GENERATING THREE-DIMENSIONAL VIRTUAL SCENE

• US 20130135304A1
• Filed: 11/30/2012
• Published: 05/30/2013
• Est. Priority Date: 11/30/2011
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Chen, Hao, Li, Qi Cheng, Mei, Li Jun, Wang, Jian, Wang, Yi Min, Zhu, Zi Yu, Hu, Guo Quang
• Granted Patent: US 11,069,130 B2
• Time in Patent Office: Days
• US Class Current: 345/420
• CPC Class Codes: G06T 17/00 Three dimensional [3D] modelling, e.g. data description of 3D objects
• 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 2210/61 Scene description
• CPC Class Codes: G06T 2219/2004 Aligning objects, relative positioning of parts
• CPC Class Codes: G06T 2219/2016 Rotation, translation, scaling

Abstract

A method and system for generating a three-dimensional (3D) virtual scene are disclosed. The method includes: identifying a two-dimensional (2D) object in a 2D picture and the position of the 2D object in the 2D picture; obtaining the three-dimensional model of the 3D object corresponding to the 2D object; calculating the corresponding position of the 3D object corresponding to the 2D object in the horizontal plane of the 3D scene according to the position of the 2D object in the picture; and simulating the falling of the model of the 3D object onto the 3D scene from a predetermined height above the 3D scene, wherein the position of the landing point the model of the 3D object in the horizontal plane is the corresponding position of the 3D object in the horizontal plane of the 3D scene.

Claims

1. A method for generating a three-dimensional (3D) virtual scene, comprising:

identifying a two-dimensional (2D) object in a 2D picture and a position of the 2D object in the 2D picture;

obtaining a three-dimensional model of a 3D object corresponding to the 2D object;

calculating a corresponding position of the 3D object corresponding to the 2D object in a horizontal plane of the 3D scene according to the position of the 2D object in the picture; and

simulating a falling of the model of the 3D object onto the 3D scene from a predetermined height above the 3D scene, wherein the position of the landing point the model of the 3D object in the horizontal plane is the corresponding position of the 3D object in the horizontal plane of the 3D scene.

2. The method according to claim 1, wherein said obtaining the three-dimensional model of the 3D object corresponding to the 2D object further comprises:

determining the 3D object corresponding to the 2D object according to a predefined mapping relationship between 2D objects and 3D objects.

3. The method according to claim 2, wherein said obtaining the three-dimensional model of the 3D object corresponding to the 2D object further comprises:

retrieving one or more models from a model database based on the determined 3D object corresponding to the 2D object, and determining a model of the 3D object corresponding to the 2D object in response to a user'"'"'s selection.

4. The method according to claim 1, wherein said calculating the corresponding position of the 3D object corresponding to the 2D object in the horizontal plane of the 3D scene according to the position of the 2D object in the picture further comprises:

calculating the coordinates of the position of the 3D object corresponding to the 2D object in the horizontal plane of the 3D scene from coordinates of the position of the 2D object in the picture based on the mapping relationship between the picture and an area of the horizontal plane of the 3D scene.

5. The method according to claim 1, wherein the 2D object in the picture is a color block.

6. The method according to claim 5, wherein said identifying a two-dimensional (2D) object in a 2D picture and the position of the 2D object in the 2D picture further comprises:

identifying a color block, a color and a position of the color block; and

said obtaining the three-dimensional model of the 3D object corresponding to the 2D object, further comprises;

determining the 3D object corresponding to the 2D object based on the predefined color-3D object mapping relationship.

7. The method according to claim 6, wherein said identifying a color block, a color and a position of the color block further comprises:

calculating the coordinates of a geometric center of the color block in the picture to represent coordinates of the position of the color block in the picture.

8. The method according to claim 1, wherein said simulating a falling of the model of the 3D object onto the 3D scene from a predetermined height above the 3D scene comprises simulating the model of the 3D object to remain on the virtual object in the 3D scene encountered during the falling.

9. The method according to claim 1, wherein said predefined height is a height associated with the picture.

10. The method according to claim 1, wherein said picture is generated in advance using a tool for generating 2D pictures.

11. A system for generating a three-dimensional (3D) virtual scene, comprising:

a 2D object identifying device, configured to identify a two-dimensional (2D) object in a 2D picture and a position of the 2D object in the 2D picture;

a model acquiring device, configured to obtain a three-dimensional model of a 3D object corresponding to the 2D object;

a position mapping device, configured to calculate a corresponding position of the 3D object corresponding to the 2D object in a horizontal plane of the 3D scene according to the position of the 2D object in the picture; and

a simulation device, configured to simulate a falling of the model of the 3D object onto the 3D scene from a predetermined height above the 3D scene, wherein the position of a landing point of the model of the 3D object in the horizontal plane is a corresponding position of the 3D object in the horizontal plane of the 3D scene.

12. The system according to claim 11, wherein the model acquiring device is further configured to determine the 3D object corresponding to the 2D object according to a predefined mapping relationship between 2D objects and 3D objects.

13. The system according to claim 12, wherein the model acquiring device is further configured to retrieve one or more models from a model database based on the determined 3D object corresponding to the 2D object, and determine a model of the 3D object corresponding to the 2D object in response to a user'"'"'s selection.

14. The system according to claim 11, wherein said position mapping device is further configured to calculate the coordinates of the position of the 3D object corresponding to the 2D object in the horizontal plane of the 3D scene from the coordinates of the position of the 2D object in the picture based on the mapping relationship between the picture and an area of the horizontal plane of the 3D scene.

15. The system according to claim 11, wherein the 2D object in the picture is a color block.

16. The system according to claim 15, wherein the 2D object identifying device is further configured to identify a color block, and a color and a position of the color block;

and the model acquiring device is further configured to determine the 3D object corresponding to the 2D object based on the predefined color-3D object mapping relationship.

17. The system according to claim 16, wherein the 2D object identifying device is further configured to calculate coordinates of the geometric center of the color block in the picture to represent the coordinates of the position of the color block in the picture.

18. The system according to claim 11, wherein the simulation device is configured to simulate the model of the 3D object to remain on the virtual object in the 3D scene encountered during the falling.

19. The system according to claim 11, wherein the predefined height is a height in association with the picture.

20. The system according to claim 11, wherein the picture is generated in advance using a tool for generating 2D pictures.