Problem
Research questions and friction points this paper is trying to address.
synthetic video detection
appearance artifacts
semantic inconsistencies
temporal patterns
generalization
TRACE: Trajectory Representation and Consistency Estimation for AI-Generated Video Detection
🤖 AI Summary
研究提出TRACE框架，通过预训练视频模型的速度响应提取表示并建模帧间一致性，有效检测AI生成的视频，超越现有方法。
📝 Abstract
Recent advances in generative video models have enabled the synthesis of visually realistic content, posing significant challenges to synthetic video detection. Existing detectors often rely on appearance artifacts, semantic inconsistencies, and temporal patterns that may be generator-specific, limitating generalization to unseen synthesis models. We investigate whether responses to a pretrained generative model provide more transferable forensic cues. Our key observation is that real and AI-generated videos exhibit distinct \emph{velocity responses} under a pretrained Flow Matching video model. This distinction persists when different pretrained video-generation backbones are used as probes, suggesting that velocity responses offer transferable forensic signals beyond visual artificts. Motivated by this observation, we propose \textbf{TRACE} (\emph{\underline{T}rajectory \underline{R}epresentation \underline{a}nd \underline{C}onsistency \underline{E}stimation}), a generation-process-aware framework for AI-generated video detection. TRACE leverages a pretrained video DiT as a velocity-field probe to extract representations at multiple flow time points, and models cross-frame consistency through velocity differences between adjacent frames. We further introduce a \emph{Real-Centered Trajectory Optimization} objective that encourages generator-invariant representation learning. Extensive experiments on AIGVDBench demonstrate that TRACE generalizes effectively across diverse generators, substantially outperforming prior state-of-the-art methods on unseen open- and closed-source video generation models.
Innovation
Methods, ideas, or system contributions that make the work stand out.
velocity responses
generation-process-aware
Real-Centered Trajectory Optimization
cross-frame consistency
🔎 Similar Papers
No similar papers found.
