StyleGAN Salon：用于姿态不变发型迁移的多视图潜空间优化
StyleGAN Salon: Multi-View Latent Optimization for Pose-Invariant Hairstyle Transfer
AI总结：
本文提出 StyleGAN Salon 多视图潜空间优化框架，利用参考合成图的两个视图引导遮挡区域，在更具挑战性的姿态不变发型迁移中保持身份与脸型并优于已有方法。
摘要：
本文致力于将参考图像的发型迁移到输入照片，以实现虚拟发型试戴。我们针对多种具有挑战性的场景，例如将带刘海的长发造型变换为精灵短发，这需要移除原有头发并推断额头的外观；或者从一位姿态不同且戴帽子的人物那里迁移仅部分可见的头发。以往的解决方案利用 StyleGAN，通过所谓的 GAN 反演或投影来幻觉生成任何缺失部分，并生成无缝的面部—头发合成结果。然而，在控制这些幻觉结果以准确迁移发型并保持输入的脸型和身份方面，仍然存在挑战。为克服这一问题，我们提出一种多视图优化框架，该框架使用参考合成图像的“两个不同视图”，在语义上引导被遮挡或模糊的区域。我们的优化在两种姿态之间共享信息，使我们能够从不完整的参考图像生成高保真且逼真的结果。我们的框架可生成高质量结果，并在一项用户研究中优于先前工作；该研究所包含的发型迁移场景比此前研究中的场景明显更具挑战性。项目页面：https://stylegan-salon.github.io/。
英文摘要：
Our paper seeks to transfer the hairstyle of a reference image to an input photo for virtual hair try-on. We target a variety of challenges scenarios, such as transforming a long hairstyle with bangs to a pixie cut, which requires removing the existing hair and inferring how the forehead would look, or transferring partially visible hair from a hat-wearing person in a different pose. Past solutions leverage StyleGAN for hallucinating any missing parts and producing a seamless face-hair composite through so-called GAN inversion or projection. However, there remains a challenge in controlling the hallucinations to accurately transfer hairstyle and preserve the face shape and identity of the input. To overcome this, we propose a multi-view optimization framework that uses "two different views" of reference composites to semantically guide occluded or ambiguous regions. Our optimization shares information between two poses, which allows us to produce high fidelity and realistic results from incomplete references. Our framework produces high-quality results and outperforms prior work in a user study that consists of significantly more challenging hair transfer scenarios than previously studied. Project page: https://stylegan-salon.github.io/.
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。
