TextureCrop: Enhancing Synthetic Image Detection through Texture-based Cropping

TL;DR

TextureCrop is a pre-processing technique that improves synthetic image detection by focusing on high-frequency textures, significantly boosting accuracy across multiple datasets and detectors.

Contribution

Introduces TextureCrop, a novel texture-based cropping method that enhances the performance of existing SID models on high-resolution images.

Findings

Improves AUC by 6.1% over center cropping.

Enhances detection performance by 15% compared to resizing.

Consistent gains across multiple datasets and detectors.

Abstract

Generative AI technologies produce increasingly realistic imagery, which, despite its potential for creative applications, can also be misused to produce misleading and harmful content. This renders Synthetic Image Detection (SID) methods essential for identifying AI-generated content online. State-of-the-art SID methods typically resize or center-crop input images due to architectural or computational constraints, which hampers the detection of artifacts that appear in high-resolution images. To address this limitation, we propose TextureCrop, an image pre-processing component that can be plugged in any pre-trained SID model to improve its performance. By focusing on high-frequency image parts where generative artifacts are prevalent, TextureCrop enhances SID performance with manageable memory requirements. Experimental results demonstrate a consistent improvement in AUC across various detectors by 6.1% compared to center cropping and by 15% compared to resizing, across high-resolution images from the Forensynths, Synthbuster and TWIGMA datasets. Code available at https : //github.com/mever-team/texture-crop.