Abstract
We extends the previous 2D cascaded object pose regression work [9] in two aspects so that it works better for 3D articulated objects. Our fifirst contribution is 3D poseindexed features that generalize the previous 2D parameterized features and achieve better invariance to 3D transformations. Our second contribution is a principled hierarchical regression that is adapted to the articulated object structure. It is therefore more accurate and faster. Comprehensive experiments verify the state-of-the-art accuracy and effificiency of the proposed approach on the challenging 3D hand pose estimation problem, on a public dataset and our new dataset.