TY - GEN
T1 - Sekai
T2 - 39th Conference on Neural Information Processing Systems, NeurIPS 2025
AU - Li, Zhen
AU - Li, Chuanhao
AU - Mao, Xiaofeng
AU - Lin, Shaoheng
AU - Li, Ming
AU - Zhao, Shitian
AU - Xu, Zhaopan
AU - Li, Xinyue
AU - Feng, Yukang
AU - Sun, Jianwen
AU - Li, Zizhen
AU - Zhang, Fanrui
AU - Ai, Jiaxin
AU - Wang, Zhixiang
AU - Wu, Yuwei
AU - He, Tong
AU - Pang, Jiangmiao
AU - Qiao, Yu
AU - Jia, Yunde
AU - Zhang, Kaipeng
N1 - Publisher Copyright:
© 2025 Neural information processing systems foundation. All rights reserved.
PY - 2025
Y1 - 2025
N2 - Video generation techniques have made remarkable progress, promising to be the foundation of interactive world exploration. However, existing video generation datasets are not well-suited for world exploration training as they suffer from some limitations: limited locations, short duration, static scenes, and a lack of annotations about exploration and the world. In this paper, we introduce Sekai (meaning “world” in Japanese), a high-quality first-person view worldwide video dataset with rich annotations for world exploration. It consists of over 5,000 hours of walking or drone view (FPV and UVA) videos from over 100 countries and regions across 750 cities. We develop an efficient and effective toolbox to collect, pre-process and annotate videos with location, scene, weather, crowd density, captions, and camera trajectories. Comprehensive analyses and experiments demonstrate the dataset's scale, diversity, annotation quality, and effectiveness for training video generation models. We believe Sekai will benefit the area of video generation and world exploration, and motivate valuable applications.
AB - Video generation techniques have made remarkable progress, promising to be the foundation of interactive world exploration. However, existing video generation datasets are not well-suited for world exploration training as they suffer from some limitations: limited locations, short duration, static scenes, and a lack of annotations about exploration and the world. In this paper, we introduce Sekai (meaning “world” in Japanese), a high-quality first-person view worldwide video dataset with rich annotations for world exploration. It consists of over 5,000 hours of walking or drone view (FPV and UVA) videos from over 100 countries and regions across 750 cities. We develop an efficient and effective toolbox to collect, pre-process and annotate videos with location, scene, weather, crowd density, captions, and camera trajectories. Comprehensive analyses and experiments demonstrate the dataset's scale, diversity, annotation quality, and effectiveness for training video generation models. We believe Sekai will benefit the area of video generation and world exploration, and motivate valuable applications.
UR - https://www.scopus.com/pages/publications/105048514386
M3 - Conference contribution
AN - SCOPUS:105048514386
T3 - Advances in Neural Information Processing Systems
SP - 28217
EP - 28236
BT - 39th Conference on Neural Information Processing Systems, NeurIPS 2025
PB - Neural information processing systems foundation
Y2 - 2 December 2025 through 7 December 2025
ER -