InjectionGAN: Unified Generative Adversarial Networks for Arbitrary Image Attribute Editing

Ding, Chen; Kang, Wei; Zhu, Jiaqi; Du, Shuangyan

doi:10.1109/access.2020.3003139

Cited by 5 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The block diagram of the proposed model is shown in Figure 2. The encoder, decoder, and FTU [20] make the Generator module, and Critic D and Classifier C make the Discriminator module.…”

Section: Methodsmentioning

confidence: 99%

Facial Attribute Editing Using Generative Adversarial Network

Upadhyay,

Lamichhane,

Nyaupane

2023

J. Eng. Sci.

View full text Add to dashboard Cite

Facial attribute editing tasks have immense applications in today’s digital world, including virtual makeup, generating faces in the animation and gaming industry, social media face image enhancement and improving face recognition systems. This task can be achieved manually or automatically. Manual facial attribute editing, performed with software such as Adobe Photoshop, is a tedious and time-consuming process that requires an expert person. However, Automatic facial attribute editing tasks that can perform facial attribute editing within a few seconds are achievable using encoder-decoder and deep learning-based generative models, such as conditional Generative Adversarial Networks. In our work, we use different attribute vectors as conditional information to generate desired target images, and encoder-decoder structures incorporate feature transfer units to choose and alter encoder-based features. Later, these encoder features are concatenated with the decoder feature to strengthen the attribute editing ability of the model. For this research, we apply reconstruction loss to preserve other details of a face image except target attributes. Adversarial loss is employed for visually realistic editing and attribute manipulation loss is employed to ensure that the generated image possesses the correct attributes. Furthermore, we adopt the WGAN-GP loss function type to improve training stability and reduce the mode collapse problem that often occurs in GAN. Experiments on the Celebi dataset show that this method produces visually realistic facial attribute edited images with PSNR/SSIM 31.7/0.95 and 89.23 % of average attribute editing accuracy for 13 facial attributes including Bangs, Mustache, Bald, Bushy Eyebrows, Blond Hair, Eyeglasses, Black Hair, Brown Hair, Mouth Slightly Open, Male, No Beard, pale Skin and Young.

show abstract

“…The block diagram of the proposed model is shown in Figure 2. The encoder, decoder, and FTU [20] make the Generator module, and Critic D and Classifier C make the Discriminator module.…”

Section: Methodsmentioning

confidence: 99%

Facial Attribute Editing Using Generative Adversarial Network

Upadhyay,

Lamichhane,

Nyaupane

2023

J. Eng. Sci.

View full text Add to dashboard Cite

show abstract

“…While the above model provides a multifaceted method of clothing style design, there are few studies research on the details of style change. The blurred shape editing effect of images (Liu et al, 2019a, b, c;Ding et al, 2020) and the inability to preserve irrelevant attributes (such as patterns and textures) are issues that need to be addressed (Chan et al, 2022;Zhang et al, 2018).…”

Section: Attribute Editingmentioning

confidence: 99%

“…The blurred shape editing effect of images (Liu et al. , 2019a, b, c; Ding et al. , 2020) and the inability to preserve irrelevant attributes (such as patterns and textures) are issues that need to be addressed (Chan et al.…”

Section: Related Workmentioning

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

“…InjectionGAN [34], shown in Figure 22, is another U-net based conditional model in which the condition vector is concatenated to the embedding extracted by the encoding part of the model. This model proposed a Feature Transformation (FT) module which is embedded in skip connections.…”

Section: A Architecturesmentioning

confidence: 99%