AniPrO：基于多维语义推理的可解释动漫图像来源检测
AniPrO: Interpretable Anime Image Provenance Detection via Multi-Dimensional Semantic Reasoning
浏览论文内容
中文总结 AI 辅助
针对动漫图像来源检测，提出AniPrO框架，利用多维描述增强和双基准评估，有效区分人类绘制、AI修复和文生图图像，揭示AI生成偏差并提升检测性能。
中文摘要 AI 辅助
随着生成式AI在动漫风格图像创作中的日益普及，区分人类绘制、AI修复和文生图图像对于版权归属、视觉来源和内容治理至关重要。现有的AI生成图像检测器主要针对真实世界照片，往往忽视动漫特有的线索，如平涂着色、夸张结构和艺术线条控制。为弥补这一空白，我们提出AniPrO，一个用于可解释动漫图像来源的多维描述增强框架。基于AnimeDL-2M，AniPrO包含从35,000张图像候选池中精选的15,000个平衡样本，涵盖真实、修复和文生图三类，并配有结构化的五维描述。我们进一步引入AniPrO-SFD-Bench和AniPrO-MFR-Bench，分别从统计特征判别和多模态融合推理的角度评估来源检测。实验表明，结构化语义引导揭示了系统性的AI生成偏差，如全局视觉合理性与局部细节连贯性之间的差距，并提升了对具有挑战性的修复样本的检测能力。数据集和代码将在以下网址发布：此https URL。
英文摘要
As generative AI becomes increasingly used in anime-style image creation, distinguishing human-drawn, AI-inpainted, and text-to-image images is important for copyright attribution, visual provenance, and content governance. Existing AI-generated image detectors mainly target real-world photographs and often overlook anime-specific cues such as flat coloring, exaggerated structures, and artistic line control. To address this gap, we propose AniPrO, a multi-dimensional description-enhanced framework for interpretable anime image provenance. Built upon AnimeDL-2M, AniPrO contains 15,000 balanced samples from a 35,000-image candidate pool, covering Real, Inpainting, and Text2Image categories with structured five-dimensional descriptions. We further introduce AniPrO-SFD-Bench and AniPrO-MFR-Bench to evaluate provenance detection from statistical feature discrimination and multimodal fusion reasoning perspectives. Experiments show that structured semantic guidance reveals systematic AI-generation biases, such as the gap between global visual plausibility and local detail coherence, and improves the detection of challenging inpainting samples. The dataset and code will be released at: https://github.com/YAN-LIU05/AniPrO.
发表机构
- Tongji University（同济大学）
机构由 AI 辅助整理，请以论文原文为准。
