arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2308.13142cs.CVcs.AI
收藏

基于扩散的图像生成模型综述:问题及其解决方案

A Survey of Diffusion Based Image Generation Models: Issues and Their Solutions

Huawei Singapore Research Center(华为新加坡研究中心)

Tianyi Zhang, Zheng Wang, Jing Huang, Mohiuddin Muhammad Tasnim, Wei Shi

AI总结:

本综述聚焦基于扩散的图像生成模型,梳理了以Imagen、DALL-E 2、stable diffusion为代表的模型发展现状,指出其仍存在未解决的挑战,并将基于开源stable diffusion框架的研究基础,梳理现存问题与对应解决方案。

摘要:

近年来,大模型的发展取得了显著进展。继ChatGPT成功之后,众多语言模型被推出,展现出卓越的性能。图像生成模型领域也出现了类似的进展,例如谷歌的Imagen模型、OpenAI的DALL-E 2以及stable diffusion(稳定扩散)模型,它们在生成图像方面展现出令人惊叹的能力。然而,与大语言模型类似,这些模型仍面临诸多尚未解决的挑战。幸运的是,开源stable diffusion模型及其底层数学原理的可用性,使得学术界能够广泛分析当前图像生成模型的性能,并基于该stable diffusion框架进行改进。本综述旨在研究图像生成模型现存的问题及当前的解决方案。

英文摘要:

Recently, there has been significant progress in the development of large models. Following the success of ChatGPT, numerous language models have been introduced, demonstrating remarkable performance. Similar advancements have also been observed in image generation models, such as Google's Imagen model, OpenAI's DALL-E 2, and stable diffusion models, which have exhibited impressive capabilities in generating images. However, similar to large language models, these models still encounter unresolved challenges. Fortunately, the availability of open-source stable diffusion models and their underlying mathematical principles has enabled the academic community to extensively analyze the performance of current image generation models and make improvements based on this stable diffusion framework. This survey aims to examine the existing issues and the current solutions pertaining to image generation models.

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。

↑