Hybrid Function Representation with Distance Properties

Abstract

This paper describes a novel framework allowing for a hybrid representation of heterogeneous objects. We consider advantages and drawbacks of the conventional representations based on scalar fields of different kinds. The main result is introducing a hybrid representation called Hybrid Function Representation (HFRep) that preserves the advantages of the Function Representation (FRep) and Signed Distance Fields (SDFs) without their drawbacks. This new representation allows for obtaining a continuous smooth distance field in the Euclidean space for the FRep. We present the mathematical basics for our approach that uses the Discrete Distance Transform (DDT) and a step-function. The procedure for generation HFRep using continuous interpolation and smoothing techniques are also described. A few examples show how the approach works in practice.