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
Proceedings ArticleDOI
SimSwap: An Efficient Framework For High Fidelity Face Swapping
TL;DR: An efficient framework, called Simple Swap (SimSwap), aiming for generalized and high fidelity face swapping, which is capable of transferring the identity of an arbitrary source face into an arbitrary target face while preserving the attributes of the target face.
Proceedings ArticleDOI
ESRGAN+ : Further Improving Enhanced Super-Resolution Generative Adversarial Network
TL;DR: A network architecture with a novel basic block to replace the one used by the original ESRGAN is designed and noise inputs to the generator network are introduced in order to exploit stochastic variation.
Proceedings ArticleDOI
OC-FakeDect: Classifying Deepfakes Using One-Class Variational Autoencoder
Hasam Khalid,Simon S. Woo +1 more
TL;DR: OC-FakeDect is proposed, which uses a one-class Variational Autoencoder (VAE) to train only on real face images and detects non-real images such as deepfakes by treating them as anomalies.
Journal ArticleDOI
Muse: Text-To-Image Generation via Masked Generative Transformers
Hui Il Chang,Han Zhang,Jarred Barber,AJ Maschinot,José Lezama,Lu Jiang,Ming-Xue Yang,Kevin Murphy,William T. Freeman,Michael Rubinstein,Yuanzhen Li,D. Krishnan +11 more
TL;DR: Muse as discussed by the authors is a text-to-image Transformer model that achieves state-of-the-art image generation performance while being significantly more efficient than diffusion or autoregressive models.
Proceedings Article
Controlling generative models with continuous factors of variations
TL;DR: In this paper, the authors propose to find meaningful directions in the latent space of any generative model along which they can move to control precisely specific properties of the generated image like position or scale of the object in the image.