Feature agnostic geometric alignment

• US 9,665,989 B1
• Filed: 02/17/2015
• Issued: 05/30/2017
• Est. Priority Date: 02/17/2015
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Aiger, Dror, Weill, Jonathan
• Primary Examiner(s): Seth, Manav
• Application Number:
  US14/624,494
• Time in Patent Office: 833 Days
• CPC Class Codes: G06T 15/20 Perspective computation
• CPC Class Codes: G06T 17/10 Constructive solid geometry [CSG] using solid primitives, e.g. cylinders, cubes
• CPC Class Codes: G06T 19/20 Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
• CPC Class Codes: G06T 2219/2004 Aligning objects, relative positioning of parts
• CPC Class Codes: G06T 2219/2021 Shape modification
• CPC Class Codes: G06T 7/40 Analysis of texture depth or shape recovery from texture G06T7/529

Abstract

Methods and apparatus for aligning objects are provided. A computing device can receive first and second object representations that are respectively associated with first and second surface representations. The computing device can apply an object transformation to the respective first and second object representations to modify geometric features of the respective first and second object representations based on one or more values of one or more characteristics of the respective first and second surface representation. The computing device can align the first object representation and the second object representation using an alignment of the transformed first object representation and the transformed second object representation. The computing device can provide an output based on the aligned first object representation and second object representation.

Claims

1. A method, comprising:

receiving, at a computing device, at least a first object representation and a second object representation, wherein the first object representation is associated with a first surface representation, and wherein the second object representation is associated with a second surface representation;

applying an object transformation to the first object representation to modify one or more geometric features of the first object representation based on one or more values of one or more characteristics of the first surface representation using the computing device;

applying the object transformation to the second object representation to modify one or more geometric features of the second object representation based on one or more values of one or more characteristics of the second surface representation using the computing device;

aligning the first object representation and the second object representation using an alignment of the transformed first object representation and the transformed second object representation by the computing device; and

providing an output of the computing device based on the aligned first object representation and second object representation.

2. The method of claim 1, wherein applying the object transformation to the first object representation to modify one or more geometric features of the first object representation based on one or more values of one or more characteristics of the first surface representation comprises:

determining a point on a two-dimensional (2D) surface of the first object representation;

determining a normal of the first object representation at the point on the 2D surface;

determining the one or more values of the one or more characteristics of the first surface representation for the point on the 2D surface;

scaling the normal of the first object representation by the one or more values; and

modifying one or more geometric features of the point on the 2D surface of the first object representation based on the scaled normal.

3. The method of claim 2, wherein the one or more values of the one or more characteristics of the first surface representation for the point on the 2D surface comprises a value related to one or more colors of the first surface representation for the point on the 2D surface.

4. The method of claim 2, wherein modifying the one or more geometric features of the point on the 2D surface of the first object representation based on the scaled normal comprises translating the point on the 2D surface along the scaled normal.

5. The method of claim 1, wherein the first object representation and the second object representation both have a same size and a same shape, and wherein the transformed first object representation has a different shape from the transformed second object representation.

6. The method of claim 1, wherein the alignment of the transformed first object representation and the transformed second object representation aligns the first surface representation and the second surface representation so to display at least a portion of an entire image on respective surfaces of the aligned first and second object representations.

7. The method of claim 6, wherein the entire image is configured to be displayed on respective surfaces of an aligned plurality of object representations that comprises the aligned first and second object representations.

8. The method of claim 6, wherein the first surface representation comprises a first portion of the entire image, wherein the second surface representation comprises a second portion of the entire image, and wherein the first surface representation differs from the second surface representation.

9. The method of claim 8, wherein the first surface representation and the second surface representation comprise overlapping portions of the entire image.

10. A computing device, comprising:

at least one processor; and

data storage including program instructions stored thereon that when executed by the at least one processor, cause the computing device to perform functions comprising;

receiving at least a first object representation and a second object representation, wherein the first object representation is associated with a first surface representation, and wherein the second object representation is associated with a second surface representation;

applying an object transformation to the first object representation to modify one or more geometric features of the first object representation based on one or more values of one or more characteristics of the first surface representation;

applying the object transformation to the second object representation to modify one or more geometric features of the second object representation based on one or more values of one or more characteristics of the second surface representation;

aligning the first object representation and the second object representation using an alignment of the transformed first object representation and the transformed second object representation; and

providing an output based on the aligned first object representation and second object representation.

11. The computing device of claim 10, wherein applying the object transformation to the first object representation to modify one or more geometric features of the first object representation based on one or more values of one or more characteristics of the first surface representation comprises:

determining a point on a two-dimensional (2D) surface of the first object representation;

determining a normal of the first object representation at the point on the 2D surface;

determining the one or more values of the one or more characteristics of the first surface representation for the point on the 2D surface;

scaling the normal of the first object representation by the one or more values; and

modifying one or more geometric features of the point on the 2D surface of the first object representation based on the scaled normal.

12. The computing device of claim 11, wherein the one or more values of the one or more characteristics of the first surface representation for the point on the 2D surface comprises a value related to one or more colors of the first surface representation for the point on the 2D surface.

13. The computing device of claim 11, wherein modifying the one or more geometric features of the point on the 2D surface of the first object representation based on the scaled normal comprises translating the point on the 2D surface along the scaled normal.

14. The computing device of claim 10, wherein the first object representation and the second object representation both have a same size and a same shape, and wherein the transformed first object representation has a different shape from the transformed second object representation.

15. The computing device of claim 10, wherein alignment of the transformed first object representation and the transformed second object representation aligns the first surface representation and the second surface representation so to display at least a portion of an entire image on respective surfaces of the aligned first and second object representations.

16. The computing device of claim 15, wherein the entire image is configured to be displayed on respective surfaces of an aligned plurality of object representations that comprises the aligned first and second object representations.

17. The computing device of claim 15, wherein the first surface representation comprises a first portion of the entire image, wherein the second surface representation comprises a second portion of the entire image, and wherein the first surface representation and the second surface representation comprise overlapping portions of the entire image.

18. A non-transitory computer readable medium having stored thereon instructions, that when executed by one or more processors of a computing device, cause the computing device to perform functions comprising:

receiving at least a first object representation and a second object representation, wherein the first object representation is associated with a first surface representation, and wherein the second object representation is associated with a second surface representation;

applying an object transformation to the first object representation to modify one or more geometric features of the first object representation based on one or more values of one or more characteristics of the first surface representation;

applying the object transformation to the second object representation to modify one or more geometric features of the second object representation based on one or more values of one or more characteristics of the second surface representation;

aligning the first object representation and the second object representation using an alignment of the transformed first object representation and the transformed second object representation; and

providing an output based on the aligned first object representation and second object representation.

19. The non-transitory computer readable medium of claim 18, wherein applying the object transformation to the first object representation to modify one or more geometric features of the first object representation based on one or more values of one or more characteristics of the first surface representation comprises:

determining a point on a two-dimensional (2D) surface of the first object representation;

determining a normal of the first object representation at the point on the 2D surface;

determining the one or more values of the one or more characteristics of the first surface representation for the point on the 2D surface;

scaling the normal of the first object representation by the one or more values; and

modifying one or more geometric features of the point on the 2D surface of the first object representation based on the scaled normal.

20. The non-transitory computer readable medium of claim 19, wherein the one or more values of the one or more characteristics of the first surface representation for the point on the 2D surface comprises a value related to one or more colors of the first surface representation for the point on the 2D surface.