TADPM：Automatic Tooth Arrangement with Joint Features of Point and Mesh Representations via Diffusion Probabilistic Models

This is the PyTorch implementation of our TADPM.

Requirements

To install python requirements:

pip install -r requirements.txt

To install chamfer distance:

cd chamfer_dist
python setup.py install

To install manifold, please refer to https://github.com/ZhaoHengJiang/MeshReconstruction/tree/main/Manifold

Data pre-process

• To get single tooth mesh files:

bash scripts/get_mesh.sh

• To get pointcloud files:

bash scripts/get_pointcloud.sh

• To get remesh files:

bash scripts/remesh.sh

Pretrain

• To pretrain MeshMAE:

bash scripts/pretrain.sh

You can also refer to https://github.com/liang3588/MeshMAE

Train

• To train the TADPM model:

bash scripts/train.sh

When training TADPM, you should set the path to pretrained MeshMAE model checkpoint.

Test

• To visualize TADPM's results, run:

bash scripts/get_result.sh