Displaying glasses with recorded images
AssigneeDitto Technologies, Inc.
InventorsSergey Surkov, Dmitry Kornilov
Life of this patent
Estimating the term…
Abstract
Processing a set of images is disclosed, including: receiving a set of images; and searching for a representation of a user's face associated with the set of images and a plurality of sets of extrinsic information corresponding to respective ones of at least a subset of the set of images. Rendering a glasses frame is disclosed, including: receiving a selection associated with the glasses frame; rendering the glasses frame using at least a representation of a user's face and a set of extrinsic information corresponding to an image in a recorded set of images; and overlaying the rendered glasses frame on the image.
Claims28
A system for processing a set of images, comprising:
- a processor configured to:
- receive a set of images, wherein the set of images corresponds to a user's face at one or more orientations;
- and
- search for a representation of the user's face associated with the set of images and a plurality of sets of extrinsic information corresponding to respective ones of at least a subset of the set of images, wherein to search for the representation of the user's face and the plurality of sets of extrinsic information comprises the processor being configured to:
- determine a plurality of candidate representations of the user's face associated with the set of images;
- determine a plurality of candidate sets of extrinsic information associated with an image of the set of images, wherein each of at least a subset of the plurality of candidate sets of extrinsic information describes the user's face at an orientation associated with the image;
- select a representation of the user's face from the plurality of candidate representations of the user's face to correspond to the set of images;
- select a set of extrinsic information from the plurality of candidate sets of extrinsic information to correspond to the image;
- and
- create an image of a rendered item corresponding to the image, wherein creating the image of the rendered item is based at least in part on a representation of an item, the representation of the user's face, and the set of extrinsic information that corresponds to the image;
- and
- a memory coupled to the processor and configured to provide the processor with instructions.
A method for processing a set of images, comprising:
- receiving a set of images, wherein the set of images corresponds to a user's face at one or more orientations;
- and
- searching for a representation of the user's face associated with the set of images and a plurality of sets of extrinsic information corresponding to respective ones of at least a subset of the set of images, wherein searching for the representation of the user's face and the plurality of sets of extrinsic information comprises:
- determining a plurality of candidate representations of the user's face associated with the set of images;
- determining a plurality of candidate sets of extrinsic information associated with an image of the set of images, wherein each of at least a subset of the plurality of candidate sets of extrinsic information describes the user's face at an orientation associated with the image;
- selecting a representation of the user's face from the plurality of candidate representations of the user's face to correspond to the set of images;
- selecting a set of extrinsic information from the plurality of candidate sets of extrinsic information to correspond to the image;
- and
- creating, using a processor, an image of a rendered item corresponding to the image, wherein creating the image of the rendered item is based at least in part on a representation of an item, the representation of the user's face, and the set of extrinsic information that corresponds to the image.
A system for rendering a glasses frame, comprising:
- a processor configured to:
- receive a selection associated with the glasses frame;
- create an image of a rendered glasses frame corresponding to a recorded image in a set of recorded images based at least in part on a representation of the glasses frame, a representation of a first face, and a set of extrinsic information corresponding to the recorded image, wherein the set of recorded images corresponds to a second face at one or more orientations, wherein the set of extrinsic information corresponding to the recorded image describes the second face at an orientation associated with the recorded image, wherein to create the image of the rendered glasses frame includes to transform the representation of the glasses frame to correspond to the second face at the orientation associated with the recorded image;
- and
- present the image, including by overlaying the image of the rendered glasses frame on the recorded image;
- and
- a memory coupled to the processor and configured to provide the processor with instructions.
A method for rendering a glasses frame, comprising:
- receiving a selection associated with the glasses frame;
- creating, using a processor, an image of a rendered glasses frame corresponding to a recorded image in a set of recorded images based at least in part on a representation of the glasses frame, a representation of a first face, and a set of extrinsic information corresponding to the recorded image, wherein the set of recorded images corresponds to a second face at one or more orientations, wherein the set of extrinsic information corresponding to the recorded image describes the second face at an orientation associated with the recorded image, wherein to create the image of the rendered glasses frame includes to transform the representation of the glasses frame to correspond to the second face at the orientation associated with the recorded image;
- and
- present the image, including by overlaying the image of the rendered glasses frame on the recorded image.
Dependencies are inferred from the claim text.