CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner
By mimicking the artist/craftsman modeling workflow, we propose CraftsMan (aka 匠心) that uses 3D Latent Set Diffusion Model that directly generate coarse meshes, then a multi-view normal enhanced image generation model is used to refine the mesh. We provide the coarse 3D diffusion part here.
If you found CraftsMan is helpful, please help to ⭐ the Github Repo. Thanks!
*If you have your own multi-view images, you can directly upload it.
Try a different seed and MV Model for better results. Good Luck :)
📝 Citation If you find our work useful for your research or applications, please cite using this bibtex:
@article{li2024craftsman,
author = {Weiyu Li and Jiarui Liu and Hongyu Yan and Rui Chen and Yixun Liang and Xuelin Chen and Ping Tan and Xiaoxiao Long},
title = {CraftsMan: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner},
journal = {arXiv preprint arXiv:2405.14979},
year = {2024},
}
🤗 Acknowledgements We use Instant Meshes to remesh the generated mesh to a lower face count, thanks to the authors for the great work. 📋 License CraftsMan is under AGPL-3.0, so any downstream solution and products (including cloud services) that include CraftsMan code or a trained model (both pretrained or custom trained) inside it should be open-sourced to comply with the AGPL conditions. If you have any questions about the usage of CraftsMan, please contact us first. 📧 Contact If you have any questions, feel free to open a discussion or contact us at weiyuli.cn@gmail.com.