A transaction session is established directly or indirectly between a wearable processing device and a cloud-based server of a store. During the session, items are recognized by placing the items in a field-of-view of a front-facing camera of the device. Item recognition does not require item barcode identification. A depth sensor associated with the camera creates a three-dimensional mapping of a given item. The mapping and image features are processed to uniquely identify the item even when the item is associated with a same category of items. Customer input during the session can be achieved through gestures (hand, eyes, head, fingers, etc.) and/or voice commands. The customer input is translated and mapped into transaction interface commands/options and processed during the session to select items, delete items, view a transaction receipt, identify a quantity of items, obtain item details for a given item, etc.

In an exemplary embodiment, software made in accordance with the present invention displays a marketplace interface, which displays at least a portion of a CAD model and a set ofmarketplace tool selectors to a user such that the user can manipulate the tool selectors to interact with an electronic marketplace. The marketplace interface may include a spectrum interface designed and configured to allow the user to selectively augment the marketplace interface with additional functionality. Various corresponding and related systems, methods, and software are described.

Techniques for providing an in-place scrolling feature are described herein. Input via a user interface may be received to update first images of first items to second images of second items where the first images are presented in a focus location of the user interface. Feature vectors may be calculated for each image associated with the first items and the second items using a neural network algorithm. The feature vectors may include a plurality of values that represent each image of the first items and the second items. Candidate images may be determined from the second images based on a distance in a feature vector space between the feature vectors of the candidate images and the feature vectors of the second images. The user interface may be updated to transition from presenting the first images to a portion of the candidate images in the focus location of the user interface.

A planar placement system can generate virtual surfaces (e.g., floors, walls) to simulate items in an augmented reality display. The system can generate the virtual surfaces using image feature tracking and plane intersection approaches that create an accurate visual simulation. The items simulated can be variable items that have unit data (e.g., rolls of wallpaper) that can be simulated on the virtual surfaces, and unit data can be displayed and updated in real time or near real time on a mobile device, such as a user's smartphone.

Embodiments of the present invention provide a computer system a computer program product, and a method that comprises predicting details associated with collected data of an activity by generating a simulated activity based on a result associated with a plurality of attributes within the collected data associated with the activity; simulating the activity within a virtual reality environment by generating virtual items for assistance with a performance of the simulated activity within the virtual reality environment; in response to receiving user feedback for each generated virtual item based on the simulated activity, generating a need-based inventory from user input based on an analysis of the received user feedback for each respective item associated with the simulated activity within the virtual environment; and automatically obtaining each respective item within the generated need-based inventory.

Systems and methods are provided that allow customers to collaborate with vehicle accessory manufacturers to design accessories in an augmented reality (AR) environment and manufacture the designed accessories through a rapid manufacturing technique, such as 3D printing. The disclosed systems and methods allow progression from augmented reality-designed accessories to 3D printed designs manufactured either at the dealer or at a regional printing center. The 3D printed designs may be installed on the customer's vehicle, enabling a dealership to provide tailor-made, custom products designed through an AR application.

Systems and method for selecting option packs using guided selection via base designs. A processor may display visualizations that represent types of option packs associated with the industrial device assembly. Each visualization may include a slide visualization that moves selectable levels. The selectable levels may include a first selectable level and a second selectable level. For instance, the first selectable level may correspond to a first rating related to a respective operation of a respective type of option pack. After receiving a first selection of a type of option pack and a second selection representative of a selectable level, the processor may identify an option pack that corresponds to the first and second selections. In turn, the processor may generate an updated base design and layout based on the identified option pack.

In order to facilitate machine learning for prediction using distinct dataset types, systems and methods include collecting content information from archived websites databases. Collecting historical event information from online sources, where the historical event information is associated with a plurality of historical events. Generating event-dependent products training datasets based on the content information and the historical event information, where the event-dependent content training datasets defines for content historical events that are associated with attributes of the content, attribute change of the content, or both. Training an attribute prediction machine learning model based on the event-dependent content training datasets. Applying the trained attribute prediction machine learning model to additional event information to predict, for content, a future attribute estimate, a future attribute change estimate, or both. Causing to display an indication representative of the future attribute estimate, the future attribute change estimate, or both.

Systems and methods for providing a personalized visual display of multiple products are provided. A described method includes receiving product information for a set of multiple products and user information for a particular user or user device and selecting a plurality of the multiple products estimated to be most relevant to the particular user or user device based on the product information for the set of multiple products and the user information for the particular user or user device. The method further includes generating a personalized visual display of the selected products including product images for multiple of the selected products. All of the products in the personalized visual display may be associated with the same content provider. The method further includes causing the personalized visual display to be presented via the user device.

Provided are systems and methods to perform colour extraction from swatch images and to define new images using extracted colours. Source images may be classified using a deep learning net (e.g. a CNN) to indicate colour representation strength and drive colour extraction. A clustering classifier is trained to use feature vectors extracted by the net. Separately, pixel clustering is useful when extracting the colour. Cluster count can vary according to classification. In another manner, heuristics (with or without classification) are useful when extracting. Resultant clusters are evaluated against a set of (ordered) expected colours to determine a match. Instances of standardized swatch images may be defined from a template swatch image and respective extracted colours using image processing. The extracted colour may be presented in an augmented reality GUI such as a virtual try-on application and applied to a user image such as a selfie using image processing.