arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.01090cs.CV
收藏

StyleGAN环形伪影的系统分析与去除

Systematic Analysis and Removal of Circular Artifacts for StyleGAN

Way Tan, Bihan Wen, Xulei Yang

摘要:

StyleGAN是最先进的图像生成器之一,以合成高分辨率和超逼真的人脸图像而闻名。虽然vanilla StyleGAN模型生成的图像在视觉上很吸引人,但它们有时会包含突出的圆形伪影,这会严重降低生成图像的质量。在这项工作中,我们通过研究香草StyleGAN架构的不同阶段的功能,结合机制分析和广泛的实验,对这些圆形工件是如何形成的进行了系统的研究。突出显示了vanilla StyleGAN的关键模块,这些模块促进了这些不需要的工件。我们的调查还解释了为什么文物通常是圆形的,相对较小,很少分裂成2个或更多的部分。此外,我们提出了一个简单而有效的解决方案,通过应用一个新的像素实例规范化(PIN)层来去除香草StyleGAN的突出圆形伪影。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