ComboStoc：扩散生成模型的组合随机性

摘要

本文研究扩散生成模型中一个尚未被充分探索但至关重要的因素——组合复杂性。数据样本通常具有高维特性，而在各类结构化生成任务中，还需将附加属性与数据样本进行组合关联。我们发现，现有扩散生成模型的训练方案可能无法充分覆盖由维度与属性组合构成的空间，这可能会限制模型在测试时的性能表现。针对此问题，我们提出了一种简易解决方案：通过构建能充分利用组合结构的随机过程（故命名为ComboStoc）来实现优化。采用这一简单策略后，我们证实在包括图像和三维结构化形状在内的多种数据模态中，网络训练速度均得到显著提升。此外，ComboStoc还启用了测试时生成的新范式——通过为不同维度和属性分配异步时间步长，从而实现对它们的差异化调控。代码已开源：https://github.com/Xrvitd/ComboStoc

English

In this paper, we study an under-explored but important factor of diffusion generative models, i.e., the combinatorial complexity. Data samples are generally high-dimensional, and for various structured generation tasks, additional attributes are combined to associate with data samples. We show that the space spanned by the combination of dimensions and attributes can be insufficiently covered by existing training schemes of diffusion generative models, potentially limiting test time performance. We present a simple fix to this problem by constructing stochastic processes that fully exploit the combinatorial structures, hence the name ComboStoc. Using this simple strategy, we show that network training is significantly accelerated across diverse data modalities, including images and 3D structured shapes. Moreover, ComboStoc enables a new way of test time generation which uses asynchronous time steps for different dimensions and attributes, thus allowing for varying degrees of control over them. Our code is available at: https://github.com/Xrvitd/ComboStoc

ComboStoc：扩散生成模型的组合随机性

ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models

摘要

Support