Abstract: In this paper we present a model-based framework for hand pose estimation, which relies on the depth and color image sequence input. The proposed framework adopts a divide-and-conquer scheme, and combines fingertip tracking and articulated iterative closest point approach to restore the hand motion. The tracked fingertip positions are used to provide an initial estimation of the hand pose, and articulated ICP are adopted for further refinement. Experiments on both synthetic data and real-world sequences show the hand pose estimation scheme can accurately capture the natural hand motion.