Abstract: A computer-implemented is disclosed. The method includes: obtaining three-dimensional geometric scan data and first texture data for a defined space, the defined space defined by interior surfaces including at least one wall; detecting an object occluding a first one of the interior surfaces of the defined space based on the three-dimensional geometric scan data; in response to detecting the object: identifying a corresponding portion of the first interior surface occluded by the detected object; and estimating texture data for the corresponding portion of the first interior surface based on the first texture data for the defined space, and outputting texture data for the interior surfaces based on the first texture data for the defined space and the estimated texture data for the corresponding portion of the first interior surface.

Abstract: A computer-implemented method is disclosed. The method includes: receiving a search query for a search of items in a database; providing, to a large language model (LLM), an input including the search query and instructions to generate query enhancement text for the search query; combining the search query and the query enhancement text output by the LLM; obtaining a query vector embedding based on the combined search query and the query enhancement text; and performing a search of an embedding space associated with the database using the query vector embedding to identify one or more search results.

Abstract: Methods and systems for indicating a resource usage parameter for prompting a large language model (LLM) are described. A user input is received, from an electronic device, for generating a prompt to a LLM. A prompt resource usage parameter is computed based on the user input. A trained resource prediction model is used to generate a predicted response resource usage parameter for a response from the LLM, based on the user input. A total resource usage parameter is computed, based on the prompt resource usage parameter and the predicted response resource usage parameter. A representation of the total resource usage parameter is communicated to the electronic device, to cause the electronic device to provide an output of the representation of the total resource usage parameter.

Abstract: A system and method for generating a three-dimensional (3D) model of an object. The method includes: determining that a first portion of an object has a lower priority; obtaining a plurality of images of the object; and training a three-dimensional model of the object using a training algorithm that processes the plurality of images as training data to generate and refine Gaussian splats defining the three-dimensional model. Obtaining the plurality of images includes obtaining images including views of the first portion of the object from a first concentration of viewpoints; and obtaining images including views of the another portion of the object from a second concentration of viewpoints, the first concentration being less than the second concentration.

Abstract: A computer-implemented is disclosed. The method includes: receiving a search query input; generating input enhancement data based on the search query input, the generating comprising processing the search query input using a large language model (LLM); causing to transform at least one of the search query input or the input enhancement data into a first vector embedding; and performing a search of an embedding space based on the first vector embedding.

Abstract: Described herein are systems and methods for generating and transmitting media data feeds location-based privacy settings. Embodiments generate, store, and reference location-based privacy settings that instruct the computing device to generate obfuscations in the media data. The obfuscations may include computer-generated or user gesture-generated obfuscation regions that instruct the computing device to apply the obfuscations to portions of the video feed. The computing device may be pre-configured to recognize certain objects or regions (or portions thereof) and remove, blur, or substitute them from the live video stream or 3D data according to privacy settings. The privacy settings may be relative to the location in which the user and computing device are situated. In operation, the computing device may determine the location and then apply the location-specific privacy settings to obfuscate a portion of the video feed while being generated and transmitted.

Abstract: Methods and systems for enforcing restrictions against actions by a software agent are described. A request is received from a software agent to cause execution of an attempted action. A policy header is extracted from the request. Data representing an instructed task assigned to the software agent is extracted from the policy header. The attempted action is selectively caused to be executed based on whether the attempted action is suitable to a semantic meaning of the instructed task.

Abstract: A textual description that includes a body of unstructured text is received. Using a rating model configured to output a rating based on a degree of similarity of the received textual description and each of a set of selected textual descriptions, a rating is generated based on the received textual description. The rating model to also used to generate a suggested modification of the received textual description that, when applied to the received textual descriptions, changes the rating of the received textual description. An indication of the suggested modification can be output to a user.

Abstract: Methods and systems for prompting a large language model (LLM) to process inputs from multiple user elements to generate a revised block of text are described. One or more text-editing instructions related to respective one or more selected text portions in a block of text are received. A prompt is generated for a LLM to generate a revised block of text, the prompt including at least a portion of an annotated block of text, the annotated block of text including each text-editing instruction inserted into the block of text relative to each respective selected text portion. The prompt is provided to the LLM and a revised block of text is received and outputted.

Abstract: Systems and methods are provided for the generation of augmented reality (AR) scenery for a physical item. The AR scenery allows a customer to interact with the physical item in the real-world, while also allowing the customer to view the physical item in a virtual setting that may be tailored to the customer and/or to the physical item. According to an embodiment, an AR scene is generated for a physical item. The AR scene includes computer-generated scenery and at least a portion of an image of the physical item, where the computer-generated scenery is based on information associated with the user and/or the physical item. The AR scene is then displayed on a device.

