Attribute-Aware Generative Design With Generative Adversarial Networks

Yuan, Chenxi; Moghaddam, Mohsen

doi:10.1109/access.2020.3032280

Cited by 32 publications

(12 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the Wasserstein GAN (WGAN) model, the stability and generation efficiency of ACGAN can be further improved 31 , 32 . The distance among distributions is measured using Wasserstein distance.…”

Section: Methodsmentioning

confidence: 99%

Interactive design generation and optimization from generative adversarial networks in spatial computing

Hu,

Lin,

Chen

et al. 2024

Sci Rep

View full text Add to dashboard Cite

This paper focuses on exploring the application possibilities and optimization problems of Generative Adversarial Networks (GANs) in spatial computing to improve design efficiency and creativity and achieve a more intelligent design process. A method for icon generation is proposed, and a basic architecture for icon generation is constructed. A system with generation and optimization capabilities is constructed to meet various requirements in spatial design by introducing the concept of interactive design and the characteristics of requirement conditions. Next, the generated icons can effectively maintain diversity and innovation while meeting the conditional features by integrating multi-feature recognition modules into the discriminator and optimizing the structure of conditional features. The experiment uses publicly available icon datasets, including LLD-Icon and Icons-50. The icon shape generated by the model proposed here is more prominent, and the color of colored icons can be more finely controlled. The Inception Score (IS) values under different models are compared, and it is found that the IS value of the proposed model is 7.05, which is higher than that of other GAN models. The multi-feature icon generation model based on Auxiliary Classifier GANs performs well in presenting multiple feature representations of icons. After introducing multi-feature recognition modules into the network model, the peak error of the recognition network is only 2.000 in the initial stage, while the initial error of the ordinary GAN without multi-feature recognition modules is as high as 5.000. It indicates that the improved model effectively helps the discriminative network recognize the core information of icon images more quickly. The research results provide a reference basis for achieving more efficient and innovative interactive space design.

show abstract

Section: Methodsmentioning

confidence: 99%

Interactive design generation and optimization from generative adversarial networks in spatial computing

Hu,

Lin,

Chen

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Generative design is an emerging approach, especially in the Computer Aided Design (CAD) community (Krish, 2011). The combination of generative design with additive manufacturing has been of great interest recently (Wu et al, 2019) with the incorporation of surrogate modeling methods into the generative design framework explored in recent literature (Oh et al, 2019;Yuan and Moghaddam, 2020;Kallioras and Lagaros, 2020). Valid designs in the dataset must satisfy the previously-discussed constraints on the design space.…”

Section: Methodsmentioning

confidence: 99%

Examining the Impact of Asymmetry in Lattice-Based Mechanical Metamaterials

Srivatsa¹,

Kumar²,

Selva³

et al. 2021

Preprint

View full text Add to dashboard Cite

Lattice-based mechanical metamaterials can be tailored for a wide variety of applications by modifying the underlying mesostructure. However, most existing lattice patterns take symmetry as a starting point. We show that asymmetric lattice patterns can be more likely to have certain mechanical properties than symmetric lattice patterns. To directly compare the effects of asymmetric versus symmetric lattice arrangements, a constrained design space is defined. A generative design process is used to randomly generate both symmetric and asymmetric lattice patterns within the design space. Asymmetric lattice patterns are shown to be more likely to have higher shear stiffness values, as well as a broader range of axial stiffness values and Poisson's ratios. Key design features are identified that are present predominantly in asymmetric lattice patterns. We show that asymmetric lattice patterns with two of these features (arrows and spider nodes) are more likely to induce a broader range of axial stiffness values and Poisson's ratios, in addition to larger shear stiffness values, compared to lattice patterns without these features. In addition, some of these features also have an impact on symmetric lattice patterns. This work provides insights into the benefits of using asymmetric lattice patterns in select metamaterial design applications.

show abstract

“…Fashion-AttGAN introduces an editing model based on the AttGAN model, whose attributes are limited to color and sleeve length. For the purpose of expressing the practicality of generative models in the field of product design, design attribute GAN (DAGAN) (Yuan and Moghaddam, 2020) adopts a new loss function on the basis of AttGAN and uses the different discriminator losses of DCGAN. Attribute manipulation GAN (AMGAN) (Ak et al, 2019) model combines CGAN, convolutional neural networks (CNN) and class activation maps (CAMs) to achieve fine control of sleeve and collar shape.…”

Section: Attribute Editingmentioning

confidence: 99%

Clothing image attribute editing based on generative adversarial network, with reference to an upper garment

Wang,

Xiao,

Fang

2024

IJCST

View full text Add to dashboard Cite

PurposeNowadays, artificial intelligence (AI) technology has demonstrated extensive applications in the field of art design. Attribute editing is an important means to realize clothing style and color design via computer language, which aims to edit and control the garment image based on the specified target attributes while preserving other details from the original image. The current image attribute editing model often generates images containing missing or redundant attributes. To address the problem, this paper aims for a novel design method utilizing the Fashion-attribute generative adversarial network (AttGAN) model was proposed for image attribute editing specifically tailored to women’s blouses.Design/methodology/approachThe proposed design method primarily focuses on optimizing the feature extraction network and loss function. To enhance the feature extraction capability of the model, an increase in the number of layers in the feature extraction network was implemented, and the structure similarity index measure (SSIM) loss function was employed to ensure the independent attributes of the original image were consistent. The characteristic-preserving virtual try-on network (CP_VTON) dataset was used for train-ing to enable the editing of sleeve length and color specifically for women’s blouse.FindingsThe experimental results demonstrate that the optimization model’s generated outputs have significantly reduced problems related to missing attributes or visual redundancy. Through a comparative analysis of the numerical changes in the SSIM and peak signal-to-noise ratio (PSNR) before and after the model refinement, it was observed that the improved SSIM increased substantially by 27.4%, and the PSNR increased by 2.8%, serving as empirical evidence of the effectiveness of incorporating the SSIM loss function.Originality/valueThe proposed algorithm provides a promising tool for precise image editing of women’s blouses based on the GAN. This introduces a new approach to eliminate semantic expression errors in image editing, thereby contributing to the development of AI in clothing design.

show abstract

Attribute-Aware Generative Design With Generative Adversarial Networks

Cited by 32 publications

References 53 publications

Interactive design generation and optimization from generative adversarial networks in spatial computing

Interactive design generation and optimization from generative adversarial networks in spatial computing

Examining the Impact of Asymmetry in Lattice-Based Mechanical Metamaterials

Clothing image attribute editing based on generative adversarial network, with reference to an upper garment

Contact Info

Product

Resources

About