SOTAVerified

Image Manipulation Detection

The task of detecting images or image parts that have been tampered or manipulated (sometimes also referred to as doctored). This typically encompasses image splicing, copy-move, or image inpainting.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 73 papers

TitleStatusHype
Weakly-supervised Localization of Manipulated Image Regions Using Multi-resolution Learned Features—0
ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and LocalizationCode2
AnimeDL-2M: Million-Scale AI-Generated Anime Image Detection and Localization in Diffusion Era—0
Context-Aware Weakly Supervised Image Manipulation Localization with SAM Refinement—0
LEGION: Learning to Ground and Explain for Synthetic Image Detection—0
IMDPrompter: Adapting SAM to Image Manipulation Detection by Cross-View Automated Prompt Learning—0
Data-Driven Fairness Generalization for Deepfake Detection—0
ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation DetectionCode1
HRGR: Enhancing Image Manipulation Detection via Hierarchical Region-aware Graph Reasoning—0
Perturb, Attend, Detect and Localize (PADL): Robust Proactive Image Defense—0
Show:102550
← PrevPage 1 of 8Next →
All datasetsCasia V1+DSO-1CocoGlideColumbiaCOVERAGECASIA (OSN-transmitted - Facebook)CASIA (OSN-transmitted - Wechat)CASIA (OSN-transmitted - Weibo)CASIA (OSN-transmitted - Whatsapp)Columbia (OSN-transmitted - Facebook)Columbia (OSN-transmitted - Wechat)Columbia (OSN-transmitted - Weibo)

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Early FusionBalanced Accuracy0.94—Unverified
2TruForBalanced Accuracy0.93—Unverified
3Late FusionBalanced Accuracy0.83—Unverified
4DF-NetAUC0.77—Unverified
5CAT-Net v2Balanced Accuracy0.53—Unverified
6ManTraNetBalanced Accuracy0.5—Unverified
7MVSS-NetBalanced Accuracy0.36—Unverified
8CR-CNNBalanced Accuracy0.29—Unverified
9SPANBalanced Accuracy0.23—Unverified