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

Figure 1 
Figure 2 
Figure 3
Abstract
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...