发表机构
University of Texas at Austin; Adobe Research（德克萨斯大学奥斯汀分校; 奥多比研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文通过扰动核视角统一谱表示学习与扩散模型，提出自监督谱对齐方法，并证明其优化等价于表示空间中的扩散分数蒸馏，在图像和3D点云上提升生成质量。
AI 中文摘要
扩散模型在各种生成任务中表现出色。近期研究发现，对扩散网络隐藏状态施加表示对齐既能促进训练收敛，又能提升采样质量，但驱动这种协同效应的机制仍未得到充分理解。本文通过扰动核的共享视角，探究自监督谱表示学习与扩散生成模型之间的联系。在扩散侧，样本（如图像、视频）通过逆转由高斯核指定的随机噪声注入过程生成；在谱表示侧，谱嵌入源自对随机扰动核诱导的正负关系进行对比。受此启发，我们提出一种自监督谱表示对齐方法以促进扩散模型训练。此外，我们从几何角度阐明联合谱学习如何有益于扩散训练。进一步，我们发现谱对齐目标的优化在表示空间中等价于扩散分数蒸馏的一种形式。基于这些发现，我们将谱正则化器整合到扩散训练目标中，以提升扩散模型在多个数据集上的性能。在图像和3D点云上的实验显示生成质量的一致提升。代码已发布在https URL。
英文摘要
Diffusion models have shown remarkable performance on diverse generation tasks. Recent work finds that imposing representation alignment on the hidden states of diffusion networks can both facilitate training convergence and enhance sampling quality, yet the mechanism driving this synergy remains insufficiently understood. In this paper, we investigate the connection between self-supervised spectral representation learning and diffusion generative models through a shared perspective on perturbation kernels. On the diffusion side, samples (e.g., images, videos) are produced by reversing a stochastic noise-injection process specified by Gaussian kernels; on the spectral representation side, spectral embeddings emerge from contrasting positive and negative relations induced by random perturbation kernels. Motivated by this, we propose a self-supervised spectral representation alignment method to facilitate diffusion model training. In addition, we clarify how joint spectral learning can benefit diffusion training from a geometric perspective. Furthermore, we find that the optimization of the spectral alignment objective is in an equivalent form of diffusion score distillation in the representation space. Building on these findings, we integrate a spectral regularizer into diffusion training objectives to improve the performance of diffusion models on multiple datasets. Experiments across images and 3D point clouds show consistent gains in generation quality. Code is released at https://github.com/yuehaowang/spectral-reg-diffusion.
CommentsICML 2026
