构建首个图像生成真实感评估数据集RAISE，助力客观衡量生成图像逼真度。
RAISE: Realness Assessment for Image Synthesis and Evaluation
- 通过大规模人类评测建立包含主观真实感评分的图像数据集
- 基于深度视觉模型特征，实现对生成图像真实感的有效预测
- 为真实感评估提供基准工具，适合图像生成与质量评测研究者
生成式AI的快速发展使得高度逼真的视觉内容得以生成，在难以获取真实数据的场景中可作为实际替代。然而，可靠地用AI生成内容替代真实图像，需要对生成内容的感知真实感进行稳健评估，这因主观性而极具挑战。为此，我们开展了一项全面的人类研究，评估真实图像与生成图像的感知真实感，构建了新的数据集RAISE，包含配对的图像及其主观真实感评分。进一步地，我们在RAISE上训练并开发多个模型，建立了真实感预测的基线。实验结果表明，来自深度基础视觉模型的特征能够有效捕捉主观真实感。因此，RAISE为开发稳健、客观的感知真实感评估模型提供了宝贵资源。
原文摘要 · Abstract (English)
The rapid advancement of generative AI has enabled the creation of highly photorealistic visual content, offering practical substitutes for real images and videos in scenarios where acquiring real data is difficult or expensive. However, reliably substituting real visual content with AI-generated counterparts requires robust assessment of the perceived realness of AI-generated visual content, a challenging task due to its inherent subjective nature. To address this, we conducted a comprehensive human study evaluating the perceptual realness of both real and AI-generated images, resulting in a new dataset, containing images paired with subjective realness scores, introduced as RAISE in this paper. Further, we develop and train multiple models on RAISE to establish baselines for realness prediction. Our experimental results demonstrate that features derived from deep foundation vision models can effectively capture the subjective realness. RAISE thus provides a valuable resource for developing robust, objective models of perceptual realness assessment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。