Solid texture synthesis from 2D exemplars

By Johannes Peter Kopf, Chi-Wing Fu, Daniel Cohen-Or, Oliver Deussen, Dani Lischinski, Tien-Tsin Wong. ACM Transactions on Graphics, 2007

308 citations recorded by the source corpus.

We present a novel method for synthesizing solid textures from 2D texture exemplars. First, we extend 2D texture optimization techniques to synthesize 3D texture solids. Next, the non-parametric texture optimization approach is integrated with histogram matching, which forces the global statistics of the synthesized solid to match those of the exemplar. This improves the convergence of the synthesis process and enables using smaller neighborhoods. In addition to producing compelling texture mapped surfaces, our method also effectively models the material in the interior of solid objects. We also demonstrate that our method is well-suited for synthesizing textures with a large number of channels per texel.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e908f389f57304d05144ab0e1ff749c74b1dbb49

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Computational microstructure characterization and reconstruction: Review of the state-of-the-art techniques (2018, methodology): “12 through 14 in [107]) and can also be used to synthesize a 3D solid texture from a 2D exemplar [107,255,260], see also Fig.”
Synthesizing structured image hybrids (2010, background): “…and Bala 2007; Wei et al. 2008], by incorporating specialized domain knowledge [Liu et al. 2004; Dischler and Zara 2006; Mohammed et al. 2009], or by automatically encouraging formation of coarse features in coarsely varying textures [Kopf et al. 2007; Han et al. 2008; Rosenberger et al. 2009].”
Learning a Neural 3D Texture Space From 2D Exemplars (2019, methodology): “Finally, all these methods require to learn the texture in the same space it will be used, while our approach can operate in any dimension and across dimensions, including the important case of generating procedural 3D solid textures from 2D observations [11] or slices [18] only.”
PatchMatch: a randomized correspondence algorithm for structural image editing (2009, methodology): “When doing approximate matching with PCA, we found that vp-trees are slower than kdtrees for equivalent error values, so we omitted them from our comparison above.”