Beyond Artifacts: Real-Centric Envelope Modeling for Reliable AI-Generated Image Detection
By: Ruiqi Liu , Yi Han , Zhengbo Zhang and more
The rapid progress of generative models has intensified the need for reliable and robust detection under real-world conditions. However, existing detectors often overfit to generator-specific artifacts and remain highly sensitive to real-world degradations. As generative architectures evolve and images undergo multi-round cross-platform sharing and post-processing (chain degradations), these artifact cues become obsolete and harder to detect. To address this, we propose Real-centric Envelope Modeling (REM), a new paradigm that shifts detection from learning generator artifacts to modeling the robust distribution of real images. REM introduces feature-level perturbations in self-reconstruction to generate near-real samples, and employs an envelope estimator with cross-domain consistency to learn a boundary enclosing the real image manifold. We further build RealChain, a comprehensive benchmark covering both open-source and commercial generators with simulated real-world degradation. Across eight benchmark evaluations, REM achieves an average improvement of 7.5% over state-of-the-art methods, and notably maintains exceptional generalization on the severely degraded RealChain benchmark, establishing a solid foundation for synthetic image detection under real-world conditions. The code and the RealChain benchmark will be made publicly available upon acceptance of the paper.
Similar Papers
Robust and Calibrated Detection of Authentic Multimedia Content
CV and Pattern Recognition
Finds fake videos even when they change.
Zero-shot Synthetic Video Realism Enhancement via Structure-aware Denoising
CV and Pattern Recognition
Makes fake videos look like real life.
Revisiting Reconstruction-based AI-generated Image Detection: A Geometric Perspective
CV and Pattern Recognition
Finds fake pictures made by computers.