Diffusion Models: A Comprehensive Survey of Methods and Applications

Diffusion models are a class of deep generative models that have shown impressive results on various tasks with a solid theoretical foundation. Despite demonstrated success than state-of-the-art approaches, diffusion models often entail costly sampling procedures and sub-optimal likelihood estimation. Significant efforts have been made to improve the performance of diffusion models in various aspects. In this article, we present a comprehensive review of existing variants of diffusion models. Specifically, we provide the taxonomy of research in diffusion models and categorize them into three types: sampling-efficiency enhancement, likelihood-maximization enhancement, and data-generalization enhancement. We also introduce the other generative models (i.e., variational autoencoders, generative adversarial networks, normalizing flow, autoregressive models, and energy-based models) and discuss the connections between diffusion models and these generative models. Then we review the applications of diffusion models, including computer vision, natural language processing, temporal data modeling, multi-modal learning, robust learning, molecular graph modeling, material design, and inverse problem solving. Furthermore, we propose new perspectives pertaining to the development of generative models. Github: https://github.com/YangLing0818/Diffusion-Models-Papers-Survey-Taxonomy.