What Matters in Detecting AI-Generated Videos like Sora?
- URL: http://arxiv.org/abs/2406.19568v1
- Date: Thu, 27 Jun 2024 23:03:58 GMT
- Title: What Matters in Detecting AI-Generated Videos like Sora?
- Authors: Chirui Chang, Zhengzhe Liu, Xiaoyang Lyu, Xiaojuan Qi,
- Abstract summary: Gap between synthetic and real-world videos remains under-explored.
In this study, we compare real-world videos with those generated by a state-of-the-art AI model, Stable Video Diffusion.
Our model is capable of detecting videos generated by Sora with high accuracy, even without exposure to any Sora videos during training.
- Score: 51.05034165599385
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Recent advancements in diffusion-based video generation have showcased remarkable results, yet the gap between synthetic and real-world videos remains under-explored. In this study, we examine this gap from three fundamental perspectives: appearance, motion, and geometry, comparing real-world videos with those generated by a state-of-the-art AI model, Stable Video Diffusion. To achieve this, we train three classifiers using 3D convolutional networks, each targeting distinct aspects: vision foundation model features for appearance, optical flow for motion, and monocular depth for geometry. Each classifier exhibits strong performance in fake video detection, both qualitatively and quantitatively. This indicates that AI-generated videos are still easily detectable, and a significant gap between real and fake videos persists. Furthermore, utilizing the Grad-CAM, we pinpoint systematic failures of AI-generated videos in appearance, motion, and geometry. Finally, we propose an Ensemble-of-Experts model that integrates appearance, optical flow, and depth information for fake video detection, resulting in enhanced robustness and generalization ability. Our model is capable of detecting videos generated by Sora with high accuracy, even without exposure to any Sora videos during training. This suggests that the gap between real and fake videos can be generalized across various video generative models. Project page: https://justin-crchang.github.io/3DCNNDetection.github.io/
Related papers
- Generating 3D-Consistent Videos from Unposed Internet Photos [68.944029293283]
We train a scalable, 3D-aware video model without any 3D annotations such as camera parameters.
Our results suggest that we can scale up scene-level 3D learning using only 2D data such as videos and multiview internet photos.
arXiv Detail & Related papers (2024-11-20T18:58:31Z) - SVG: 3D Stereoscopic Video Generation via Denoising Frame Matrix [60.48666051245761]
We propose a pose-free and training-free approach for generating 3D stereoscopic videos.
Our method warps a generated monocular video into camera views on stereoscopic baseline using estimated video depth.
We develop a disocclusion boundary re-injection scheme that further improves the quality of video inpainting.
arXiv Detail & Related papers (2024-06-29T08:33:55Z) - Splatter a Video: Video Gaussian Representation for Versatile Processing [48.9887736125712]
Video representation is crucial for various down-stream tasks, such as tracking,depth prediction,segmentation,view synthesis,and editing.
We introduce a novel explicit 3D representation-video Gaussian representation -- that embeds a video into 3D Gaussians.
It has been proven effective in numerous video processing tasks, including tracking, consistent video depth and feature refinement, motion and appearance editing, and stereoscopic video generation.
arXiv Detail & Related papers (2024-06-19T22:20:03Z) - Turns Out I'm Not Real: Towards Robust Detection of AI-Generated Videos [16.34393937800271]
generative models in creating high-quality videos have raised concerns about digital integrity and privacy vulnerabilities.
Recent works to combat Deepfakes videos have developed detectors that are highly accurate at identifying GAN-generated samples.
We propose a novel framework for detecting videos synthesized from multiple state-of-the-art (SOTA) generative models.
arXiv Detail & Related papers (2024-06-13T21:52:49Z) - VideoPhy: Evaluating Physical Commonsense for Video Generation [93.28748850301949]
We present VideoPhy, a benchmark designed to assess whether the generated videos follow physical commonsense for real-world activities.
We then generate videos conditioned on captions from diverse state-of-the-art text-to-video generative models.
Our human evaluation reveals that the existing models severely lack the ability to generate videos adhering to the given text prompts.
arXiv Detail & Related papers (2024-06-05T17:53:55Z) - Distinguish Any Fake Videos: Unleashing the Power of Large-scale Data and Motion Features [21.583246378475856]
We introduce an extensive video dataset designed specifically for AI-Generated Video Detection (GenVidDet)
We also present the Dual-Branch 3D Transformer (DuB3D), an innovative and effective method for distinguishing between real and generated videos.
DuB3D can distinguish between real and generated video content with 96.77% accuracy, and strong generalization capability even for unseen types.
arXiv Detail & Related papers (2024-05-24T08:26:04Z) - Sora Generates Videos with Stunning Geometrical Consistency [75.46675626542837]
We introduce a new benchmark that assesses the quality of the generated videos based on their adherence to real-world physics principles.
We employ a method that transforms the generated videos into 3D models, leveraging the premise that the accuracy of 3D reconstruction is heavily contingent on the video quality.
arXiv Detail & Related papers (2024-02-27T10:49:05Z) - VGMShield: Mitigating Misuse of Video Generative Models [7.963591895964269]
We introduce VGMShield: a set of three straightforward but pioneering mitigations through the lifecycle of fake video generation.
We first try to understand whether there is uniqueness in generated videos and whether we can differentiate them from real videos.
Then, we investigate the textittracing problem, which maps a fake video back to a model that generates it.
arXiv Detail & Related papers (2024-02-20T16:39:23Z) - Detecting Deepfake Videos Using Euler Video Magnification [1.8506048493564673]
Deepfake videos are manipulating videos using advanced machine learning techniques.
In this paper, we examine a technique for possible identification of deepfake videos.
Our approach uses features extracted from the Euler technique to train three models to classify counterfeit and unaltered videos.
arXiv Detail & Related papers (2021-01-27T17:37:23Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.