arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.11989cs.HCcs.AIcs.CV
收藏

表征扩散模型生成图像中的照片级真实感与伪影

Characterizing Photorealism and Artifacts in Diffusion Model-Generated Images

Northwestern University(西北大学);Utrecht University(乌得勒支大学)

Negar Kamali, Karyn Nakamura, Aakriti Kumar, Angelos Chatzimparmpas, Jessica Hullman, Matthew Groh

AI总结:

该研究通过大规模人类检测实验考察扩散模型图像的真实感与伪影,分析场景复杂度、伪影类型、显示时间和人工筛选的影响,并提出伪影分类体系。

摘要:

扩散模型生成的图像可能看起来与真实照片难以区分,但这些图像通常包含揭示其AI生成来源的伪影和不合理之处。鉴于照片级真实的AI生成图像对媒体公共信任构成的挑战,我们开展了一项大规模实验,测量人类对450张扩散模型生成图像和149张真实图像的检测准确率。基于从50,444名参与者处收集的749,828条观察结果和34,675条评论,我们发现图像的场景复杂度、图像内的伪影类型、图像的显示时间以及AI生成图像的人工筛选,都在人们区分真实图像与AI生成图像的准确率方面发挥重要作用。此外,我们提出了一种分类体系,用于表征扩散模型生成图像中经常出现的伪影。我们的实证观察和分类体系为2024年扩散模型生成照片级真实图像的能力和局限提供了细致的见解。

英文摘要:

Diffusion model-generated images can appear indistinguishable from authentic photographs, but these images often contain artifacts and implausibilities that reveal their AI-generated provenance. Given the challenge to public trust in media posed by photorealistic AI-generated images, we conducted a large-scale experiment measuring human detection accuracy on 450 diffusion-model generated images and 149 real images. Based on collecting 749,828 observations and 34,675 comments from 50,444 participants, we find that scene complexity of an image, artifact types within an image, display time of an image, and human curation of AI-generated images all play significant roles in how accurately people distinguish real from AI-generated images. Additionally, we propose a taxonomy characterizing artifacts often appearing in images generated by diffusion models. Our empirical observations and taxonomy offer nuanced insights into the capabilities and limitations of diffusion models to generate photorealistic images in 2024.

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。

↑