Adjusting faces displayed in images

摘要

A computing device can acquire a set of images, each image including at least a portion of a user's face. The images can be acquired using one or more cameras and/or from an image library/database associated with the user. Based on the images including the user's face (or portions thereof), a virtual representation for the user's face can be generated. The device can subsequently receive or identify an image including a facial representation (e.g., face or portion thereof) to be adjusted. The device can analyze the image including the facial representation and determine that the facial representation sufficiently matches the virtual representation. Using the virtual representation, (at least a portion of) the face can be adjusted. For example, one or more variations or details associated with the user's face, which are provided via the virtual representation, can be used to replace, improve, or otherwise modify the face in the image.

主权项

1. A computing device for adjusting faces in images, the computing device comprising:
a camera; at least one processor; and a memory including instructions that, when executed by the at least one processor, cause the computing device to:
acquire a plurality of high resolution images, each high resolution image of the plurality of high resolution images including at least a portion of a first representation of a face, wherein at least some of the plurality of high resolution images are acquired using the camera;generate a set of manifolds representing the first representation of the face based, at least in part, on variations of the portion of the first representation of the face included in the plurality of images, the set of manifolds provide information about one or more displayable variations associated with the face and include at least a low-dimensional manifold that represents a downscaled version of the first representation of the face;acquire a subsequent image that includes a second representation of the face;determine that at least portions of the second representation of the face included in the subsequent image match, within an allowable deviation, the downscaled version of the first representation of the face;select at least one displayable variation from the one or more displayable variations associated with the face to be applied to the second representation of the face; andgenerate an adjusted second representation based at least in part on the second representation of the face included in the subsequent image and based at least in part by applying the at least one displayable variation to the subsequent image.