Object refinement using many data sets

摘要

Digitizing objects in a picture is discussed herein. A user presents the object to a camera, which captures the image comprising color and depth data for the front and back of the object. The object is recognized and digitized using color and depth data of the image. The user's client queries a server managing images uploaded by other users for virtual renditions of the object, as recognized in the other images. The virtual renditions from the other images are merged with the digitized version of the object in the image captured by the user to create a composite rendition of the object.

主权项

1. One or more computer hardware storage devices having computer-executable instructions embodied thereon that, when executed by one or more processors, cause the one or more processors to perform operations, the operations comprising:
receiving an image of an object, the image having been captured by a first user using a camera associated with a client device; creating a virtual representation of the object based on the image; performing object recognition on the image to recognize the object; in response to recognizing the object from the image, querying a server-side database containing a plurality of three-dimensional renditions of objects to identify one or more three-dimensional renditions of the object created from other images captured by other users; receiving the one or more three-dimensional renditions in response to the querying; merging the virtual representation with the one or more three-dimensional renditions to create a composite rendition of the object; and causing a display of the composite rendition of the object on a display device associated with the client device.