, and an annotation manager to associate the assigned characteristics as label data for respective ones of the quantity of placeholder human models.

Abstract: In a graphics processing unit (GPU), receiving an input image comprising an array of pixels. Each pixel having a gray scale value from a range of N grayscale values. For each particular input patch of pixels of a set of input patches partitioning the input image and in parallel for each particular grayscale value the range, counting the number of pixels in the particular input patch having the particular grayscale value. In parallel for each particular input patch of pixels of a set of input patches partitioning the input image, creating an output image patch as an ordered sequence of N pixels, with the color value of the nth pixel in each corresponding output patch representing the count of pixels in the particular input patch having the nth grayscale value. Combining the output image patches into a single composite output image of N pixels, the pixel value of the nth pixel in the single composite output image corresponding to the count of pixels in the input image having the nth grayscale value.

Abstract: A method for generating a virtual operating object is provided for an electronic device. The method includes obtaining a target portrait picture on a configuration interface of a target application on the electronic device; obtaining a first picture region of the target portrait picture where a first part presents and a first part feature of the first part; determining a target part matching the first picture region in a pre-established feature image library, the target part being a part of a to-be-generated target virtual operating object in the target application; determining a target feature parameter matching the first part feature in a value range of a target part feature of the target part pre-recorded in the feature image library; and generating the target part in the target application according to the target feature parameter.

Abstract: A system on a chip (SoC) includes a digital signal processor (DSP) and a graphics processing unit (GPU) coupled to the DSP. The DSP is configured to receive a stream of received depth measurements and generate a virtual bowl surface based on the stream of received depth measurements. The DSP is also configured to generate a bowl to physical camera mapping based on the virtual bowl surface. The GPU is configured to receive a first texture and receive a second texture. The GPU is also configured to perform physical camera to virtual camera transformation on the first texture and on the second texture, based on the bowl to physical camera mapping, to generate an output image.

Abstract: A display control apparatus includes an acquisition unit that acquires an image, a memory that stores multiple images acquired by the acquisition unit, a recognition unit that recognizes a size of a character included in an image to be displayed on a display from among the images stored on the memory, and a display controller that causes the display to display the images stored on the memory while switching from one image to another every set time period. The display controller determines a display setting of the image to be displayed on the display in response to the size of the character included in the image that the recognition unit has recognized and causes the display to display the image in the determined display setting.

Abstract: A vehicle display device includes: a projection device which includes a display surface for displaying an image and projects display light via an opening toward a reflection unit disposed to face a driver; an acquisition unit which acquires an eye position of the driver; and a controller which controls the projection device. The controller sets an image display area on the display surface so that the driver is capable of visually recognizing an image to be displayed according to the acquired eye position.

Abstract: Systems and methods are provided for planning a procedure. A display device is configured to display a first virtual element. A controller device having a processor is configured to be in communication with the display device, and the controller device is further configured to direct the display device to display the first virtual element. A physical control element is in communication with the controller device, and is configured to correspond to the first virtual element such that an actual manipulation of the control element is displayed, via the processor of the controller device and on the display device, as a corresponding response of the first virtual element to the actual manipulation of the control element. Associated systems, methods, and computer program products are also provided.

Abstract: The present disclosure relates generally to systems and methods for creating a mixed reality environment. A mixed reality system includes a performance area for generating a mixed reality environment, a motion determination module that determines and tracks the motion of an object within the performance area, a physical article module that generates a physical article within the performance area, and a mixed reality display that displays a virtual article within the performance area, wherein the physical article and the virtual article are correlated to the motion of the object.

Abstract: An electronic device includes a main body; a flexible display to be rolled up and placed in the main body; a sensor configured to detect unrolling of the flexible display; and a controller configured. The controller is configured to control the flexible display to present information while the flexible display is exposed from the main body, and, based on detecting the flexible display being rolled into the main body while the information is presented, control to change a presentation position of the information on the flexible display according to the rolling of the flexible display.

Abstract: A method and system for transforming simple user input into customizable animated images for use in text-messaging applications.

Abstract: An apparatus comprises a unit that acquires observation data indicating an observation value representing a state of a crop, the observation value being associated with any of a plurality of observation types representing types of observation objects, the observation value being obtained by observing a crop; and a control unit that visualizes and displays the observation value at a position on a map where the observation has been performed, the observation value being indicated by the acquired observation data, wherein when displaying the observation values simultaneously or in a switchable manner, in a case where the control unit visualizes the observation value exceeding or less than a predetermined value specified for each of the plurality of observation types, it visualizes and displays the observation value on the map by using an identical display form for each of the plurality of observation types.

Abstract: A method and system for generating a three-dimensional representation of a vehicle to assess damage to the vehicle. A mobile device may capture multispectral scans of a vehicle from each a plurality of cameras configured to scan the vehicle at a different wavelength of the electromagnetic spectrum. A virtual model of the vehicle may be generated from the multispectral scan of the vehicle, such that anomalous conditions or errors in individual wavelength data are omitted from model generation. A representation of the virtual model may be presented to the user via the display of the mobile device. The virtual model of the vehicle may further be analyzed to assess damage to the vehicle.