We present an algorithm that uses multiple cues to recover shading and reflectance intrinsic images from a single image. Using both color information and a classifier trained to recognize gray-scale patterns, each image derivative is classified as being caused by shading or a change in the surface's reflectance. Generalized Belief Propagation is then used to propagate information from areas where the correct classification is clear to areas where it is ambiguous. We also show results on real images.
| Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/6703 |
| Date | 01 September 2002 |
| Creators | Tappen, Marshall F., Freeman, William T., Adelson, Edward H. |
| Source Sets | M.I.T. Theses and Dissertation |
| Language | en_US |
| Detected Language | English |
| Format | 12 p., 1591784 bytes, 1186163 bytes, application/postscript, application/pdf |
| Relation | AIM-2002-015 |
Page generated in 0.2427 seconds