System and method for image composition using non-destructive editing model and fast gradient solver
Systems and methods for interactive image compositing may integrate image searching using visual search criteria (e.g., color, composition, tonal distribution, or lighting effects), non-destructive image compositing, and high-performance rendering using a fast gradient solver to provide an efficient workflow for users. An image compositing application, executable by a CPU and/or GPU, may employ a sketch-and-refine approach, whereby a user draws a rough perimeter around an object of interest in an image and (following an initial application of the fast gradient solver to a lower-resolution version of the image) receives a preview of how it would fit into a composition. The fast gradient solver may differentiate between the object and its background by applying artificial intelligence techniques and/or dependent on user-supplied hints. In a second stage, the fast gradient solver may refine the solution for a final rendering of the composite image by operating on successively higher-resolution versions of the image.
1. A method comprising:
receiving an input to initiate a preview of a composite image that includes an object extracted from one image as included in another image;
displaying the composite image in a first resolution during the preview of the composite image; and
subsequent to displaying the composite image during the preview, rendering a refined version of the composite image as a result of a compositing operation, the refined version of the composite image being in a second resolution that is higher than the first resolution displayed during the preview of the composite image.
2. A method as described in claim 1 , further comprising displaying a copy of the one image.
3. A method as described in claim 2 , wherein the displaying is performed responsive to selection of the one image.
4. A method as described in claim 2 , wherein the displaying is performed such that the copy of the one image is displayed as superimposed over the other image.
5. A method as described in claim 1 , wherein the display of the preview includes merging the object and the other image to generate the preview of the composite image such that the object appears to be inserted in the other image.
6. A method as described in claim 1 , wherein the object is extracted through identification of a perimeter drawn around the object in a graphical user interface.
7. A method as described in claim 1 , wherein the object is extracted by distinguishing pixels as belonging to a foreground object or a background object.
8. A method as described in claim 7 , wherein the distinguishing is performed based at least in part on a distance of the pixels from pixels along a perimeter, color values of pixels, intensity values of pixels, or gradient values of pixels.
9. A method as described in claim 1 , further comprising modifying the object responsive to a user input and wherein the displaying of the preview includes the modified object.
10. A method as described in claim 1 , wherein the composite image is editable during the preview.
11. A method comprising:
displaying a preview of a composite image in a first resolution, the composite image including an object extracted from one image as included in another image; and
rendering, after displaying the preview, a refined version of the composite image including the object extracted from the one image as included in the another image in a second resolution that is higher than the first resolution.
12. A method as described in claim 11 , further comprising displaying a copy of the one image responsive to selection of the one image.
13. A method as described in claim 12 , wherein the displaying of the copy is performed such that the copy of the one image is displayed as superimposed over the other image.
14. A method as described in claim 11 , wherein the display of the preview includes merging the object and the other image to generate the preview of the composite image such that the object appears to be inserted in the other image.
15. A method as described in claim 11 , wherein the object is extracted through identification of a perimeter drawn around the object in a graphical user interface.
16. A method as described in claim 11 , wherein the object is extracted by distinguishing pixels as belonging to a foreground object or a background object.
17. A method as described in claim 16 , wherein the distinguishing is performed based at least in part on a distance of the pixels from pixels along a perimeter, color values of pixels, intensity values of pixels, or gradient values of pixels.
18. A computing system having program instructions stored thereon that are executable by the computer system to cause the computer system to perform operations comprising:
displaying a preview of a composite image in a first resolution, the composite image including an object extracted from one image as included in another image;
rendering, after displaying the preview, a refined version of the composite image in a second resolution that is higher than the first resolution displayed during the preview; and
displaying the refined version.
19. A computing system as described in claim 18 , wherein the object is extracted through identification of a perimeter drawn around the object in a graphical user interface.
20. A computing system as described in claim 18 , wherein the object is extracted by distinguishing pixels as belonging to a foreground object or a background object.