一种用于灵活迁移与编辑的可控外观表示
A Controllable Appearance Representation for Flexible Transfer and Editing
AI总结：
本文提出一种基于自监督FactorVAE的可控外观表示，通过解耦的紧凑潜在空间实现材质外观迁移与细粒度编辑，并利用轻量级IP-Adapter驱动扩散流程完成灵活的外观迁移。
摘要：
我们提出了一种方法，在高度紧凑、解耦的潜在空间中计算可解释的材质外观表示。该表示通过改进的FactorVAE以自监督方式学习得到。我们使用精心设计的无标签数据集训练模型，避免了人工生成标签可能引入的偏差。尽管缺乏显式监督，我们的模型仍能有效编码材质外观和光照，展现出强大的解耦能力和可解释性。随后，我们将该表示作为指导，训练一个轻量级IP-Adapter，以条件化扩散流程，将一张或多张图像的外观迁移到目标几何体上，并允许用户进一步编辑生成的外观。我们的方法对生成结果提供了细粒度控制：得益于结构良好的紧凑潜在空间，用户可以在图像空间中直观地操纵色调或光泽度等属性，以获得所需的最终外观。
英文摘要：
We present a method that computes an interpretable representation of material appearance within a highly compact, disentangled latent space. This representation is learned in a self-supervised fashion using an adapted FactorVAE. We train our model with a carefully designed unlabeled dataset, avoiding possible biases induced by human-generated labels. Our model demonstrates strong disentanglement and interpretability by effectively encoding material appearance and illumination, despite the absence of explicit supervision. Then, we use our representation as guidance for training a lightweight IP-Adapter to condition a diffusion pipeline that transfers the appearance of one or more images onto a target geometry, and allows the user to further edit the resulting appearance. Our approach offers fine-grained control over the generated results: thanks to the well-structured compact latent space, users can intuitively manipulate attributes such as hue or glossiness in image space to achieve the desired final appearance.
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。
