Abstract: According to an aspect, a method includes receiving a first three-dimensional model (3D) model of at least a body part of a person, receiving a second 3D model of a wearable device, and predicting, by at least one machine-learning (ML) model, a plurality of contact points between the first 3D model and the second 3D model.

Abstract: Techniques and systems are provided for light estimation. In some examples, a system receives a plurality of frames associated with a scene. The plurality of frames includes a first frame and a second frame occurring after the first frame. The system determines, based on image data of the first frame, a first light estimate associated with the scene. The system also determines, based on image data of the second frame, a second light estimate associated with the scene. The system further generates an aggregate light estimate associated with the scene based on combining the second light estimate with at least the first light estimate.

Abstract: In described examples, a geometric progression of structured light elements is iteratively projected for display on a projection screen surface. The displayed progression is for determining a three-dimensional characterization of the projection screen surface. Points of the three-dimensional characterization of a projection screen surface are respaced in accordance with a spacing grid and an indication of an observer position. A compensated depth for each of the respaced points is determined in response to the three-dimensional characterization of the projection screen surface. A compensated image can be projected on the projection screen surface in response to the respaced points and respective compensated depths.

Abstract: A machine learning (ML) based asset monitoring system that automatically determines damage mechanisms (DMs) and generates automatically updated visualizations of assets that include equipment and lines of a processing plant is disclosed. The asset monitoring system is communicatively coupled to the assets of the plant and continuously receives process parameters associated with the various processes and equipment in the plant. Corrosion loops (CLs) are identified and automatically demarcated by the asset monitoring system. DMs are predicted for each of the assets using a ML model based on the process parameters and the corrosion loops. The data regarding the DMs, CLs and the process parameters are used to obtain equipment risk rankings for the assets. Multi-dimensional visualizations of the assets that display the state of the plant assets in real-time are generated.

Abstract: A non-volatile memory device includes arrays of non-volatile memory cells that are configured to the store weights for a recurrent neural network (RNN) inference engine with a gated recurrent unit (GRU) cell. A set three non-volatile memory arrays, such as formed of storage class memory, store a corresponding three sets of weights and are used to perform compute-in-memory inferencing. The hidden state of a previous iteration and an external input are applied to the weights of the first and the of second of the arrays, with the output of the first array used to generate an input to the third array, which also receives the external input. The hidden state of the current generation is generated from the outputs of the second and third arrays.

Abstract: A user interface to a virtual camera for a 3-D rendering application provides various features. A rendering engine can continuously refine the image being displayed through the virtual camera, and the user interface can contain an element for indicating capture of the image as currently displayed, which causes saving of the currently displayed image. Autofocus (AF) and autoexposure (AE) reticles can allow selection of objects in a 3-D scene, from which an image will be rendered, for each of AE and AF. A focal distance can be determined by identifying a 3-D object visible at a pixel overlapped by the AF reticle, and a current viewpoint. The AF reticle can be hidden in response to a depth of field selector being set to infinite depth of field. The AF and AE reticles can be linked and unlinked, allowing different 3-D objects for each of AF and AE.

Abstract: Eye-tracking systems of the present disclosure may include at least one light source configured to emit modulated radiation toward an intended location for a user's eye. The modulated radiation may be modulated in a manner that enables the light source to be identified by detection and analysis of the modulated radiation. At least one optical sensor including at least one sensing element may be configured to detect at least a portion of the modulated radiation. A processor may be configured to identify, based on the modulated radiation detected by the optical sensor, the light source that emitted the modulated radiation. Various other methods, systems, and devices are also disclosed.

Abstract: A method further includes the following steps. Firstly, a three-dimensional picture under a generated background condition is generated, wherein the three-dimensional picture includes a three-dimensional object image. Then, a two-dimensional picture of the three-dimensional picture is captured, wherein the two-dimensional picture includes a two-dimensional object image of the three-dimensional object image. Then, an object region of the two-dimensional object image is recognized. Then, an exposed ratio of an exposed area of an exposed region of the object region to an object area of the object region is obtained. Then, whether the exposed ratio is greater than a preset ratio is determined. Then the exposed region is defined as the pick-and-place region when the exposed ratio is greater than the preset ratio.

Abstract: Systems and methods are described for retexturing portions of surface in a 2-D image, where the surface is an image of a 3-D object. The systems and methods analyze, with user input, the 2-D image and then, in computer memory, generate a 3-D model of the imaged surface. The surface may then be retextured, that is, for example, artwork may be added to the 2-D image in a realistic manner, taking into account a 3-D geometry in the scene of the 2-D image.

Abstract: System and method are provided to detect objects in a scene frame of two-dimensional (2D) video using image processing and determine object image coordinates of the detected objects in the scene frame. The system and method deploy a virtual camera in a three-dimensional (3D) environment to create a virtual image frame in the environment and generate a floor in the environment in a plane below the virtual camera. The system and method adjust the virtual camera to change a height and angle relative to the virtual image frame. The system and method generate at an extended reality (XR) coordinate location relative to the floor for placing the detected object in the environment. The XR coordinate location is a point of intersection of a ray cast of the virtual camera through the virtual frame on the floor that translates to the image coordinate in the virtual image frame.

