Quality-Aware Calibration for AI-Generated Image Detection in the Wild

2026-04-16

AI Summary

This work addresses the inconsistency of existing AI-generated image detectors when confronted with near-duplicate images degraded by common online operations such as compression and cropping, which hinders their real-world applicability. To tackle this challenge, we propose QuAD, a novel framework that introduces, for the first time, a quality-aware fusion mechanism for near-duplicate images: it retrieves all online near-duplicate versions of a given image and aggregates their detection scores weighted by image quality assessments. To facilitate this research, we construct AncesTree, a synthetic dataset simulating web-induced degradations, and ReWIND, a real-world web-collected dataset. Experiments demonstrate that QuAD consistently improves balanced accuracy by approximately 8% across multiple state-of-the-art detectors, substantially enhancing the robustness and practicality of in-the-wild AI-generated image detection.

Technology Category

• Computer Vision: Image and Video Retrieval
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• Web Mining and Content Analysis: Web data quality in the era of algorithmically-generated content
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Significant progress has been made in detecting synthetic images, however most existing approaches operate on a single image instance and overlook a key characteristic of real-world dissemination: as viral images circulate on the web, multiple near-duplicate versions appear and lose quality due to repeated operations like recompression, resizing and cropping. As a consequence, the same image may yield inconsistent forensic predictions based on which version has been analyzed. In this work, to address this issue we propose QuAD (Quality-Aware calibration with near-Duplicates) a novel framework that makes decisions based on all available near-duplicates of the same image. Given a query, we retrieve its online near-duplicates and feed them to a detector: the resulting scores are then aggregated based on the estimated quality of the corresponding instance. By doing so, we take advantage of all pieces of information while accounting for the reduced reliability of images impaired by multiple processing steps. To support large-scale evaluation, we introduce two datasets: AncesTree, an in-lab dataset of 136k images organized in stochastic degradation trees that simulate online reposting dynamics, and ReWIND, a real-world dataset of nearly 10k near-duplicate images collected from viral web content. Experiments on several state-of-the-art detectors show that our quality-aware fusion improves their performance consistently, with an average gain of around 8% in terms of balanced accuracy compared to plain average. Our results highlight the importance of jointly processing all the images available online to achieve reliable detection of AI-generated content in real-world applications. Code and data are publicly available at https://grip-unina.github.io/QuAD/

Problem

• AI-generated image detection
• near-duplicates
• image quality degradation
• forensic inconsistency
• real-world dissemination

Innovation

• quality-aware calibration
• near-duplicate aggregation
• AI-generated image detection
• image forensics
• stochastic degradation