Revisiting Reconstruction-based AI-generated Image Detection: A Geometric Perspective

• URL: http://arxiv.org/abs/2510.25141v1
• Date: Wed, 29 Oct 2025 03:45:03 GMT
• Title: Revisiting Reconstruction-based AI-generated Image Detection: A Geometric Perspective
• Authors: Wan Jiang, Jing Yan, Ruixuan Zhang, Xiaojing Chen, Changtao Miao, Zhe Li, Chenhao Lin, Yunfeng Diao, Richang Hong,
• Abstract summary: We introduce the Jacobian-Spectral Lower Bound for reconstruction error from a geometric perspective.<n>We show that real images off the reconstruction manifold exhibit a non-trivial error lower bound, while generated images on the manifold have near-zero error.<n>We propose ReGap, a training-free method that computes dynamic reconstruction error by leveraging structured editing operations.
• Score: 50.83711509908479
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The rise of generative Artificial Intelligence (AI) has made detecting AI-generated images a critical challenge for ensuring authenticity. Existing reconstruction-based methods lack theoretical foundations and on empirical heuristics, limiting interpretability and reliability. In this paper, we introduce the Jacobian-Spectral Lower Bound for reconstruction error from a geometric perspective, showing that real images off the reconstruction manifold exhibit a non-trivial error lower bound, while generated images on the manifold have near-zero error. Furthermore, we reveal the limitations of existing methods that rely on static reconstruction error from a single pass. These methods often fail when some real images exhibit lower error than generated ones. This counterintuitive behavior reduces detection accuracy and requires data-specific threshold tuning, limiting their applicability in real-world scenarios. To address these challenges, we propose ReGap, a training-free method that computes dynamic reconstruction error by leveraging structured editing operations to introduce controlled perturbations. This enables measuring error changes before and after editing, improving detection accuracy by enhancing error separation. Experimental results show that our method outperforms existing baselines, exhibits robustness to common post-processing operations and generalizes effectively across diverse conditions.

Related papers

• A Difference-in-Difference Approach to Detecting AI-Generated Images [12.73070476746517]
  Diffusion models are able to produce AI-generated images that are almost indistinguishable from real ones.<n>This raises concerns about their potential misuse and poses substantial challenges for detecting them.<n>We propose a novel difference-in-difference method for distinguishing real from fake images.
  arXiv  Detail & Related papers  (2026-02-27T06:57:39Z)
• GRRE: Leveraging G-Channel Removed Reconstruction Error for Robust Detection of AI-Generated Images [21.903079107456424]
  G-channel Removed Reconstruction Error (GRRE) is a simple yet effective method that exploits this discrepancy for robust AI-generated image detection.<n> GRRE consistently achieves high detection accuracy across multiple generative models, including those unseen during training.<n>These results highlight the potential of channel-removal-based reconstruction as a powerful forensic tool for safeguarding image authenticity in the era of generative AI.
  arXiv  Detail & Related papers  (2026-01-06T04:53:10Z)
• The Consistency Critic: Correcting Inconsistencies in Generated Images via Reference-Guided Attentive Alignment [105.31858867473845]
  ImageCritic can be integrated into an agent framework to automatically detect inconsistencies and correct them with multi-round and local editing.<n>In experiments, ImageCritic can effectively resolve detail-related issues in various customized generation scenarios, providing significant improvements over existing methods.
  arXiv  Detail & Related papers  (2025-11-25T18:40:25Z)
• Detecting Generated Images by Fitting Natural Image Distributions [75.31113784234877]
  We propose a novel framework that exploits geometric differences between the data manifold of natural and generated images.<n>We employ a pair of functions engineered to yield consistent outputs for natural images but divergent outputs for generated ones.<n>An image is identified as generated if a transformation along its data manifold induces a significant change in the loss value of a self-supervised model pre-trained on natural images.
  arXiv  Detail & Related papers  (2025-11-03T07:20:38Z)
• Circular Image Deturbulence using Quasi-conformal Geometry [3.239589979987861]
  In this paper, we introduce the Circular Quasi-Conformal Deturbulence (CQCD) framework, an unsupervised approach for removing image distortions.<n>This design ensures that the restored image remains both geometrically accurate and visually faithful while preventing the accumulation of incorrect estimations.<n> Experimental results demonstrate that CQCD not only outperforms existing state-of-the-art deturbulence methods in terms of image restoration quality but also provides highly accurate deformation field estimations.
  arXiv  Detail & Related papers  (2025-04-18T03:07:25Z)
• Limited-angle x-ray nano-tomography with machine-learning enabled iterative reconstruction engine [0.820550741199358]
  We propose an approach dubbed Perception Fused Iterative Tomography Reconstruction Engine.<n>It integrates a convolutional neural network (CNN) with perceptional knowledge as a smart regularizer into an iterative solving engine.<n>We demonstrate the effectiveness of the proposed approach using various experimental datasets obtained with different x-ray microscopy techniques.
  arXiv  Detail & Related papers  (2025-03-25T01:14:16Z)
• Uniform Attention Maps: Boosting Image Fidelity in Reconstruction and Editing [66.48853049746123]
  We analyze reconstruction from a structural perspective and propose a novel approach that replaces traditional cross-attention with uniform attention maps.<n>Our method effectively minimizes distortions caused by varying text conditions during noise prediction.<n> Experimental results demonstrate that our approach not only excels in achieving high-fidelity image reconstruction but also performs robustly in real image composition and editing scenarios.
  arXiv  Detail & Related papers  (2024-11-29T12:11:28Z)
• Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection [58.87142367781417]
  A naively trained detector tends to favor overfitting to the limited and monotonous fake patterns, causing the feature space to become highly constrained and low-ranked.<n>One potential remedy is incorporating the pre-trained knowledge within the vision foundation models to expand the feature space.<n>By freezing the principal components and adapting only the remained components, we preserve the pre-trained knowledge while learning fake patterns.
  arXiv  Detail & Related papers  (2024-11-23T19:10:32Z)
• Making Reconstruction-based Method Great Again for Video Anomaly Detection [64.19326819088563]
  Anomaly detection in videos is a significant yet challenging problem. Existing reconstruction-based methods rely on old-fashioned convolutional autoencoders. We propose a new autoencoder model for enhanced consecutive frame reconstruction.
  arXiv  Detail & Related papers  (2023-01-28T01:57:57Z)
• Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection [77.3530907443279]
  We propose a novel self-supervised framework to detect objects in degraded low resolution images. Our methods has achieved superior performance compared with existing methods when facing variant degradation situations.
  arXiv  Detail & Related papers  (2022-08-05T09:36:13Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)
• Toward Real-world Image Super-resolution via Hardware-based Adaptive Degradation Models [3.9037347042028254]
  Most single image super-resolution (SR) methods are developed on synthetic low-resolution (LR) and high-resolution (HR) image pairs. We propose a novel supervised method to simulate an unknown degradation process with the inclusion of prior hardware knowledge. Experiments on the real-world datasets validate that our degradation model can estimate LR images more accurately than the predetermined degradation operation.
  arXiv  Detail & Related papers  (2021-10-20T19:53:48Z)
• Improved anomaly detection by training an autoencoder with skip connections on images corrupted with Stain-shaped noise [25.85927871251385]
  anomaly detection relies on the reconstruction residual or, alternatively, on the reconstruction uncertainty. We consider an autoencoder architecture with skip connections to improve the sharpness of the reconstruction. We show that this model favors the reconstruction of clean images from arbitrary real-world images, regardless of the actual defects appearance.
  arXiv  Detail & Related papers  (2020-08-29T13:50:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.