This work introduces the first large-scale benchmark for this task by collecting real portraits and fake portraits from multiple sources and evaluates representative existing detectors on this benchmark, revealing their lack of explicit mechanisms for retaining fine-grained information and maintaining feature consisten...
Yu-Jie Gao, Zijian Yu, Yan Hong et al.· 0 citations
GAP-SAM encodes an image and its frozen VAE reconstruction into a global artifact token and injects it into SAM3's feature pyramid via zero-gated FiLM via zero-gated FiLM before pixel decoding to preserve localization while suppressing semantic-boundary shortcuts.
Haozhen Yan, Siyuan Shan, Zijian Yu et al.· 0 citations
Defake-o3 is presented, an explainable AIGI detector that moves from speculative rationales to verifiable evidence, and Experiments show that Defake-o3 improves both detection accuracy and explanation quality, producing more localized, verifiable, and persuasive evidence.
Bowen Deng, Jiahui Zhan, Yikun Ji et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.