Abstract In this work, we address the problem of estimating 2d hu man pose from still images. Recent methods that rely on discriminatively trained deformable parts organized in a tree model have shown to be very successful in solving this task. Within such a pictorial structure framework, we address the problem of obtaining good part templates by proposing novel, non-linear joint regressors. In particular, we em ploy two-layered random forests as joint regressors. The ?rst layer acts as a discriminative, independent body part classi?er. The second layer takes the estimated class distri butions of the ?rst one into account and is thereby able to predict joint locations by modeling the interdependence and co-occurrence of the parts. This results in a pose estimatio framework that takes dependencies between body parts already for joint localization into account and is thus able t circumvent typical ambiguities of tree structures, such as for legs and arms. In the experiments, we demonstrate that our body parts dependent joint regressors achieve a higher joint localization accuracy than tree-based state-of-the-art methods.