State of the Art in Example-based Texture Synthesis

By Li-Yi Wei, Sylvain Lefebvre, Vivek Kwatra, Greg Turk. Eurographics, 2009

452 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/4b41e19f757a1c149e2cbdd2e15314bedc2ac722

How researchers see this paper

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

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Infill Optimization for Additive Manufacturing—Approaching Bone-Like Porous Structures (2016, background): “For instance, Liu and Shapiro [30] proposed to reconstruct 3D micro-structures from 2D sample images using example-based texture synthesis [31], such that the synthesized structures preserve statistical features of the given sample.”
A Survey of Procedural Noise Functions (2010, methodology): “In this respect noise functions are distinguished from texture synthesis algorithms (see, for example, Wei et al. [WLKT09]) that closely reproduce example textures and thus necessarily re-produce their statistics.”
STAR: A Structure and Texture Aware Retinex Model (2019, background): “Here, texture refers to the small patterns in object surface, which are similar in local statistics [54].”
Shape Completion from a Single RGBD Image (2017, methodology): “Inspired by texture synthesis techniques [10], contextbased methods exploit self-similarity priors to complete input object with rich textures or repetitive elements.”
Procedural Content Generation via Machine Learning (PCGML) (2017, background): “types of cosmetic game content that we exclude are textures and sound, as those do not directly impact the effects of in-game actions the way levels or rules do in most games, and there is already much research on the generation of such content outside of games [14], [15].”
Texture Synthesis Using Convolutional Neural Networks (2015, background): “These non-parametric resampling techniques and their numerous extensions and improvements (see [27] for review) are capable of producing high quality natural textures very efficiently.”
The Synthesizability of Texture Examples (2014, background): “Textures are usually referred to as visual surfaces composed of repeating patterns, that are similar in appearance [37].”
Texture Modeling with Convolutional Spike-and-Slab RBMs and Deep Extensions (2012, background): “Probably the most popular tex- ture synthesis strategies are currently example-based or nonparametric methods (Wei et al., 2009).”
Structure extraction from texture via relative total variation (2012, background): “We do not assume or manually determine the type of textures, as the patterns could vary a lot in different examples.”
Synthesizing structured image hybrids (2010, background): “…hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profi t or direct commercial advantage and that copies show this notice on the fi rst page or initial screen of a display along with the full citation.”
Neural Style Transfer: A Review (2017, methodology): “how to reconstruct an image with desired style information but also preserves its semantic content. There comes Image Reconstruction techniques. 3.1. Visual Texture Modelling Visual texture modelling [90] is previously studied as the heart of texture synthesis. Throughout the history of visual textu”