Metraipolis › archive › dc_aeecc4be83e0
RED: Reconstruction Evolution Dynamics for Generalizable AI-Generated Image Detection — arXiv:2609.36822
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36822
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T18:38:30.617Z
- SHA-256 of the archived text
d8d9be8f252e76956a64b01ebb605d0277fa311c9dd4b3aa44b4922e4b5315c2- Stable URL of this page
https://metraipolis.com/documento/dc_aeecc4be83e0
How to cite
RED: Reconstruction Evolution Dynamics for Generalizable AI-Generated Image Detection — arXiv:2609.36822 — arXiv (en), https://arxiv.org/abs/2609.36822 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aeecc4be83e0 (Metraipolis archive dc_aeecc4be83e0, sha256 d8d9be8f252e76956a64b01ebb605d0277fa311c9dd4b3aa44b4922e4b5315c2)
BibTeX
@misc{dcaeecc4be83e0,
title = {RED: Reconstruction Evolution Dynamics for Generalizable AI-Generated Image Detection — arXiv:2609.36822},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36822},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aeecc4be83e0; sha256 d8d9be8f252e76956a64b01ebb605d0277fa311c9dd4b3aa44b4922e4b5315c2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36822. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The rapid evolution of image generators calls for forensic cues that generalize beyond known generation mechanisms. Existing detectors often rely on static image representations or endpoint reconstruction discrepancies, leaving the evolution of intermediate reconstruction stages underexplored. We observe that the relative token predictability of real and generated images can reverse across reconstruction scales, suggesting that intermediate stages may expose forensic evidence overlooked by endpoint comparisons. Motivated by this observation, we propose RED (Reconstruction Evolution Dynamics), a framework that captures transferable forensic cues from coarse-to-fine reconstruction evolution. To our knowledge, RED is the first framework to use scale-wise token predictability to guide forensic evidence aggregation across intermediate reconstruction states. It represents the reconstruction trajectory produced by a frozen multiscale VQ-VAE in the shared feature space of a frozen CLIP encoder. To connect the observed predictability variations with visual evidence, RED learns image-adaptive stage weights from scale-wise token negative log-likelihoods provided by a frozen VAR model. A cross-stage evidence aggregation module then jointly models the original-image representation and the weighted reconstruction features, capturing complementary forensic cues through interactions along the reconstruction trajectory. Experiments on six diverse benchmarks demonstrate that RED achieves the highest average accuracy of 92.5\% and average precision of 97.5\% among the evaluated methods. Further evaluations show strong robustness to common image degradations, supporting the value of reconstruction evolution for generalizable AI-generated image detection. The code will be made publicly available upon acceptance of this paper. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.36822 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T18:04:24.753Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).