Texture optimization-based non-homogeneous image synthesis method

Abstract

The invention discloses a texture optimization-based non-homogeneous image synthesis method. The image synthesis method comprises the following steps of: 1) generating a tag image A, a color image A', and a Gaussian pyramid of a new tag image B, wherein AL, A'L, BL, and B'L indicate the Lth layer of the pyramid; 2) setting an initial layer L, and generating an initial master drawing; 3) defining different global measurement rules for different types of images; and 4) starting from the roughest layer L and performing the following steps on the pyramid from a rough layer to a fine layer circularly: 4.1) performing the steps on each neighbourhood in a neighbourhood window pyramid winSizePyr of the layer: 4.1.1) executing the step M according to the AL, the A'L, the BL and the B'L to obtain Match L; and 4.1.2) executing the step E according to the AL, the A'L, the BL, the B'L and the Match L to obtain optimized new B'L; and 4.2) performing super-sampling on the B'L to obtain B'L-1. The texture optimization-based non-homogeneous image synthesis method is high in synthesis speed, high in synthesis quality and high in synthesis efficiency.

Description

technical field [0001] The invention relates to image synthesis technology, in particular to an image synthesis method. Background technique [0002] Sample-based texture synthesis aims to generate visually similar large-block textures from small-block sample textures, which can reduce heavy modeling work and improve rendering efficiency. It is a hot research direction in computer graphics. For texture, it can be roughly divided into two types: homogeneous texture and non-homogeneous texture. Homogeneous textures satisfy local and stationary properties in Markov random fields. Non-homogeneous textures, that is, textures that change globally do not satisfy the static property. For non-homogeneous textures, a control map is usually added during the synthesis process to constrain the synthesis process. With the progress of texture synthesis work, the quality and efficiency of homogeneous texture synthesis have been greatly improved. But for non-homogeneous textures, research...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the disadvantages of poor rapidity and poor synthesis quality of existing non-homogeneous texture synthesis methods, the present invention provides a non-homogeneous texture optimization based texture optimization method with good rapidity, high synthesis quality and faster synthesis efficiency. Quality Image Synthesis Method

Images