深度曲线编辑：预训练深度生成模型的交换性与非线性图像操作
Deep Curvilinear Editing: Commutative and Nonlinear Image Manipulation for Pretrained Deep Generative Model
AI总结：
针对预训练深度生成模型缺乏语义编辑能力的问题，提出深度曲线编辑（DeCurvEd）方法，通过交换向量场实现非线性且顺序无关的多属性编辑，提升解耦与编辑质量。
摘要：
图像的语义编辑是计算机视觉的基本目标。尽管深度学习方法，如生成对抗网络（GANs），能够生成高质量图像，但它们通常缺乏内在的语义编辑生成图像的方式。近期研究探索了操纵潜在变量以决定生成图像的方法。然而，假设线性语义算术的方法在图像编辑质量上存在一定限制，而发现非线性语义路径的方法则提供非交换性编辑，在不同顺序应用时结果不一致。本研究提出了一种名为深度曲线编辑（DeCurvEd）的新方法，用于确定潜在空间上的语义交换向量场。我们从理论上证明，由于交换性，多属性编辑仅取决于编辑量而非顺序。此外，我们通过实验证明，与先前方法相比，DeCurvEd的非线性和交换性特性有助于图像属性的解耦，并提供更高质量的编辑。
英文摘要：
Semantic editing of images is the fundamental goal of computer vision. Although deep learning methods, such as generative adversarial networks (GANs), are capable of producing high-quality images, they often do not have an inherent way of editing generated images semantically. Recent studies have investigated a way of manipulating the latent variable to determine the images to be generated. However, methods that assume linear semantic arithmetic have certain limitations in terms of the quality of image editing, whereas methods that discover nonlinear semantic pathways provide non-commutative editing, which is inconsistent when applied in different orders. This study proposes a novel method called deep curvilinear editing (DeCurvEd) to determine semantic commuting vector fields on the latent space. We theoretically demonstrate that owing to commutativity, the editing of multiple attributes depends only on the quantities and not on the order. Furthermore, we experimentally demonstrate that compared to previous methods, the nonlinear and commutative nature of DeCurvEd facilitates the disentanglement of image attributes and provides higher-quality editing.
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。
