发表机构
Shanghai Jiao Tong University; Tencent Youtu Lab（上海交通大学; 腾讯优图实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对AI生成图像检测问题，提出LoRC框架，利用生成器语义残差的低秩坍缩特征，在多基准测试中平均提升7.0%准确率，在39个未见过的生成器上达97.0%准确率，具备强泛化性与鲁棒性。
AI 中文摘要
现代生成器能够忠实地建模宏观语义，生成的合成图像看起来高度逼真，因此决定性的取证线索存在于细微的非语义视觉差异中。为揭示这些线索，我们从几何视角重新审视AI生成图像（AIGI）检测，并识别出一种与架构无关的特征：现代生成器在语义残差正交子空间中表现出低秩坍缩（即秩退化），同时在很大程度上保留了主导语义方向，这种结构扁平化在最终解码阶段持续出现，形成了不同生成器架构间的共享瓶颈。受此特征启发，我们提出了LoRC框架，该框架通过解耦语义主导性来捕获由生成解码瓶颈诱导的坍缩残差几何。我们的方法在多个基准测试中平均提高了7.0%的准确率，在39个未见过的生成器上达到了97.0%的准确率，这些结果证明了其强大的跨模型泛化能力和鲁棒性，使LoRC成为复杂现实环境中AIGI检测的可靠方法。
英文摘要
Modern generators faithfully model macroscopic semantics, producing synthetic images that appear highly realistic. Consequently, decisive forensic cues reside in subtle non-semantic visual discrepancies. To reveal these cues, we revisit AIGI detection from a geometric perspective and identify an architecture-agnostic signature. Specifically, modern generators exhibit low-rank collapse (\textit{i.e.}, rank degeneracy) in the semantic-residual orthogonal subspace while largely preserving the dominant semantic direction. This structural flattening consistently emerges during the final decoding stage, forming a shared bottleneck across diverse generator architectures. Motivated by this signature, we propose \textbf{LoRC}, a framework that decouples semantic dominance to capture the collapsed residual geometry induced by the generative decoding bottleneck. Our method improves accuracy by an average of 7.0\% across multiple benchmarks and achieves 97.0\% accuracy on 39 unseen generators. These results demonstrate strong cross-model generalization and robustness, making LoRC a reliable approach for AIGI detection in complex real-world environments.
CommentsECCV 2026 Spotlight
