Abstract: Described herein is a graphics processing unit (GPU) configured to receive an instruction having multiple operands, where the instruction is a single instruction multiple data (SIMD) instruction configured to use a bfloat16 (BF16) number format and the BF16 number format is a sixteen-bit floating point format having an eight-bit exponent. The GPU can process the instruction using the multiple operands, where to process the instruction includes to perform a multiply operation, perform an addition to a result of the multiply operation, and apply a rectified linear unit function to a result of the addition.

Abstract: A method for ascertaining the pose of an object. The method includes recording a first and a second camera image of the object, ascertaining a correspondence between camera pixels of the camera images and vertices of a 3D model of the object, and ascertaining the pose of the object from a set of poses by minimizing, across the set of poses, a loss function, the loss function for a pose being provided by accumulation of distance measures between projections of the object in the pose onto the respective camera image plane and the corresponding pixels of the respective camera image.

Abstract: A method for providing device support to a user using an augmented reality (AR) interface includes establishing, by a computer system, a real-time communication session streaming audio and video between (i) a local application executing on a local user device and (ii) a remote application executing a remote user device. The method further includes transmitting, via the real-time communication session, images depicting equipment captured by the local application. Annotations to the images are received from the remote application. Each annotation is anchored to user-selected positions on the equipment. The annotations are presented on the remote user device overlaid on the equipment at the user-selected positions. The real-time communication session is used to transmit audio or video instructional information related to the equipment and referencing the annotations. The computing system stores a new session record that includes the images, the annotations, and the audio or video instructional information.

Abstract: Solutions for adapting machine learning (ML) models to neural networks (NNs) include receiving an ML pipeline comprising a plurality of operators; determining operator dependencies within the ML pipeline; determining recognized operators; for each of at least two recognized operators, selecting a corresponding NN module from a translation dictionary; and wiring the selected NN modules in accordance with the operator dependencies to generate a translated NN. Some examples determine a starting operator for translation, which is the earliest recognized operator having parameters. Some examples connect inputs of the translated NN to upstream operators of the ML pipeline that had not been translated. Some examples further tune the translated NN using backpropagation. Some examples determine whether an operator is trainable or non-trainable and flag related parameters accordingly for later training.

Abstract: A system for modeling a roof structure comprising an aerial imagery database and a processor in communication with the aerial imagery database. The aerial imagery database stores a plurality of stereoscopic image pairs and the processor selects at least one stereoscopic image pair among the plurality of stereoscopic image pairs and related metadata from the aerial imagery database based on a geospatial region of interest. The processor identifies a target image and a reference image from the at least one stereoscopic pair and calculates a disparity value for each pixel of the identified target image to generate a disparity map. The processor generates a three dimensional point cloud based on the disparity map, the identified target image and the identified reference image. The processor optionally generates a texture map indicative of a three-dimensional representation of the roof structure based on the generated three dimensional point cloud.

Abstract: One variation of a method for automatically capturing data from non-networked production equipment includes: detecting a location of a mobile device within a facility, the mobile device manipulated by an operator while performing a step of an augmented digital procedure at a machine in the facility; estimating a position of a display on the machine relative to a field of view of an optical sensor in the mobile device based on the location of the mobile device and a stored location of the machine within the facility; in response to the position of the display falling within the field of view of the optical sensor, selecting an image captured by the optical sensor; extracting a value, presented on the display, from a region of the image depicting the display; and storing the value in a procedure file for the augmented digital procedure completed at the machine.

Abstract: A method includes receiving, by a model generation engine, an image of a dental arch of a user, executing, by the model generation engine, a machine learning model that is trained to receive the image and output a representation of the image, where in at least one iteration during training, the machine learning model determines a difference between one or more features extracted from an iteration of the representation of the image and a corresponding one or more features extracted from the image, and the method further includes outputting, by the model generation engine, an output representation of the image.

Abstract: The present disclosure describes techniques for creating effects based on facial features. A mesh comprising a set of vertices based on detecting key points of at least one facial part may be created. A mask may be created based on rendering the mesh. A filter may be created by applying a function to a texture based on the mask. A portion of at least one image may be extracted based at least in part on the mask. The portion may correspond to the at least one facial part. An effect may be created on the extracted portion using the filter.

Abstract: Embodiments described herein include an expressive icon system to present an animated graphical icon, wherein the animated graphical icon is generated by capture facial tracking data at a client device. In some embodiments, the system may track and capture facial tracking data of a user via a camera associated with a client device (e.g., a front facing camera, or a paired camera), and process the facial tracking data to animate a graphical icon.

Abstract: An information processing device configured to present a virtual space at a display mounted on the head of a user, the information processing device inputs detection information from a sensor that detects movement of the head of the user. The information processing device generates the virtual space including a body image representing at least a part of a body of the user in response to the detection information. The information processing device inputs correction information from a device operated to perform correction of an angle in a pitch direction of the head of the user. The information processing device corrects a pitch direction angle employed when presenting the virtual space at the display based on the correction information. The information processing device presents the virtual space at the display with the corrected pitch direction angle.

