Rapid computer modeling of faces for animation
First Claim
1. One or more computer-readable media containing a program that is executable by a computer to create a 3D model of a face, the program comprising the following actions:
- capturing at least two images of the face;
finding matched points in the two images based on locations identified by a human user on at least one of the images;
estimating rotation and translation of the face based on the matched points in the images;
determining 3D positions of the matched points based on the estimated rotation and translation to create a 3D representation of the face;
capturing a succession of 2D images containing the face in a range of poses;
determining poses of the face by performing the following actions for each 2D image in succession;
matching points of the face in the 2D image with corresponding points of a previous 2D image whose pose is already known, wherein the matched points of the images have corresponding 3D positions in fitted neutral face model, the 3D positions being determined by the poses of the images; and
calculating a pose for the 2D image that minimizes differences between projections of 3D positions of matched points of the previous image onto the given image and the corresponding matched points of the given image.
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
15 Claims
-
1. One or more computer-readable media containing a program that is executable by a computer to create a 3D model of a face, the program comprising the following actions:
-
capturing at least two images of the face; finding matched points in the two images based on locations identified by a human user on at least one of the images; estimating rotation and translation of the face based on the matched points in the images; determining 3D positions of the matched points based on the estimated rotation and translation to create a 3D representation of the face; capturing a succession of 2D images containing the face in a range of poses; determining poses of the face by performing the following actions for each 2D image in succession; matching points of the face in the 2D image with corresponding points of a previous 2D image whose pose is already known, wherein the matched points of the images have corresponding 3D positions in fitted neutral face model, the 3D positions being determined by the poses of the images; and calculating a pose for the 2D image that minimizes differences between projections of 3D positions of matched points of the previous image onto the given image and the corresponding matched points of the given image. - View Dependent Claims (2, 3, 4, 5)
-
-
6. A method to create a 3D model of a face, the method comprising the following actions:
-
capturing at least two images of the face; finding matched points in the two images based on locations identified by a human user on at least one of the images; estimating rotation and translation of the face based on the matched points in the images; determining 3D positions of the matched points based on the estimated rotation and translation to create a 3D representation of the face; capturing a succession of 2D images containing the face in a range of poses; determining poses of the face by performing the following actions for each 2D image in succession; matching points of the face in the 2D image with corresponding points of a previous 2D image whose pose is already known, wherein the matched points of the images have corresponding 3D positions in fitted neutral face model, the 3D positions being determined by the poses of the images; and calculating a pose for the 2D image that minimizes differences between projections of 3D positions of matched points of the previous image onto the given image and the corresponding matched points of the given image. - View Dependent Claims (7, 8, 9, 10)
-
-
11. A device that creates a 3D model of a face, the device being configured to perform actions comprising:
-
means for capturing at least two images of the face; means for finding matched points in the two images based on locations identified by a human user on at least one of the images; means for estimating rotation and translation of the face based on the matched points in the images; means for determining 3D positions of the matched points based on the estimated rotation and translation to create a 3D representation of the face; means for capturing a succession of 2D images containing the face in a range of poses; means for determining poses of the face by performing the following actions for each 2D image in succession; means for matching points of the object in the 2D image with corresponding points of a previous 2D image whose pose is already known, wherein the matched points of the images have corresponding 3D positions in fitted neutral face model, the 3D positions being determined by the poses of the images; and means for calculating a pose for the 2D image that minimizes differences between projections of 3D positions of matched points of the previous image onto the given image and the corresponding matched points of the given image. - View Dependent Claims (12, 13, 14, 15)
-
Specification