Semantic Manipulation Localization

TL;DR

This paper introduces Semantic Manipulation Localization (SML), a new task and benchmark for detecting subtle semantic edits in images, and proposes TRACE, a framework that models semantic sensitivity for improved localization.

Contribution

The paper defines SML as a novel task, creates a dedicated benchmark, and proposes TRACE, an end-to-end framework that captures semantic sensitivity for localization of subtle edits.

Findings

TRACE outperforms existing IML methods on the benchmark.

TRACE produces more complete, compact, and semantically coherent localization results.

Moving beyond artifact detection is essential for complex semantic editing scenarios.

Abstract

Image Manipulation Localization (IML) aims to identify edited regions in an image. However, with the increasing use of modern image editing and generative models, many manipulations no longer exhibit obvious low-level artifacts. Instead, they often involve subtle but meaning-altering edits to an object's attributes, state, or relationships while remaining highly consistent with the surrounding content. This makes conventional IML methods less effective because they mainly rely on artifact detection rather than semantic sensitivity. To address this issue, we introduce Semantic Manipulation Localization (SML), a new task that focuses on localizing subtle semantic edits that significantly change image interpretation. We further construct a dedicated fine-grained benchmark for SML using a semantics-driven manipulation pipeline with pixel-level annotations. Based on this task, we propose TRACE (Targeted Reasoning of Attributed Cognitive Edits), an end-to-end framework that models semantic sensitivity through three progressively coupled components: semantic anchoring, semantic perturbation sensing, and semantic-constrained reasoning. Specifically, TRACE first identifies semantically meaningful regions that support image understanding, then injects perturbation-sensitive frequency cues to capture subtle edits under strong visual consistency, and finally verifies candidate regions through joint reasoning over semantic content and semantic scope. Extensive experiments show that TRACE consistently outperforms existing IML methods on our benchmark and produces more complete, compact, and semantically coherent localization results. These results demonstrate the necessity of moving beyond artifact-based localization and provide a new direction for image forensics in complex semantic editing scenarios.