The Promise and Perils of Near-Regular Texture
read more
Citations
Learning Visual Attributes
Near-regular texture analysis and manipulation
From BoW to CNN: Two Decades of Texture Representation for Texture Classification
A computational model for periodic pattern perception based on frieze and wallpaper groups
Parallel controllable texture synthesis
References
International tables for X-ray crystallography
Texture synthesis by non-parametric sampling
Image quilting for texture synthesis and transfer
A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients
Tilings and patterns
Related Papers (5)
Frequently Asked Questions (15)
Q2. What future works have the authors mentioned in the paper "The promise and perils of near-regular texture∗" ?
Their long term goal is to model a continuous texture spectrum from regular to near-regular to chaotic patterns, and to study texture variations along different dimensions of symmetry ( Liu, 2001 ).
Q3. What is the focus of this paper?
The focus of this paper is on faithful texture synthesis of near-regular textures where departure from regularity is primarily caused by statistical color and intensity variations, while the underlying structural regularity remains.
Q4. What is the long term goal of the paper?
Their long term goal is to model a continuous texture spectrum from regular to near-regular to chaotic patterns, and to study texture variations along different dimensions of symmetry (Liu, 2001).
Q5. Why does local texture synthesis work on near-regular textures?
The reason that local texture synthesis algorithms work on certain near-regular textures (patterns of dots or knots, for example) is due to a judicious choice of the window size and shape that happens to match the tile shape and orientation of the input sample.
Q6. What is the purpose of the texture synthesis process?
This process provides the promise of capturing statistical color and intensity variations from different tiles, which can give the generated texture more natural appearance, while reproducing its regularity.
Q7. How did Liu and Collins develop an algorithm to find tiles in a given pattern?
In order to find tiles in a given 2D near-regular pattern the authors developed an algorithm in Liu and Collins (2000) and refined in Liu et al. (2004), based on regions of dominance, for locating the underlying lattice of a given pattern.
Q8. What are the two perils of near-regular texture?
The two perils of near-regular texture are:1. random treatment: ignoring the special property of regularity, thus regularity (a global property) is no longer preserved (images (b) in Figs. 2 and 3); 2. regular treatment: only recognizing that the texture is regular, thus ended up repeating a single tile (Fig. 7).
Q9. What is the key factor in reproducing regularity?
A key factor in reproducing regularity is to recognize, simultaneously, the shape, orientation and size of a basic tile of the input near-regular texture.
Q10. What is the definition of a minimum tile?
The authors define these tiles as minimum tiles {ti } since by definition of regular patterns there are no 2D regions smaller than these tiles that can tile the whole texture pattern under its translation subgroup.
Q11. What is the advantage of their approach?
One advantage of their approach is that the tile shape (not necessarily a square), orientation (not necessarily upright), and size are determined up front, explicitly, and customized to each input near-regular texture pattern (Fig. 5).
Q12. What is the main theme of texture synthesis?
Though tiling is the central theme and appropriate means for many artistic and design tasks (Washburn and Crowe, 1991; Grünbaum and Shephard, 1987), it is usually not suited for providing natural visual effects in the context of texture synthesis.
Q13. What is the parameter that the user can control to make the boundary of the tiles align with low?
This is one parameter that the user can control to make the boundary of the tiles align with low frequency regions for the benefit of better blending results.
Q14. What is the purpose of the periodicity measure?
Their lattice detection algorithm (Liu and Collins, 2000) or other future robust lattice extraction algorithms can also serve asa periodicity measure.
Q15. What is the way to measure regularity in a texture?
One can push the window size argument to the extreme: imagine using the whole input texture as the largest possible patch, even then the regularity of the input texture will still not be preserved, unless the cut-offs happen right at the matching line (e.g. the short bricks happen to have half-brick length in Fig. 13).