Stylegan-t: Unlocking the power of gans for fast large-scale text-to-image synthesis

A Sauer, T Karras, S Laine… - … on machine learning, 2023‏ - proceedings.mlr.press
Text-to-image synthesis has recently seen significant progress thanks to large pretrained
language models, large-scale training data, and the introduction of scalable model families …

Stylesdf: High-resolution 3d-consistent image and geometry generation

R Or-El, X Luo, M Shan, E Shechtman… - Proceedings of the …, 2022‏ - openaccess.thecvf.com
We introduce a high resolution, 3D-consistent image and shape generation technique which
we call StyleSDF. Our method is trained on single view RGB data only, and stands on the …

Hyperstyle: Stylegan inversion with hypernetworks for real image editing

Y Alaluf, O Tov, R Mokady, R Gal… - Proceedings of the …, 2022‏ - openaccess.thecvf.com
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 …

Semanticstylegan: Learning compositional generative priors for controllable image synthesis and editing

Y Shi, X Yang, Y Wan, X Shen - Proceedings of the IEEE …, 2022‏ - openaccess.thecvf.com
Recent studies have shown that StyleGANs provide promising prior models for downstream
tasks on image synthesis and editing. However, since the latent codes of StyleGANs are …

State‐of‐the‐Art in the Architecture, Methods and Applications of StyleGAN

AH Bermano, R Gal, Y Alaluf, R Mokady… - Computer Graphics …, 2022‏ - Wiley Online Library
Abstract Generative Adversarial Networks (GANs) have established themselves as a
prevalent approach to image synthesis. Of these, StyleGAN offers a fascinating case study …

Stylegan knows normal, depth, albedo, and more

A Bhattad, D McKee, D Hoiem… - Advances in Neural …, 2024‏ - proceedings.neurips.cc
Intrinsic images, in the original sense, are image-like maps of scene properties like depth,
normal, albedo, or shading. This paper demonstrates that StyleGAN can easily be induced …

Spatially-adaptive multilayer selection for gan inversion and editing

G Parmar, Y Li, J Lu, R Zhang… - Proceedings of the …, 2022‏ - openaccess.thecvf.com
Existing GAN inversion and editing methods work well for aligned objects with a clean
background, such as portraits and animal faces, but often struggle for more difficult …

Fine-grained face swap** via regional gan inversion

Z Liu, M Li, Y Zhang, C Wang… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
We present a novel paradigm for high-fidelity face swap** that faithfully preserves the
desired subtle geometry and texture details. We rethink face swap** from the perspective …

Linkgan: Linking gan latents to pixels for controllable image synthesis

J Zhu, C Yang, Y Shen, Z Shi, B Dai… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
This work presents an easy-to-use regularizer for GAN training, which helps explicitly link
some axes of the latent space to a set of pixels in the synthesized image. Establishing such …

Gan-based facial attribute manipulation

Y Liu, Q Li, Q Deng, Z Sun… - IEEE transactions on …, 2023‏ - ieeexplore.ieee.org
Facial Attribute Manipulation (FAM) aims to aesthetically modify a given face image to
render desired attributes, which has received significant attention due to its broad practical …