Conference 5–9 August 2012
Exhibition 7–9 August 2012
Los Angeles Convention Center

Noise and Texture

Technical Papers

Noise and Texture

Tuesday, 7 August 3:45 PM - 5:35 PM | Los Angeles Convention Center, Room 408A
Session Chair: Wojciech Jarosz, Disney Research Zürich

Gabor Noise by Example

Gabor noise by example is a method of estimating the parameters of bandwidth-quantized Gabor noise, a procedural noise function that can generate noise with an arbitrary power spectrum from exemplar Gaussian textures, a class of textures that is completely characterized by their power spectrum.

Bruno Galerne
Université Paris Descartes

Ares Lagae
Katholieke Universiteit Leuven

Sylvain Lefebvre
Alice/INRIA

George Drettakis
REVES/INRIA Sophia-Antipolis

Diffusion Curve Textures for Resolution-Independent Texture Mapping

Introducing a vector representation called diffusion curve textures for mapping diffusion-curve images (DCI) onto arbitrary surfaces. Diffusion-curve textures provide an explicit representation from which the texture value at any point can be solved directly, while preserving the compactness and resolution independence of diffusion curves.

Xin Sun
Microsoft Research Asia

Guofu Xie
Chinese Academy of Sciences

Yue Dong
Microsoft Research Asia

Stephen Lin
Microsoft Research Asia

Weiwei Xu
Microsoft Research Asia

Wencheng Wang
Chinese Academy of Sciences

Xin Tong
Microsoft Research Asia

Baining Guo
Microsoft Research Asia

Structure-Aware Synthesis for Predictive Woven Fabric Appearance

A technique for generating high-quality, micron-resolution volumetric appearance models of woven fabrics with user-specified designs. First, a small exemplar database is created by scanning fabric samples with elementary weave structures. Output volumes can then be synthesized by copying data from the exemplars at each yarn crossing.

Shuang Zhao
Cornell University

Kavita Bala
Cornell University

Steve Marschner
Cornell University

Wenzel Jakob
Cornell University

Point Sampling With General Noise Spectrum

The key contribution of this paper is an algorithm for generating point samples that match user-defined noise spectrum, such as blue, green, pink, and magenta noise. The algorithm supports adaptive sampling and is accelerated on the GPU. The paper shows a variety of sample patterns generated using the algorithm and demonstrates suitable applications.

Yahan Zhou
University of Massachusetts Amherst

Haibin Huang
University of Massachusetts Amherst

Li-Yi Wei
The University of Hong Kong

Rui Wang
University of Massachusetts Amherst

Symmetry-Guided Texture Synthesis and Manipulation

This paper presents a framework for symmetry-guided texture synthesis and manipulation. Methods are provided to control the symmetries of a texture and to transfer symmetries from one texture to another.

Vladimir Kim
Princeton University

Yaron Lipman
Weizmann Institute of Science

Thomas Funkhouser
Princeton University