DINO-Detect: A Simple yet Effective Framework for Blur-Robust AI-Generated Image Detection

TL;DR

This paper introduces DINO-Detect, a framework that enhances AI-generated image detection robustness against motion blur by using teacher-student knowledge distillation from sharp to blurred images, achieving state-of-the-art results.

Contribution

It proposes a novel blur-robust detection method leveraging teacher-student distillation with a fixed teacher to improve real-world AIGI detection under motion degradation.

Findings

Achieves state-of-the-art performance on blurred and clean images.

Improves generalization of AIGI detection in real-world scenarios.

Demonstrates robustness against motion blur in various conditions.

Abstract

With growing concerns over image authenticity and digital safety, the field of AI-generated image (AIGI) detection has progressed rapidly. Yet, most AIGI detectors still struggle under real-world degradations, particularly motion blur, which frequently occurs in handheld photography, fast motion, and compressed video. Such blur distorts fine textures and suppresses high-frequency artifacts, causing severe performance drops in real-world settings. We address this limitation with a blur-robust AIGI detection framework based on teacher-student knowledge distillation. A high-capacity teacher (DINOv3), trained on clean (i.e., sharp) images, provides stable and semantically rich representations that serve as a reference for learning. By freezing the teacher to maintain its generalization ability, we distill its feature and logit responses from sharp images to a student trained on blurred counterparts, enabling the student to produce consistent representations under motion degradation. Extensive experiments benchmarks show that our method achieves state-of-the-art performance under both motion-blurred and clean conditions, demonstrating improved generalization and real-world applicability. Source codes will be released at: https://github.com/JiaLiangShen/Dino-Detect-for-blur-robust-AIGC-Detection.