Abstract: A method of operating a graphics processor that executes a graphics processing pipeline that includes an early culling tester that can access plural different culling test data buffers is disclosed. Information is maintained indicating which of the plural culling test data buffers is expected to be accessed, and the information is used to control the early culling tester. The information may be used to control the early culling tester such that processing delays associated with waiting for dependencies to resolve are reduced.

Abstract: A system and a method for improved generation of 3D avatars for virtual try-on of garments is provided. Inputs from a first user type are received, via a first input unit, for generating one or more garment types in a graphical format. Further, a 3D avatar of a second user type is generated in a semi-automatic manner or an automatic manner based on capturing a first input type or a second input type respectively received via a second input unit. The first input type comprises measurements of body specifications of the second user type and the second input type comprises body images of the second user type. Further, the generated garments are rendered on the generated 3D avatar of the second user type for carrying out a virtual try-on operation.

Abstract: Automatic selection of region in 3D point cloud is provided. Neighbor points are determined for given seed point of seed points. Responsive to a color difference of a given neighbor point from given seed point being less than neighbor color distance threshold and responsive to an angle between a normal of given neighbor point and a normal of given seed point being less than neighbor normal angle threshold, given neighbor point is added to region in 3D point cloud. Responsive to curvature at given neighbor point being less than curvature threshold, responsive to color difference of given neighbor point from initial seed point being less than initial seed color distance threshold and responsive to an angle between a normal of given neighbor point and a normal of initial seed point being less than an initial seed normal angle, given neighbor point is added to seed points for processing.

Abstract: A system that measures the motion of a camera traveling over a living subject by reference to images taken from the camera, while measuring the subject's shape, pose and motion. The system can segment each image into pixels containing the subject and pixels not containing the subject, and ascribe each pixel containing the subject to a precise location on the subject's body. In one embodiment, a computer connected to a camera and an Inertial Measurement Unit (IMU) provides estimates of the camera's location, attitude and velocity by integrating the motion of the camera with respect to features in the environment and on the surface of the subject, corrected for the motion of the subject. The system corrects accumulated errors in the integration of camera motion by recognizing the subject's body shape in the collected data.

Abstract: The present disclosure relates to an information processing apparatus, an information processing method, and a program that allow for preventing a decrease in marker recognition rate. Display of a content image that moves in a first display surface on which a marker image is displayed in a display form in which at least a part of the marker image is not shielded is controlled on the basis of first information regarding feature points of the marker image displayed on the first display surface of a terminal device; and second information regarding the feature points of the marker image on the first display surface in the display form is acquired from image data of a captured image obtained by imaging the first display surface, and a position and an orientation of the terminal device are detected on the basis of the image data.

Abstract: A test system for stability of video interfaces includes a display, a signal generator, a controller, and an image capturing sensor. The signal generator is configured to transmit multiple video signals to multiple video interfaces of the display. The controller is configured to control the display to sequentially display images according to each video signal. The image capturing sensor is configured to capture the images displayed sequentially by the display according to each video signal, and detect whether an image corresponding to each video signal is abnormal, and transmit a detection result to the controller.

Abstract: An electronic device and a method for generating an augmented reality (AR) content in an electronic device are provided. The method includes determining a posture and an action of each object of the plurality of the objects in the scene displayed on a field of view of the electronic device, classifying the posture and the action of each object of the plurality of the objects in the scene, identifying an intent and an interaction of each object from the plurality of objects in the scene based on at least one of the classified posture and the classified action, and generating the AR content for the at least one object in the scene of at least one of the identified intent and the identified interaction of the at least one object.

Abstract: Systems and methods are described to detect a location to place an advertisement in a media asset, the method comprising, identifying a plurality of points in a video frame of a media asset, detecting a color associated with each point of the plurality of points, calculating a change in color between each point of the plurality of points, comparing the change in color between each point of the plurality of points with a threshold, identifying, based on the comparing, an area within the frame that constitutes a surface; and selecting an advertisement to be placed on the surface.

Abstract: A method for implementing a full sweep in a digital instrument cluster system without a graphical processing unit (GPU) is disclosed. The method includes displaying a static asset as background for displaying of dynamic assets that point to different position values on the static asset, sequentially retrieving each of a plurality of subsets of dynamic assets such that each subset provides position indicators with a different level of position granularity, wherein an order of retrieving each subset moves from a lowest granularity subset to a highest granularity subset until all of the plurality of subsets of dynamic assets have been retrieved, and performing a full sweep, prior to retrieving of the dynamic assets, by sequentially displaying the dynamic assets from a minimum position to a maximum position of the static asset, and back, the sequentially displaying being based on a highest available granularity of dynamic assets that have been retrieved.

Abstract: Data processing systems (e.g. image processing systems) and methods are provided for processing a stream of data values (e.g. pixel values). The image processing system comprises a processing module configured to: receive a plurality of pixel values; and implement processing of a particular pixel value by operating on a particular subset of the received pixel values, by: defining a set of one or more groups into which pixel values within the particular subset can be grouped; classifying each of the pixel values within the particular subset into one of the groups of the set of one or more groups based on the value of that pixel value; processing the particular pixel value using one or more of the pixel values of the particular subset in dependence on the classification of the pixel values of the particular subset into the one or more groups; and outputting the processed particular pixel value.

