Refined embroidery texture migration method based on sample domain

A refined and textured technology, applied in the field of fine embroidery texture transfer based on the sample domain, which can solve problems such as unsatisfactory output

CN110097609AActive Publication Date: 2019-08-06SHANGHAI LINCTEX DIGITAL TECH CO LTD
3 Cites 15 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2019-08-06

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a refined embroidery texture migration method based on a sample domain, which comprises the following steps: in a model training stage, based on a cyclic generative adversarialnetwork, adding a Waserstein loss item, a feature matching loss item and an MS-in loss item into a loss function, and performing feature matching on the loss item and the MS-in loss item; according to the SSIM loss item, a self-attention mechanism is added to a generator G network, and a resolution enhancement method from coarse to fine is introduced. A training model is used for synthesizing embroidery textures; performing color quantization processing based on self-organizing network mapping on the input embroidery vector design drawing, performing color correction on the generated embroidery textures through the quantization method, and finally combining the embroidery textures with the generated normal map to obtain an embroidery texture map which meets the three-dimensional display requirement and has both embroidery colors and concave-convex textures. According to the method, rapid generation from image design to refined embroidery texture is realized, and the rework rate of production personnel is reduced while the communication efficiency of the design personnel is improved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of computer vision, in particular to a sample domain-based refined embroidery texture migration method. Background technique

[0002] Textiles are the necessities of people's life and production. As the world's largest producer, consumer and exporter of textiles and clothing, in 2017, the total trade volume of my country's textile and clothing industry was about 293.15 billion US dollars, and the growth rate of market share was stable. With a series of background advantages such as low labor costs, high demand, early production start, and abundant raw material resources, my country's textile industry has formed a relatively complete industrial chain, but in a series of subdivisions such as research and development and design with higher added value Compared with the current international advanced level, there is still a certain gap. .

[0003] In order to solve the problems of high design cost, unstable qu...

Examples

Embodiment Construction

[0091] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments. It should be understood that these examples are only used to illustrate the present invention and are not intended to limit the scope of the present invention. For the experimental methods without specific conditions indicated in the following examples, the conventional conditions or the conditions suggested by the manufacturer are usually followed.

[0092] Such as Figure 7 As shown, the refined embroidery texture transfer method based on the sample domain in this embodiment includes a training phase and a synthesis phase, and the specific steps include:

[0093] (1) Using an existing image as a sample, an improved cyclic generation adversarial network is used for model training; the improved cyclic generation adversarial network is to add Wasserstein loss term, feature matching loss term and MS-SSIM to the loss function The loss item introdu...