作者: F. Dellaert , V. Kwatra , Sang Min Oh
关键词:
摘要: We introduce mixture trees, a tree-based data-structure for modeling joint probability densities using greedy hierarchical density estimation scheme. show that the tree models data efficiently at multiple resolutions, and present fast conditional sampling as one of many possible applications. In particular, development this was spurred by multi-target tracking application, where memory-based motion calls from large empirical densities. However, it is also suited to applications such texture synthesis, play central role. Results are presented both these