Geometric texture synthesis by example

Abstract

Patterns on real-world objects are often due to variations in geometry across the surface. Height fields and other common parametric methods cannot synthesize many forms of geometric surface texture such as thorns, scales, and bark. We present an example-based technique for synthesizing a variety of geometric textures on a model's surface. The applied textures can be from models specifically created for this purpose, or may be drawn from user-specified regions of an example model. We extend existing neighborhood-based texture synthesis algorithms to operate on volumetric models. Similar to image analogies [11], given a training pair of unfiltered and filtered source models and an unfiltered destination model (all volumetric grids), we synthesize a filtered fourth model that exhibits the desired geometric texture. The user defines vector fields to specify the direction of texture anisotropy on the source and destination models. The vector field defines a coordinate frame on the destination object's surface that is used to sample the voxel density values in the neighborhood near a given voxel, which then gives a feature vector that is matched to the neighborhoods in the source model. Destination voxels are visited in an order that is dictated by the vector field. We show geometric synthesis results on a variety of models using textures such as pits, grooves, thru-holes and thorns.

Discrete element textures

“…Our method is also related to geometry synthesis, especially those via example-based texturing methods such as surface meshes ], volumetric models [Bhat et al 2004;Merrell and Manocha 2008], or terrains [Zhou et al input exemplar pixel synthesis our method Figure 3: Comparison with pixel-based synthesis. The pixel synthesis result is produced by combining discrete optimization [Han et al 2006] with a texton mask [Zhang et al 2003].…”

Example-based hair geometry synthesis

“…Existing texture synthesis methods are not directly applicable to hair because either 2D or 3D texture synthesis addresses only one of the two aspects of hair. There exists much work on generalizing texture synthesis to curves [Hertzmann et al 2002] and geometric synthesis [Bhat et al 2004;Lai et al 2005;Lagae et al 2005;Zhou et al 2006;Zhou et al 2007]. Nevertheless, none of them is applicable to a volumetric packing of thin curves, such as hair.…”

A compact representation for scanned 3D objects

“…In this case, methods have been developed that attempt to extract detail from basic shape of one object, and then apply detail to a new shape. Bhat et al [2] synthesize geometric textures using voxel definitions of the object and fine scale geometry. A vector field on the surface is used to guide the synthesis on the base surface.…”