The paper argues that AI‑generated image detection has focused too much on model design and not enough on how supervision is structured. By replacing blended supervision with orthogonal, disentangled supervision—semantic signals for a vision‑language model and artifact signals for a vision expert—the authors show a 9.5% improvement on five in‑the‑wild benchmarks. They also introduce the AIGI‑Now benchmark to evaluate detectors on eight modern generators with separate semantic and pixel‑level tests.
By Ruoxin Chen, Jiahui Gao, Kaiqing Lin, Keyue Zhang, Yandan Zhao, Isabel Guan, Taiping Yao, Shouhong Ding
arXiv:2610.01778v1 Announce Type: new
Abstract: Reliable evaluation of image forgery localization (IFL) requires assessing models under diverse distribution changes, yet existing benchmarks often cov...
By Baoke Dou, Ziye Wang, Hao Wang, Guoqing Cai, Wende Tan, Chenyang Si, Liucheng Guo, Yueming Lyu
FUSED is a new framework that jointly detects and localizes AI-generated inpainting by combining low-level forensic cues with high-level semantic features through a sparsely-gated Mixture-of-Experts architecture. It predicts both an image-level manipulation score and a pixel-level mask of the inpainted region. On the OpenSDID cross-generator benchmark, FUSED outperforms existing methods, especially on unseen generators, and transfers effectively to the AutoSplice and CocoGlide benchmarks, doubling localization performance.
By Anton Nuzhdin, Marcel Worring, Ivona Najdenkoska
arXiv:2607. 06445v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are increasingly utilized as the conditioning backbone for diffusion-based image editing due to their remarkable multimodal reasoning capabilities.
By Yoav Baron, Sara Dorfman, Roni Paiss, Daniel Cohen-Or, Or Patashnik
arXiv:2607.18227v2 Announce Type: replace
Abstract: In line with the prevailing direction of vision research, we explore the integration of both generation and editing capabilities for video and imag...
By Dingyun Zhang, Lixue Gong, Wei Liu
arXiv:2608.20929v1 Announce Type: new
Abstract: AI-generated image manipulation localization identifies edited pixels, but its OOD performance lags behind image-level detection partly because pixel s...
By Haozhen Yan, Siyuan Shan, Zijian Yu, Youqi Wang, Yan Hong, Jun Lan, Jianfu Zhang
Semantically Aligned Gradient-Driven Context-Preserving Image Editing (IABEdit) is a model‑agnostic framework that embeds differentiable semantic verification into the training of generative image editors. By using a frozen vision‑language model to extract spatially‑aware descriptors from ground‑truth edits and a trainable aligner to reproduce them from generated outputs, the residual becomes a gradient that teaches the generator both what to edit and where, without adding inference‑time VLM cost. IABEdit is compatible with various backbones (e.g., U‑Net in Stable Diffusion and MMDiT in FLUX) and improves structural fidelity on MagicBrush, achieves state‑of‑the‑art instruction adherence on RealEdit and EMU Edit, and outperforms the proprietary Gemini agent on the D‑LORD surveillance benchmark under heavy occlusion.
"whyItMatters":"IABEdit demonstrates that incorporating semantic verification during training can produce more accurate, well‑localized edits and outperform existing methods even in challenging surveillance scenarios, as shown by its superior metrics and human/GPT‑4o evaluations."
By Chiranjeev Chiranjeev, Muskan Dosi, Mayank Vatsa, Richa Singh
BRIDGE is a dual‑path architecture for coarse‑mask local editing that separates background preservation from subject generation. It uses a full‑canvas Main Path, a local Subject Path, and a learned binary gate to route subject‑token embeddings between subject‑centric and background‑anchored coordinates, keeping the mask outside the DiT backbone and training with independent noise. Experiments on Qwen‑Image‑Edit‑2511 and BRIDGE‑Bench show that BRIDGE outperforms ACE++ and FLUX.1‑Fill in local precision, and when instantiated on FLUX.2 it achieves leading performance on ICE‑Bench tasks, improving local generation while maintaining the surrounding scene.
By Peilin Xiong, Honghui Yuan, Junwen Chen, Keiji Yanai
arXiv:2607. 18230v1 Announce Type: cross Abstract: Modern vision-language models (VLMs) have significantly improved image generation and editing capabilities, making pixel-level image tampering detection increasingly important yet challenging under cross-model and out-of-distribution shifts.
By Yi Tang, Xinyi Shang, Jiacheng Cui, Sondos Mahmoud Bsharat, Jiacheng Liu, Xiaohan Zhao, Tran Dinh Tien, Ahmed Elhagry, Salwa K. Al Khatib, Tianjun Yao, Yonina C. Eldar, Jing-Hao Xue, Hao Li, Salman Khan, Zhiqiang Shen
The paper introduces Relative Patch Response Learning (PRL) to detect AI‑generated images by comparing patch responses across two mixed views of aligned real‑generated image pairs. PRL uses a relative response objective, a reference coherence objective, and an area ranking objective to address contextual shifts caused by self‑attention, providing precise supervision for patch‑level detection. Experiments show PRL outperforms prior methods by 4.3% and 5.9% in average balanced accuracy on standard and in‑the‑wild benchmarks.
By Tianyu Wang, Ouxiang Li, Yanbin Hao, Zhenhua Tang, Shuo Wang
arXiv:2605.16879v2 Announce Type: replace
Abstract: With the rapid evolution of synthetic media, Image Manipulation Localization (IML) has emerged as a critical component in multimedia forensics for...
By Yunfei Wang, Bo Du, Zhe Yang, Xin Liu, Zhiyu Lin, Tianxin Xu, Ji-Zhe Zhou
The paper introduces a framework for auditing image editors that can satisfy regional plausibility constraints while lacking a single latent explanation for the entire output. It defines a common witness grade and witness nerve to formalize local-to-global failures, separating auditing from causal identification. Using Helly-type arguments and a blocker-hypergraph formula, the authors provide short incompatibility certificates, sharp partial-identification bounds for specified image features, and finite-sample outer coverage of identified intervals, validated through controlled MNIST, Morpho-MNIST, and smallNORB experiments.
By Usef Faghihi, Amir Saki