StyleGAN

E290872

deep learning model generative adversarial network architecture image synthesis model

StyleGAN is a state-of-the-art generative adversarial network architecture known for producing highly realistic, controllable images by manipulating disentangled style representations at different layers of the network.

Try in SPARQL Jump to: Surface forms Statements Referenced by

All labels observed (7)

Label	Occurrences
StyleGAN canonical	2
A Style-Based Generator Architecture for Generative Adversarial Networks	1
StyleGAN family	1
StyleGAN-ADA	1
StyleGAN-XL	1
StyleGAN2	1
StyleGAN3	1

Statements (50)

Predicate	Object
instanceOf	deep learning model ⓘ generative adversarial network architecture ⓘ image synthesis model ⓘ
applicationDomain	art generation ⓘ data augmentation ⓘ face generation ⓘ image synthesis ⓘ
basedOn	GAN ⓘ Progressive GAN ⓘ surface form: Progressive Growing of GANs
controlsCoarseFeatures	high-level styles ⓘ
controlsFeaturesAt	different layers of the network ⓘ
controlsFineFeatures	low-level styles ⓘ
developedBy	NVIDIA Corporation ⓘ surface form: NVIDIA
discriminatorType	convolutional neural network ⓘ
firstPublicReleaseYear	2019 ⓘ
firstPublishedYear	2018 ⓘ
generatorType	style-based generator ⓘ
hasComponent	mapping network ⓘ noise inputs ⓘ style blocks ⓘ synthesis network ⓘ
hasKeyConcept	adaptive instance normalization ⓘ disentangled latent representations ⓘ multi-scale style control ⓘ noise injection ⓘ stochastic variation ⓘ style modulation ⓘ style-based generator ⓘ
hasOfficialRepository	https://github.com/NVlabs/stylegan ⓘ
hasSuccessor	StyleGAN self-linksurface differs ⓘ surface form: StyleGAN2 StyleGAN self-linksurface differs ⓘ surface form: StyleGAN3
implementedIn	TensorFlow ⓘ
influenced	StyleGAN self-linksurface differs ⓘ surface form: StyleGAN-ADA StyleGAN self-linksurface differs ⓘ surface form: StyleGAN-XL many subsequent GAN architectures ⓘ
introducedBy	Samuli Laine ⓘ Tero Karras ⓘ Timo Aila ⓘ
introducedInPaper	StyleGAN self-linksurface differs ⓘ surface form: A Style-Based Generator Architecture for Generative Adversarial Networks
license	NVIDIA Source Code License ⓘ
mapsLatentSpaceWith	mapping network ⓘ
notableFor	disentangled style representations ⓘ fine-grained control over image attributes ⓘ highly realistic images ⓘ
publishedAtConference	IEEE Computer Society Conference on Computer Vision and Pattern Recognition ⓘ surface form: CVPR 2019
trainingDataset	CelebA ⓘ surface form: CelebA-HQ FFHQ ⓘ
usesLatentSpace	W space ⓘ Z space ⓘ
usesOperation	AdaIN ⓘ

Referenced by (8)

Full triples — surface form annotated when it differs from this entity's canonical label.

Generative Adversarial Networks → notableVariant → StyleGAN ⓘ

Deep Convolutional GAN → inspired → StyleGAN ⓘ

this entity surface form: StyleGAN family

StyleGAN → introducedInPaper → StyleGAN self-linksurface differs ⓘ

this entity surface form: A Style-Based Generator Architecture for Generative Adversarial Networks

StyleGAN → hasSuccessor → StyleGAN self-linksurface differs ⓘ

this entity surface form: StyleGAN2

StyleGAN → hasSuccessor → StyleGAN self-linksurface differs ⓘ

this entity surface form: StyleGAN3

StyleGAN → influenced → StyleGAN self-linksurface differs ⓘ

this entity surface form: StyleGAN-ADA

StyleGAN → influenced → StyleGAN self-linksurface differs ⓘ

this entity surface form: StyleGAN-XL

Progressive GAN → inspired → StyleGAN ⓘ