Inverse texture mapping using weighted pyramid blending and view-dependent weight maps

• US 6,271,847 B1
• Filed: 09/25/1998
• Issued: 08/07/2001
• Est. Priority Date: 09/25/1998
• Status: Expired due to Term

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Szeliski, Richard S., Shum, Heung-Yeung
• Primary Examiner(s): Hjerpe, Richard
• Assistant Examiner(s): Sealey, Lance W.
• Application Number:
  US09/160,898
• Time in Patent Office: 1,047 Days
• Field of Search: 345/430, 345/418, 345/419
• US Class Current: 345/418
• CPC Class Codes: G06T 15/04 Texture mapping

Abstract

A system and method for creating weight maps capable of indicating how much each pixel in an image should contribute to a blended image. One such map is a view-dependent weight map created by inputting an image that has been characterized as a collection of regions. A 2D perspective transform is computed for each region that is to be part of the weight map. The transforms are used to warp the associated regions to prescribed coordinates to create a warped image. Once the warped image is created, a Jacobian matrix is computed for each pixel. The determinant of each Jacobian matrix is then computed to establish a weight factor for that pixel. The weight map for the inputted image is created using these computed determinants. Another advantageous weight map is a combination weight map. The process for creating type of weight map is identical to the view-dependant map up to the point the warped image has been created. After that, a first weight factor is computed for each pixel of the warped image using a first weight mapping process. At least one additional weight factor is also computed for each pixel using one or more additional weight mapping processes. The weight factors computed for each pixel are then combined to create a combined weight factor and the weight map is formed from these factors. Preferably, one of the weight mapping processes used to create the combination weight map is the aforementioned view-dependent weight mapping process.

Claims

1. A computer-implemented process for creating a view-dependent weight map for an image comprising using a computer to perform the following steps:

inputting an image;

identifying regions of the inputted image which are to become part of the weight map;

computing a 2D perspective transform for each identified region, said transform being capable of projecting the associated region to prescribed coordinates;

warping each identified region to the prescribed coordinates using the 2D perspective transforms;

computing a Jacobian matrix for each pixel of each warped region;

computing the determinant of each Jacobian matrix to establish a weight factor for the associated pixel; and

creating the weight map of the inputted image using the computed determinants.

9. The system of claim 1, wherein the first weight mapping sub-module comprises a feather weight mapping sub-module, and wherein said at least one additional weight mapping sub-module comprises a view-dependent weight mapping sub-module.

10. The system of claim 9, wherein the view-dependent weight mapping sub-module comprises sub-modules for:

computing a Jacobian matrix for each pixel of each warped region;

computing the determinant of each Jacobian matrix to establish a weight factor for the associated pixel; and

creating the weight map for the inputted image using the computed determinants.

11. The system of claim 10, wherein the program module for combining the weight factors computed for each pixel of each warped region comprises a sub-module for multiplying together the weight factors associated with a particular pixel location.

2. A system for creating a view-dependent weight map for an image, comprising:

a general purpose computing device;

a computer program comprising program modules executable by the computing device, wherein the computing device is directed by the program modules of the computer program to,

input an image,

identify regions of the inputted image which are to become part of the weight map,

compute a 2D perspective transform for each identified region, said transform being capable of projecting the associated region to prescribed coordinates,

warp each identified region to the prescribed coordinates using the 2D perspective transforms,

compute a Jacobian matrix for each pixel of each warped region,

compute the determinant of each Jacobian matrix to establish a weight factor for the associated pixel, and

create the weight map of the inputted image using the computed determinants.

3. A computer-readable memory for causing a computer to create a view-dependent weight map for an image, comprising:

a computer-readable storage medium; and

a computer program comprising program modules stored in the storage medium, wherein the storage medium is so configured by the computer program that it causes the computer to,

input an image,

identify regions of the inputted image which are to become part of the weight map,

compute a 2D perspective transform for each identified region, said transform being capable of projecting the associated region to prescribed coordinates,

warp each identified region to the prescribed coordinates using the 2D perspective transforms,

compute a Jacobian matrix for each pixel of each warped region,

compute the determinant of each Jacobian matrix to establish a weight factor for the associated pixel, and

create the weight map of the inputted image using the computed determinants.

4. A computer-implemented process for creating a combination weight map for an image comprising using a computer to perform the following steps:

inputting an image;

identifying regions of the inputted image which are to become part of the weight map;

computing a 2D perspective transform for each identified region, said transform being capable of projecting the associated region to prescribed coordinates;

warping each identified region to the prescribed coordinates using the 2D perspective transforms;

computing a first weight factor for each pixel of each warped region using a first weight mapping process;

computing at least one additional weight factor for each pixel of each warped region using at least one additional weight mapping process;

combining the weight factors computed for each pixel of each warped region to create a combined weight factor; and

creating said combination weight map of the inputted image using the combined weight factors.

5. The process of claim 4, wherein the first weight mapping process comprises a feather weight mapping process, and wherein said at least one additional weight mapping process comprises a view-dependent weight mapping process.

6. The process of claim 5, wherein the view-dependent weight mapping process comprises the steps of:

computing a Jacobian matrix for each pixel of each warped region;

computing the determinant of each Jacobian matrix to establish a weight factor for the associated pixel; and

creating the weight map for the inputted image using the computed determinants.

7. The process of claim 6, wherein the step of combining the weight factors computed for each pixel of each warped region comprises the step of multiplying together the weight factors associated with a particular pixel location.

8. A system for creating a combination weight map for an image, comprising:

a general purpose computing device;

a computer program comprising program modules executable by the computing device, wherein the computing device is directed by the program modules of the computer program to,

input an image,

identify regions of the inputted image which are to become part of the weight map,

compute a 2D perspective transform for each identified region, said transform being capable of projecting the associated region to prescribed coordinates,

warp each identified region to the prescribed coordinates using the 2D perspective transforms,

compute a first weight factor for each pixel of each warped region using a first weight mapping sub-module,

compute at least one additional weight factor for each pixel of each warped region using at least one additional weight mapping sub-module,

combine the weight factors computed for each pixel of each warped region to create a combined weight factor, and

create said combination weight map of the inputted image using the combined weight factors.

12. A computer-readable memory for causing a computer to create a combination weight map for an image, comprising:

a computer-readable storage medium; and

a computer program comprising program modules stored in the storage medium, wherein the storage medium is so configured by the computer program that it causes the computer to,

input an image,

identify regions of the inputted image which are to become part of the weight map,

compute a 2D perspective transform for each identified region, said transform being capable of projecting the associated region to prescribed coordinates,

warp each identified region to the prescribed coordinates using the 2D perspective transforms,

compute a first weight factor for each pixel of each warped region using a first weight mapping sub-module,

compute at least one additional weight factor for each pixel of each warped region using at least one additional weight mapping sub-module,

combine the weight factors computed for each pixel of each warped region to create a combined weight factor, and

create said combination weight map of the inputted image using the combined weight factors.

13. The computer-readable memory of claim 12, wherein the first weight mapping sub-module comprises a feather weight mapping sub-module, and wherein said at least one additional weight mapping sub-module comprises a view-dependent weight mapping sub-module.

14. The computer-readable memory of claim 13, wherein the view-dependent weight mapping sub-module comprises sub-modules for:

computing a Jacobian matrix for each pixel of each warped region;

computing the determinant of each Jacobian matrix to establish a weight factor for the associated pixel; and

creating the weight map for the inputted image using the computed determinants.

15. The computer-readable memory of claim 14, wherein the program module for combining the weight factors computed for each pixel of each warped region comprises a sub-module for multiplying together the weight factors associated with a particular pixel location.