https://github.com/tencentarc/freesplatter
FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction
https://github.com/tencentarc/freesplatter
Last synced: about 1 year ago
JSON representation
FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction
- Host: GitHub
- URL: https://github.com/tencentarc/freesplatter
- Owner: TencentARC
- Created: 2024-12-12T01:43:41.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-12-17T03:19:07.000Z (over 1 year ago)
- Last Synced: 2024-12-17T04:24:31.866Z (over 1 year ago)
- Size: 455 KB
- Stars: 49
- Watchers: 9
- Forks: 1
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction
---
This repo is the official implementation of FreeSplatter, a feed-forward framework capable of generating high-quality 3D Gaussians from uncalibrated sparse-view images and recovering their camera parameters in mere seconds.
https://github.com/user-attachments/assets/0c73b693-9428-46bd-843c-132434b9686f
# ⚙️ Installation
We recommend using `Python>=3.10`, `PyTorch>=2.1.0`, and `CUDA>=12.1`.
```bash
conda create --name freesplatter python=3.10
conda activate freesplatter
pip install -U pip
# Install PyTorch and xformers
# You may need to install another xformers version if you use a different PyTorch version
pip install torch==2.4.0 torchvision==0.19.0 --index-url https://download.pytorch.org/whl/cu121
pip install xformers==0.0.27.post2
# Install other requirements
pip install -r requirements.txt
```
# 🤖 Pretrained Models
We provide the following pretrained models:
| Model | Description | #Params | Download |
| --- | --- | --- | --- |
| FreeSplatter-O | Object-level reconstruction model | 306M | [Download](https://huggingface.co/TencentARC/FreeSplatter/blob/main/freesplatter-object.safetensors) |
| FreeSplatter-O-2dgs | Object-level reconstruction model using [2DGS](https://surfsplatting.github.io/) (finetuned from FreeSplatter-O) | 306M | [Download](https://huggingface.co/TencentARC/FreeSplatter/blob/main/freesplatter-object-2dgs.safetensors) |
| FreeSplatter-S | Scene-level reconstruction model | 306M | [Download](https://huggingface.co/TencentARC/FreeSplatter/blob/main/freesplatter-scene.safetensors) |
# 💫 Inference
We recommand to start a gradio demo in your local machine, simply run:
```bash
python app.py
```
# ⚖️ License
FreeSplatter's code and models are licensed under the [Apache 2.0 License](LICENSE.txt) with additional restrictions to comply with Tencent's open-source policies. Besides, the libraries [Hunyuan3D-1](https://github.com/Tencent/Hunyuan3D-1) and [BRIAAI RMBG-2.0](https://huggingface.co/briaai/RMBG-2.0) have their own non-commercial licenses.
# :books: Citation
If you find our work useful for your research or applications, please cite using this BibTeX:
```BibTeX
@article{xu2024freesplatter,
title={FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction},
author={Xu, Jiale and Gao, Shenghua and Shan, Ying},
journal={arXiv preprint arXiv:2412.09573},
year={2024}
}
```