Salvato in:
Dettagli Bibliografici
Autori principali: He, Xinan, Lin, Kaiqing, Zhou, Yue, Zhong, Jiaming, Ye, Wei, Yi, Wenhui, Fan, Bing, Ding, Feng, Li, Haodong, Cao, Bo, Li, Bin
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2601.21408
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914300311896064
author He, Xinan
Lin, Kaiqing
Zhou, Yue
Zhong, Jiaming
Ye, Wei
Yi, Wenhui
Fan, Bing
Ding, Feng
Li, Haodong
Cao, Bo
Li, Bin
author_facet He, Xinan
Lin, Kaiqing
Zhou, Yue
Zhong, Jiaming
Ye, Wei
Yi, Wenhui
Fan, Bing
Ding, Feng
Li, Haodong
Cao, Bo
Li, Bin
contents With the rapid advancement of video generation models such as Veo and Wan, the visual quality of synthetic content has reached a level where macro-level semantic errors and temporal inconsistencies are no longer prominent. However, this does not imply that the distinction between real and cutting-edge high-fidelity fake is untraceable. We argue that AI-generated videos are essentially products of a manifold-fitting process rather than a physical recording. Consequently, the pixel composition logic of consecutive adjacent frames residual in AI videos exhibits a structured and homogenous characteristic. We term this phenomenon `Manifold Projection Fluctuations' (MPF). Driven by this insight, we propose a hierarchical dual-path framework that operates as a sequential filtering process. The first, the Static Manifold Deviation Branch, leverages the refined perceptual boundaries of Large-Scale Vision Foundation Models (VFMs) to capture residual spatial anomalies or physical violations that deviate from the natural real-world manifold (off-manifold). For the remaining high-fidelity videos that successfully reside on-manifold and evade spatial detection, we introduce the Micro-Temporal Fluctuation Branch as a secondary, fine-grained filter. By analyzing the structured MPF that persists even in visually perfect sequences, our framework ensures that forgeries are exposed regardless of whether they manifest as global real-world manifold deviations or subtle computational fingerprints.
format Preprint
id arxiv_https___arxiv_org_abs_2601_21408
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MPF-Net: Exposing High-Fidelity AI-Generated Video Forgeries via Hierarchical Manifold Deviation and Micro-Temporal Fluctuations
He, Xinan
Lin, Kaiqing
Zhou, Yue
Zhong, Jiaming
Ye, Wei
Yi, Wenhui
Fan, Bing
Ding, Feng
Li, Haodong
Cao, Bo
Li, Bin
Computer Vision and Pattern Recognition
With the rapid advancement of video generation models such as Veo and Wan, the visual quality of synthetic content has reached a level where macro-level semantic errors and temporal inconsistencies are no longer prominent. However, this does not imply that the distinction between real and cutting-edge high-fidelity fake is untraceable. We argue that AI-generated videos are essentially products of a manifold-fitting process rather than a physical recording. Consequently, the pixel composition logic of consecutive adjacent frames residual in AI videos exhibits a structured and homogenous characteristic. We term this phenomenon `Manifold Projection Fluctuations' (MPF). Driven by this insight, we propose a hierarchical dual-path framework that operates as a sequential filtering process. The first, the Static Manifold Deviation Branch, leverages the refined perceptual boundaries of Large-Scale Vision Foundation Models (VFMs) to capture residual spatial anomalies or physical violations that deviate from the natural real-world manifold (off-manifold). For the remaining high-fidelity videos that successfully reside on-manifold and evade spatial detection, we introduce the Micro-Temporal Fluctuation Branch as a secondary, fine-grained filter. By analyzing the structured MPF that persists even in visually perfect sequences, our framework ensures that forgeries are exposed regardless of whether they manifest as global real-world manifold deviations or subtle computational fingerprints.
title MPF-Net: Exposing High-Fidelity AI-Generated Video Forgeries via Hierarchical Manifold Deviation and Micro-Temporal Fluctuations
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.21408