Fast Learning of Sprites using Invariant

A popular framework for the interpretation of image sequences is the layers or sprite model of e.g. Wang and Adelson (1994), Irani et al. (1994). Jojic and Frey (2001) provide a generative probabilistic model framework for this task, but their algorithm is slow as it needs to search over discretized transformations (e.g. translations, or affines) for each layer. In this paper we show that by using invariant features (e.g. Lowe’s SIFT features) and clustering their motions we can reduce or eliminate the search and thus learn the sprites much faster. We demonstrate our algorithm on two image sequences.