A Style-Based Generator Architecture for Generative Adversarial Networks
Tero Karras,Samuli Laine,Timo Aila +2 more
- pp 4396-4405
Reads0
Chats0
TLDR
This paper proposed an alternative generator architecture for GANs, borrowing from style transfer literature, which leads to an automatically learned, unsupervised separation of high-level attributes (e.g., pose and identity when trained on human faces) and stochastic variation in the generated images.Abstract:
We propose an alternative generator architecture for generative adversarial networks, borrowing from style transfer literature. The new architecture leads to an automatically learned, unsupervised separation of high-level attributes (e.g., pose and identity when trained on human faces) and stochastic variation in the generated images (e.g., freckles, hair), and it enables intuitive, scale-specific control of the synthesis. The new generator improves the state-of-the-art in terms of traditional distribution quality metrics, leads to demonstrably better interpolation properties, and also better disentangles the latent factors of variation. To quantify interpolation quality and disentanglement, we propose two new, automated methods that are applicable to any generator architecture. Finally, we introduce a new, highly varied and high-quality dataset of human faces.read more
Citations
More filters
Journal ArticleDOI
InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs
TL;DR: InterFaceGAN as discussed by the authors proposes a framework called InterFaceGAN to interpret the disentangled face representation learned by the state-of-the-art GAN models and study the properties of the facial semantics encoded in the latent space.
Proceedings ArticleDOI
Tag2Pix: Line Art Colorization Using Text Tag With SECat and Changing Loss
TL;DR: In this article, a generative adversarial network (GAN) is proposed for line art colorization, which takes as input a grayscale line art and color tag information and produces a quality colored image.
Journal ArticleDOI
Learning Spatial Attention for Face Super-Resolution
TL;DR: A novel SPatial Attention Residual Network (SPARNet) built on the authors' newly proposed Face Attention Units (FAUs) for face super-resolution is introduced, and a spatial attention mechanism to the vanilla residual blocks is introduced to enable the convolutional layers to adaptively bootstrap features related to the key face structures and pay less attention to those less feature-rich regions.
Posted Content
ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows
TL;DR: ArtFlow is proposed to prevent content leak during universal style transfer using reversible neural flows and an unbiased feature transfer module that supports both forward and backward inferences and operates in a projection-transfer-reversion scheme.
Posted Content
Adversarial score matching and improved sampling for image generation
TL;DR: This work proposes two improvements to DSM-ALS: 1) Consistent Annealed Sampling as a more stable alternative to Annealed Langevin Sampling, and 2) a hybrid training formulation, composed of both Denoising Score Matching and adversarial objectives.