Rapid computer modeling of faces for animation
First Claim
1. One or more computer-readable media containing instructions to process two or more images for distinguishing a head in the images from other portions of the images, the instructions being executable to perform actions comprising:
- computing a first mask image that marks any image pixels whose colors are different in the two or more images;
creating a second mask image that marks any image pixels having skin colors;
noting marked pixels on the first mask image and also noting unmarked pixels of the first mask image that correspond in location to marked pixels in the second mask image; and
combining the first and second mask images to create a final mask image which marks the noted pixels as being part of the head.
2 Assignments
0 Petitions
Accused Products
Abstract
Described herein is a technique for creating a 3D face model using images obtained from an inexpensive camera associated with a general-purpose computer. Two still images of the user are captured, and two video sequences. The user is asked to identify five facial features, which are used to calculate a mask and to perform fitting operations. Based on a comparison of the still images, deformation vectors are applied to a neutral face model to create the 3D model. The video sequences are used to create a texture map. The process of creating the texture map references the previously obtained 3D model to determine poses of the sequential video images.
-
Citations
20 Claims
-
1. One or more computer-readable media containing instructions to process two or more images for distinguishing a head in the images from other portions of the images, the instructions being executable to perform actions comprising:
-
computing a first mask image that marks any image pixels whose colors are different in the two or more images; creating a second mask image that marks any image pixels having skin colors; noting marked pixels on the first mask image and also noting unmarked pixels of the first mask image that correspond in location to marked pixels in the second mask image; and combining the first and second mask images to create a final mask image which marks the noted pixels as being part of the head. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. An apparatus configured to process two or more images for distinguishing a head in the images from other portions of the images, the apparatus comprising:
-
means for computing a first mask image that marks any image pixels whose colors are different in the two or more images; means for creating a second mask image that marks any image pixels having skin colors; means for noting marked pixels on the first mask image and also noting unmarked pixels of the first mask image that correspond in location to marked pixels in the second mask image; and means for combining the first and second mask images to create a final mask image which marks the noted pixels as being part of the head. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
-
15. A method to process two or more images for distinguishing a head in the images from other portions of the images, the method is comprising:
-
creating a first mask image that marks any image pixels whose colors are different in the two images; creating a second mask image that marks any image pixels whose colors correspond to skin colors; noting marked pixels on the first mask image and also noting unmarked pixels of the first mask image that correspond in location to marked pixels in the second mask image; and forming a final mask image that marks the noted pixels as being part of the head. - View Dependent Claims (16, 17, 18, 19, 20)
-
Specification