用生成模型让扭曲图像直接看也看得懂，还保留特殊视角才显现的视觉效果。
LookingGlass: Generative Anamorphoses via Laplacian Pyramid Warping
- 用拉普拉斯金字塔变形技术，按频率分层扭曲图像以保持视觉质量
- 在直接观看时仍能识别图像内容，同时保留特定视角下的真实形态
- 适用于多种空间变换，扩展了生成式视觉错觉的应用范围
仿形图像是一种故意扭曲的图像，直接观看时无法辨认，只有从特定视角通过镜面或透镜等光学设备才能看清真实形态。尽管这类数学装置可追溯至17世纪，但其意义仅在特定视角下成立，日常观看时失去含义。本文以生成式方法重访这一经典光学幻象：借助潜在修正流模型，提出一种新方法，使仿形图像在直接观看时仍具可解释性，同时保留特定视角下的真实呈现。核心是引入拉普拉斯金字塔变形（Laplacian Pyramid Warping）——一种频率感知的图像变形技术，用于生成高质量视觉结果。本工作将视觉字谜（Visual Anagrams, arXiv:2311.17919）拓展至潜在空间模型与更广泛的几何变换，实现了新型生成式感知幻觉的创造。
原文摘要 · Abstract (English)
Anamorphosis refers to a category of images that are intentionally distorted, making them unrecognizable when viewed directly. Their true form only reveals itself when seen from a specific viewpoint, which can be through some catadioptric device like a mirror or a lens. While the construction of these mathematical devices can be traced back to as early as the 17th century, they are only interpretable when viewed from a specific vantage point and tend to lose meaning when seen normally. In this paper, we revisit these famous optical illusions with a generative twist. With the help of latent rectified flow models, we propose a method to create anamorphic images that still retain a valid interpretation when viewed directly. To this end, we introduce Laplacian Pyramid Warping, a frequency-aware image warping technique key to generating high-quality visuals. Our work extends Visual Anagrams (arXiv:2311.17919) to latent space models and to a wider range of spatial transforms, enabling the creation of novel generative perceptual illusions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。