# AMSEANet: An Edge-Guided Adaptive Multi-Scale Network for Image Splicing Detection and Localization

## TL;DR

This paper introduces AMSEANet, a new network for detecting and locating image splicing by combining semantic and artifact analysis with frequency-domain information.

## Contribution

AMSEANet integrates semantic understanding and artifact perception into a single frequency-aware process using adaptive filters and cross-scale feature fusion.

## Key findings

- AMSEANet outperforms existing methods on public datasets for image splicing detection.
- The network shows robustness against common attacks like noise and JPEG compression.
- Cross-scale feature fusion preserves subtle tampering clues and boundary details effectively.

## Abstract

In image splicing tamper detection, forgery operations simultaneously introduce macroscopic semantic inconsistencies and microscopic tampering artifacts. Conventional methods often treat semantic understanding and low-level artifact perception as separate tasks, which impedes their effective synergy. Meanwhile, frequency-domain information, a crucial clue for identifying traces of tampering, is frequently overlooked. However, a simplistic fusion of frequency-domain and spatial features can lead to feature conflicts and information redundancy. To resolve these challenges, this paper proposes an Adaptive Multi-Scale Edge-Aware Network (AMSEANet). This network employs a synergistic enhancement cascade architecture, recasting semantic understanding and artifact perception as a single, frequency-aware process guided by deep semantics. It leverages data-driven adaptive filters to precisely isolate and focus on edge artifacts that signify tampering. Concurrently, the dense fusion and enhancement of cross-scale features effectively preserve minute tampering clues and boundary details. Extensive experiments demonstrate that our proposed method achieves superior performance on several public datasets and exhibits excellent robustness against common attacks, such as noise and JPEG compression.