Video as Natural Augmentation: Towards Unified AI-Generated Image and Video Detection

TL;DR

VINA is a unified detection framework that enhances AI-generated image and video detection by training on both modalities and aligning their representations, significantly improving robustness and transferability.

Contribution

The paper introduces VINA, a novel approach that jointly trains on images and videos, addressing cross-modal gaps and achieving state-of-the-art detection performance.

Findings

VINA improves detection robustness across diverse benchmarks.

It achieves state-of-the-art results without complex tuning.

VINA enhances transferability between image and video detection tasks.

Abstract

AI-generated content (AIGC) is rapidly improving, creating an urgent need for detectors that generalize across data sources, deployment pipelines, and visual modalities. A strongly generalizable detector should remain robust under distributional variations. However, we identify a consistent failure mode: SOTA AI-generated image detectors often collapse when applied to frames extracted from videos. Through systematic analysis, we show that this cross-modal gap arises from both entangled synthesis-agnostic video processing shifts, including color conversion, codec compression, resizing, and blur, and model-specific fingerprints introduced by modern video generators. Motivated by these findings, we propose VINA (Video as Natural Augmentation), a unified AIGC detection framework that jointly trains on image and video data. VINA uses video frames as physically grounded natural augmentations and further introduces a cross-modal supervised contrastive objective to align image and video representations under a shared real/fake decision boundary. Extensive experiments on 14 image, video, and in-the-wild benchmarks show that VINA delivers bidirectional gains, improves robustness and transferability, and achieves state-of-the-art performance across nearly all evaluated settings without complex augmentation or dataset-specific tuning.