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

Texture synthesis method based on multiplexing

A texture synthesis and texture technology, which is applied in the generation of 2D images, image data processing, and filling planes with attributes. It can solve problems such as limited speed and unfavorable generation of extra-large textures.

Inactive Publication Date: 2010-08-18
INST OF SOFTWARE - CHINESE ACAD OF SCI
View PDF5 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, the latter can synthesize textures of 1024*1024 pixels in real time, which is more suitable for the synthesis of large textures, but the speed is still limited, and due to the limitation of GPU memory space, it is not conducive to generating large-scale textures

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 multiplexing
  • Texture synthesis method based on multiplexing
  • Texture synthesis method based on multiplexing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] In this embodiment, the sample texture of 128*128 (such as Figure 5 As shown in a) to get 256*256 (such as Figure 5 The target texture shown in b).

[0059] The whole method flow is as Figure 4 Shown: Select P from the sample texture E 0 The size of the texture block, according to the synthetic method of texture block interval distribution to generate S 0 The synthesized textured region shown in ; then from S 0 Select P in the area where the texture has been synthesized 1 The size of the texture block is connected with the generated texture area to generate S 1 Composited texture regions as indicated in ; if target texture size not reached yet, continue from S 1 Select P in the area where the texture has been synthesized 2 Texture blocks of size , concatenated with generated texture regions, until the target texture size is reached.

[0060] Specifically include the following steps:

[0061] a) Analyze the sample texture to find the size of the main part and...

Embodiment 2

[0100] This embodiment is respectively by the same method as embodiment 1 Figure 6 a and Figure 7 The sample texture synthesis shown in a Figure 6 b and Figure 7 Target texture shown in b.

[0101] Meanwhile, according to the global optimization method by Figure 6 The sample texture synthesis shown in a Figure 6 The target texture is 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.

[0102] Depend on Figure 5-7 It can be seen that the method of the present invention can generate high-quality textures, which can be compared with the current global optimization method with the best synthesis quality, and can even better maintain the structured information of textures, such as Figure 6 The global optimization method in will also destroy some structured units inside the texture, but the present invention will not.

Embodiment 3

[0104] This example is generated by the same method as Example 1 Figure 8 b. Figure 8 d. Figure 9 a. Figure 9 The target texture of b, the size of the target texture here is 512*512.

[0105] Depend on Figure 8 , 9 It can be seen that the method of the present invention can generate various types of textures with high quality, and can be better applied in applications such as developable planes.

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 multiplexing, which comprises the following steps: after analyzing the texture of the sample, generating a small texture block by using a texture block interval distribution synthesis method; selecting a group of new larger texture blocks from the synthesized texture region according to the phase positions, and filling the larger texture blocks into the target texture so as to increase the size of the synthesized texture region; and continuously selecting a new larger texture block from the synthesized texture region through multiplexing to enlarge the synthesized texture region until the target texture is generated. By using the method of the invention, the completed block selection calculation and seaming calculation can be multiplexed, thereby reducing the amount of calculation for block selection and seaming calculation and saving the synthesis time; all the synthesis steps can be realized on CPU, thereby being beneficial to avoiding generating oversize texture due to space limitation; and the invention adopts the multithreading acceleration technology and can acquire higher synthesis velocity.

Description

technical field [0001] The invention relates to texture synthesis, which belongs to the technical fields of computer algorithm, computer graphics technology, image processing technology and texture generation, and specifically relates to a texture synthesis method based on multiplexing. Background technique [0002] Texture synthesis technology can generate visually similar large 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 important and extensive applications in many fields such as realistic rendering and virtual reality. [0003] At present, the texture synthesis technology is mainly calculated according to the Markov chain probability model, that is, the color of any position is determined by the distribution of other colors within a certain range near it. As far as the synthesis order is concerned, the texture...

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 Applications(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