Methods and Apparatus for Facial Feature Replacement
First Claim
1. A computer-implemented method, comprising:
- selecting three-dimensional models corresponding to a target image and a reference image based on a set of feature points defining features in the target image and the reference image;
associating the set of feature points defining the features in the target image and the reference image with the three-dimensional models;
computing a 3D motion flow between the three-dimensional models;
projecting the 3D motion flow onto a 2D image plane to create a 2D optical field flow;
warping the target image and the reference image using the 2D optical field flow; and
copying a selected feature from the reference image to the target image.
2 Assignments
0 Petitions
Accused Products
Abstract
Three dimensional models corresponding to a target image and a reference image are selected based on a set of feature points defining facial features in the target image and the reference image. The set of feature points defining the facial features in the target image and the reference image are associated with corresponding 3-dimensional models. A 3D motion flow between the 3-dimensional models is computed. The 3D motion flow is projected onto a 2D image plane to create a 2D optical field flow. The target image and the reference image are warped using the 2D optical field flow. A selected feature from the reference image is copied to the target image.
35 Citations
20 Claims
-
1. A computer-implemented method, comprising:
-
selecting three-dimensional models corresponding to a target image and a reference image based on a set of feature points defining features in the target image and the reference image; associating the set of feature points defining the features in the target image and the reference image with the three-dimensional models; computing a 3D motion flow between the three-dimensional models; projecting the 3D motion flow onto a 2D image plane to create a 2D optical field flow; warping the target image and the reference image using the 2D optical field flow; and copying a selected feature from the reference image to the target image. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A system, comprising:
at least one processor; and a memory comprising program instructions, wherein the program instructions are executable by the at least one processor to; select three dimensional models corresponding to a target image and a reference image based on a set of feature points defining features in the target image and the reference image, associate the set of feature points defining the features in the target image and the reference image with the three-dimensional models, compute a 3D motion flow between the three-dimensional models, project the 3D motion flow onto a 2D image plane to create a 2D optical field flow, warp the target image and the reference image using the 2D optical field flow, and copy a selected feature from the reference image to the target image. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
15. A non-transitory computer-readable storage medium storing program instructions, wherein the program instructions are computer-executable to implement:
-
selecting three dimensional models corresponding to a target image and a reference image based on a set of feature points defining features in the target image and the reference image; associating the set of feature points defining the features in the target image and the reference image with the three-dimensional models; computing a 3D motion flow between the three-dimensional models; projecting the 3D motion flow onto a 2D image plane to create a 2D optical field flow; warping the target image and the reference image using the 2D optical field flow; and copying a selected feature from the reference image to the target image. - View Dependent Claims (16, 17, 18, 19, 20)
-
Specification