Unlock instant, AI-driven research and patent intelligence for your innovation.

Semantic restriction texture synthesis method based on geometric space

A technology of semantic constraints and geometric space, applied in the generation of 2D images, image data processing, instruments, etc., to achieve the effect of improving the synthesis effect

Inactive Publication Date: 2013-06-05
BEIHANG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Solve the defect that existing texture synthesis methods can only synthesize textures with the same structural characteristics as the sample texture

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
  • Semantic restriction texture synthesis method based on geometric space
  • Semantic restriction texture synthesis method based on geometric space
  • Semantic restriction texture synthesis method based on geometric space

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] Our method relies on texture meshes, which are structures within a two-dimensional geometric space that describe the structural characteristics of textures, consisting of vertices and edges. The grid can be obtained according to the image processing technique ( figure 2 ): First generate the primitive mask of the sample texture (a binary image, the white part is the primitive area, and the other areas are black), and then generate the feature map according to the primitive mask. Each line in the feature map is a single pixel A wide, textured grid of sample textures is generated with the feature map at the end. This mesh is used as a sample mesh for compositing the target texture mesh. Because the sample grid can also be given artificially, the user can decide what kind of structural features the target texture has according to his own wishes.

[0026] The geometric space-based semantic constraint texture synthesis method of the present invention is specifically as fo...

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 semantic restriction texture synthesis method based on geometric space, and the synthesis result has the structural characteristics different from the master drawing. The method has the key point that a texture topological structure is analyzed and processed, and a two-dimension texture grid is used for describing the particular characteristics of the texture. Firstly, pixel mask of the sample texture is used for forming a sample texture gird. Then the target texture grid is synthesized according to the restriction conditions of the given topological structure, namely the small blocks of grids given by a user. Finally, under the guide and control of the texture grid, each pixel of the target texture is synthesized by adopting a per-pixel synthesis algorithm basedon characteristic vector, so that the aim of changing the texture topological structure can be realized. The invention realizes the aim of synthesizing a plurality of textures with different structural characteristics based on one sample texture.

Description

technical field [0001] The invention relates to a texture synthesis method based on sample images. Background technique [0002] Texture synthesis based on samples is a very popular and important research direction in the field of computer graphics and imaging. In the early days, people mainly studied how to use a small sample texture to obtain a large texture, and many excellent methods such as pixel-by-pixel synthesis based on the neighborhood matching algorithm and block-by-block synthesis based on the idea of ​​block splicing emerged. In the middle and late stages, especially in recent years, a lot of research is no longer purely dedicated to improving the quality and speed of synthesis, but showing divergence from many aspects, such as feature matching synthesis, dynamic texture synthesis, non-uniform texture Synthesis, multi-scale texture synthesis, and texture blending and smooth transitions. [0003] 1) Plane texture synthesis method [0004] The pixel-by-pixel te...

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): G06T11/00
Inventor 王莉莉金其江马志强何兵
Owner BEIHANG UNIV