viningr / stable-fast-3d

SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement

This is the official codebase for Stable Fast 3D, a state-of-the-art open-source model for fast feedforward 3D mesh reconstruction from a single image.

Stable Fast 3D is based on TripoSR but introduces several new key techniques. For one we explicitly optimize our model to produce good meshes without artifacts alongside textures with UV unwrapping. We also delight the color and predict material parameters so the assets can be easier integrated in a game. We achieve all of this and still keep the fast inference speeds of TripoSR.

Getting Started

Installation

Ensure your environment is:

• Python >= 3.8
• Has CUDA available
• Has PyTorch installed according to your platform: https://pytorch.org/get-started/locally/ [Make sure the Pytorch CUDA version matches your system's one.]
• Update setuptools by pip install -U setuptools==69.5.1

Then install the remaining requirements with pip install -r requirements.txt. For the gradio demo an additional pip install -r requirements-demo.txt is required.

Manual Inference

python run.py demo_files/examples/chair1.png --output-dir output/

This will save the reconstructed 3D model as a GLB file to output/. You can also specify more than one image path separated by spaces. The default options takes about 6GB VRAM for a single image input.

You may also use --texture-resolution to specify the resolution in pixels of the output texture and --remesh_option to specify the remeshing operation (None, Triangle, Quad).

For detailed usage of this script, use python run.py --help.

Local Gradio App

python gradio_app.py

Citation

@article{sf3d2024,
  title={SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement},
  author={Boss, Mark and Huang, Zixuan and Vasishta, Aaryaman and Jampani, Varun},
  journal={arXiv preprint},
  year={2024}
}