AnimeDL-2M: Million-Scale AI-Generated Anime Image Detection and Localization in Diffusion Era

2025-04-15

AI Summary

AI-generated fake images increasingly threaten the anime domain through copyright infringement and content manipulation; however, existing image manipulation detection and localization (IMDL) methods—designed for natural images—suffer severe performance degradation on anime imagery due to domain shift. Method: We introduce AnimeDL-2M, the first large-scale anime-specific IMDL benchmark comprising over two million samples: authentic, locally manipulated, and fully AI-generated. We systematically characterize the substantial domain gap between anime and natural images and propose AniXplore, a dedicated model leveraging diffusion-based forgery analysis, multi-scale feature aggregation, local anomaly response modeling, and domain-adaptive training. Contribution/Results: On AnimeDL-2M, AniXplore achieves 92.7% detection accuracy and 84.3% localization mAP—significantly outperforming natural-image pre-trained models and state-of-the-art methods—establishing a new foundation for robust anime integrity verification.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Recent advances in image generation, particularly diffusion models, have significantly lowered the barrier for creating sophisticated forgeries, making image manipulation detection and localization (IMDL) increasingly challenging. While prior work in IMDL has focused largely on natural images, the anime domain remains underexplored-despite its growing vulnerability to AI-generated forgeries. Misrepresentations of AI-generated images as hand-drawn artwork, copyright violations, and inappropriate content modifications pose serious threats to the anime community and industry. To address this gap, we propose AnimeDL-2M, the first large-scale benchmark for anime IMDL with comprehensive annotations. It comprises over two million images including real, partially manipulated, and fully AI-generated samples. Experiments indicate that models trained on existing IMDL datasets of natural images perform poorly when applied to anime images, highlighting a clear domain gap between anime and natural images. To better handle IMDL tasks in anime domain, we further propose AniXplore, a novel model tailored to the visual characteristics of anime imagery. Extensive evaluations demonstrate that AniXplore achieves superior performance compared to existing methods. Dataset and code can be found in https://flytweety.github.io/AnimeDL2M/.

Problem

• Detect AI-generated anime images to combat forgeries
• Address domain gap between anime and natural image detection
• Localize manipulated regions in anime imagery effectively

Innovation

• Large-scale anime image detection benchmark
• AniXplore model for anime characteristics
• Comprehensive real and AI-generated image dataset