Abstract: A three-dimensional (3D) terrain reconstruction method for a scoured area around bridge pier foundation based on a mechanical scanned imaging sonar includes scanning an overall terrain of a scoured area around bridge pier foundation with a sonar from different azimuths to acquire n sonar images of a foundation scouring terrain; intercepting multiple analysis sections from each of acquired sonar images at a same distance; extracting key parameters of upper and lower edges on a terrain imaging strip in each of the analysis sections in the image, and transforming extracted parameters to a 3D space, a fan-shaped beam surface of the sonar being represented with a fan-shaped arc; recognizing a scour terrain profile in the analysis section; recognizing terrain profiles one by one, and respectively extracting spatially scattered 3D coordinate data; and performing interpolation and fitting on the spatially scattered data, thus implementing 3D reconstruction for the foundation scouring terrain.

Abstract: Surroundings data, relating to at least one surrounding area in the surroundings of a motor vehicle situated in a field of vision of a vehicle occupant, are obtained by a sensor system of the motor vehicle. At least one piece of information, which needs to be output to the user, is provided by an information source. The information is at least partially overlaid on a display of the surrounding area by a display device with the type of information presentation and/or the position at, and/or the orientation in, which the information presentation is visualized being dependent on the surroundings data.

Abstract: Embodiments include systems and methods for generating a 3D mesh from a video stream or other image captured contemporaneously with AR data. The AR data is used to create a depth map, which is then fused with images from frames of the video to form a full 3D mesh. The images and depth map can also be used with an object detection algorithm to recognize 3D objects within the 3D mesh. Methods for fingerprinting the video with AR data captured contemporaneously with each frame are disclosed.

Abstract: A messaging system performs virtual clothing try-on. A method of virtual clothing try-on may include accessing a target garment image and a person image of a person wearing a source garment and processing the person image to generate a source garment mask and a person mask. The method may further include processing the source garment mask, the person mask, the target garment image, and a target garment mask to generate a warping, the warping indicating a warping to apply to the target garment image. The method may further include processing the target garment to warp the target garment in accordance with the warping to generate a warped target garment image, processing the warped target garment image to blend with the person image to generate a person with a blended target garment image, and processing the person with blended target garment image to fill in holes to generate an output image.

Abstract: A system comprises a frame, a mirror coupled to the frame, an electronic display device coupled to the frame, a camera coupled to the frame, one or more processors, and one or more memory devices. The one or more processors are configured to execute instructions that are stored in the one or more memory devices. The one or more processors executing the instructions causes the system to continuously display, on the electronic display device, a real-time video feed of a user within a field of view of the camera; identify and object within the field of view of the camera; and, subsequent to the identification, modify the continuously displayed real-time video feed based on at least the identified object.

Abstract: Disclosed herein are systems and methods for methods of developing a database of controllable objects in an environment. For example, a method includes a mobile device having a camera to capture images of objects in an environment. For each object, the method includes, in response to receiving a user selection of the object, training a machine-learning model to recognize the object. The method includes receiving a command associated with the object and receiving a plurality of images of the object and training the machine-learning model to recognize the object based on the plurality of images. The method further includes transmitting the trained model and the command to a wearable electronic device causing the wearable electronic device to save the trained machine-learning model to a data store and to associate the command with the trained machine-learning model.

Abstract: An apparatus for processing media content includes at least one hardware processor coupled to at least one memory. The at least one memory stores instructions that when executed cause the at least one hardware processor to perform operations. The operations include generating three-dimensional (3D) representations of media elements present in one or more two-dimensional (2D) images representing a 2D scene with the media content. A 3D volume representation of the 2D scene is generated based on aggregating the 3D representations. A 3D void space associated with the 2D scene is segmented into a plurality of 3D void segments. The segmenting is based on the 3D volume representation. A 3D media element is inserted into at least one 3D void segment of the plurality of 3D void segments. The one or more 2D images are modified to include the at least one 3D void segment with the 3D media element.

Abstract: According to some embodiments, a system for transmitting and rendering a visualization of at least one object is described herein. The system includes a web server having access to at least one web page that includes three-dimensional embedding (“3D embedding”) instructions for requesting at least one 3D visualization associated with an object; a client computer in the data communication with the at least one web server, the client computer configured to receive the at least one web page and execute the 3D-embedding instructions included therein to send a request for the visualization associated with the object; and a visualization server in data communication with the client computer configured to determine whether the visualization is available, and determine whether the client computer is operable to render the 3D visualization, and determine whether to provide the 3D visualization data to the client computer.

Abstract: A processor may receive user command generated by a user. A processor may analyze user information for one or more official activities. The one or more official activities are based, at least in part, on a security policy. A processor may identify the user information is associated with the one or more official activities. A processor may prevent, responsive to determining the user command is associated with the one or more official activities, the one or more personal devices from collecting the user command.

Abstract: Method and devices for creating a sedentary virtual-reality system are provided. A user interface is provided that allows for the intuitive navigation of the sedentary virtual-reality system based on the position of the users head. The sedentary virtual-reality system can render a desktop computing environment. The user can switch the virtual-reality system into an augmented reality viewing mode or a real-world viewing mode that allow the user to control and manipulate the rendered sedentary environment. The modes can also change to allow the user greater situational awareness and a longer duration of use.

