arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2311.03335cs.CVcs.GR
收藏

用于零样本外观迁移的跨图像注意力机制

Cross-Image Attention for Zero-Shot Appearance Transfer

Tel Aviv University(特拉维夫大学)

Yuval Alaluf, Daniel Garibi, Or Patashnik, Hadar Averbuch-Elor, Daniel Cohen-Or

AI总结:

本研究提出一种基于文本到图像生成模型自注意力层的跨图像注意力机制,通过建立图像间语义对应实现零样本外观迁移,结合三种去噪优化机制提升质量,在多类别上有效且对形状、视角等变化鲁棒。

摘要:

文本到图像生成模型的最新进展已展现出捕捉图像深层语义理解的卓越能力。在本研究中,我们利用这种语义知识,在语义相似但形状可能差异显著的物体之间迁移视觉外观。为此,我们基于这些生成模型的自注意力层,提出了一种跨图像注意力机制,可隐式建立图像间的语义对应关系。具体而言,给定一对图像——一张呈现目标结构,另一张指定期望外观——我们的跨图像注意力将结构图像对应的查询(query)与外观图像的键(key)和值(value)相结合。该操作在去噪过程中应用时,会利用已建立的语义对应关系生成融合期望结构与外观的图像。此外,为提升输出图像质量,我们采用了三种机制,在整个去噪过程中对噪声潜码或模型的内部表征进行调整。重要的是,我们的方法是零样本的,无需任何优化或训练。实验表明,该方法在广泛的物体类别上均有效,且对两张输入图像之间的形状、尺寸和视角变化具有鲁棒性。

英文摘要:

Recent advancements in text-to-image generative models have demonstrated a remarkable ability to capture a deep semantic understanding of images. In this work, we leverage this semantic knowledge to transfer the visual appearance between objects that share similar semantics but may differ significantly in shape. To achieve this, we build upon the self-attention layers of these generative models and introduce a cross-image attention mechanism that implicitly establishes semantic correspondences across images. Specifically, given a pair of images -- one depicting the target structure and the other specifying the desired appearance -- our cross-image attention combines the queries corresponding to the structure image with the keys and values of the appearance image. This operation, when applied during the denoising process, leverages the established semantic correspondences to generate an image combining the desired structure and appearance. In addition, to improve the output image quality, we harness three mechanisms that either manipulate the noisy latent codes or the model's internal representations throughout the denoising process. Importantly, our approach is zero-shot, requiring no optimization or training. Experiments show that our method is effective across a wide range of object categories and is robust to variations in shape, size, and viewpoint between the two input images.

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。

↑