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

ArXi:2604.15027v1 Announce Type: new 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.