When 2D Cues Fail: Improving Image Manipulation Localization with Reliable 3D Geometry
Existing image manipulation localization (IML) methods rely heavily on 2D forensic cues, such as low-level artifacts, noise traces, and semantic inconsistencies in the manipulated image. While effective in many cases, these cues become much less discriminative when manipulated regions are well blended with their surrounding context in appearance. In such cases, a manipulated region may remain locally appearance-consistent, but still violate the geometric structure of the surrounding scene. This limitation motivates us to go beyond purely 2D evidence and introduce geometric reasoning into IML.
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%Tongyi-MAI/Z-Image-Turbo →
“Fuzzy title match (0.73): “When 2D Cues Fail: Improving Image Manipulation Localization” ≈ “Tongyi-MAI/Z-Image-Turbo””
- FuzzySimilar name plus overlapping authors · 89%mudler/LocalAI →
“Title similarity 0.92; shared authors: guo”
- LinkedLinked via arxiv author · 85%Guofeng Yu →
“When 2D Cues Fail: Improving Image Manipulation Localization with Reliable 3D Geometry”
- LinkedLinked via arxiv author · 85%Zhiqing Guo →
“When 2D Cues Fail: Improving Image Manipulation Localization with Reliable 3D Geometry”
- LinkedLinked via arxiv author · 85%Dan Ma →
“When 2D Cues Fail: Improving Image Manipulation Localization with Reliable 3D Geometry”
- LinkedLinked via arxiv author · 85%Gaobo Yang →
“When 2D Cues Fail: Improving Image Manipulation Localization with Reliable 3D Geometry”