Shape-controllable geometry completion for point cloud models.

Geometry completion is an important operation for generating a complete model. In this paper, we present a novel geometry completion algorithm for point cloud models, which is capable of filling holes on either smooth models or surfaces with sharp features. Our method is built on the physical diffusion pattern. We first decompose each pass hole-boundary contraction into two steps, namely normal propagation and position sampling. Then the normal dissimilarity constraint is incorporated into these two steps to fill holes with sharp features. Our algorithm implements these two steps alternately and terminates until generating no new hole boundary. Experimental results demonstrate its feasibility and validity of recovering the potential geometry shapes. [ABSTRACT FROM AUTHOR]