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 2410.08608cs.CVcs.AIcs.LG
收藏

基于生成对抗网络的文本到图像生成

Text-To-Image with Generative Adversarial Networks

Sharif university of technology international campus-kish island(谢里夫理工大学国际校区基什岛)

Mehrshad Momen-Tayefeh

AI总结:

本文针对从文本生成逼真图像的挑战,比较了五种基于生成对抗网络(GAN)的文本到图像生成方法,通过分析不同分辨率及关键评估指标,确定了该问题的最佳模型。

摘要:

从人类文本生成逼真图像是计算机视觉(CV)领域最具挑战性的问题之一。现有文本到图像方法能够粗略反映所给描述的含义。在本文中,我们的主要目的是对基于生成对抗网络(GAN)从文本生成图像的五种不同方法进行简要比较。此外,每种模型架构合成的图像具有不同的分辨率。并且,获得的最佳和最差分辨率分别为64*64和256*256。然而,我们检查并比较了一些用于衡量各模型准确性的指标。同时,通过这项研究,我们通过比较这些不同方法的关键指标,找出了针对该问题的最佳模型。

英文摘要:

Generating realistic images from human texts is one of the most challenging problems in the field of computer vision (CV). The meaning of descriptions given can be roughly reflected by existing text-to-image approaches. In this paper, our main purpose is to propose a brief comparison between five different methods base on the Generative Adversarial Networks (GAN) to make image from the text. In addition, each model architectures synthesis images with different resolution. Furthermore, the best and worst obtained resolutions is 64*64, 256*256 respectively. However, we checked and compared some metrics that introduce the accuracy of each model. Also, by doing this study, we found out the best model for this problem by comparing these different approaches essential metrics.

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。

↑