We present a unifying framework in which "object-independent" modes of variation are learned from continuous-time data such as video sequences. These modes of variation can be used as "generators" to produce a manifold of images of a new object from a single example of that object. We develop the framework in the context of a well-known example: analyzing the modes of spatial deformations of a scene under camera movement. Our method learns a close approximation to the standard affine deformations that are expected from the geometry of the situation, and does so in a completely unsupervised (i.e. ignorant of the geometry of the situation) fashion. We stress that it is learning a "parameterization", not just the parameter values, of the data. We then demonstrate how we have used the same framework to derive a novel data-driven model of joint color change in images due to common lighting variations. The model is superior to previous models of color change in describing non-linear color changes due to lighting.
| Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/6659 |
| Date | 01 September 2001 |
| Creators | Miller, Erik G., Tieu, Kinh, Stauffer, Chris P. |
| Source Sets | M.I.T. Theses and Dissertation |
| Language | en_US |
| Detected Language | English |
| Format | 9 p., 8233900 bytes, 814636 bytes, application/postscript, application/pdf |
| Relation | AIM-2001-021 |
Page generated in 0.0018 seconds