Augmented reality self-portraits

A system comprising:

• one or more processors;
• memory coupled to the one or more processors and storing instructions that, when executed, cause the one or more processors to perform operations comprising:
• capturing, using a camera of a mobile device, image data of a subject in a real-world environment;
• capturing, using one or more sensors of the mobile device, depth data indicating a distance of the subject from the camera in the real-world environment, the depth data including first depth data and second depth data that are distinct from one another;
• generating a matte from the depth data, comprising:
• projecting the depth data into a first binary depth matte including the first depth data, the first binary depth matte having a first foreground region and a first background region;
• projecting the depth data into a second binary depth matte including the second depth data, the second binary depth matte having a second foreground region and a second background region;
• obtaining, from the first binary depth matte, inner contour data corresponding to an inner contour of a foreground subject;
• obtaining, from the second binary depth matte, outer contour data corresponding to an outer contour of the foreground subject, the inner contour data and the outer contour data bounding a blended region of the depth data;
• and
• generating a matte by combining the inner contour data and the outer contour data and including depth data in the blended region in one of a foreground region or a background region of the matte, wherein the foreground region of the matte includes the first foreground region and the second foreground region, and the background region of the matte includes the first background region and the second background region;
• generating a composite image data, using at least the image data and the matte;
• and
• causing display of the composite image data on a display of the mobile device.

One or more non-transitory storage media storing instructions that, when executed, cause one or more processors to perform operations comprising:

• capturing, using a camera of a mobile device, image data of a subject in a real-world environment;
• capturing, using one or more sensors of the mobile device, depth data indicating a distance of the subject from the camera in the real-world environment, the depth data including first depth data and second depth data that are distinct from one another;
• generating a matte from the depth data, comprising:
• projecting the depth data into a first binary depth matte including the first depth data, the first binary depth matte having a first foreground region and a first background region;
• projecting the depth data into a second binary depth matte including the second depth data, the second binary depth matte having a second foreground region and a second background region;
• obtaining, from the first binary depth matte, inner contour data corresponding to an inner contour of a foreground subject;
• obtaining, from the second binary depth matte, outer contour data corresponding to an outer contour of the foreground subject, the inner contour data and the outer contour data bounding a blended region of the depth data;
• and
• generating a matte by combining the inner contour data and the outer contour data and including depth data in the blended region in one of a foreground region or a background region of the matte, wherein the foreground region of the matte includes the first foreground region and the second foreground region, and the background region of the matte includes the first background region and the second background region;
• generating a composite image data, using at least the image data and the matte;
• and
• causing display of the composite image data on a display of the mobile device.