Abstract: Methods and systems for indicating a resource usage parameter for prompting a large language model (LLM) are described. A user input is received, from an electronic device, for generating a prompt to a LLM. A prompt resource usage parameter is computed based on the user input. A trained resource prediction model is used to generate a predicted response resource usage parameter for a response from the LLM, based on the user input. A total resource usage parameter is computed, based on the prompt resource usage parameter and the predicted response resource usage parameter. A representation of the total resource usage parameter is communicated to the electronic device, to cause the electronic device to provide an output of the representation of the total resource usage parameter.

Abstract: In an augmented reality (AR) experience, virtual content may be rendered at a particular position within a 3D spatial map and overlaid onto a view of the real-world space. There may be scenarios in which the user wants to limit a 3D model to being rendered within a particular subspace of the space defined by the 3D spatial map. Computer-implemented methods are disclosed that include receiving input defining a subspace of a 3D spatial map of a real-world space. A set of 3D models may then be filtered to identify a subset of the 3D models that fit within the subspace defined by the input. AR content including a render of a particular 3D model from the subset and overlaid onto a view of the real-world space in a position within the subspace may be output for display.

Abstract: Described herein are systems and methods for generating and transmitting media data feeds location-based privacy settings. Embodiments generate, store, and reference location-based privacy settings that instruct the computing device to generate obfuscations in the media data. The obfuscations may include computer-generated or user gesture-generated obfuscation regions that instruct the computing device to apply the obfuscations to portions of the video feed. The computing device may be pre-configured to recognize certain objects or regions (or portions thereof) and remove, blur, or substitute them from the live video stream or 3D data according to privacy settings. The privacy settings may be relative to the location in which the user and computing device are situated. In operation, the computing device may determine the location and then apply the location-specific privacy settings to obfuscate a portion of the video feed while being generated and transmitted.

Abstract: A computer-implemented method is disclosed. The method includes: receiving an indication of a first point on a three-dimensional (3D) model; determining a second point in a texture map of the 3D model that corresponds to the first point; performing segmentation of the texture map for identifying portions of the texture map that are related to the second point; and outputting a 3D representation of the identified related portions of the texture map.

Abstract: A textual description that includes a body of unstructured text is received. Using a rating model configured to output a rating based on a degree of similarity of the received textual description and each of a set of selected textual descriptions, a rating is generated based on the received textual description. The rating model to also used to generate a suggested modification of the received textual description that, when applied to the received textual descriptions, changes the rating of the received textual description. An indication of the suggested modification can be output to a user.

Abstract: In virtual reality (VR) and augmented reality (AR), eye tracking may be performed to determine the user's gaze direction. The gaze direction may be used to enhance user interaction. However, when a user gazes in a particular direction, it could sometimes be the case that there are multiple items located in that gaze direction, each at a different depth. The gaze of direction alone might not be indicative of the item at which the user is looking. Therefore, in some embodiments, to try to further enhance user interaction, a gaze depth of the gaze may be determined. Some embodiments are directed to performing eye tracking to detect a gaze depth of a human's gaze and modifying a user interface (UI) responsive to a change in the gaze depth.

Abstract: A computer-implemented is disclosed. The method includes: obtaining image data from a plurality of cameras providing views of a designated assembly zone; updating a three-dimensional model of an assembly of a structure based on the obtained image data; and determining a location of a first component of the structure based on the updated three-dimensional model of the assembly.

Abstract: The present disclosure describes a technical solution that enables a trained large language model (LLM) to generate a revised text in a manner that enables the LLM to preserve formatting that was present in the original text. When a text-editing instruction is received for a text passage having a formatting tag, the text passage is processed to identify the formatting tag in the text passage. The LLM is prompted to generate a revised text passage, using a prompt that includes the text-editing instruction and that also includes a formatting-specific instruction to format the revised text passage using the formatting tag in the revised text passage. The revised text passage is received and caused to be displayed based on the formatting tag, such that the formatting of the original text is maintained.

Abstract: Methods and systems for prompting a large language model (LLM) to generate a description of an object with indications of any unsubstantiated information are disclosed. A prompt is generated to a LLM to generate a description of an object, where the prompt includes one or more object attributes to include in the generated description. The prompt also includes an instruction for the LLM to annotate any portions of the generated description that are, involve, and/or include unsubstantiated information according to a defined format. The prompt is provided to the LLM and the generated description is received. The generated description is parsed to identify, based on the defined format, one or more annotated portions indicating unsubstantiated information. The generated description is presented for display via a user device.

Abstract: The present disclosure is related to a system and method for generating a three-dimensional (3D) model of an object. The method includes: determining that a first portion of an object has a lower priority; obtaining a plurality of images of the object; and training a three-dimensional model of the object using a training algorithm that processes the plurality of images as training data to generate and refine Gaussian splats defining the three-dimensional model. Obtaining the plurality of images includes obtaining images including views of the first portion of the object from a first concentration of viewpoints; and obtaining images including views of the another portion of the object from a second concentration of viewpoints, the first concentration being less than the second concentration.