Research on clothing patterns generation based on multi-scales self-attention improved generative adversarial network

Abstract

PurposeClothing patterns play a dominant role in costume design and have become an important link in the perception of costume art. Conventional clothing patterns design relies on experienced designers. Although the quality of clothing patterns is very high on conventional design, the input time and output amount ratio is relative low for conventional design. In order to break through the bottleneck of conventional clothing patterns design, this paper proposes a novel way based on generative adversarial network (GAN) model for automatic clothing patterns generation, which not only reduces the dependence of experienced designer, but also improve the input-output ratio.Design/methodology/approachIn view of the fact that clothing patterns have high requirements for global artistic perception and local texture details, this paper improves the conventional GAN model from two aspects: a multi-scales discriminators strategy is introduced to deal with the local texture details; and the self-attention mechanism is introduced to improve the global artistic perception. Therefore, the improved GAN called multi-scales self-attention improved generative adversarial network (MS-SA-GAN) model, which is used for high resolution clothing patterns generation.FindingsTo verify the feasibility and effectiveness of the proposed MS-SA-GAN model, a crawler is designed to acquire standard clothing patterns dataset from Baidu pictures, and a comparative experiment is conducted on our designed clothing patterns dataset. In experiments, we have adjusted different parameters of the proposed MS-SA-GAN model, and compared the global artistic perception and local texture details of the generated clothing patterns.Originality/valueExperimental results have shown that the clothing patterns generated by the proposed MS-SA-GAN model are superior to the conventional algorithms in some local texture detail indexes. In addition, a group of clothing design professionals is invited to evaluate the global artistic perception through a valence-arousal scale. The scale results have shown that the proposed MS-SA-GAN model achieves a better global art perception.

Mixed Attention Mechanism Generative Adversarial Network Painting Image Conversion Algorithm Based on Multi-Class Scenes

“…It used multi-scale discriminators to process local texture details and utilizes self attention mechanisms to enhance the system's artistic perception ability. This method has good running speed and can effectively generate paper pattern schemes that meet the requirements [14]. Y Fan et al proposed a GAN-based perception method for detecting abnormal behavior in videos, which alternates training between generative adversarial and perceptual adversarial algorithms to establish a dual stream structure for policy updates.…”

The application of robotics and artificial intelligence in embroidery: challenges and benefits

“…It has been popular to take Chinese traditional textile patterns as the investigation entity and adopt conditional generative adversarial network models and computer-aided solutions to research the generation of Chinese traditional textile patterns to solve the problems of old styles, lack of innovation and high cost of manual design of Chinese traditional textile patterns (Liu and Zhou, 2022). Researchers have performed the academic investigation and creative practice of the conditional generative adversarial network models in creating traditional Chinese patterns for cultural and creative objectives (Wu et al, 2021;Cui et al, 2018;Yu and Luo, 2021). Wu et al (2021) proposed a framework called ClothGAN for innovative clothes pattern and style design.…”

Bearing Fault Diagnosis Using ACWGAN-GP Enhanced by Principal Component Analysis

“…These new samples are different from the original samples, but their distribution is similar. However, GAN often has problems, such as gradient explosion or disappearance, slow convergence speed, and poor ability to learn data features during training [13]. In order to increase the stability of the GAN model during the training process and improve the ability of the generated samples to express features, scholars have improved the GAN accordingly.…”