AttGAN: Facial Attribute Editing by Only Changing What You Want

He, Zhenliang; Zuo, Wangmeng; Kan, Meina; Shan, Shiguang; Chen, Xilin

doi:10.48550/arxiv.1711.10678

Cited by 31 publications

(93 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides producing impressive image samples, generative adversarial networks (GANs) [9] have been shown to learn meaningful latent spaces [18] with extensive studies on multiple derived spaces [15,44] and various knobs and controls for conditional human face generation [12,28,42]. Encoding an image to the GAN's latent space requires an optimization-based inversion process [19,45] or an external image encoder [30], which has limited reconstruction fidelity (or produces latent codes in much higher dimensions outside the learned manifold).…”

Section: Related Workmentioning

confidence: 99%

Diffusion Autoencoders: Toward a Meaningful and Decodable Representation

Preechakul¹,

Chatthee²,

Wizadwongsa³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

Diffusion Autoencoders: Toward a Meaningful and Decodable Representation

Preechakul¹,

Chatthee²,

Wizadwongsa³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…ELEGANT [27] applies a U-Net structure [22] on the basis of DNA-GAN for high-resolution image generation. Star-GAN [4] and AttGAN [8] realize attribute transfer by introducing an attribute classification loss. Moreover, Star-GAN [4] designs a conditional attribute transfer network to learn attributes in a cyclic process, while AttGAN [8] devises an encoder-decoder architecture to model the relationship between the latent representations and the attributes.…”

Section: Image Attribute Transfermentioning

confidence: 99%

“…Star-GAN [4] and AttGAN [8] realize attribute transfer by introducing an attribute classification loss. Moreover, Star-GAN [4] designs a conditional attribute transfer network to learn attributes in a cyclic process, while AttGAN [8] devises an encoder-decoder architecture to model the relationship between the latent representations and the attributes. Both StarGAN and AttGAN are designed for learning multiple attributes simultaneously.…”

Section: Image Attribute Transfermentioning

confidence: 99%

Fully-Featured Attribute Transfer

Xie¹,

Yang²,

Deng³

et al. 2019

Preprint

View full text Add to dashboard Cite

Image attribute transfer aims to change an input image to a target one with expected attributes, which has received significant attention in recent years. However, most of the existing methods lack the ability to de-correlate the target attributes and irrelevant information, i.e., the other attributes and background information, thus often suffering from blurs and artifacts. To address these issues, we propose a novel Attribute Manifold Encoding GAN (AME-GAN) for fully-featured attribute transfer, which can modify and adjust every detail in the images. Specifically, our method divides the input image into image attribute part and image background part on manifolds, which are controlled by attribute latent variables and background latent variables respectively. Through enforcing attribute latent variables to Gaussian distributions and background latent variables to uniform distributions respectively, the attribute transfer procedure becomes controllable and image generation is more photo-realistic. Furthermore, we adopt a conditional multi-scale discriminator to render accurate and high-quality target attribute images. Experimental results on three popular datasets demonstrate the superiority of our proposed method in both performances of the attribute transfer and image generation quality.

show abstract

“…Recently, class-conditional extensions of GANs were applied to not only to image generation but also to image-to-image translation [6,14,44,61] (including Star-GAN [6]). Their goal is to achieve multi-domain image-to-image translation (i.e., to obtain mappings among multiple domains) using few-parameter models.…”

Section: Related Workmentioning

confidence: 99%

“…network architecture is the same as that of StarGAN [6]. 14 As a GAN objective, we used WGAN-GP [12] and trained the model using the Adam optimizer [22] with a minibatch of size 16. We set the parameters to the default values of the StarGAN, i.e., λ rec = 10, λ GP = 10, n D = 5, α = 0.0001, β 1 = 0.5, and β 2 = 0.999.…”

Section: C3 Clothing1mmentioning

confidence: 99%

Class-Distinct and Class-Mutual Image Generation with GANs

Kaneko¹,

Ushiku²,

Harada³

2018

Preprint

View full text Add to dashboard Cite

Class-conditional extensions of generative adversarial networks (GANs), such as auxiliary classifier GAN (AC-GAN) and conditional GAN (cGAN), have garnered attention owing to their ability to decompose representations into class labels and other factors and to boost the training stability. However, a limitation is that they assume that each class is separable and ignore the relationship between classes even though class overlapping frequently occurs in a real-world scenario when data are collected on the basis of diverse or ambiguous criteria. To overcome this limitation, we address a novel problem called class-distinct and class-mutual image generation, in which the goal is to construct a generator that can capture between-class relationships and generate an image selectively conditioned on the class specificity. To solve this problem without additional supervision, we propose classifier's posterior GAN (CP-GAN), in which we redesign the generator input and the objective function of AC-GAN for class-overlapping data. Precisely, we incorporate the classifier's posterior into the generator input and optimize the generator so that the classifier's posterior of generated data corresponds with that of real data. We demonstrate the effectiveness of CP-GAN using both controlled and real-world class-overlapping data with a model configuration analysis and comparative study. Our code is available at https://github.com/takuhirok/CP-GAN/.

show abstract

AttGAN: Facial Attribute Editing by Only Changing What You Want

Cited by 31 publications

References 0 publications

Diffusion Autoencoders: Toward a Meaningful and Decodable Representation

Diffusion Autoencoders: Toward a Meaningful and Decodable Representation

Fully-Featured Attribute Transfer

Class-Distinct and Class-Mutual Image Generation with GANs

Contact Info

Product

Resources

About