Skull reconstruction through shape completion

In this study, we present a shape completion approach to skull reconstruction. Our final goal is to reconstruct the complete mesh of a skull starting from its defective point cloud. Our approach is based on an existing deep neural network, opportunely modified, trained to reconstruct a complete 3D point cloud from an incomplete one. The complete point clouds are then processed through a multi-step pipeline in order to reconstruct the original skull surface. Moreover, we analyze and refine the Sant'Orsola skull dataset, designing functional pipelines for its processing. On the test set, the proposed approach is able to complete missing areas effectively, reaching high accuracy in terms of the predicted point locations and a good qualitative approximation of the complete skull.