Pop-up light field

• US 7,633,511 B2
• Filed: 04/01/2004
• Issued: 12/15/2009
• Est. Priority Date: 04/01/2004
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Sun, Jian, Shum, Heung-Yeung, Yamazaki, Shuntaro, Li, Yin
• Primary Examiner(s): Caschera; Antonio A
• Application Number:
  US10/817,516
• Publication Number:
  US 20050219264A1
• Time in Patent Office: 2,084 Days
• Field of Search: 345/628
• US Class Current: 345/628
• CPC Class Codes: G06T 15/205 Image-based rendering

Abstract

Virtual views of a complex scene are produced for a user to view. The virtual views are substantially free from aliasing even when using a relatively sparse set of images of the scene. In a described implementation, a scene is split into one or more coherent layers. The boundaries of the coherent layers are propagated across a plurality of frames corresponding to the scene. The splitting may be further refined (e.g., in accordance with user feedback) to present a virtual view of the scene.

Claims

1. One or more computer-storage media comprising computer executable instructions that configure one or more processors to perform a method comprising:

utilizing one or more computers to split a scene into one or more coherent layers, wherein;

each coherent layer of the scene has a corresponding plane equation to represent a local geometry of that coherent layer; and

the one or more coherent layers in combination represent a single plane of the scene;

propagating boundaries of the coherent layers across a plurality of frames corresponding to the scene;

refining the splitting to present a virtual view of the scene; and

rendering the coherent layers with a corresponding background layer to present the virtual view of the scene, wherein the background layer is provided by combining a plurality of under-segmented regions.

2. One or more computer-storage media as recited in claim 1, wherein the virtual view of the scene is substantially free from aliasing.

3. One or more computer-storage media as recited in claim 1, wherein each of the coherent layers has a corresponding background layer.

4. One or more computer-storage media as recited in claim 1, wherein the plurality of frames correspond to different images of the scene.

5. One or more computer-storage media as recited in claim 1, wherein the refining is initiated by a user.

6. One or more computer-storage media as recited in claim 1, wherein each layer of the scene has a corresponding plane equation to represent a local geometry of that layer.

7. One or more computer-storage media as recited in claim 1, wherein the scene represents a set of images.

8. A system comprising:

one or more processors configured to execute computer-readable instructions;

a computer storage medium configured to store the computer-readable instructions;

a layer pop-up module to split a scene into one or more coherent layers;

a boundary propagation module to propagate boundaries of the coherent layers across a plurality of frames corresponding to the scene;

a refinement module to refine the splitting to present a virtual view of the scene; and

a rendering module to render the coherent layers with a corresponding background layer to present the virtual view of the scene, wherein the background layer is provided by combining a plurality of under-segmented regions.

9. A system as recited in claim 8, wherein the virtual view of the scene is substantially free from aliasing.

10. A system as recited in claim 8, wherein the plurality of frames correspond to different images of the scene.

11. A system as recited in claim 8, wherein the refinement module is activated by a user.

12. A system as recited in claim 8, wherein each layer of the scene has a corresponding plane equation to represent a local geometry of that layer.

13. One or more computer-storage media comprising instructions stored thereon that direct a machine to perform acts comprising:

splitting a scene into one or more coherent layers, wherein;

each coherent layer of the scene has a corresponding plane equation to represent a local geometry of that coherent layer; and

the one or more coherent layers in combination represent a single plane of the scene;

propagating boundaries of the coherent layers across a plurality of frames corresponding to the scene, wherein the plurality of frames correspond to different images of the scene;

refining the splitting to present a virtual view of the scene, wherein the refining;

is initiated by a user;

allows the user to select at least one of the coherent layers;

allows the user to refine the corresponding plane equation of the selected coherent layer; and

allows the user to inspect and adjust a rendering quality of the selected coherent layer in real time;

rendering the coherent layers with a corresponding background layer to present the virtual view of the scene, wherein the background layer is provided by combining a plurality of under-segmented regions.

14. One ore more computer-storage media as recited in claim 13, wherein the virtual view of the scene is substantially free from aliasing.

15. One ore more computer storage media as recited in claim 13, wherein the scene represents a set of images.

16. An apparatus comprising:

means for splitting a scene into one or more coherent layers;

means for propagating boundaries of the coherent layers across a plurality of frames corresponding to the scene;

means for refining the splitting to present a virtual view of the scene; and

means for rendering the coherent layers with a corresponding background layer to display the virtual view of the scene, wherein the background layer is provided by combining a plurality of under-segmented regions.