分类 - IML
M2SFormer:Multi-Spectral and Multi-Scale Attention with Edge-Aware Difficulty Guidance for Image Forgery Localization
M2SFormer:Multi-Spectral and Multi-Scale Attention with Edge-Aware Difficulty Guidance for Image Forgery Localization

发表于ICCV2025,拿到了Highlight,M2SFormer通过在跳跃连接中统一多频段和多尺度注意力机制,借助全局上下文信息,能更精准捕捉各类伪造特征。此外,框架通过采用全局先验图(一种反映伪造检测难度的曲率度量指标)来解决上采样过程中细节丢失的问题。该方法使用分割的指标而不是图像篡改的传统指标,而且比较的方法并不是公认的sota。

11
Rethinking Image Forgery Detection via Soft Contrastive Learning and Unsupervised Clustering
Rethinking Image Forgery Detection via Soft Contrastive Learning and Unsupervised Clustering

TDSC2025的文章,首次使用对比学习加聚类的方法做图像篡改检测。

12
OmniGuard:Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarking
OmniGuard:Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarking

发表于CVPR2025,将版权水印和图像篡改主动保护两个任务联合起来。

13
Image Operation Chain Detection with Machine Translation Framework
Image Operation Chain Detection with Machine Translation Framework

发表于TMM2022,将机器学习应用到操作链检测的任务中,将每一个操作视为一个元素进行翻译。

14
Employing Reinforcement Learning to Construct a Decision-Making Environment for Image Forgery Localization
Employing Reinforcement Learning to Construct a Decision-Making Environment for Image Forgery Localization

发表于TIFS2024,将强化学习引入到了图像篡改检测。

15
Reinforced Multi-teacher Knowledge Distillation for Efficient General Image Forgery Detection and Localization
Reinforced Multi-teacher Knowledge Distillation for Efficient General Image Forgery Detection and Localization

发表于AAAI2025,该框架的核心是Re-DTS策略,动态选择最合适的教师模型,将专业知识转移到学生模型。这一策略增强了学生模型处理各种篡改痕迹的能力,并提高了IFDL性能,将强化学习引入到了图像篡改检测。

16
Rethinking Image Editing Detection in the Era of Generative AI Revolution
Rethinking Image Editing Detection in the Era of Generative AI Revolution

发表于ACMMM 2025,提出了基于图像编辑技术的新数据集。

17
Image Copy-Move Forgery Detection via Deep PatchMatch and Pairwise Ranking Learning
Image Copy-Move Forgery Detection via Deep PatchMatch and Pairwise Ranking Learning

发表于TIP 2024,图像复制-移动伪造检测方向的图像篡改检测方法。

18
DiRLoc:Disentanglement Representation Learning for Robust Image Forgery Localization
DiRLoc:Disentanglement Representation Learning for Robust Image Forgery Localization

发表于TDSC2024,针对JPEG压缩导致的性能下降,使用解纠缠的方法,分离出jpeg压缩对篡改痕迹的影响,提出了一种鲁棒的图像伪造定位框架。

19
IMDL-BenCo:A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization
IMDL-BenCo:A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization

发表于NeurIPS 2024,因为图像篡改检测没有统一的标准,所以构建一个全面的基准,并且设计了一个框架将部分sota网络集成:Mantra-Net,MVSS-net,CAT-Net,ObjectFormer,PSCC-Net,NCL-IML,Trufor和IML-ViT。

20