paper-with-me

Papers

Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection

2025-10-09 · Shuhai Zhang, ZiHao Lian, Jiahao Yang, Daiyuan Li, Guoxuan Pang, Feng Liu, Bo Han, Shutao Li, Mingkui Tan arxiv

AI-generated videos have achieved near-perfect visual realism (e.g., Sora), urgently necessitating reliable detection mechanisms. However, detecting such videos faces significant challenges in modeling high-dimensional spatiotemporal dynamics and identifying subtle anomalies that violate physical laws. In this paper, we propose the first physics-driven AI-generated video detection paradigm based on probability flow conservation principles. Specifically, we propose a statistic called Normalized Spatiotemporal Gradient (NSG), which quantifies the ratio of spatial probability gradients to temporal density changes, explicitly capturing deviations from natural video dynamics. Leveraging pre-trained diffusion models, we develop an NSG estimator through spatial gradients approximation and motion-aware temporal modeling without complex motion decomposition while preserving physical constraints. Building on this, we propose an NSG-based video detection method (NSG-VD) that computes the Maximum Mean Discrepancy (MMD) between NSG features of the test and real videos as a detection metric. Last, we derive an upper bound of NSG feature distances between real and generated videos, proving that generated videos exhibit amplified discrepancies due to distributional shifts. Extensive experiments confirm that NSG-VD outperforms state-of-the-art baselines by 16.00% in Recall and 10.75% in F1-Score, validating the superior performance of NSG-VD. The source code is available at https://github.com/ZSHsh98/NSG-VD.

📄 PDF Abstract BibTeX arXiv:2510.08073

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Phys4D: Fine-Grained Physics-Consistent 4D Modeling from Video Diffusion

2026-03-03 · Haoran Lu, Shang Wu, Songling Liu, Jianshu Zhang 외 arxiv

Recent video diffusion models have achieved impressive capabilities as large-scale generative world models. However, these models often struggle with fine-grained physical consistency, exhibiting physically implausible d…

Reinforcement Learning

Hard Encoding of Physics for Learning Spatiotemporal Dynamics

2021-05-02 · Chengping Rao, Hao Sun, Yang Liu

Modeling nonlinear spatiotemporal dynamical systems has primarily relied on partial differential equations (PDEs). However, the explicit formulation of PDEs for many underexplored processes, such as climate systems, bioc…

Epidemiology

Physics-Guided Fully Convolutional Spatiotemporal Learning Toward Digital-Twin-Enabled Microstructure Evolution Prediction

2026-06-18 · Michael Trimboli, Wenxi Liu, Xianqi Li arxiv

Understanding and predicting microstructure evolution is central to materials design, yet purely data-driven spatiotemporal learning models often suffer from limited physical consistency and degraded long-term prediction…

Computational Efficiency

Physics-guided spatiotemporal neural models for fuel density prediction

2026-07-08 · Tolga Caglar, Jaynil Jaiswal, Saqib Azim, Yudhir Gala 외 arxiv

This paper presents a physics-guided machine learning (PGML) framework for fuel density prediction, integrating physics constraints and domain knowledge into deep learning models to enhance model accuracy and stability. …

PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation

2025-09-24 · Chen Wang, Chuhao Chen, Yiming Huang, Zhiyang Dou 외 arxiv

Existing video generation models excel at producing photo-realistic videos from text or images, but often lack physical plausibility and 3D controllability. To overcome these limitations, we introduce PhysCtrl, a novel f…

Video Generation