We propose a new method to quickly and accurately predict 3D positions of body joints from a single depth image, using no temporal information. We take an object recognition approach, designing an intermediate body parts representation that maps the dif?cult pose estimation problem into a simpler per-pixel classi?cation problem. Our large and highly varied training dataset allows the classi?er to estimate body parts invariant to pose, body shape, clothing, etc. Finally we generate con?dence-scored 3D proposals of several body joints by reprojecting the classi?cation result and ?nding local modes. The system runs at 200 frames per second on consumer hardware. Our evaluation shows high accuracy on both synthetic and real test sets, and investigates the effect of several training parameters. We achieve state of the art accuracy in our comparison with related work and demonstrate improved generalization over exact whole-skeleton nearest neighbor matching