Show simple item record

dc.contributor.authorFreeman, William T.en_US
dc.contributor.authorTorralba, Antonioen_US
dc.date.accessioned2004-10-08T20:38:34Z
dc.date.available2004-10-08T20:38:34Z
dc.date.issued2002-09-01en_US
dc.identifier.otherAIM-2002-016en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/6704
dc.description.abstractThe 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.en_US
dc.format.extent12 p.en_US
dc.format.extent2606902 bytes
dc.format.extent1497926 bytes
dc.format.mimetypeapplication/postscript
dc.format.mimetypeapplication/pdf
dc.language.isoen_US
dc.relation.ispartofseriesAIM-2002-016en_US
dc.subjectAIen_US
dc.subjectscene representationen_US
dc.subjectshapeen_US
dc.subjectstereoen_US
dc.subjectshape recipesen_US
dc.titleShape Recipes: Scene Representations that Refer to the Imageen_US


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record