PS-StyleGAN：基于注意力的风格自适应进行示意性人像素描
PS-StyleGAN: Illustrative Portrait Sketching using Attention-Based Style Adaptation
AI总结：
本文提出PS-StyleGAN，利用StyleGAN的W+潜空间和注意力仿射变换模块，在少量成对样本和短训练时间下实现可编辑且保持身份的人像素描生成，并在多个数据集上优于现有方法。
摘要：
人像素描涉及用抽象线条和阴影捕捉真实人脸的身份特定属性。与照片级真实图像不同，一种好的人像素描生成方法需要对细节进行选择性关注，这使得该问题具有挑战性。本文介绍了人像素描StyleGAN（PS-StyleGAN），这是一种专为人像素描合成而定制风格迁移方法。我们利用StyleGAN的语义W+潜空间来生成人像素描，使我们能够在不损害身份的情况下进行有意义的编辑，如姿态和表情变化。为了实现这一目标，我们提出在我们的架构中使用注意力仿射变换模块，以及一种训练策略，使我们无需微调即可改变StyleGAN的输出。这些模块通过同时关注内容和风格潜特征来学习修改风格潜码，使我们能够以反演一致的方式调整StyleGAN的输出。我们的方法仅使用少量成对示例（约100个）来建模一种风格，并且训练时间短。我们在各种数据集上定性和定量地证明了PS-StyleGAN优于当前最先进的方法。
英文摘要：
Portrait sketching involves capturing identity specific attributes of a real face with abstract lines and shades. Unlike photo-realistic images, a good portrait sketch generation method needs selective attention to detail, making the problem challenging. This paper introduces \textbf{Portrait Sketching StyleGAN (PS-StyleGAN)}, a style transfer approach tailored for portrait sketch synthesis. We leverage the semantic $W+$ latent space of StyleGAN to generate portrait sketches, allowing us to make meaningful edits, like pose and expression alterations, without compromising identity. To achieve this, we propose the use of Attentive Affine transform blocks in our architecture, and a training strategy that allows us to change StyleGAN's output without finetuning it. These blocks learn to modify style latent code by paying attention to both content and style latent features, allowing us to adapt the outputs of StyleGAN in an inversion-consistent manner. Our approach uses only a few paired examples ($\sim 100$) to model a style and has a short training time. We demonstrate PS-StyleGAN's superiority over the current state-of-the-art methods on various datasets, qualitatively and quantitatively.
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。
