paper-with-me

홈 › Papers

StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets

2022-02-01 · Axel Sauer, Katja Schwarz, Andreas Geiger

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.

📄 PDF Abstract BibTeX arXiv:2202.00273

Code (2)

autonomousvision/stylegan_xl 공식 구현 pytorch
autonomousvision/stylegan-xl pytorch

Tasks

Image Generation

Methods 이 논문이 사용한 방법론

HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…
Adaptive Instance Normalization 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
R1 Regularization R_INLINE_MATH_1 Regularization is a regularization technique and gradient penalty for training [generative adversarial…
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…

Similar Papers 제목 키워드 기반

Feature Proliferation -- the "Cancer" in StyleGAN and its Treatments

2023-10-13 · ICCV 2023 1 · Shuang Song, Yuanbang Liang, Jing Wu, Yu-Kun Lai 외

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 Generation

Self-Distilled StyleGAN: Towards Generation from Internet Photos

2022-02-24 · Ron Mokady, Michal Yarom, Omer Tov, Oran Lang 외

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 Generation

StyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned Faces

2023-03-10 · ICCV 2023 1 · Shuai Yang, Liming Jiang, Ziwei Liu, Chen Change Loy

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-Resolution

Re-Training StyleGAN -- A First Step Towards Building Large, Scalable Synthetic Facial Datasets

2020-03-24 · Viktor Varkarakis, Shabab Bazrafkan, Peter Corcoran

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 Network

Exploring StyleGAN Latent Space for Face Alignment with Limited Training Data

2022-09-16 · HAL 2022 9 · Martin Dornier, Philippe-Henri Gosselin, Christian Raymond, Yann Ricquebourg 외

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