Image processing using image web
First Claim
1. A computer-implemented method for determining correspondence between images, the method comprising:
- receiving images in a computer system;
performing iterations using the computer system to find respective mappings for each patch of pixels in the images to a patch in another one of the images such that the mappings have minimal patch distance, the iterations including at least;
(i) evaluation of a nearby-pixel mapping in a current image, (ii) evaluation of a randomly selected mapping in the current image, and (iii) evaluation of a randomly selected mapping in another one of the images; and
generating a mapping record that results from the iterations, the mapping record having a specific sparsity with less than one mapping per pixel.
2 Assignments
0 Petitions
Accused Products
Abstract
A computer-implemented method for determining correspondence between images includes: receiving images in a computer system; performing iterations using the computer system to find respective mappings for each patch of pixels in the images to a patch in another one of the images such that the mappings have minimal patch distance, the iterations including at least: (i) evaluation of a nearby-pixel mapping in a current image, (ii) evaluation of a randomly selected mapping in the current image, and (iii) evaluation of a randomly selected mapping in another one of the images; and generating a mapping record that results from the iterations.
41 Citations
21 Claims
-
1. A computer-implemented method for determining correspondence between images, the method comprising:
-
receiving images in a computer system; performing iterations using the computer system to find respective mappings for each patch of pixels in the images to a patch in another one of the images such that the mappings have minimal patch distance, the iterations including at least;
(i) evaluation of a nearby-pixel mapping in a current image, (ii) evaluation of a randomly selected mapping in the current image, and (iii) evaluation of a randomly selected mapping in another one of the images; andgenerating a mapping record that results from the iterations, the mapping record having a specific sparsity with less than one mapping per pixel. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A computer program product embodied in a non-transitory storage device and comprising instructions that when executed by a processor perform a method comprising:
-
receiving images in a computer system; performing iterations using the computer system to find respective mappings for each patch of pixels in the images to a patch in another one of the images such that the mappings have minimal patch distance, the iterations including at least;
(i) evaluation of a nearby-pixel mapping in a current target image, and (ii) evaluation of a randomly selected mapping in another one of the images; andgenerating a mapping record that results from the iterations, the mapping record having a specific sparsity with less than one mapping per pixel. - View Dependent Claims (9, 10, 11, 12, 13, 14, 15)
-
-
16. A system comprising:
-
a repository of images; and an image processing component that performs iterations to find respective mappings for each patch of pixels in the images to a patch in another one of the images such that the mappings have minimal patch distance, the iterations including at least;
(i) evaluation of a nearby-pixel mapping in a current image, (ii) evaluation of a randomly selected mapping in the current image, and (iii) evaluation of a randomly selected mapping in another one of the images; andgenerates a mapping record based on the iterations, the mapping record having a specific sparsity with less than one mapping per pixel. - View Dependent Claims (17, 18, 19, 20, 21)
-
Specification