Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Texture synthesis method based on interval distribution of texture blocks

A technology of texture synthesis and texture blocks, which is applied in the generation of 2D images, image data processing, filling planes with attributes, etc., can solve the problems of slow calculation speed and difficulty in effectively maintaining the global characteristics of textures, and achieve speed improvement and simple calculation Effect

Inactive Publication Date: 2011-09-21
INST OF SOFTWARE - CHINESE ACAD OF SCI
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The local synthesis technology is to infer the color of the adjacent area according to the color distribution in a small range. This kind of method is generally faster, but it is difficult to effectively maintain the global characteristics of the texture.
The global synthesis technology first randomly generates a texture with the size of the target texture, and then gradually optimizes the target texture based on the similarity measure of the global texture features to obtain the final target texture. This method can effectively Reflect the global characteristics of the texture, but the calculation speed is relatively slow

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Texture synthesis method based on interval distribution of texture blocks
  • Texture synthesis method based on interval distribution of texture blocks
  • Texture synthesis method based on interval distribution of texture blocks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] In this embodiment, 128*128 sample textures (such as Figure 4 a) to get 256*256 (as Figure 4 b) The target texture.

[0050] The whole method includes the following steps:

[0051] a) Analyze the sample texture and find the size of the main part of the texture block and the overlapped part that reflect its global texture characteristics;

[0052] The size of the main part of the texture block is set by the following method:

[0053] i. Set the size of various main parts, such as: 2*2, 3*3, 4*3, 6*5, 7*2, etc. The sample texture can be visually checked for this setting;

[0054] ii. Sort various sizes according to information inclusiveness measure:

[0055] The following uses 4*3 as an example to describe the content of the information inclusiveness measurement, and other dimensions are the same measurement:

[0056] 1. Divide the sample texture with 4*3 as the main part size (the texture period is not considered at this time) to obtain n texture blocks;

[0057] 2. Calculate the g...

Embodiment 2

[0085] In this embodiment, by the same method as in embodiment 1, Figure 5 a. Image 6 a and Figure 7 The sample texture synthesis shown in a Figure 5 b. Image 6 b and Figure 7 The target texture shown in b.

[0086] At the same time, according to the global optimization method, Figure 5 a and Image 6 The sample texture synthesis shown in a Figure 5 c and Image 6 The target texture shown in c, and according to the parallel controllable method by Figure 7 The sample texture synthesis shown in a Figure 7 The target texture shown in c.

[0087] by Figure 4-7 It can be seen that the method of the present invention can generate high-quality texture, which is comparable to the current global optimization method with the best synthesis quality, and can even better maintain the structured information of the texture, such as Figure 5 with Image 6 The global optimization method in will also destroy some structural units inside the texture, but the present invention will not.

Embodiment 3

[0089] In this embodiment, target textures of multiple sizes are synthesized from the same sample texture on a Dell Optiplex 755 microcomputer.

[0090] The PC is equipped with a Core TM 2 Duo E6550 2.33GHz CPU, 2G RAM, and a NVIDIA Geforce 8600GTS GPU.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a texture synthesis method based on interval distribution of texture blocks, belonging to the fields of computer algorithm, computer graphic technology, image processing technology and texture generating technology. The method comprises the following steps: (a) analyzing the sample texture to determine the size of a main body portion and an overlapping portion of the texture blocks; (b) dividing the sample texture according to the size to obtain a texture block aggregation M; (c) classifying the texture block according to phase, wherein each phase corresponds to one type; (d) obtaining four compatible adjoining aggregation of each texture block; (e) obtaining a proper texture block aggregation; (f) selecting any texture blocks to fill a target texture from the proper texture block aggregation, wherein blank blocks with or without texture blocks are distributed at intervals in transverse direction or longitudinal direction; (g) filling the left blank blocks; and(h) seaming the overlapping portion. The invention can be used for texture synthesis.

Description

Technical field [0001] The invention relates to texture synthesis, and belongs to the fields of computer algorithm, computer graphics technology, image processing technology, and texture generation technology, in particular to a texture synthesis method based on texture block interval distribution. Background technique [0002] The texture synthesis technology can generate large visually similar samples from a small sample, which can effectively reuse the calculation or measurement results of lighting and color, so as to generate high-quality rendering results with less overhead. This technology has very important and extensive applications in many fields such as photorealistic rendering and virtual reality. [0003] The current texture synthesis technology is mainly calculated based on the Markov chain probability model, that is, the color of any position is determined by other color distributions in a certain range near it. According to the scope of calculation, texture synthesi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T11/00G06T11/40
Inventor 王文成陈昕
Owner INST OF SOFTWARE - CHINESE ACAD OF SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com