metadata
license: apache-2.0
datasets:
- SpatialVID/SpatialVID
base_model:
- Wan-AI/Wan2.1-T2V-14B
- lightx2v/Wan2.1-T2V-14B-StepDistill-CfgDistill-Lightx2v
pipeline_tag: video-to-video
tags:
- video generation
- 4D World Model
- novel view synthesis
NeoVerse : Enhancing 4D World Model with in-the-wild Monocular Videos
📑 arXiv | 🌐 Project | 🖥️ GitHub | 🤗 Hugging Face | 🤖 ModelScope | 🎞️ BiliBili | 🎥 YouTube
NeoVerse is a versatile 4D world model that is capable of 4D reconstruction, novel-trajectory video generation, and rich downstream applications.
Please refer to the GitHub repository for detailed instructions on how to use the model.
If you find this work helpful, please help star the repository and consider citing it as follows. It would be greatly appreciated!
@article{yang2026neoverse,
author = {Yang, Yuxue and Fan, Lue and Shi, Ziqi and Peng, Junran and Wang, Feng and Zhang, Zhaoxiang},
title = {NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos},
journal = {arXiv preprint arXiv:2601.00393},
year = {2026},
}