Pixel-Inconsistency Modeling for Image Manipulation Localization

TL;DR

This paper introduces a robust image manipulation localization model based on pixel inconsistency artifacts, utilizing global and local pixel dependency modeling, novel data augmentation, and a comprehensive benchmark, achieving state-of-the-art generalization.

Contribution

The paper proposes a novel pixel-inconsistency based model with masked self-attention, local dependency streams, and a new data augmentation strategy for improved forgery localization.

Findings

Achieves state-of-the-art generalization across datasets.

Demonstrates robustness to real-world image perturbations.

Establishes a comprehensive benchmark for forgery detection models.

Abstract

Digital image forensics plays a crucial role in image authentication and manipulation localization. Despite the progress powered by deep neural networks, existing forgery localization methodologies exhibit limitations when deployed to unseen datasets and perturbed images (i.e., lack of generalization and robustness to real-world applications). To circumvent these problems and aid image integrity, this paper presents a generalized and robust manipulation localization model through the analysis of pixel inconsistency artifacts. The rationale is grounded on the observation that most image signal processors (ISP) involve the demosaicing process, which introduces pixel correlations in pristine images. Moreover, manipulating operations, including splicing, copy-move, and inpainting, directly affect such pixel regularity. We, therefore, first split the input image into several blocks and design masked self-attention mechanisms to model the global pixel dependency in input images. Simultaneously, we optimize another local pixel dependency stream to mine local manipulation clues within input forgery images. In addition, we design novel Learning-to-Weight Modules (LWM) to combine features from the two streams, thereby enhancing the final forgery localization performance. To improve the training process, we propose a novel Pixel-Inconsistency Data Augmentation (PIDA) strategy, driving the model to focus on capturing inherent pixel-level artifacts instead of mining semantic forgery traces. This work establishes a comprehensive benchmark integrating 15 representative detection models across 12 datasets. Extensive experiments show that our method successfully extracts inherent pixel-inconsistency forgery fingerprints and achieve state-of-the-art generalization and robustness performances in image manipulation localization.