paper-with-me

홈 › Papers

Lifting 2D StyleGAN for 3D-Aware Face Generation

2020-11-26 · CVPR 2021 1 · Yichun Shi, Divyansh Aggarwal, Anil K. Jain

We propose a framework, called LiftedGAN, that disentangles and lifts a pre-trained StyleGAN2 for 3D-aware face generation. Our model is "3D-aware" in the sense that it is able to (1) disentangle the latent space of StyleGAN2 into texture, shape, viewpoint, lighting and (2) generate 3D components for rendering synthetic images. Unlike most previous methods, our method is completely self-supervised, i.e. it neither requires any manual annotation nor 3DMM model for training. Instead, it learns to generate images as well as their 3D components by distilling the prior knowledge in StyleGAN2 with a differentiable renderer. The proposed model is able to output both the 3D shape and texture, allowing explicit pose and lighting control over generated images. Qualitative and quantitative results show the superiority of our approach over existing methods on 3D-controllable GANs in content controllability while generating realistic high quality images.

📄 PDF Abstract BibTeX arXiv:2011.13126

Code (1)

seasonSH/LiftedGAN 공식 구현 pytorch

Tasks

Face 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…
Path Length Regularization 설명 없음
R1 Regularization R_INLINE_MATH_1 Regularization is a regularization technique and gradient penalty for training [generative adversarial…
Weight Demodulation 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…
StyleGAN2 StyleGAN2 is a generative adversarial network that builds on StyleGAN with several improvements. First, [adaptive instance…

Similar Papers 제목 키워드 기반

Face Generation and Editing with StyleGAN: A Survey

2022-12-18 · Andrew Melnik, Maksim Miasayedzenkau, Dzianis Makarovets, Dzianis Pirshtuk 외

Our goal with this survey is to provide an overview of the state of the art deep learning methods for face generation and editing using StyleGAN. The survey covers the evolution of StyleGAN, from PGGAN to StyleGAN3, and …

Deep LearningFace GenerationFace SwappingStyle Transfer+1

Grasping the Arrow of Time from the Singularity: Decoding Micromotion in Low-dimensional Latent Spaces from StyleGAN

2022-04-27 · Qiucheng Wu, Yifan Jiang, Junru Wu, Kai Wang 외

The disentanglement of StyleGAN latent space has paved the way for realistic and controllable image editing, but does StyleGAN know anything about temporal motion, as it was only trained on static images? To study the mo…

DisentanglementFace Generation

DrawingInStyles: Portrait Image Generation and Editing with Spatially Conditioned StyleGAN

2022-03-05 · Wanchao Su, Hui Ye, Shu-Yu Chen, Lin Gao 외

The research topic of sketch-to-portrait generation has witnessed a boost of progress with deep learning techniques. The recently proposed StyleGAN architectures achieve state-of-the-art generation ability but the origin…

Image Generation

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

Tackling fake images in cybersecurity -- Interpretation of a StyleGAN and lifting its black-box

2025-07-18 · Julia Laubmann, Johannes Reschke arxiv

In today's digital age, concerns about the dangers of AI-generated images are increasingly common. One powerful tool in this domain is StyleGAN (style-based generative adversarial networks), a generative adversarial netw…