Abstract: The disclosed artificial reality system can provide a user self representation in an artificial reality environment based on a self portion from an image of the user. The artificial reality system can generate the self representation by applying a machine learning model to classify the self portion of the image. The machine learning model can be trained to identify self portions in images based on a set of training images, with portions tagged as either depicting a user from a self-perspective or not. The artificial reality system can display the self portion as a self representation in the artificial reality environment by positioning them in the artificial reality environment relative to the user's perspective in the artificial reality environment. The artificial reality system can also identify movements of the user and can adjust the self representation to match the user's movement, providing more accurate self representations.

Abstract: In a presentation control, another presentation request of another content is accepted from another application while presenting a content of one application, which content is preferentially presented is arbitrated based on a rule definition including: an attribute of the content that defines either a cancellation for withdrawing the presentation request or an on-standby without withdrawing the presentation request; and a constraint equation that defines an exception rule for defining a setting of the content that has lost arbitration as either the on-standby or the cancellation; and one of the contents arbitrated is presented to a presentation area.

Abstract: In an embodiment, a virtual hair coloration system includes: a projector 22 configured to project digital content including a makeup application tutorial onto the user's hair; and a dynamic mapping unit 24; 30 operably coupled to the projector, wherein the dynamic mapping unit is configured to establish a dynamic correspondence between pixels of the projector 22 and features of the user's hair.

Abstract: An image processing method may include steps of obtaining a plurality of image data from an object, generating, from the image data, a three-dimensional (3-D) model having at least two different representation modes, and displaying the generated 3-D model. There is an advantage in that a user can check various information of a 3-D model without changing a representation mode by displaying a 3-D model having at least two different representation modes.

Abstract: In some implementations, the device may include receiving the address of an emergency to a central system. The device may include the central system retrieving an informal two-dimensional rendering of the premises from at least one external data store with the central system analyzing said informal two-dimensional rendering. Moreover, the device may include the central system determining features found on the premises depicted by the two-dimensional rendering. Also, the device may include the central system automatically generating a three-dimensional model of the premises on demand for the first responders using only the two-dimensional rendering of the premises. In addition, the device may include the central system presents multiple views of the three-dimensional rendering containing interactive objects.

Abstract: A system surrounds an area with a first set of display panels. A second set of display panels is positioned above the area, and a third set of display panels is positioned below the area. A subject is positioned within the area and may be on an omnidirectional treadmill within the area. A controller communicates content to the first set of display panels, the second set of display panels, and the third set of display panels that presents a multidimensional scene when displayed. A set of sensors capture sensor data of the subject within the area while content is displayed. One or more of the sensors may be coupled to a repositioning system that repositions sensors so the subject remains in a field of view of different sensors. From sensor data of the subject, a representation of the subject may be generated for insertion into other video content.

Abstract: One variation of a method for automatically capturing data from non-networked production equipment includes: detecting a location of a mobile device within a facility, the mobile device manipulated by an operator while performing a step of an augmented digital procedure at a machine in the facility; estimating a position of a display on the machine relative to a field of view of an optical sensor in the mobile device based on the location of the mobile device and a stored location of the machine within the facility; in response to the position of the display falling within the field of view of the optical sensor, selecting an image captured by the optical sensor; extracting a value, presented on the display, from a region of the image depicting the display; and storing the value in a procedure file for the augmented digital procedure completed at the machine.

Abstract: A crowd-sourced modeling system to perform operations that include: receiving image data that comprises image attributes; accessing a 3D model based on at least the image attributes of the image data, wherein the 3D model comprises a plurality of parts that collectively depict an object or environment; identifying a change in the object or environment based on a comparison of the image data with the plurality of parts of the 3D model, the change corresponding to a part of the 3D model from among the plurality of parts; and generating an update to the part of the 3D model based on the image attributes of the image data.

Abstract: Systems and methods are provided that are directed to generating video sequences including physio-realistic avatars. In examples, an albedo for an avatar is received, a sub-surface skin color associated with the albedo is modified based on physiological data associated with physiologic characteristic, and an avatar based on the albedo and the modified sub-surface skin color is rendered. The rendered avatar may then be synthesized in a frame of video. In some examples, a video including the synthesized avatar may be used to train a machine learning model to detect a physiological characteristic. The machine learning model may receive a plurality of video segments, where one or more of the video segments includes a synthetic physio-realistic avatar generated with the physiological characteristic. The machine learning model may be trained using the plurality of video segments. The trained model may be provided to a requesting entity.

Abstract: Provided is an apparatus for preventing a content leak, including: a view request receiving unit for receiving a content view request for view target content to obtain content viewer information; a marker form determining unit for determining a marker form regarding a location of the view target content where a marker for each character is added, according to the content viewer information; a marking method determining unit for determining a marking method regarding a type or order of markers added to the marker form; and a modified content generating unit for generating modified content by adding, to the view target content, one or more markers corresponding to the content viewer information, based on the marker form and the marking method.