Tan, W., Wen, B., Chen, C., Zeng, Z., & Yang, X. (2021). Systematic Analysis of Circular Artifacts for Stylegan. 2021 IEEE International Conference on Image Processing (ICIP). doi:10.1109/icip42928.2021.9506279
Abstract:
Recent research works have pointed out that the synthesized images by StyleGAN 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 modules that are used in the StyleGAN architecture. We present both analysis of the StyleGAN mechanism and extensive experiments to verify our claims. The key modules of StyleGAN that promote such undesired artifacts are highlighted based on the analysis. Besides, we propose a simple yet effective solution to remove the prominent circular artifacts for StyleGAN, by applying a simple but efficient pixel-instance normalization
layer. The improved StyleGAN model trained via our proposed approach successfully prevents the appearance of circular artifacts in the generated images.
License type:
Publisher Copyright
Funding Info:
There was no specific funding for the research done