Abstract

We propose a method for human pose estimation which ex- tends common unary and pairwise terms of graphical models with a global foreground term. Given knowledge of per pixel foreground, a pose should not only be plausible according to the graphical model but also explain the foreground well. However, while inference on a standard tree-structured graphical model for pose estimation can be computed easily and very efficiently using dy- namic programming, this no longer holds when the global foreground term is added to the problem. We therefore propose a branch and bound based algorithm to retrieve the globally optimal solution to our pose estimation problem. To keep infer- ence tractable and avoid the obvious combinatorial explosion, we propose upper bounds allowing for an intelligent exploration of the solution space. We evaluated our method on several publicly available datasets, show- ing the benefits of our method.