---
license: mit
datasets:
- nikoloside/break4models
pipeline_tag: other
tags:
- fracture
- vq-vae
- physical-simulation
---
# DeepFracture: A Generative Approach for Predicting Brittle Fractures with Neural Discrete Representation Learning

This is a collection of pre-trained models for deepfracture: a conditional vq-vae model for predicting fracture pattern from impulse code, trained on the [Break4Models](https://huggingface.co/datasets/nikoloside/break4models) dataset created by [FractureRB](https://github.com/david-hahn/FractureRB).


📖 **For more details, please visit:**
- [GitHub Repository](https://github.com/nikoloside/TEBP)
- [Project Page](https://nikoloside.graphics/deepfracture/)

## Overview

These models are designed to predict fracture patterns based on impact conditions. Each model is trained on a specific target shape and can be used for real-time physics simulation and computer graphics applications.

## Model Architecture

The models use an encoder-decoder architecture:
- **Encoder**: Processes input impulse conditions and generates latent representations
- **Decoder**: Reconstructs GS-SDF(Geometrically-Segmented Signed Distance Fields) from latent representations
- **Training**: Supervised learning on physics simulation data

## Available Models

```
pre-trained-v2/
├── base/           # Base object model
├── pot/            # Pot object model
├── squirrel/       # Squirrel object model
├── bunny/          # Bunny object model
├── lion/           # Lion object model
├── objs/           # Different original mesh files
├── csv/            # Initial collision scene
└── README.md       # This file
```

Each model directory contains:
- `{shape}-encoder.pt` - Encoder weights
- `{shape}-decoder.pt` - Decoder weights
- `{shape}-1000-encoder.pt` - Encoder weights (1000 epoch version)
- `{shape}-1000-decoder.pt` - Decoder weights (1000 epoch version)

Other folders:
- `{shape}.obj` - Reference original 3D mesh file
- `{shape}-{csv_num}.obj` - Reference initial collision scene. Containing pos, direct, impulse strength.

## Usage

### Loading Models

```python
import torch
from your_model_architecture import Encoder, Decoder

# Load encoder
encoder = Encoder()
encoder.load_state_dict(torch.load('base/base-encoder.pt'))
encoder.eval()

# Load decoder  
decoder = Decoder()
decoder.load_state_dict(torch.load('base/base-decoder.pt'))
decoder.eval()

# Load reference mesh
reference_mesh = 'objs/base.obj'
init_collision = 'csv/base-261.txt'
work_path = 'result/base-exp-1/
```

### Inference

- [Example](https://github.com/nikoloside/TEBP/blob/main/04.Run-time/predict-runtime.py)

- [Details](https://github.com/nikoloside/TEBP/blob/main/04.Run-time/MorphoImageJ.py#L34)

```python
# Prepare input conditions
input_conditions = prepare_impact_conditions(impact_point, velocity, impulse_strength)

# Encode
with torch.no_grad():
    latent = encoder(input_conditions)
    
# Decode
latent = decoder.cook(latent)
gssdf_voxel = deocoder.predict(latent)

# Apply to reference mesh
result_mesh = processCagedSDFSeg(gssdf_voxel, work_path, reference_mesh, isBig = False, maxValue = 1.0)
```

## Model Performance

(metrics and performance)[https://doi.org/10.1111/cgf.70002]


## Training Details

- **Dataset**: Break4Model dataset
- **Framework**: PyTorch
- **Optimizer**: Adam
- **Loss Function**: L2 Loss
- **Training Time**: ~24 hours per model on NVIDIA RTX 3090

## Citation

If you use these models in your research, please cite:

```bibtex
@article{huang2025deepfracture,
author = {Huang, Yuhang and Kanai, Takashi},
title = {DeepFracture: A Generative Approach for Predicting Brittle Fractures with Neural Discrete Representation Learning},
journal = {Computer Graphics Forum},
pages = {e70002},
year = {2025},
keywords = {animation, brittle fracture, neural networks, physically based animation},
doi = {https://doi.org/10.1111/cgf.70002},
url = {https://onlinelibrary.wiley.com/doi/abs/10.1111/cgf.70002},
eprint = {https://onlinelibrary.wiley.com/doi/pdf/10.1111/cgf.70002}
}
```

## License

MIT

## Contact

For questions or issues, please open an issue on the Hugging Face model page.