Abstract: A digital human development platform can enable a user to generate a digital human. The digital human development platform can receive user input specifying a dialogue for the digital human and one or more behaviors for the digital human, the one or more specified behaviors corresponding with one or more portions of the dialog on a common timeline. Scene data can be generated with the digital human development platform by merging the one or more behaviors with one or more portions of the dialogue based on times of the one or more behaviors and the one or more portions of the dialog on the common timeline.

Abstract: The disclosure discloses a method and system for adjusting user field of view (FoV) in a three-dimensional virtual reality (VR) scene. The method includes: acquiring two consecutive frames of scene pictures during a period of a user experiencing a VR scene by using a VR device; determining a projected scene flow vector on the basis of the two consecutive frames of scene pictures; generating a virtual scene graph of the two consecutive frames of scene pictures; determining a projected scene flow value of the virtual scene graph on the basis of the projected scene flow vector; determining a peripheral vision pixel of the virtual scene graph; calculating a projected scene flow average value of the peripheral vision pixel on the basis of the projected scene flow value of the virtual scene graph; and dynamically adjust a FoV of the user on the basis of the projected scene flow average value.

Abstract: An avatar editing environment is disclosed that allows users to create custom avatars for use in online games and other applications. Starting with a blank face the user can add, rescale and position different elements (e.g., eyes, nose, mouth) on the blank face. The user can also change the shape of the avatar's face, the avatar's skin color and the color of all the elements. In some implementations, touch input and gestures can be used to manually edit the avatar. Various controls can be used to create the avatar, such as controls for resizing, rotating, positioning, etc. The user can choose between manual and automatic avatar creation. The avatar editing environment can be part of a framework that is available to applications. One or more elements of the avatar can be animated.

Abstract: Described are systems and methods to determine one or more body dimensions of a body based on a processing of one or more two-dimensional images that include a representation of the body. Body dimensions include any length, circumference, etc., of any part of a body, such as shoulder circumference, chest circumference, waist circumference, hip circumference, inseam length, bicep circumference, leg circumference, etc.

Abstract: An information processing apparatus acquires first physical makeup information representing a physical makeup of a first object. The first physical makeup information is information generated based on images obtained by imaging the first object with a plurality of imaging apparatuses in a plurality of directions. The information processing apparatus acquires second physical makeup information representing a physical makeup of a second object and motion information representing motion of a plurality of parts of the second object. The information processing apparatus generates motion information associated with the first physical makeup information based on the second physical makeup information and the motion information relating to the second object.

Abstract: The present disclosure discloses a method and apparatus for processing data, a computer device and computer-readable storage medium. The method comprises: acquiring image data of a human body; identifying a two-dimensional posture of the human body based on the image data; comparing the identified two-dimensional posture to a posture database to determine preset parts of the two-dimensional posture; and assigning cloth physical property of to-be-tried-on apparel to a part of the preset parts of the two-dimensional posture covered by original apparel. The present disclosure can greatly improve the efficiency of data processing, thereby improving user experiences.

Abstract: Systems and methods enable users to engage in meaningful, authentic, online interactions by extracting objects (virtual or real) from an image or video and transferring the extracted objects into a real-world environment of another user in three-dimensional augmented reality. An object to be sent from the first user to the second user is generated using a drawing application, extracted from an image or a video, or an AR object is captured. A video is recorded showing the object responding to an action of the first user and metadata is generated relating to the response of the object to the action of the first user. The video and metadata are sent to the second user. Upon receipt, the video is watched by the second user and the object is selected for presentation in a display environment of the second user. The state of the object is preserved by the metadata.

Abstract: In some implementations, a method is performed by a device including a non-transitory memory and one or more processors coupled with the non-transitory memory. In some implementations, the method includes obtaining user movement information. In some implementations, the user movement information characterizes a first body pose of the user at a first time and a second body pose of the user at a second time. In some implementations, the method includes determining whether a transition from the first body pose to the second body pose satisfies an acceptability threshold. In some implementations, the method includes in response to determining that the transition from the first body pose to the second body pose satisfies the acceptability threshold, generating a sequence of movements for a synthesized reality (SR) representation of the user.

Abstract: An operation status display device displays an operation status of a board work machine, in which an operator replenishes an article to be used in production of a board product, and the operation status display device includes an acquisition section and a display section. The acquisition section is configured to acquire a first time, which is a wait time from when the article is insufficient in the board work machine to when the operator starts replenishment work of the article, and a second time, which is a work time from when the operator starts the replenishment work to when the article is replenished in the board work machine. The display section is configured to display the first time and the second time when the article is insufficient in the board work machine to when the article is replenished.

Abstract: Aspects described herein relate to three-dimensional (3D) characters and rapidly generating 3D characters from a plurality of 3D source models. In generating the 3D characters, one or more 3D source models may be standardized, applied to a base mesh with material ID assignments, and decomposed to isolate particular polygonal mesh pieces and/or texture map feature selections denoted by the material IDs of the base mesh. The disparate isolated polygonal mesh pieces and/or texture map feature selections may be assembled in a modular fashion to compose unique 3D characters unlike any of those of the one or more 3D models. The 3D characters may be further refined through the addition of features and/or accessories, and may also be processed through machine learning algorithms to further ascertain uniqueness.