SOTAVerified

Image Manipulation Localization

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

Papers

Showing 110 of 31 papers

TitleStatusHype
Beyond Fully Supervised Pixel Annotations: Scribble-Driven Weakly-Supervised Framework for Image Manipulation Localization0
ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and LocalizationCode2
Context-Aware Weakly Supervised Image Manipulation Localization with SAM Refinement0
Can We Get Rid of Handcrafted Feature Extractors? SparseViT: Nonsemantics-Centered, Parameter-Efficient Image Manipulation Localization through Spare-Coding TransformerCode2
Mesoscopic Insights: Orchestrating Multi-scale & Hybrid Architecture for Image Manipulation LocalizationCode2
Omni-IML: Towards Unified Image Manipulation Localization0
ForgeryTTT: Zero-Shot Image Manipulation Localization with Test-Time Training0
A Noise and Edge extraction-based dual-branch method for Shallowfake and Deepfake Localization0
Digital Image Forensics: A quantitative & qualitative comparison between State-of-the-art-AI and Traditional Techniques for detection and localization of image manipulationsCode0
M^3:Manipulation Mask Manufacturer for Arbitrary-Scale Super-Resolution Mask0
Show:102550
← PrevPage 1 of 4Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1IML-ViTPixel Binary F10.65Unverified
2MesorchPixel Binary F10.59Unverified
3MVSS-NetPixel Binary F10.5Unverified
4TruforPixel Binary F10.46Unverified
5CAT-NetPixel Binary F10.43Unverified
6PSCCPixel Binary F10.38Unverified
7ObjectFormerPixel Binary F10.26Unverified
8Mantra-NetPixel Binary F10.2Unverified