M2SFormer: Multi-Spectral and Multi-Scale Attention with Edge-Aware Difficulty Guidance for Image Forgery Localization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nam, Ju-Hyeon, Moon, Dong-Hyun, Lee, Sang-Chul
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909660257189888
author Nam, Ju-Hyeon
Moon, Dong-Hyun
Lee, Sang-Chul
author_facet Nam, Ju-Hyeon
Moon, Dong-Hyun
Lee, Sang-Chul
contents Image editing techniques have rapidly advanced, facilitating both innovative use cases and malicious manipulation of digital images. Deep learning-based methods have recently achieved high accuracy in pixel-level forgery localization, yet they frequently struggle with computational overhead and limited representation power, particularly for subtle or complex tampering. In this paper, we propose M2SFormer, a novel Transformer encoder-based framework designed to overcome these challenges. Unlike approaches that process spatial and frequency cues separately, M2SFormer unifies multi-frequency and multi-scale attentions in the skip connection, harnessing global context to better capture diverse forgery artifacts. Additionally, our framework addresses the loss of fine detail during upsampling by utilizing a global prior map, a curvature metric indicating the difficulty of forgery localization, which then guides a difficulty-guided attention module to preserve subtle manipulations more effectively. Extensive experiments on multiple benchmark datasets demonstrate that M2SFormer outperforms existing state-of-the-art models, offering superior generalization in detecting and localizing forgeries across unseen domains.
format Preprint
id arxiv_https___arxiv_org_abs_2506_20922
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle M2SFormer: Multi-Spectral and Multi-Scale Attention with Edge-Aware Difficulty Guidance for Image Forgery Localization
Nam, Ju-Hyeon
Moon, Dong-Hyun
Lee, Sang-Chul
Computer Vision and Pattern Recognition
Image editing techniques have rapidly advanced, facilitating both innovative use cases and malicious manipulation of digital images. Deep learning-based methods have recently achieved high accuracy in pixel-level forgery localization, yet they frequently struggle with computational overhead and limited representation power, particularly for subtle or complex tampering. In this paper, we propose M2SFormer, a novel Transformer encoder-based framework designed to overcome these challenges. Unlike approaches that process spatial and frequency cues separately, M2SFormer unifies multi-frequency and multi-scale attentions in the skip connection, harnessing global context to better capture diverse forgery artifacts. Additionally, our framework addresses the loss of fine detail during upsampling by utilizing a global prior map, a curvature metric indicating the difficulty of forgery localization, which then guides a difficulty-guided attention module to preserve subtle manipulations more effectively. Extensive experiments on multiple benchmark datasets demonstrate that M2SFormer outperforms existing state-of-the-art models, offering superior generalization in detecting and localizing forgeries across unseen domains.
title M2SFormer: Multi-Spectral and Multi-Scale Attention with Edge-Aware Difficulty Guidance for Image Forgery Localization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.20922