An automatic assembly and completion framework for fragmented skulls

Abstract

We develop a completion pipeline for fragmented and damaged skulls. The goal of this work is to convert scanned incomplete skull fragments to a complete skull model for subsequent forensic or archeological tasks such as facial reconstruction. The proposed assembly and completion algorithms can also be used to repair other fragmented objects with inherent symmetry. A two-step assembly framework is proposed: (1) rough assembly by an ICP-like template matching algorithm integrated with the slippage features and spin-image descriptors; (2) assembly refinement by a global optimization on least square transformation error (LSTE) of break-curves. The assembled skull is finally repaired by a symmetry-based completion algorithm. Experiments on repairing scanned skull fragments demonstrate the efficacy and robustness of this framework.