Video Forgery Detection with Optical Flow Residuals and Spatial-Temporal Consistency

TL;DR

This paper introduces a novel video forgery detection method that combines RGB appearance features with optical flow residuals to effectively identify synthetic videos, especially those generated by advanced diffusion models.

Contribution

It proposes a dual-branch framework that integrates spatial-temporal consistency for improved detection of AI-generated videos, addressing limitations of existing methods.

Findings

Effective detection across diverse generative models

Robustness to high-fidelity synthetic videos

Strong generalization ability demonstrated

Abstract

The rapid advancement of diffusion-based video generation models has led to increasingly realistic synthetic content, presenting new challenges for video forgery detection. Existing methods often struggle to capture fine-grained temporal inconsistencies, particularly in AI-generated videos with high visual fidelity and coherent motion. In this work, we propose a detection framework that leverages spatial-temporal consistency by combining RGB appearance features with optical flow residuals. The model adopts a dual-branch architecture, where one branch analyzes RGB frames to detect appearance-level artifacts, while the other processes flow residuals to reveal subtle motion anomalies caused by imperfect temporal synthesis. By integrating these complementary features, the proposed method effectively detects a wide range of forged videos. Extensive experiments on text-to-video and image-to-video tasks across ten diverse generative models demonstrate the robustness and strong generalization ability of the proposed approach.