在扩散模型中探索低维子空间以实现可控图像编辑
Exploring Low-Dimensional Subspaces in Diffusion Models for Controllable Image Editing
AI总结：
本文通过分析扩散模型中后验均值预测器的局部线性和Jacobian奇异向量的低维特性，提出无需训练的LOCO Edit方法，实现精准局部图像编辑，并扩展至文本监督下的图像编辑。
摘要：
近年来，扩散模型已成为一种强大的生成模型。尽管取得成功，但对其语义空间的理解仍有限，这使得在无监督方式下实现精确且解耦的图像生成具有挑战性。本文通过观察发现，在一定噪声水平范围内，扩散模型中的后验均值预测器（PMP）在局部上是线性的，其雅可比矩阵的奇异向量位于低维语义子空间中。这些发现为PMP的线性和低秩性提供了理论依据。基于此，我们提出了一种无监督、单步、无需训练的LOCO Edit方法，用于精确的局部图像编辑。LOCO Edit识别出具有良好性质的编辑方向：同质性、可迁移性、可组合性和线性。这些特性很大程度上得益于低维语义子空间。本方法还可扩展至各种文本到图像扩散模型中的无监督或文本监督编辑（T-LOCO Edit）。最后，广泛的实验证明了LOCO Edit的有效性和效率。
英文摘要：
Recently, diffusion models have emerged as a powerful class of generative models. Despite their success, there is still limited understanding of their semantic spaces. This makes it challenging to achieve precise and disentangled image generation without additional training, especially in an unsupervised way. In this work, we improve the understanding of their semantic spaces from intriguing observations: among a certain range of noise levels, (1) the learned posterior mean predictor (PMP) in the diffusion model is locally linear, and (2) the singular vectors of its Jacobian lie in low-dimensional semantic subspaces. We provide a solid theoretical basis to justify the linearity and low-rankness in the PMP. These insights allow us to propose an unsupervised, single-step, training-free LOw-rank COntrollable image editing (LOCO Edit) method for precise local editing in diffusion models. LOCO Edit identified editing directions with nice properties: homogeneity, transferability, composability, and linearity. These properties of LOCO Edit benefit greatly from the low-dimensional semantic subspace. Our method can further be extended to unsupervised or text-supervised editing in various text-to-image diffusion models (T-LOCO Edit). Finally, extensive empirical experiments demonstrate the effectiveness and efficiency of LOCO Edit.
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。
