StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
Computer graphics has experienced a recent surge of data-centric approaches for photorealistic and controllable content creation. StyleGAN in particular sets new standards for generative modeling regarding image quality and controllability. However, StyleGAN's performance severely degrades on large unstructured datasets such as ImageNet. StyleGAN was designed for controllability; hence, prior works suspect its restrictive design to be unsuitable for diverse datasets. In contrast, we find the main limiting factor to be the current training strategy. Following the recently introduced Projected GAN paradigm, we leverage powerful neural network priors and a progressive growing strategy to successfully train the latest StyleGAN3 generator on ImageNet. Our final model, StyleGAN-XL, sets a new state-of-the-art on large-scale image synthesis and is the first to generate images at a resolution of $1024^2$ at such a dataset scale. We demonstrate that this model can invert and edit images beyond the narrow domain of portraits or specific object classes.
Code (2)
Tasks
Image GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Feature Proliferation -- the "Cancer" in StyleGAN and its Treatments
Despite the success of StyleGAN in image synthesis, the images it synthesizes are not always perfect and the well-known truncation trick has become a standard post-processing technique for StyleGAN to synthesize high-qua…
Image GenerationSelf-Distilled StyleGAN: Towards Generation from Internet Photos
StyleGAN is known to produce high-fidelity images, while also offering unprecedented semantic editing. However, these fascinating abilities have been demonstrated only on a limited set of datasets, which are usually stru…
Image GenerationStyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned Faces
Recent advances in face manipulation using StyleGAN have produced impressive results. However, StyleGAN is inherently limited to cropped aligned faces at a fixed image resolution it is pre-trained on. In this paper, we p…
AttributeSuper-ResolutionRe-Training StyleGAN -- A First Step Towards Building Large, Scalable Synthetic Facial Datasets
StyleGAN is a state-of-art generative adversarial network architecture that generates random 2D high-quality synthetic facial data samples. In this paper, we recap the StyleGAN architecture and training methodology and p…
Generative Adversarial NetworkExploring StyleGAN Latent Space for Face Alignment with Limited Training Data
With deep learning models growing in size over the years, sometimes exceeding a billion parameters now, the need for large, annotated training datasets grows too. To alleviate this problem, the interest in self-supervise…
Face AlignmentImage GenerationSelf-Supervised Learning