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
Book ChapterDOI
GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images
TL;DR: This paper proposed a method that is able to produce credible handwritten word images by conditioning the generative process with both calligraphic style features and textual content, guided by three complementary learning objectives: to produce realistic images, to imitate a certain handwriting style and to convey a specific textual content.
Proceedings ArticleDOI
Learning Formation of Physically-Based Face Attributes
Ruilong Li,Karl Bladin,Yajie Zhao,Chinmay Chinara,Owen Ingraham,Pengda Xiang,Xinglei Ren,Pratusha Prasad,Bipin Kishore,Jun Xing,Hao Li +10 more
TL;DR: In this article, a non-linear morphable face model is proposed to generate multifarious face geometry of pore-level resolution, coupled with material attributes for use in physically-based rendering.
Proceedings ArticleDOI
Generative Multiplane Images: Making a 2D GAN 3D-Aware
TL;DR: This work modifies a classical GAN, i.e .
Journal ArticleDOI
MimicGAN: Robust Projection onto Image Manifolds with Corruption Mimicking
TL;DR: Corruption mimicking is proposed—a new robust projection technique that utilizes a surrogate network to approximate the unknown corruption directly at test time, without the need for additional supervision or data augmentation, thereby enabling a more effective use of GANs in real-world applications.
Posted Content
TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up
TL;DR: TransGAN as discussed by the authors proposes a memory-friendly transformer-based generator that progressively increases feature resolution, and correspondingly a multi-scale discriminator to capture simultaneously semantic contexts and low-level textures.