| pipeline_tag: image-to-3d # Specify the task | |
| library_name: fastgs # Specify the library | |
| language: | |
| - en # List languages your model supports | |
| license: mit | |
| base_model: fastgs/base | |
| big_model: fastgs/Big | |
| tags: # Add extra tags which would make the repo searchable using the tag | |
| - trianing acceleration | |
| - 3DGS | |
| - 3D Gaussian splatting | |
| - Novel view synthesis | |
| <div align="center"> | |
| <h1>FastGS: Training 3D Gaussian Splatting in 100 Seconds</h1> | |
| [🌐 Homepage](https://fastgs.github.io/) | [📄 Paper](https://arxiv.org/abs/2511.04283) | [🖥️ GitHub](https://github.com/fastgs/FastGS) | |
| </div> | |
| <p align="center"> | |
| <img src="assets/teaser_fastgs.jpg" width="800px"/> | |
| </p> | |
| ## 🚀 What Makes FastGS Special? | |
| FastGS is a **general acceleration framework** that supercharges 3D Gaussian Splatting training while maintaining Comparable rendering quality. Our method stands out with: | |
| - **⚡ Blazing Fast Training**: Achieve SOTA results within **100 seconds**. **3.32× faster** than DashGaussian on Mip-NeRF 360 dataset. **15.45× acceleration** vs vanilla 3DGS on Deep Blending. | |
| - **⚡ High fidelity**: Comparable rendering quality with SOTA methods | |
| - **🎯 Easy Integration**: Seamlessly integrates with various backbones (Vanilla 3DGS, Scaffold-GS, Mip-splatting, etc.) | |
| - **🛠️ Multi-Task Ready**: Proven effective across dynamic scenes, surface reconstruction, sparse-view, large-scale, and SLAM tasks | |
| - **💡 Memory-Efficient**: Low GPU Memory requirements make it accessible for various hardware setups | |
| - **🔧 Easy Deployment**: Simple post-training tool for feedforward 3DGS that works out-of-the-box | |