Dyadic T-mesh subdivision

Meshes with T-joints (T-meshes) and related high-order surfaces have many advantages in situations where flexible local refinement is needed. At the same time, designing subdivision rules and bases for T-meshes is much more difficult, and fewer options are available. For common geometric modeling tasks it is desirable to retain the simplicity and flexibility of commonly used subdivision surfaces, and extend them to handle T-meshes. We propose a subdivision scheme extending Catmull-Clark and NURSS to a special class of quad T-meshes, dyadic T-meshes, which have no more than one T-joint per edge. Our scheme is based on a factorization with the same structure as Catmull-Clark subdivision. On regular T-meshes it is a refinement scheme for a subset of standard T-splines. While we use more variations of subdivision masks compared to Catmull-Clark and NURSS, the minimal size of the stencil is maintained, and all variations in formulas are due to simple changes in coefficients.