M2SFormer, a Transformer encoder architecture with multi-spectral/multi-scale skip-connection attention and curvature-based difficulty guidance, achieves state-of-the-art cross-domain image forgery localization on several benchmarks.
Rru-net: The ringed residual u-net for image splicing forgery detec- tion
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
M2SFormer: Multi-Spectral and Multi-Scale Attention with Edge-Aware Difficulty Guidance for Image Forgery Localization
M2SFormer, a Transformer encoder architecture with multi-spectral/multi-scale skip-connection attention and curvature-based difficulty guidance, achieves state-of-the-art cross-domain image forgery localization on several benchmarks.