No Pixel Left Behind: A Detail-Preserving Architecture for Robust High-Resolution AI-Generated Image Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mu, Lianrui, Xingze, Zou, Bai, Jianhong, Hu, Jiaqi, Zheng, Wenjie, Ye, Jiangnan, Zhuang, Jiedong, Ali, Mudassar, Wang, Jing, Hu, Haoji
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908500278378496
author Mu, Lianrui
Xingze, Zou
Bai, Jianhong
Hu, Jiaqi
Zheng, Wenjie
Ye, Jiangnan
Zhuang, Jiedong
Ali, Mudassar
Wang, Jing
Hu, Haoji
author_facet Mu, Lianrui
Xingze, Zou
Bai, Jianhong
Hu, Jiaqi
Zheng, Wenjie
Ye, Jiangnan
Zhuang, Jiedong
Ali, Mudassar
Wang, Jing
Hu, Haoji
contents The rapid growth of high-resolution, meticulously crafted AI-generated images poses a significant challenge to existing detection methods, which are often trained and evaluated on low-resolution, automatically generated datasets that do not align with the complexities of high-resolution scenarios. A common practice is to resize or center-crop high-resolution images to fit standard network inputs. However, without full coverage of all pixels, such strategies risk either obscuring subtle, high-frequency artifacts or discarding information from uncovered regions, leading to input information loss. In this paper, we introduce the High-Resolution Detail-Aggregation Network (HiDA-Net), a novel framework that ensures no pixel is left behind. We use the Feature Aggregation Module (FAM), which fuses features from multiple full-resolution local tiles with a down-sampled global view of the image. These local features are aggregated and fused with global representations for final prediction, ensuring that native-resolution details are preserved and utilized for detection. To enhance robustness against challenges such as localized AI manipulations and compression, we introduce Token-wise Forgery Localization (TFL) module for fine-grained spatial sensitivity and JPEG Quality Factor Estimation (QFE) module to disentangle generative artifacts from compression noise explicitly. Furthermore, to facilitate future research, we introduce HiRes-50K, a new challenging benchmark consisting of 50,568 images with up to 64 megapixels. Extensive experiments show that HiDA-Net achieves state-of-the-art, increasing accuracy by over 13% on the challenging Chameleon dataset and 10% on our HiRes-50K.
format Preprint
id arxiv_https___arxiv_org_abs_2508_17346
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle No Pixel Left Behind: A Detail-Preserving Architecture for Robust High-Resolution AI-Generated Image Detection
Mu, Lianrui
Xingze, Zou
Bai, Jianhong
Hu, Jiaqi
Zheng, Wenjie
Ye, Jiangnan
Zhuang, Jiedong
Ali, Mudassar
Wang, Jing
Hu, Haoji
Computer Vision and Pattern Recognition
The rapid growth of high-resolution, meticulously crafted AI-generated images poses a significant challenge to existing detection methods, which are often trained and evaluated on low-resolution, automatically generated datasets that do not align with the complexities of high-resolution scenarios. A common practice is to resize or center-crop high-resolution images to fit standard network inputs. However, without full coverage of all pixels, such strategies risk either obscuring subtle, high-frequency artifacts or discarding information from uncovered regions, leading to input information loss. In this paper, we introduce the High-Resolution Detail-Aggregation Network (HiDA-Net), a novel framework that ensures no pixel is left behind. We use the Feature Aggregation Module (FAM), which fuses features from multiple full-resolution local tiles with a down-sampled global view of the image. These local features are aggregated and fused with global representations for final prediction, ensuring that native-resolution details are preserved and utilized for detection. To enhance robustness against challenges such as localized AI manipulations and compression, we introduce Token-wise Forgery Localization (TFL) module for fine-grained spatial sensitivity and JPEG Quality Factor Estimation (QFE) module to disentangle generative artifacts from compression noise explicitly. Furthermore, to facilitate future research, we introduce HiRes-50K, a new challenging benchmark consisting of 50,568 images with up to 64 megapixels. Extensive experiments show that HiDA-Net achieves state-of-the-art, increasing accuracy by over 13% on the challenging Chameleon dataset and 10% on our HiRes-50K.
title No Pixel Left Behind: A Detail-Preserving Architecture for Robust High-Resolution AI-Generated Image Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.17346