March 26, 2024, 4:47 a.m. | Chengxuan Li, Di Huang, Zeyu Lu, Yang Xiao, Qingqi Pei, Lei Bai

cs.CV updates on arXiv.org arxiv.org

arXiv:2403.16407v1 Announce Type: new
Abstract: Video generation is a rapidly advancing research area, garnering significant attention due to its broad range of applications. One critical aspect of this field is the generation of long-duration videos, which presents unique challenges and opportunities. This paper presents the first survey of recent advancements in long video generation and summarises them into two key paradigms: divide and conquer temporal autoregressive.
We delve into the common models employed in each paradigm, including aspects of network …

abstract applications arxiv attention challenges cs.cv opportunities paper prospects research survey type video video generation videos

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

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne