arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.00796cs.LGcs.AIcs.CV
收藏

扩散模型:方法与应用综合综述

Diffusion Models: A Comprehensive Survey of Methods and Applications

Peking University(北京大学);OpenAI;University of California, Los Angeles(加州大学洛杉矶分校);Carnegie Mellon University(卡内基梅隆大学);University of California at Merced(加州大学默塞德分校)

Ling Yang, Zhilong Zhang, Yang Song, Shenda Hong, Runsheng Xu, Yue Zhao, Wentao Zhang, Bin Cui, Ming-Hsuan Yang

AI总结:

本文系统综述扩散模型的三类核心方法、与其他生成模型的结合潜力及其在多领域的广泛应用,并梳理研究现状与未来方向。

摘要:

扩散模型已成为一类强大的新型深度生成模型,在图像合成、视频生成和分子设计等众多应用中取得了破纪录的性能。在本综述中,我们概述了迅速扩展的扩散模型研究体系,并将相关研究划分为三个关键领域:高效采样、改进的似然估计,以及处理具有特殊结构的数据。我们还讨论了将扩散模型与其他生成模型相结合以获得更好结果的潜力。我们进一步回顾了扩散模型的广泛应用,领域涵盖计算机视觉、自然语言生成、时间数据建模,以及其他科学学科中的跨学科应用。本综述旨在结合背景、深入审视扩散模型的发展现状,识别关键的研究重点领域,并指出未来可进一步探索的潜在方向。GitHub:https://github.com/YangLing0818/Diffusion-Models-Papers-Survey-Taxonomy。

英文摘要:

Diffusion models have emerged as a powerful new family of deep generative models with record-breaking performance in many applications, including image synthesis, video generation, and molecule design. In this survey, we provide an overview of the rapidly expanding body of work on diffusion models, categorizing the research into three key areas: efficient sampling, improved likelihood estimation, and handling data with special structures. We also discuss the potential for combining diffusion models with other generative models for enhanced results. We further review the wide-ranging applications of diffusion models in fields spanning from computer vision, natural language generation, temporal data modeling, to interdisciplinary applications in other scientific disciplines. This survey aims to provide a contextualized, in-depth look at the state of diffusion models, identifying the key areas of focus and pointing to potential areas for further exploration. Github: https://github.com/YangLing0818/Diffusion-Models-Papers-Survey-Taxonomy.

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。

↑