README.md

---
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
---

<div style="text-align: center;">
<h1>
    <strong style="background: linear-gradient(to right, #3b82f6, #8b5cf6); -webkit-background-clip: text; -webkit-text-fill-color: transparent; background-clip: text;">NeoVerse</strong>
    <span>: Enhancing 4D World Model with in-the-wild Monocular Videos</span>
</h1>
<p>
    📑 <a href="https://arxiv.org/abs/2601.00393">arXiv</a> &nbsp&nbsp | &nbsp&nbsp 🌐 <a href="https://neoverse-4d.github.io">Project</a> &nbsp&nbsp  | &nbsp&nbsp🖥️ <a href="https://github.com/IamCreateAI/NeoVerse">GitHub</a> &nbsp&nbsp  | &nbsp&nbsp🤗 <a href="https://huggingface.co/Yuppie1204/NeoVerse">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href="https://www.modelscope.cn/models/Yuppie1204/NeoVerse">ModelScope</a>&nbsp&nbsp | &nbsp&nbsp 🎞️ <a href="https://www.bilibili.com/video/BV1ezvYBBEMi">BiliBili</a> &nbsp&nbsp | &nbsp&nbsp 🎥 <a href="https://youtu.be/1k8Ikf8zbZw">YouTube</a> &nbsp&nbsp
</p>
</div>

**NeoVerse** is a versatile 4D world model that is capable of 4D reconstruction, novel-trajectory video generation, and rich downstream applications.

<div align="center">
    <video width="80%" controls>
        <source src="https://neoverse-4d.github.io/resources/NeoVerse_public.mp4" type="video/mp4">
        Your browser does not support the video tag.
    </video>
</div>

Please refer to the [GitHub repository](https://github.com/IamCreateAI/NeoVerse) for detailed instructions on how to use the model.

If you find this work helpful, please help star the [repository](https://github.com/IamCreateAI/NeoVerse) and consider citing it as follows. It would be greatly appreciated!

```bib
@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},
}
```