paper-with-me

Papers

AE-StyleGAN: Improved Training of Style-Based Auto-Encoders

2021-10-17 · Ligong Han, Sri Harsha Musunuri, Martin Renqiang Min, Ruijiang Gao, Yu Tian, Dimitris Metaxas

StyleGANs have shown impressive results on data generation and manipulation in recent years, thanks to its disentangled style latent space. A lot of efforts have been made in inverting a pretrained generator, where an encoder is trained ad hoc after the generator is trained in a two-stage fashion. In this paper, we focus on style-based generators asking a scientific question: Does forcing such a generator to reconstruct real data lead to more disentangled latent space and make the inversion process from image to latent space easy? We describe a new methodology to train a style-based autoencoder where the encoder and generator are optimized end-to-end. We show that our proposed model consistently outperforms baselines in terms of image inversion and generation quality. Supplementary, code, and pretrained models are available on the project website.

📄 PDF Abstract BibTeX arXiv:2110.08718

Code (1)

phymhan/stylegan2-pytorch 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

HOC 설명 없음

Similar Papers 제목 키워드 기반

Adversarial Latent Autoencoders

2020-04-09 · CVPR 2020 6 · Stanislav Pidhorskyi, Donald Adjeroh, Gianfranco Doretto

Autoencoder networks are unsupervised approaches aiming at combining generative and representational properties by learning simultaneously an encoder-generator map. Although studied extensively, the issues of whether the…

DisentanglementImage Generation

HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing

2021-11-30 · CVPR 2022 1 · Yuval Alaluf, Omer Tov, Ron Mokady, Rinon Gal 외

The inversion of real images into StyleGAN's latent space is a well-studied problem. Nevertheless, applying existing approaches to real-world scenarios remains an open challenge, due to an inherent trade-off between reco…

Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation

2020-08-03 · CVPR 2021 1 · Elad Richardson, Yuval Alaluf, Or Patashnik, Yotam Nitzan 외

We present a generic image-to-image translation framework, pixel2style2pixel (pSp). Our pSp framework is based on a novel encoder network that directly generates a series of style vectors which are fed into a pretrained …

Conditional Image GenerationFace GenerationImage-to-Image TranslationTranslation

Overparameterization Improves StyleGAN Inversion

2022-05-12 · Yohan Poirier-Ginter, Alexandre Lessard, Ryan Smith, Jean-François Lalonde

Deep generative models like StyleGAN hold the promise of semantic image editing: modifying images by their content, rather than their pixel values. Unfortunately, working with arbitrary images requires inverting the Styl…

Image Reconstruction

Pose and Facial Expression Transfer by using StyleGAN

2025-04-17 · Petr Jahoda, Jan Cech

We propose a method to transfer pose and expression between face images. Given a source and target face portrait, the model produces an output image in which the pose and expression of the source face image are transferr…