Jul 29, 2022 · Employing priors from different generative models allows GLEAN to be applied to diverse categories (\eg~human faces, cats, buildings, and cars).

Abstract—We show that pre-trained Generative Adversarial Networks (GANs) such as StyleGAN and BigGAN can be used as a latent bank to improve the performance ...

We show that pre-trained Generative Adversarial Networks (GANs), eg, StyleGAN, can be used as a latent bank to improve the restoration quality of large-factor ...

We show that pre-trained Generative Adversarial Networks (GANs) such as StyleGAN and BigGAN can be used as a latent bank to improve the performance of image ...

GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution (CVPR 2021) Note: This repository is to provide meta info for training and test only.

Our work goes beyond previous works and pushes the limit to 64× and generalizes to more cate- gories. Such a large magnification factor is challenging due to ...

Abstract: We show that pre-trained Generative Adversarial Networks (GANs), e.g., StyleGAN, can be used as a latent bank to improve the restoration quality ...

We show that pre-trained Generative Adversarial Networks (GANs) such as StyleGAN and BigGAN can be used as a latent bank to improve the performance of image ...

We present a new way to exploit pre-trained GANs for the task of large-scale super-resolution, up to 64× upscaling factor.

Dec 1, 2020 · This work shows that pre-trained Generative Adversarial Networks (GANs), e.g., StyleGAN, can be used as a latent bank to improve the ...