Abstract: Systems and techniques are provided for determining one or more poses of one or more objects. For example, a process can include determining, using a machine learning system, a plurality of keypoints from an image. The plurality of keypoints are associated with at least one object in the image. The process can include determining a plurality of features from the machine learning system based on the plurality of keypoints. The process can include classifying the plurality of features into a plurality of joint types. The process can include determining pose parameters for the at least one object based on the plurality of joint types.

Abstract: Ray tracing hardware accelerators supporting multiple specifiers for controlling the traversal of a ray tracing acceleration data structure are disclosed. For example, traversal efficiency and complex ray tracing effects can be achieved by specifying traversals through such data structures using both programmable ray operations and explicit node masking. The explicit node masking utilizes dedicated fields in the ray and in nodes of the acceleration data structure to control traversals. Ray operations, however, are programmable per ray using opcodes and additional parameters to control traversals. Traversal efficiency is improved by enabling more aggressive culling of parts of the data structure based on the combination of explicit node masking and programmable ray operations. More complex ray tracing effects are enabled by providing for dynamic selection of nodes based on individual ray characteristics.

Abstract: A display driving device and a control method thereof, and a display device. The control method includes: generating, by the master processing chip, a read/write synchronization signal, and receiving, by each of the slave processing chip, the read/write synchronization signal; in response to the read/write synchronization signal, caching, by the master processing chip, the received display data of the current to-be-displayed frame image into the frame address of the corresponding memory, reading and processing cached display data of a previous to-be-displayed frame image and transmitting the processed display data; and in response to the read/write synchronization signal, caching synchronously, by each of the slave processing chip, the received display data of the current to-be-displayed frame image into the frame address of the corresponding memory, and reading and processing synchronously cached display data of the previous to-be-displayed frame image and transmitting the processed display data.

Abstract: A terminal is a display control device for displaying a virtual space including an avatar that is operated by a user wearing a head-mounted display, the terminal being provided with: an avatar control unit which generates control data of the avatar corresponding to the movement of the user; a computation unit which, when the avatar and an object have collided with each other, computes physical behaviors of the avatar and the object that correspond to the collision; a VR space management unit which applies the result of the computation made by the computation unit to the virtual space; and a rendering unit which renders, as an image to be supplied to the head-mounted display, the avatar the behavior of which corresponding to the collision is kept within a predetermined range.

Abstract: Various techniques for adaptive rendering of images with noise reduction are described. More specifically, the present disclosure relates to approaches for rendering and denoising images—such as ray-traced images—in an iterative process that distributes computational efforts to pixels where denoised output is predicted with higher uncertainty. In some embodiments, an input image may be fed into a deep neural network (DNN) to jointly predict a denoised image and an uncertainty map. The uncertainty map may be used to create a distribution of additional samples (e.g., for one or more samples per pixel on average), and the additional samples may be used with the input image to adaptively render a higher quality image. This process may be repeated in a loop, until some criterion is satisfied, for example, when the denoised image converges to a designated quality, a time or sampling budget is satisfied, or otherwise.

Abstract: The disclosure describes one or more embodiments of systems, methods, and non-transitory computer-readable media that generate a transferred hairstyle image that depicts a person from a source image having a hairstyle from a target image. For example, the disclosed systems utilize a face-generative neural network to project the source and target images into latent vectors. In addition, in some embodiments, the disclosed systems quantify (or identify) activation values that control hair features for the projected latent vectors of the target and source image. Furthermore, in some instances, the disclosed systems selectively combine (e.g., via splicing) the projected latent vectors of the target and source image to generate a hairstyle-transfer latent vector by using the quantified activation values.

Abstract: An electronic device includes a device housing and one or more displays presenting one or more user actuation targets defining one or more virtual buttons in a predefined arrangement relative to a first end of the device housing. One or more sensors detect a condition of the electronic device, such as an approaching object, change in the direction of gravity, or an object tapping or pushing the electronic device. One or more processors cause, in response to the one or more sensors detecting the condition, the one or more displays to present the one or more user actuation targets defining the one or more virtual buttons in another predefined arrangement that is different from the predefined arrangement.

Abstract: A method includes capturing, by an image-capturing device, a one or more images of at least a portion of a pharmacy workstation. The method also includes identifying, by a processor in communication with the image capturing device, objects of interest in a first image of the one or more images and classifying, by the processor, the detected objects of interest using a convolutional neural network associated with the processor. The method also includes identifying, by the processor, a boundary defining an opening of a container in a second image of the one or more images. The method also includes updating, by the processor, an objects in container list based on a determination that at least one of the classified objects passed the boundary.

Abstract: An augmented reality system to perform operations that include: accessing image data at a client device; determining a position of a user of the client device based on the image data; causing display of a projection that extends from the position of the user upon a presentation of the image data at the client device; detecting an intersection of the projection and a surface of an object; generating a request that includes an identification of the portion of the surface of the object at the client device; and presenting the portion of the surface of the object based on the graphical property of the projection at the client device in response to the request that includes the identification of the portion of the surface of the object.

Abstract: The present invention provides a data processing method and an electronic terminal. The electronic terminal obtains target data that includes at least one data item, converts the target data into a data image by using a data visualization technology, and then sets the data image as wallpaper, where the data image includes at least one graphic element, and the graphic element is in a one-to-one correspondence with the data item. The target data is user data, and may include operation event information of operating the electronic terminal by a user, or information that is associated with a user account and that is based on at least one network platform, so as to automatically generate the wallpaper, show the user data to the user by using the wallpaper, and improve user experience.