paper-with-me

홈 › Papers

StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation

2020-11-25 · CVPR 2021 1 · Zongze Wu, Dani Lischinski, Eli Shechtman

We explore and analyze the latent style space of StyleGAN2, a state-of-the-art architecture for image generation, using models pretrained on several different datasets. We first show that StyleSpace, the space of channel-wise style parameters, is significantly more disentangled than the other intermediate latent spaces explored by previous works. Next, we describe a method for discovering a large collection of style channels, each of which is shown to control a distinct visual attribute in a highly localized and disentangled manner. Third, we propose a simple method for identifying style channels that control a specific attribute, using a pretrained classifier or a small number of example images. Manipulation of visual attributes via these StyleSpace controls is shown to be better disentangled than via those proposed in previous works. To show this, we make use of a newly proposed Attribute Dependency metric. Finally, we demonstrate the applicability of StyleSpace controls to the manipulation of real images. Our findings pave the way to semantically meaningful and well-disentangled image manipulations via simple and intuitive interfaces.

📄 PDF Abstract BibTeX arXiv:2011.12799

Code (6)

betterze/StyleSpace 공식 구현 tf
eladrich/pixel2style2pixel pytorch
futscdav/Chunkmogrify pytorch
mikelasz/fair-psp pytorch
orpatashnik/StyleCLIP pytorch
xrenaa/StyleSpace-pytorch pytorch

Tasks

AttributeImage Generation

Methods 이 논문이 사용한 방법론

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

Similar Papers 제목 키워드 기반

Explaining in Style: Training a GAN to explain a classifier in StyleSpace

2021-04-27 · ICCV 2021 10 · Oran Lang, Yossi Gandelsman, Michal Yarom, Yoav Wald 외

Image classification models can depend on multiple different semantic attributes of the image. An explanation of the decision of the classifier needs to both discover and visualize these properties. Here we present StylE…

image-classificationImage Classification

Third Time's the Charm? Image and Video Editing with StyleGAN3

2022-01-31 · Yuval Alaluf, Or Patashnik, Zongze Wu, Asif Zamir 외

StyleGAN is arguably one of the most intriguing and well-studied generative models, demonstrating impressive performance in image generation, inversion, and manipulation. In this work, we explore the recent StyleGAN3 arc…

DisentanglementImage GenerationVideo Editing

Video2StyleGAN: Disentangling Local and Global Variations in a Video

2022-05-27 · Rameen Abdal, Peihao Zhu, Niloy J. Mitra, Peter Wonka

Image editing using a pretrained StyleGAN generator has emerged as a powerful paradigm for facial editing, providing disentangled controls over age, expression, illumination, etc. However, the approach cannot be directly…

Facial Editing

StyleDomain: Efficient and Lightweight Parameterizations of StyleGAN for One-shot and Few-shot Domain Adaptation

2022-12-20 · ICCV 2023 1 · Aibek Alanov, Vadim Titov, Maksim Nakhodnov, Dmitry Vetrov

Domain adaptation of GANs is a problem of fine-tuning GAN models pretrained on a large dataset (e.g. StyleGAN) to a specific domain with few samples (e.g. painting faces, sketches, etc.). While there are many methods tha…

Domain AdaptationImage MorphingImage-to-Image Translation

Which Style Makes Me Attractive? Interpretable Control Discovery and Counterfactual Explanation on StyleGAN

2022-01-24 · Bo Li, Qiulin Wang, JiQuan Pei, Yu Yang 외

The semantically disentangled latent subspace in GAN provides rich interpretable controls in image generation. This paper includes two contributions on semantic latent subspace analysis in the scenario of face generation…

counterfactualCounterfactual ExplanationDisentanglementFace Generation+2