Content aware image editing

摘要

An image is displayed using a computer system. The image includes contents that have a visible feature therein at a first location. A first input is received that includes a user movement of at least the visible feature from the first location. During the user movement, the first location is synthesized with content from where the visible feature is currently located. A second input is received that specifies an end of the user movement at a second location. A source area in the image is identified. The method further includes identifying additional contents within the source area. The additional contents are identified using a patch-based optimization algorithm on the image. The method further includes updating the image to have the additional contents at least in the first location.

主权项

1. A computer-implemented method for modifying an image, the method comprising:
displaying the image using a computer system, the image comprising contents that have a feature therein at a first location; selecting a region of the image containing the feature using a selection mark that borders the region; receiving a first input comprising a user movement, from the first location, of the selection mark corresponding to the feature; updating, during the user movement of the selection mark away from the first location, the region in the first location of the image with content from where the selection mark is currently located to replace the feature; receiving a second input that specifies an end of the user movement of the selection mark at a second location; identifying additional contents for the first location based at least in part upon the second location and an area around the first location, the additional contents identified using a patch-based optimization algorithm on the image; and updating the image to have the additional contents at least in the first location.