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.
Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/6704 |
Date | 01 September 2002 |
Creators | Freeman, William T., Torralba, Antonio |
Source Sets | M.I.T. Theses and Dissertation |
Language | en_US |
Detected Language | English |
Format | 12 p., 2606902 bytes, 1497926 bytes, application/postscript, application/pdf |
Relation | AIM-2002-016 |
Page generated in 0.0014 seconds