Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A Unreal Engine 5 (UE5) based plugin aiming to provide real-time visulization, management, editing, and scalable hybrid rendering of Guassian Splatting model.
| Date | Stars |
|---|---|
| 2026-07-24 | 1112 |
| 2026-07-25 | 1112 |
| 2026-07-28 | 1113 |
| 2026-07-30 | 1113 |
| 2026-08-06 | 1113 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# XScene-UEPlugin
<a href="./LICENSE">
<img alt="License" src="https://img.shields.io/badge/License-Apache_2.0-blue.svg"></a>
English | [中文](./README_CN.md)
[
<img src="UEPlugin/Media/image/XVERSE.jpg" width="600" />
](http://xverse.cn/)
---
## Table of Contents
- [Introduction](#introduction)
- [Project Structure](#project-structure)
- [Training Module](#training-module)
- [UE Plugin](#ue-plugin)
- [Getting Started](#getting-started)
- [Roadmap](#roadmap)
- [Contributing](#contributing)
- [Release Note](#release-note)
---
## Introduction
XScene-UEPlugin is an Unreal Engine 5 (UE5) plugin developed by XVERSE Technology Inc. (Shenzhen, China). It provides real-time visualization, management, editing, and scalable hybrid rendering of Gaussian Splatting models—a novel technique for reconstructing 3D scenes from multi-view photos. For more details, see [3D Gaussian Splatting](https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/).
---
## Project Structure
```text
📦 XScene-UEPlugin
├─ 📁 Training
│ ├─ gaussian-splatting/ # Core algorithm and training scripts
│ ├─ README.md # English training guide
│ └─ README_CN.md # 中文训练指南
├─ 📁 UEPlugin
│ ├─ Config/ # Plugin configuration presets
│ ├─ Content/ # Example assets and Niagara emitters
│ ├─ Media/ # Documentation images and videos
│ ├─ Plugin/ # Plugin source code
│ ├─ README.md # English plugin guide
│ └─ README_CN.md # 中文插件指南
├─ LICENSE
└─ README.md # Main overview file
```
---
## Training Module
The `Training` folder contains everything you need to train your own 3D Gaussian Splatting models from videos or image sequences.
**Quick Links:**
- [Training Guide (EN)](./Training/README.md)
- [训练指南 (中文)](./Training/README_CN.md)
### Highlights
- **Data Preparation:** Tools to convert multi-view images or videos into training-ready formats
- **Model Configuration:** Easily tweak `.yaml` config files for custom resolution, point count, and learning rate
- **Training Scripts:** Single-command launch on Windows using `XV3DTools.exe` or Python scripts for advanced users
- **Monitoring:** Integrated TensorBoard support for loss curves, PSNR, and other metrics
---
## UE Plugin
The `UEPlugin` folder contains all UE5 plugin assets, source code, and documentation.
**Quick Links:**
- [Plugin Guide (EN)](./UEPlugin/README.md)
- [插件指南 (中文)](./UEPlugin/README_CN.md)
### Features
- **Real-time Gaussian Splatting rendering using Niagara**
- **Drag-and-drop .gspl assets into UE5 Content Browser**
- **Fully Blueprint-compatible and extendable**
- **Dynamic lighting and LOD generation**
- **Hybrid rendering with native UE assets**
- **Crop regions & pure VFX Niagara emitters**
---
## Getting Started
### 1. Clone the Repository
```bash
git clone https://github.com/xverse-engine/XScene-UEPlugin.git
cd XScene-UEPlugin
```
### 2. Install Dependencies
#### For Training
Ensure you have Python 3.8+, PyTorch, and the required packages:
```bash
pip install -r Training/gaussian-splatting/requirements.txt
```
#### For UE Plugin
Install Unreal Engine 5.0+ and enable the **Niagara Plugin**.
### 3. Build & Run
- **Training:** See `Training/README.md` or `README_CN.md` for training steps
- **UE Plugin:** Copy `UEPlugin/Plugin` to your UE project `Plugins/` directory and enable `XVERSE3DGS` in the Plugin Browser
---
## Roadmap
- [ ] Dynamic LOD Rendering in Editor & Runtime
- [ ] Automatic Collision & Physics Proxy Generation
- [ ] Real-time Preview Window for quick iterations
- [ ] Interactive 3D-GS Asset Editing
- [ ] Compression & Streaming of 3D-GS Assets
Contributions and feature requests are welcome!
---
## Contributing
1. Fork the repository
2. Create a branch (`git checkout -b feature/my-feature`)
3. Commit your changes (`git commit -m "Add feature"`)
4. Push (`git push origin feature/my-feaExcerpt of 6,588 characters
Read on GitHub
Pythonix Huang · The University of Hong Kong · Hong Kong
17
16
2
2
2
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:43b1c787ed8ae823, topic:computer-vision, readme:gaussian splatting