Abstract: In some embodiments, apparatuses and methods are provided herein useful to providing data files associated with orthodontic appliances. In some embodiments, a system for providing data files associated with orthodontic appliances comprises a database, wherein the database stores the data files associated with the orthodontic appliances and a control circuit, wherein the control circuit is communicatively coupled to the database, a user device, and a printer, wherein the control circuit is configured to receive, from the user device, an indication of a selected orthodontic device, retrieve, based on the indication of the selected orthodontic device from the database, one of the data files associated with the orthodontic appliances, wherein the one of the data files associated with the orthodontic appliances corresponds to the selected orthodontic appliance, and transmit, to the printer, the one of the data files associated with the orthodontic appliances.

Abstract: Systems and methods for data asset acquisition and obfuscation can be helpful for retrieving augmented reality rendering data assets from third parties. The sending of a software development kit and receiving back data assets can ensure the data assets are compatible with the augmented reality rendering experience in the user interface. The data acquisition system with obfuscation can also ensure the code generated by third parties is stripped of semantics and has reduced readability.

Abstract: Disclosed is a method for using a virtual representation of an indoor environment to identify contents that have been damaged (e.g., by flooding). A virtual representation of a physical scene of an indoor environment is processed to identify a list of contents in the physical scene. The virtual representation may include 2-dimensional representations of the physical scene (e.g., images or video) or a 3-dimensional representation of the physical scene (e.g., 3D digital model). A reference line is determined in the virtual representation that is indicative of a maximum vertical extent of the damage in the physical scene. The position of the reference line is compared with the position of the identified contents in the virtual representation to determine contents that are likely to be damaged. For example, the contents that are at or below a plane represented by the reference line in the virtual representation may be identified as damaged.

Abstract: Apparatus, systems, and/or methods are disclosed relating to augmented reality welding systems. In some examples, an augmented reality welding system is configured to apply a visual effect to a simulated rendering of the augmented reality welding system when a simulated arc is present, so as to emulate an auto-darkening lens of a welding helmet. In some examples, the visual effect is impacted by several user adjustable settings. The settings may be adjusted by a user, such as via a helmet interface and/or the user interface of the augmented reality welding system, for example. In some examples, the settings may emulate auto-darkening settings found on conventional auto-darkening welding helmets (e.g., shade, sensitivity, and/or delay). In some examples, the settings may also include other settings unique to the augmented reality welding system, such as, for example a helmet model/type, a difficulty setting, a realism setting, and/or an effect area setting.

Abstract: Methods, apparatus, systems and articles of manufacture for generating a three-dimensional (3D) model for 3D scene reconstruction are disclosed. An example apparatus includes a 3D scene generator to generate a 3D model for digital image scene reconstruction based on a trained generative model and a digital image captured in a real environment. An image simulator is to generate a simulated image based on the 3D model, the simulated image corresponding to the captured image. A discriminator is to apply a discriminative model to the simulated image to determine whether the simulated image is simulated.

Abstract: Systems and methods are provided for depicting information about a vehicle in augmented reality. An exemplary method may include determining identification information of a vehicle based on input received from a client device and obtaining, from an information source, vehicle information based on the identification information. The method may also include analyzing the vehicle information using an artificial intelligence engine and extracting vehicle history data from the vehicle information based on the analysis. The method may also include identifying a portion of the vehicle associated with the vehicle history data and providing instructions, based on the vehicle history data, to an augmented reality-enabled device to superimpose an indicator on a visual representation of the vehicle at a location corresponding to the portion of the vehicle.

Abstract: According to one implementation, an augmented reality image generation system includes a display, and a computing platform having a hardware processor and a system memory storing a software code. The hardware processor executes the software code to receive a camera image depicting one or more real-world object(s), and to identify one or more reference point(s) corresponding to the camera image, each of the reference point(s) having a predetermined real-world location. The software code further maps the real-world object(s) to their respective real-world location(s) based on the predetermined real-world location(s) of the reference point(s), merges the camera image with a virtual object to generate an augmented reality image including the real-world object(s) and the virtual object, and renders the augmented reality image on the display. The location of the virtual object in the augmented reality image is determined based on the real-world location(s) of the real-world object(s).

Abstract: A system is provided for recommending guidance instructions to a user. The system includes a memory having computer readable instructions and a processor for executing the computer readable instructions. The computer readable instructions control the processor to perform operations of monitoring an ongoing task comprising at least one act performed by a user, generating image data depicting the ongoing task, and displaying the ongoing task based on the image data. The system analyzes the ongoing task and generates an augmented image. The augmented image is overlaid on the image data so that the augmented image is displayed simultaneously with the ongoing task to direct the user to progress the ongoing task.

Abstract: A mechanism is described for facilitating memory-based software barriers to emulate hardware barriers at graphics processors in computing devices. A method of embodiments, as described herein, includes facilitating converting thread scheduling at a processor from hardware barriers to software barriers, where the software barriers emulate the hardware barriers.

Abstract: An image processing method and apparatus, and a computer-readable storage medium are provided. The method includes: determining a first region matching a target object in a first image; determining a deformation parameter based on a preset deformation effect, the deformation parameter being used for determining a position deviation, generated based on the preset deformation effect, of each pixel point of the target object; and performing deformation processing on the target object in the first image based on the deformation parameter to obtain a second image.