Bridging the Micro--Macro Gap: Frequency-Aware Semantic Alignment for Image Manipulation Localization

ArXi:2604.12341v1 Announce Type: new As generative image editing advances, image manipulation localization (IML) must handle both traditional manipulations with conspicuous forensic artifacts and diffusion-generated edits that appear locally realistic. Existing methods typically rely on either low-level forensic cues or high-level semantics alone, leading to a fundamental micro--macro gap. To bridge this gap, we propose FASA, a unified framework for localizing both traditional and diffusion-generated manipulations.