Abstract: Techniques for generating one or more images of a space in one or more target styles using a generative machine learning model is described. Furnishing products similar to furnishings detected in the generated images are identified in a catalog of furnishing products and information about the identified furnishing products is provided to a user via a user interface. Also describes are techniques for generating modified images of a space using a generative machine learning model. Furnishing products similar to alternative furnishings in modified image are identified in the catalog of furnishing products and information about the identified furnishing products is provided to a user via a user interface.

Abstract: Techniques for generating images of furniture and using the generated images for image-based search. The techniques include obtaining a first image depicting first furniture, generating, using the first image and a neural network model, a second image depicting second furniture different from the first furniture, searching for one or more images of furniture similar to the second furniture using the second image to obtain search results comprising a third image of furniture, and outputting the third image.

Abstract: Techniques for generating product images in a user's space. The techniques include: receiving, by a mobile device having a camera, information indicating a position in the user's space at which to place a proxy product model serving as a proxy for a product of a first type; generating, using augmented reality (AR), a visualization of the proxy product model, at the indicated position, in the user's space; receiving information indicating dimensions for the proxy product model; guiding, using AR, the user to capture one or more images of the user's space, with the mobile device, at one or more respective camera positions and/or orientations relative to the indicated position, in the user's space; obtaining, based on the information indicating the dimensions for the proxy product model and the one or more images of the user's space, at least one image of at least one product of the first type in the user's space; and displaying the at least one image of the at least one product.

Abstract: Some embodiments provide a mobile device configured to guide a user, via an augmented reality (AR) interface generated by the mobile device, to capture images of the physical object using a camera of the mobile device. The mobile device may be configured to obtain boundary information indicative of a boundary enclosing the physical object (e.g., a box enclosing the physical object). The mobile device may be configured to use the boundary information to determine positions from which the user is to capture images of the physical object. The mobile device may be configured to guide the user to capture the images using the AR interface by guiding the user to each of the positions in the AR interface (e.g., by generating on or more GUI elements in the AR interface that indicate a position from which the user is to capture an image).

Abstract: Some embodiments provide a mobile device configured to guide a user, via an augmented reality (AR) interface generated by the mobile device, to capture images of the physical object using a camera of the mobile device. The mobile device may be configured to obtain boundary information indicative of a boundary enclosing the physical object (e.g., a box enclosing the physical object). The mobile device may be configured to use the boundary information to determine positions from which the user is to capture images of the physical object. The mobile device may be configured to guide the user to capture the images using the AR interface by guiding the user to each of the positions in the AR interface (e.g., by generating on or more GUI elements in the AR interface that indicate a position from which the user is to capture an image).

Abstract: Some embodiments provide a mobile device configured to guide a user, via an augmented reality (AR) interface generated by the mobile device, to capture images of the physical object using a camera of the mobile device. The mobile device may be configured to obtain boundary information indicative of a boundary enclosing the physical object (e.g., a box enclosing the physical object). The mobile device may be configured to use the boundary information to determine positions from which the user is to capture images of the physical object. The mobile device may be configured to guide the user to capture the images using the AR interface by guiding the user to each of the positions in the AR interface (e.g., by generating on or more GUI elements in the AR interface that indicate a position from which the user is to capture an image).

Abstract: Some embodiments provide a mobile device configured to guide a user, via an augmented reality (AR) interface generated by the mobile device, to capture images of the physical object using a camera of the mobile device. The mobile device may be configured to obtain boundary information indicative of a boundary enclosing the physical object (e.g., a box enclosing the physical object). The mobile device may be configured to use the boundary information to determine positions from which the user is to capture images of the physical object. The mobile device may be configured to guide the user to capture the images using the AR interface by guiding the user to each of the positions in the AR interface (e.g., by generating on or more GUI elements in the AR interface that indicate a position from which the user is to capture an image).