PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

Yuchen Lin^*, Chenguo Lin^*, Panwang Pan^†, Honglei Yan, Yiqiang Feng, Yadong Mu, Katerina Fragkiadaki

Code and checkpoints will be released before July 15th!

This repository will contain the official implementation of the paper: PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers. PartCrafter is a structured 3D generative model that jointly generates multiple parts and objects from a single RGB image in one shot. Here is our Project Page.

Feel free to contact me (linyuchen@stu.pku.edu.cn) or open an issue if you have any questions or suggestions.

📢 News

• 2025-06-09: PartCrafter is on arXiv.

📋 TODO

• Release inference scripts and pretrained checkpoints before July 15th. Stay tuned!
• Release training code and data.
• Provide a HuggingFace🤗 demo.

😊 Acknowledgement

We would like to thank the authors of DiffSplat, TripoSG, HoloPart, and MIDI-3D for their great work and generously providing source codes, which inspired our work and helped us a lot in the implementation.

📚 Citation

If you find our work helpful, please consider citing:

@misc{lin2025partcrafter,
  title={PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers}, 
  author={Yuchen Lin and Chenguo Lin and Panwang Pan and Honglei Yan and Yiqiang Feng and Yadong Mu and Katerina Fragkiadaki},
  year={2025},
  eprint={2506.05573},
  url={https://arxiv.org/abs/2506.05573}
}