Synthesizing natural textures

By Michael Ashikhmin. 2001

919 citations recorded by the source corpus.

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

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

In Generative Models

Citations in the corpus

Free-Form Image Inpainting With Gated Convolution (2018, methodology): “To improve image inpainting, different user guidance is explored including dots or lines [Ashikhmin 2001; Barnes et al. 2009; Drori et al. 2003; Sun et al. 2005], structures [Huang et al. 2014], transformation or distortion information [Huang et al. 2013; Pavi´c et al. 2006] and image exemplars…”
Texture optimization for example-based synthesis (2005, background): “Ashikhmin [2001] allows a user to specify large scale properties of the output texture through a paintinglike interface.”
Text-Guided Neural Image Inpainting (2020, background): “User-guided Image inpainting Many user-guidance mechanisms are explored to enhance image inpainting systems, including dots or lines [1], structures [10], transformation or distortion [26], and exemplars [7, 13].”
On pixel-based texture synthesis by non-parametric sampling (2006, methodology): “Ashikhmin [2] exploited spatial coherency to remedy the blurring artifact observed in a texture generated by the method of Wei and Levoy.”
Parallel controllable texture synthesis (2005, methodology): “Improvements include hierarchical synthesis [Popat and Picard 1993], fast VQ matching [Wei and Levoy 2000], coherent synthesis to favor patch formation [Ashikhmin 2001], and precomputed similarity sets [Tong et al 2002; Zelinka and Garland 2002].”
PatchMatch: a randomized correspondence algorithm for structural image editing (2009, methodology): “Further improvements modify the search and sampling approaches for better structure preservation [Wei and Levoy 2000; Ashikhmin 2001; Liang et al. 2001; Efros and Freeman 2001; Kwatra et al. 2003; Criminisi et al. 2003; Drori et al. 2003].”
Image quilting for texture synthesis and transfer (2001, methodology): “The idea of texture transfer based on variations of [6] has been proposed by several authors [9, 1, 11] (in particular, see the elegant paper by Hertzmann et.”
Fragment-based image completion (2003, background): “Texture transfer [Ashikhmin 2001] adds the constraint that the synthesized texture match an example image.”
Texture synthesis over arbitrary manifold surfaces (2001, methodology): “In addition, for textures that are not well modeled by [25], we could generate better results by combining our surface-synthesis framework with other improved texture synthesis algorithms such as [1].”
State of the Art in Example-based Texture Synthesis (2009, methodology): “[HJO ∗ 01] further extended the ideas in [Ash01] by proposing the notion of image analogies .”
Image Analogies (2001, methodology): “…an approximate search , which attempts to efﬁciently ﬁnd the closest-matching pixel according to the feature vectors of p , q , and their neighborhoods; and a coherence search , based on Ashikhmin’s approach [2], which attempts to preserve coherence with the neighboring synthesized pixels.”
Near-regular texture analysis and manipulation (2004, background): “Existing work on image samplebased texture synthesis has achieved impressive results for a variety of textures [De Bonet 1997; Efros and Leung 1999; Ashikhmin 2001; Efros and Freeman 2001; Hsu and Wilson 1998; Wei and Levoy 2000; Hertzmann et al. 2001; Xu et al. 2001; Liang et al. 2001].”
Image Inpainting : Overview and Recent Advances (2014, methodology): “The remaining unknown pixels are in a third step estimated using a texture synthesis method as in [19].”
Interactive image completion with perspective correction (2006, methodology): “Example-based approaches have their origin in texture synthesis, where large texture patches are synthesized from small texture samples on a per-pixel basis using a pixel neighborhood for color prediction [2, 14, 32].”
Foreground-Aware Image Inpainting (2019, methodology): “Traditional methods such as [3, 4] fill in holes by propagating the neighborhood appearance based on techniques like isophote direction field.”