April 25, 2024, 7:45 p.m. | Danial Samadi Vahdati, Tai D. Nguyen, Aref Azizpour, Matthew C. Stamm

cs.CV updates on arXiv.org arxiv.org

arXiv:2404.15955v1 Announce Type: new
Abstract: Recent advances in generative AI have led to the development of techniques to generate visually realistic synthetic video. While a number of techniques have been developed to detect AI-generated synthetic images, in this paper we show that synthetic image detectors are unable to detect synthetic videos. We demonstrate that this is because synthetic video generators introduce substantially different traces than those left by image generators. Despite this, we show that synthetic video traces can be …

abstract advances ai-generated videos arxiv beyond cs.cv deepfake deepfake images detectors development generate generated generative image images paper show synthetic type video videos while

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Machine Learning Research Scientist

@ d-Matrix | San Diego, Ca