Taking Consensus of Signed Distance Field for Hole Filling

When we use range finders to observe the shape of an object, many occluded areas may occur. These become holes and gaps in the model and make it undesirable to utilize the model for various applications. We propose a novel method to fill holes and gaps and complement such an incomplete model. We use a signed distance field (SDF) as an intermediate representation, which stores Euclidean signed distances from a voxel to the nearest point of the mesh model. Since the signs of a SDF is computed by using normal vectors, which are local features of range images, the signs of a SDF become unstable around holes or gaps. Thus, we take a consensus of the signed distances of neighbor voxels by estimating the consistency of the SDF. Once we make the SDF globally consistent by iterative computation, we can efficiently fill holes and gaps.