NeuralGS

KO | EN

gitlite — search

#typescript #ai-agents #deepseek-harness #dsh-plugin #open-source #ai #cli #dsh #claude-code #codex #developer-tools #react

★ 184 Open GitHub ↗

[AAAI 2026 🔥] Official implementation of "NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representation"

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

<h2 align="center"> 
  <a href="https://github.com/PKU-YuanGroup/NeuralGS"> NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representation</a>
</h2>
<h5 align="center"> 
If you like our project, please give us a star ⭐ on GitHub for latest update.  </h5>
<h5 align="center">

[![arXiv](https://img.shields.io/badge/Arxiv-2503.23162-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2503.23162)
[![License](https://img.shields.io/badge/License-MIT-yellow)](https://github.com/PKU-YuanGroup/NeuralGS/blob/main/LICENSE) 
[![GitHub repo stars](https://img.shields.io/github/stars/PKU-YuanGroup/NeuralGS?style=flat&logo=github&logoColor=whitesmoke&label=Stars)](https://github.com/PKU-YuanGroup/NeuralGS/stargazers)&#160;
[![GitHub repo forks](https://img.shields.io/github/forks/PKU-YuanGroup/NeuralGS?style=flat&logo=github&logoColor=whitesmoke&label=Forks)](https://github.com/PKU-YuanGroup/NeuralGS/network)&#160;
[![GitHub repo watchers](https://img.shields.io/github/watchers/PKU-YuanGroup/NeuralGS?style=flat&logo=github&logoColor=whitesmoke&label=Watchers)](https://github.com/PKU-YuanGroup/NeuralGS/watchers)&#160;

</h5>Implemetation of Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representation.
<img src="docs/static/img/pipeline.png"/>

## 🗓️ TODO
We will update the following list after the paper is accepted.
- [x] [2025-02-07] We have released our [project page](https://pku-yuangroup.github.io/NeuralGS).
- [x] We have uploaded our paper, NeuralGS on [arXiv](https://arxiv.org/abs/2503.23162).
- [ ] Upload the code

## 🍭 Novel Synthesis Results
### 🌅 Qualitative comparison
<img src="docs/static/img/vis_comprison.png"/>

### 📊 Quantitative comparison

<div class="is-centered">
    <figure style="text-align: center;">
        <figcaption style="text-align: center; margin-top: 0.5rem;"> Table 1. Quantitative results evaluated on <em>Mip-NeRF 360, Tanks&Temples, and Deep Blending</em> datasets. We highlight the best-performing results in <strong>bold</strong> and the second-best results in <u>underline</u> for all compression methods. </figcaption>
        <img src="docs/static/img/tables/table1.png" alt="Compression Pipeline" style="display: inline-block;">
    </figure>
</div>
<div class="is-centered">
    <figure style="text-align: center;">
        <figcaption style="text-align: center; margin-top: 0.5rem;"> Table 2. Comparison of the rendering speed(FPS↑). The rendering speed of all methods is measured on our machine. </figcaption>
        <img src="docs/static/img/tables/table2.png" alt="Compression Pipelin 2" style=""width: 60%; max-width: 600px; height: auto;">
    </figure>
</div>

## 🙏 Acknowledgements

This source code is derived from multiple sources, in particular: 
[gaussian-splatting](https://github.com/graphdeco-inria/gaussian-splatting/tree/main). We thank the authors for releasing their code.

```bibtex

To be contunied...

```

## 🤝 Contributors

NeuralGS

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README