# Systematic Analysis and Removal of Circular Artifacts for StyleGAN

arXiv: https://arxiv.org/abs/2103.01090 · HTML: https://mlsanity.com/paper/2103.01090/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 19 references that are in the map.
- First posted on arXiv 1 Mar 2021.

## Builds on (most cited first, 14 of 14)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?](https://mlsanity.com/paper/1904.03189/) (2019)
- [Coupled Generative Adversarial Networks](https://mlsanity.com/paper/1606.07536/) (2016)
- [Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks](https://mlsanity.com/paper/1805.07925/) (2018)
- [Towards the Automatic Anime Characters Creation with Generative Adversarial Networks](https://mlsanity.com/paper/1708.05509/) (2017)
- [Switchable Normalization for Learning-to-Normalize Deep Representation](https://mlsanity.com/paper/1907.10473/) (2019)

## Built on by (most cited first, 1 of 1)

- [DiffGAR: Model-Agnostic Restoration from Generative Artifacts Using Image-to-Image Diffusion Models](https://mlsanity.com/paper/2210.08573/) (2022)

## Abstract (arXiv)

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 architecture, with both mechanism analysis and extensive experiments. The key modules of vanilla StyleGAN that promote such undesired artifacts are highlighted. Our investigation also explains why the artifacts are usually circular, relatively small and rarely split into 2 or more parts. Besides, we propose a simple yet effective solution to remove the prominent circular artifacts for vanilla StyleGAN, by applying a novel pixel-instance normalization (PIN) layer.