Abstract: A virtual model placement system can generate virtual floors and virtual walls to correspond to a real-world environment. Virtual items such as doors, windows, lamps, can be placed on the generated virtual walls and the system can generate dynamic updates of the placed items in response to movement by a user's device (e.g., a smartphone moving from right to left). The virtual items can be initially placed as primitives and then rendered to new positions upon the user selecting a render or lock instruction.

Abstract: An object can be simulated in an environment using a three-dimensional model of the object as viewed from a virtual camera at a position in the environment. The position in the environment can be determined using user input or through visual analysis of a video recording. Composite frames depicting the modeled object may be played back based on the orientation of the playback device.

Abstract: A description-based search system can generate descriptions from item properties (e.g., item attribute) combinations. A user search request can be matched to one or more closest matching descriptions. The matching descriptions can be submitted as a query to a datastore, which returns results for display to the user. Additionally, the description based search system can link selected descriptions to pre-linked one or more pre-linked results.

Abstract: 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.

Abstract: A system for replacing physical items in images is discussed. A depicted item can be selected and removed from an image via image mask data and pixel merging techniques. Virtual light source positions can be generated based on real-world light source data from the image. A rendered simulation of a virtual item can then be integrated into the image to create a modified image for display.

Abstract: Embodiments of the present invention, as presented herein, relate to an augmented reality application-based service, which facilitates the sharing of a design request, by a first end-user, via a messaging application or social networking service. The design request may be included as part of a content posting published to a feed and shared with members of a social networking service, and enables the members to select and position products (e.g., images of household items) using a room design application, such that the selected and positioned products can be rendered in a live AR viewing session by the first end-user.

Abstract: Described herein is an augmented reality application-based service, which facilitates techniques for aiding a first end-user (e.g., a room designer) with the selection and placement of objects (e.g., images of home furnishing and related products) in an augmented reality scene that is being, or has been, generated via a mobile computing device that is remote from the first end-user, such that a second end-user (e.g., a potential consumer) operating the mobile computing device can view objects, in the augmented reality scene, as placed by the first, remote end-user.

Abstract: An approach for simulating items in an environment, such as a room, is disclosed. A package file can store information including an image of the environment and metadata including an identifier that uniquely identifies a selected image. The package file can be used to regenerate a simulation of the item arranged over the image of the environment. Later changes can be made to the simulation of the item by accessing the metadata.

Abstract: A virtual model placement system can generate virtual floors and virtual walls to correspond to a real-world environment. Virtual items such as doors, windows, lamps, can be placed on the generated virtual walls and the system can generate dynamic updates of the placed items in response to movement by a user's device (e.g., a smartphone moving from right to left). The virtual items can be initially placed as primitives and then rendered to new positions upon the user selecting a render or lock instruction.

Abstract: Disclosed are various embodiments for simulating one or more virtual objects (e.g., renders) based on characteristics of detected surfaces. Mask data may be generated which can be used to delineate borders depicted in a given image. The mask data can be refined based on a quantity of depicted image features (e.g., edges). The mask data can be used to generate one or more planes on which virtual items can be applied and rendered.

Abstract: Disclosed are various embodiments for simulating one or more virtual objects (e.g., renders) specified spatial areas of a real-world environment. Options of item models for modeling in a given spatial area can be filtered based on specified dimensions and identified features of an image of a given spatial area. A selected item model can be rendered. and continuously updated on a display device as the client device is physical moved.

Abstract: A flat scene modeler can more accurately simulate items in environments by receiving instructions to model a given 2D depiction of an item in a given 2D depiction of a room. The flat scene modeler can analyze the instructions and arrange a 3D model of the item in a 3D model of the room. Textures, materials, lighting, and virtual camera position are modified per the received instructions. Two-dimensional images rendered from the 3D models can be provided to a user as a simulation.

Abstract: An improved approach for returning aesthetically relevant search results is disclosed. A training set of images (e.g., designer-created images) is used to train a detection engine that detects items in the images as features. A classification engine is configured to analyze the features and generate classification indices for the features. A user can select an item, and the classification index for the feature corresponding to the item is retrieved. The classification index is used to identify result images, which can be returned ranked according user action data and other parameters, such as style.

Abstract: A platform allows experts, for example home improvement professionals, to upload their portfolios, i.e. content such as photos, videos, text, and sound, to a publicly available resource, such as a Web browser accessible, network based commerce system. Users may then browse the content, for example by room, style, and metro area. The content is arranged in collections that are in part passively sorted, based upon user relevance. Tags are shown on objects, for example within photos, for which there is more information. In the case of a movable display device, the tags can simulate the physics of real tags, for example they can move back and forth when the device is shaken. In another embodiment, a snap point is set to impart either a scrolling transition or a step transition between display pages, based upon user scroll activity.

Abstract: A platform allows experts, for example home improvement professionals, to upload their portfolios, i.e. content such as photos, videos, text, and sound, to a publicly available resource, such as a Web browser accessible, network based commerce system. Users may then browse the content, for example by room, style, and metro area. The content is arranged in collections that are in part passively sorted, based upon user relevance. Tags are shown on objects, for example within photos, for which there is more information. In the case of a movable display device, the tags can simulate the physics of real tags, for example they can move back and forth when the device is shaken. In another embodiment, a snap point is set to impart either a scrolling transition or a step transition between display pages, based upon user scroll activity.

Abstract: Disclosed are various embodiments for simulating one or more virtual objects (e.g., renders) on real-world walls of a room. Some embodiments detect a floor of the room, detect lack of movement of a device, determine an angle of the client device, and place a virtual object in a virtual environment. As the device is moved, a virtual camera can be continuously updated to correspond to movement of the device.

Abstract: Disclosed are various embodiments for simulating one or more virtual objects (e.g., renders) based on characteristics of detected surfaces. Mask data may be generated which can be used to delineate borders depicted in a given image. The mask data can be refined based on a quantity of depicted image features (e.g., edges). The mask data can be used to generate one or more planes on which virtual items can be applied and rendered.

Abstract: An object can be simulated in an environment using a three-dimensional model of the object as viewed from a virtual camera at a position in the environment. The position in the environment can be determined using user input or through visual analysis of a video recording. Composite frames depicting the modeled object may be played back based on the orientation of the playback device.

Abstract: Disclosed are various embodiments for simulating one or more virtual objects (e.g., renders) in specified spatial areas of a real-world environment. Options of item models for modeling in a given spatial area can be filtered based on specified dimensions and identified features of an image of a given spatial area. A selected item model can be rendered and continuously updated on a display device as the client device is physical moved.

Abstract: An approach for simulating items in an environment, such as a room, is disclosed. A package file can store information including an image of the environment and metadata including an identifier that uniquely identifies a selected image. The package file can be used to regenerate a simulation of the item arranged over the image of the environment. Later changes can be made to the simulation of the item by accessing the metadata.