Symmetry-Guided Texture Synthesis and Manipulation

Abstract

This paper presents a framework for symmetry-guided texture synthesis and processing. It is motivated by the long-standing problem of how to optimize, transfer, and control the spatial patterns in textures. The key idea is that symmetry representations that measure autocorrelations with respect to all transformations of a group are a natural way to describe spatial patterns in many real-world textures. To leverage this idea, we provide methods to transfer symmetry representations from one texture to another, process the symmetries of a texture, and optimize textures with respect to properties of their symmetry representations. These methods are automatic and robust, as they don't require explicit detection of discrete symmetries. Applications are investigated for optimizing, processing and transferring symmetries and textures.


Symmetry-Guided Texture Synthesis and Manipulation
     Vladimir G. Kim, Yaron Lipman, and Thomas Funkhouser
     Transactions on Graphics, 2012 (Presented at SIGGRAPH 2012)

Paper: high-res (76.6Mb) low-res (3.5Mb)
BibTex: bib
Slides: pdf

Distributables

Sourcecode:
      →  Code (2Mb)Using Code
      →  Binaries (3Mb)Using Binaries
Data:
      →  Input images (6Mb)License restrictions
      →  Results (35Mb)Paper results + some additional animations