Completion and Reconstruction with Primitive Shapes

TLDR

Reconstruction from incomplete point‑clouds is a challenging problem. The authors aim to produce a closed mesh by guiding reconstruction with detected primitive shapes. They formulate a surface energy functional that incorporates primitive shapes into a guiding vector field, then minimize it with a graph‑cut algorithm and a greedy strategy that enforces connectivity of primitive‑associated surface patches. The resulting method can generate an idealized CAD‑ready model from the primitives.

Abstract

Abstract We consider the problem of reconstruction from incomplete point‐clouds. To find a closed mesh the reconstruction is guided by a set of primitive shapes which has been detected on the input point‐cloud (e.g. planes, cylinders etc.). With this guidance we not only continue the surrounding structure into the holes but also synthesize plausible edges and corners from the primitives' intersections. To this end we give a surface energy functional that incorporates the primitive shapes in a guiding vector field. The discretized functional can be minimized with an efficient graph‐cut algorithm. A novel greedy optimization strategy is proposed to minimize the functional under the constraint that surface parts corresponding to a given primitive must be connected. From the primitive shapes our method can also reconstruct an idealized model that is suitable for use in a CAD system.