Systematic Analysis and Removal of Circular Artifacts for StyleGAN
This work addresses a specific quality issue in StyleGAN for image generation, offering an incremental improvement to enhance visual fidelity.
The paper tackled the problem of circular artifacts in StyleGAN-generated images, which degrade quality, and proposed a pixel-instance normalization (PIN) layer to effectively remove these artifacts, as demonstrated through systematic analysis and experiments.
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.