Relief pattern segmentation using 2D-grid patches on a locally ordered mesh manifold

The mesh manifold support has been analyzed to perform several different tasks. Recently, it emerged the need for new methods capable of analyzing relief patterns on the surface. In particular, a new and not investigated problem is that of segmenting the surface according to the presence of different relief patterns. In this paper, we introduce this problem and propose a new approach for segmenting such relief patterns (also called geometric texture) on the mesh-manifold. Operating on regular and ordered mesh, we design, in the first part of the paper, a new mesh re-sampling technique complying with this requirement. This technique ensures the best trade-off between mesh regularization and geometric texture preservation, when compared with competitive methods. In the second part, we present a novel scheme for segmenting a mesh surface into three classes: textured-surface, non-textured surface, and edges (i.e., surfaces at the border between the two). This technique leverages the ordered structure of the mesh for deriving 2D-grid patches allowing us to approach the segmentation problem as a patch-classification technique using a CNN network in a transfer learning setting. Experiments performed on surface samples from the SHREC'18 contest show remarkable performance with an overall segmentation accuracy of over 99%.