Fast texture synthesis using tree-structured vector quantization

By Li-Yi Wei, Marc Levoy. International Conference on Computer Graphics and Interactive Techniques, 2000

1,750 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/e1e1a39534aed2cf4894896de75d0ba1fa75ab6a

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

Image Style Transfer Using Convolutional Neural Networks (2016, background): “For texture synthesis there exist a large range of powerful non-parametric algorithms that can synthesise photorealistic natural textures by resampling the pixels of a given source texture [7, 30, 8, 20].”
Image completion with structure propagation (2005, methodology): “…1997; Harrison 2001; Bornard et al. 2002; Barret and Cheney 2002] have also been proposed for image completion by synthesizing pixels using texture synthesis techniques [Efros and Leung 1999; Wei and Levoy 2000; Liang et al. 2001; Ashikhmin 2001; Efros and Freeman 2001; Hertzmann et al. 2001].”
On pixel-based texture synthesis by non-parametric sampling (2006, methodology): “This method also exhibited better time efficiency than that of Wei and Levoy even without employing the TSVQ acceleration.”
Super-resolution through neighbor embedding (2004, methodology): “These methods typically require only one sample texture as input, possibly with some random noise [23] or a target model [24].”
MoCoGAN: Decomposing Motion and Content for Video Generation (2017, methodology): “Due to limitations in computation, data, and modeling tools, early video generation works focused on generating dynamic texture patterns [35, 42, 9, 43].”
Deep Filter Banks for Texture Recognition, Description, and Segmentation (2015, background): “1994), synthesis (Efros and Leung 1999; Wei and Levoy 2000; Portilla and Simoncelli 2000), and shape from texture (Gårding 1992; Forsyth 2001; Malik and Rosenholtz 1997).”
Transformation guided image completion (2013, background): “, [9, 24, 16]), it is not surprising that that the example-based approaches are used for image completion.”
Analysis and synthesis of textured motion: particles and waves (2004, background): “For example, the motion of particle objects floating in a river, such as leaves and balls, should be coupled with the motion of waves.”
Dynamic Textures (2003, methodology): “Deterministic methods to extend and extrapolate sequences have to go back and query the input texture in one way or the other to obtain information that generates the next [12, 41] 6.”
Region filling and object removal by exemplar-based image inpainting (2004, positive): “This is based on a large body of texturesynthesis research, which seeks to replicate texture ad infinitum, given a small source sample of pure texture [1], [9], [11], [12], [13], [14], [16], [17], [18], [22], [25].”
From BoW to CNN: Two Decades of Texture Representation for Texture Classification (2018, background): “Texture synthesis is the process of generating new texture images which are perceptually equivalent to a given texture sample [56, 65, 186, 189, 243, 270].”
Image Completion Using Efficient Belief Propagation Via Priority Scheduling and Dynamic Pruning (2007, background): “The remaining labels are called the “active labels” for that node.”
Non-local Regularization of Inverse Problems (2008, methodology): “This non-local averaging shares similarities with patch-based computer graphics synthesis [7,8].”
Example Based 3D Reconstruction from Single 2D Images (2006, methodology): “3.1, makes an implicit stationarity assumption [ 25 ]: Put simply, the probability for the depth at any pixel, given those of its neighbors, is the same throughout the output image.”