An automatic coloring method for ethnic costume sketches based on generative adversarial networks

Liu, Bo; Gan, Jianhou; Wen, Bangchun; Liufu, Yiping; Gao, Wei

doi:10.1016/j.asoc.2020.106786

Cited by 17 publications

(15 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhenrong et al 26 proposed Zhuang ethnic costume images generation method based on GAN. Liu et al 27 proposed a GAN‐based method for coloring ethnic costume sketches. Currently, there are no specific research results on the subject of grayscale image coloring of ethnic costumes.…”

Section: Related Workmentioning

confidence: 99%

Fine‐grained semantic ethnic costume high‐resolution image colorization with conditional GAN

Gan

Zhou

et al. 2021

Int J of Intelligent Sys

Self Cite

View full text Add to dashboard Cite

Grayscale image colorization, especially for ethnic costume images, is highly challenging due to its rich and complex color features. The existing image colorization methods usually take the costume image as a whole in practical applications that lead to the ignorance of the semantic information of different parts of the costume. It is known that each part's color distribution of the ethnic costume is different. So, the color mapping of other parts is also diverse, which is determined by distinctive ethnic characteristics. This study introduces fine‐grained level semantic information and proposes a high‐resolution image colorization model for ethnic costumes targeting enhancement, inspired by semantic‐level colorization. The semantic information of different regions of ethnic costumes has a significant impact on the performance of the coloring task. Using Pix2PixHD as the backbone network, we create a new network architecture that maintains color distribution correspondence and spatial consistency of costume images using fine‐grained semantic information. In our network, we take the splice result of fine‐grained semantic for ethnic costume and grayscale image as the conditions and then feed them into the generative adversarial networks. We also discuss and analyze the influences of the grayscale channel and fine‐grained semantics on discriminator. Extensive experiments demonstrate that our method performs well compared with other state‐of‐the‐art automatic colorization methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Fine‐grained semantic ethnic costume high‐resolution image colorization with conditional GAN

Gan

Zhou

et al. 2021

Int J of Intelligent Sys

Self Cite

View full text Add to dashboard Cite

show abstract

“…GAN can automatically color the sketch and quickly generated multiple alternatives. Liu et al [219] established an end-to-end GAN model for ethnic costume sketches colorization. Their results showed that GAN has an excellent ability to learn the color rules of ethnic costumes.…”

Section: Product Design Based On Image Datamentioning

confidence: 99%

Big Data driven Product Design: A Survey

Quan¹,

Li²,

Zeng³

et al. 2021

Preprint

View full text Add to dashboard Cite

With the improvement of living standards, user requirements of modern products are becoming increasingly more diversified and personalized. Traditional product design methods can no longer satisfy the market needs due to their strong subjectivity, small survey scope, poor real-time data, and lack of visual display, which calls for the development of big data driven product design methodology. Big data in the product lifecycle contains valuable information for guiding product design, such as customer preferences, market demands, product evaluation, and visual display: online product reviews reflect customer evaluations and requirements; product images contain information of shape,color, and texture which can inspire designers to get initial design schemes more quickly or even directly generate new product images. How to efficiently collect product design related data and exploit them effectively during the whole product design process is thus critical to modern product design. This paper aims to conduct a comprehensive survey on big data driven product design. It will help researchers and practitioners to comprehend the latest development of relevant studies and applications centered on how big data can be processed, analyzed, and exploited in aiding product design. We first introduce several representative traditional product design methods and highlight their limitations. Then we discuss current and potential applications of textual data, image data, audio data, and video data in product design cycles. Finally, major deficiencies of existing data driven product design studies and future research directions are summarized. We believe that this study can draw increasing attention to modern data driven product design.Keywords product design • big data • Kansei engineering • QFD • generative design * Correspondence.

show abstract

“…In recent years, the digital technology of image analysis has been gradually applied to the field of color analysis. Xu et al [5] and Hagtvedt et al [6] quantitatively analyzed the main colors extracted from ethnic costumes; Liu et al [7][8] proposed an improved color network model to succinctly express the quantitative elements of color; Liu et al [9] proposed a generative adversarial network-based automatic coloring model for ethnic costume sketching, which could obtain better coloring effects; Zhao [10], on the other hand, used an association rule algorithm to explore the color matching law in Miao costume color, which helps to explore and protect the color of Miao costumes. However, the current research on ethnic costume color still favors perceptual, and the scientific and innovative application of data samples on color characteristics is less.…”

Section: Introductionmentioning

confidence: 99%

Automatic Imagery Coloration and Regenerative Design of Ethnic Costume

Cao

Lin

et al. 2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

The imagery colors of traditional ethnic costumes are unique and have great reference value for modern design. In this paper, 3 representative minority costume images of Miao, Tibetan, and Korean were respectively selected as imagery sources, and 20 different structure types of patterns were chosen as the object to be colored. Image pre-processing, adaptive color extraction, and multi-dimensional features extraction were executed to build a color nexus network model. Based on the color parsing results, an algorithm for color migration of clothing images was designed and developed, which could output multiple types of color schemes. The overall rating of each color scheme was compared to introduce the optimal scheme. Also, the experimental part tested the effect of the color schemes in various scenarios. The average pre-processing time cost of a single image is 0.05 seconds, the output time of the color network diagram is 0.38 seconds, and the output time of a single-color scheme is 1.44 seconds. The study can quickly provide an auxiliary decision for contemporary pattern color design.

show abstract

An automatic coloring method for ethnic costume sketches based on generative adversarial networks

Cited by 17 publications

References 10 publications

Fine‐grained semantic ethnic costume high‐resolution image colorization with conditional GAN

Fine‐grained semantic ethnic costume high‐resolution image colorization with conditional GAN

Big Data driven Product Design: A Survey

Automatic Imagery Coloration and Regenerative Design of Ethnic Costume

Contact Info

Product

Resources

About