arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.18103cs.LGcs.CV
收藏

成像与视觉中的扩散模型教程

Tutorial on Diffusion Models for Imaging and Vision

School of Electrical and Computer Engineering, Purdue University(普渡大学电气与计算机工程学院)

Stanley H. Chan

AI总结:

本文是一份面向本科生与研究生的教程,介绍扩散模型的基本思想及其在文本到图像、文本到视频生成等成像与视觉任务中的应用。

摘要:

近年来,生成式工具的惊人增长推动了文本到图像生成和文本到视频生成中许多令人兴奋的应用。这些生成式工具背后的基本原理是扩散(diffusion)概念,这是一种特殊的采样机制,克服了以往方法中被认为难以解决的一些缺点。本教程的目标是讨论扩散模型背后的核心思想。教程的目标受众包括有兴趣研究扩散模型或应用这些模型解决其他问题的本科生和研究生。

英文摘要:

The astonishing growth of generative tools in recent years has empowered many exciting applications in text-to-image generation and text-to-video generation. The underlying principle behind these generative tools is the concept of diffusion, a particular sampling mechanism that has overcome some shortcomings that were deemed difficult in the previous approaches. The goal of this tutorial is to discuss the essential ideas underlying the diffusion models. The target audience of this tutorial includes undergraduate and graduate students who are interested in doing research on diffusion models or applying these models to solve other problems.

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。

↑