MIRROR通过建模真实图像的稳定规律，更精准识别生成图像。
MIRROR: Manifold Ideal Reference ReconstructOR for Generalizable AI-Generated Image Detection
- 用可学习的离散记忆库编码真实图像先验，构建理想参考。
- 在14个基准上优于已有方法，野拍数据提升8.1%。
- 首次在人类难察觉数据集上超越视觉专家，适合安全检测场景。
高保真生成模型缩小了合成图像与真实图像的感知差距，严重威胁媒体安全。现有AI生成图像（AIGI）检测器依赖特定伪影分类，难以泛化到新生成痕迹。相比之下，人类判断基于稳定的现实规律，偏离认知流形即为伪造信号。受此启发，我们将AIGI检测重构为参考对比问题：验证输入是否与真实图像流形一致，而非拟合特定伪造线索。提出MIRROR（Manifold Ideal Reference ReconstructOR），通过可学习离散记忆库显式编码现实先验，利用稀疏线性组合将输入投影至流形一致的理想参考，以残差作为鲁棒检测信号。为评估检测器是否达到替代人类专家的“超人交叉点”，引入人类不可察觉子集的人工智能-真实图像基准（Human-AIGI）。在14个基准上，MIRROR持续领先，标准基准平均提升2.1%，野拍基准提升8.1%。在Human-AIGI上，对27个生成器实现89.6%准确率，超越普通用户与视觉专家，并随预训练主干扩大逐步逼近人类感知极限。代码已公开于https://github.com/349793927/MIRROR。
原文摘要 · Abstract (English)
High-fidelity generative models have narrowed the perceptual gap between synthetic and real images, posing serious threats to media security. Most existing AI-generated image (AIGI) detectors rely on artifact-based classification and struggle to generalize to evolving generative traces. In contrast, human judgment relies on stable real-world regularities, with deviations from the human cognitive manifold serving as a more generalizable signal of forgery. Motivated by this insight, we reformulate AIGI detection as a Reference-Comparison problem that verifies consistency with the real-image manifold rather than fitting specific forgery cues. We propose MIRROR (Manifold Ideal Reference ReconstructOR), a framework that explicitly encodes reality priors using a learnable discrete memory bank. MIRROR projects an input into a manifold-consistent ideal reference via sparse linear combination, and uses the resulting residuals as robust detection signals. To evaluate whether detectors reach the "superhuman crossover" required to replace human experts, we introduce the Human-AIGI benchmark, featuring a psychophysically curated human-imperceptible subset. Across 14 benchmarks, MIRROR consistently outperforms prior methods, achieving gains of 2.1% on six standard benchmarks and 8.1% on seven in-the-wild benchmarks. On Human-AIGI, MIRROR reaches 89.6% accuracy across 27 generators, surpassing both lay users and visual experts, and further approaching the human perceptual limit as pretrained backbones scale. The code is publicly available at: https://github.com/349793927/MIRROR
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。