• Corpus ID: 232092169

Systematic Analysis and Removal of Circular Artifacts for StyleGAN

@article{Tan2021SystematicAA,
  title={Systematic Analysis and Removal of Circular Artifacts for StyleGAN},
  author={Way Tan and Bihan Wen and XuLei Yang},
  journal={ArXiv},
  year={2021},
  volume={abs/2103.01090}
}
StyleGAN is one of the state-of-the-art image generators which is well-known for synthesizing high-resolution and hyper-realistic face images. Though images generated by vanilla StyleGAN model are visually appealing, they sometimes contain prominent circular artifacts which severely degrade the quality of generated images. In this work, we provide a systematic investigation on how those circular artifacts are formed by studying the functionalities of different stages of vanilla StyleGAN… 

References

SHOWING 1-10 OF 20 REFERENCES
Analyzing and Improving the Image Quality of StyleGAN
TLDR
This work redesigns the generator normalization, revisit progressive growing, and regularize the generator to encourage good conditioning in the mapping from latent codes to images, and thereby redefines the state of the art in unconditional image modeling.
A Style-Based Generator Architecture for Generative Adversarial Networks
TLDR
An alternative generator architecture for generative adversarial networks is proposed, borrowing from style transfer literature, that improves the state-of-the-art in terms of traditional distribution quality metrics, leads to demonstrably better interpolation properties, and also better disentangles the latent factors of variation.
Generative Adversarial Networks
  • arXiv e-prints arXiv:1406.2661.
  • 2014
Switchable Normalization for Learning-to-Normalize Deep Representation
TLDR
Switchable Normalization (SN), which learns to select different normalizers for different normalization layers of a deep neural network, is proposed and will help ease the usage and understand the normalization techniques in deep learning.
Improved Precision and Recall Metric for Assessing Generative Models
TLDR
This work presents an evaluation metric that can separately and reliably measure both the quality and coverage of the samples produced by a generative model and the perceptual quality of individual samples, and extends it to study latent space interpolations.
Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?
We propose an efficient algorithm to embed a given image into the latent space of StyleGAN. This embedding enables semantic image editing operations that can be applied to existing photographs.
HYPE: Human eYe Perceptual Evaluation of Generative Models
TLDR
The authors' human evaluation metric, HYPE, consistently distinguishes models from each other, and is compared to StyleGAN, ProGAN, BEGAN, and WGAN-GP on CelebA, and StyleGAN with and without truncation trick sampling on FFHQ.
Semantic Image Synthesis With Spatially-Adaptive Normalization
TLDR
S spatially-adaptive normalization is proposed, a simple but effective layer for synthesizing photorealistic images given an input semantic layout that allows users to easily control the style and content of image synthesis results as well as create multi-modal results.
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
TLDR
This work presents an analytic framework to visualize and understand GANs at the unit-, object-, and scene-level, and provides open source interpretation tools to help researchers and practitioners better understand their GAN models.
Large Scale GAN Training for High Fidelity Natural Image Synthesis
TLDR
It is found that applying orthogonal regularization to the generator renders it amenable to a simple "truncation trick," allowing fine control over the trade-off between sample fidelity and variety by reducing the variance of the Generator's input.
...
...