In this paper, targeting to understand the underlying explainable factors behind observations and modeling the conditional generation process on these factors, we propose a new task, disentanglement of diffusion probabilistic models (DPMs), to take advantage of the remarkable modeling ability of DPMs. To tackle this task, we further devise an unsupervised approach named DisDiff. For the first time, we achieve disentangled representation learning in the framework of diffusion probabilistic models. Given a pre-trained DPM, DisDiff can automatically discover the inherent factors behind the image data and disentangle the gradient fields of DPM into sub-gradient fields, each conditioned on the representation of each discovered factor. We propose a novel Disentangling Loss for DisDiff to facilitate the disentanglement of the representation and sub-gradients. The extensive experiments on synthetic and real-world datasets demonstrate the effectiveness of DisDiff.

翻译：本文旨在理解观测数据背后的可解释因素，并模拟基于这些因素的条件生成过程，我们提出了一项新任务——扩散概率模型（DPM）的解缠，以充分利用DPM卓越的建模能力。为解决此任务，我们进一步设计了一种无监督方法DisDiff。首次在扩散概率模型框架内实现了解缠表示学习。给定预训练的DPM，DisDiff可自动发现图像数据中的固有因素，并将DPM的梯度场解缠为子梯度场，每个子梯度场以各发现因素的表征为条件。我们提出一种新颖的DisDiff解缠损失，以促进表征与子梯度的解缠。在合成数据集和真实数据集上的大量实验证明了DisDiff的有效性。