Please use this identifier to cite or link to this item:
http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/6704Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.creator | Freeman, William T. | - |
| dc.creator | Torralba, Antonio | - |
| dc.date | 2004-10-08T20:38:34Z | - |
| dc.date | 2004-10-08T20:38:34Z | - |
| dc.date | 2002-09-01 | - |
| dc.date.accessioned | 2013-10-09T02:46:30Z | - |
| dc.date.available | 2013-10-09T02:46:30Z | - |
| dc.date.issued | 2013-10-09 | - |
| dc.identifier | AIM-2002-016 | - |
| dc.identifier | http://hdl.handle.net/1721.1/6704 | - |
| dc.identifier.uri | http://koha.mediu.edu.my:8181/xmlui/handle/1721 | - |
| dc.description | The goal of low-level vision is to estimate an underlying scene, given an observed image. Real-world scenes (e.g., albedos or shapes) can be very complex, conventionally requiring high dimensional representations which are hard to estimate and store. We propose a low-dimensional representation, called a scene recipe, that relies on the image itself to describe the complex scene configurations. Shape recipes are an example: these are the regression coefficients that predict the bandpassed shape from bandpassed image data. We describe the benefits of this representation, and show two uses illustrating their properties: (1) we improve stereo shape estimates by learning shape recipes at low resolution and applying them at full resolution; (2) Shape recipes implicitly contain information about lighting and materials and we use them for material segmentation. | - |
| dc.format | 12 p. | - |
| dc.format | 2606902 bytes | - |
| dc.format | 1497926 bytes | - |
| dc.format | application/postscript | - |
| dc.format | application/pdf | - |
| dc.language | en_US | - |
| dc.relation | AIM-2002-016 | - |
| dc.subject | AI | - |
| dc.subject | scene representation | - |
| dc.subject | shape | - |
| dc.subject | stereo | - |
| dc.subject | shape recipes | - |
| dc.title | Shape Recipes: Scene Representations that Refer to the Image | - |
| Appears in Collections: | MIT Items | |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.