Beyond Artifacts: Real-Centric Envelope Modeling for Reliable AI-Generated Image Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Ruiqi, Han, Yi, Zhang, Zhengbo, Yao, Liwei, Yan, Zhiyuan, Shen, Jialiang, Chen, ZhiJin, Sun, Boyi, Weng, Lubin, Dong, Jing, Wang, Yan, Wu, Shu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918262722265088
author Liu, Ruiqi
Han, Yi
Zhang, Zhengbo
Yao, Liwei
Yan, Zhiyuan
Shen, Jialiang
Chen, ZhiJin
Sun, Boyi
Weng, Lubin
Dong, Jing
Wang, Yan
Wu, Shu
author_facet Liu, Ruiqi
Han, Yi
Zhang, Zhengbo
Yao, Liwei
Yan, Zhiyuan
Shen, Jialiang
Chen, ZhiJin
Sun, Boyi
Weng, Lubin
Dong, Jing
Wang, Yan
Wu, Shu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_20937
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond Artifacts: Real-Centric Envelope Modeling for Reliable AI-Generated Image Detection
Liu, Ruiqi
Han, Yi
Zhang, Zhengbo
Yao, Liwei
Yan, Zhiyuan
Shen, Jialiang
Chen, ZhiJin
Sun, Boyi
Weng, Lubin
Dong, Jing
Wang, Yan
Wu, Shu
Computer Vision and Pattern Recognition
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.
title Beyond Artifacts: Real-Centric Envelope Modeling for Reliable AI-Generated Image Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.20937