Discrete 2-Tensor Fields on Triangulations

• Published in: Computer graphics forum Vol. 33; no. 5; pp. 13 - 24
• Main Authors: de Goes, Fernando, Liu, Beibei, Budninskiy, Max, Tong, Yiying, Desbrun, Mathieu
• Format: Journal Article
• Language: English
• Published: Oxford Blackwell Publishing Ltd 01.08.2014
• Subjects: Analysis; Anisotropy; Calculus; Categories and Subject Descriptors (according to ACM CCS); Computer graphics; Computer Graphics [I.3.5]: Computational Geometry and Object Modeling-Curve and surface representations; Exact solutions; Mathematical analysis; Operators; Representations; Studies; Tensors; Topological manifolds; Triangulation
• ISSN: 0167-7055; 1467-8659; 1467-8659
• DOI: 10.1111/cgf.12427

Geometry processing has made ample use of discrete representations of tangent vector fields and antisymmetric tensors (i.e., forms) on triangulations. Symmetric 2‐tensors, while crucial in the definition of inner products and elliptic operators, have received only limited attention. They are often discretized by first defining a coordinate system per vertex, edge or face, then storing their components in this frame field. In this paper, we introduce a representation of arbitrary 2‐tensor fields on triangle meshes. We leverage a coordinate‐free decomposition of continuous 2‐tensors in the plane to construct a finite‐dimensional encoding of tensor fields through scalar values on oriented simplices of a manifold triangulation. We also provide closed‐form expressions of pairing, inner product, and trace for this discrete representation of tensor fields, and formulate a discrete covariant derivative and a discrete Lie bracket. Our approach extends discrete/finite‐element exterior calculus, recovers familiar operators such as the weighted Laplacian operator, and defines discrete notions of divergence‐free, curl‐free, and traceless tensors–thus offering a numerical framework for discrete tensor calculus on triangulations. We finally demonstrate the robustness and accuracy of our operators on analytical examples, before applying them to the computation of anisotropic geodesic distances on discrete surfaces.