BiGS Models

The pretrained models for BiGS: Bidirectional Primitives for Relightable 3D Gaussian Splatting (3DV 2025). Please refer to our code release (github) for using the checkpoints. Also check out our project page, dataset, and paper (arxiv).

Citation

If you use our work in your research, please consider citing us with the below bibtex entry:

@misc{zhenyuan2024bigs,
      title={BiGS: Bidirectional Primitives for Relightable 3D Gaussian Splatting}, 
      author={Liu Zhenyuan and Yu Guo and Xinyuan Li and Bernd Bickel and Ran Zhang},
      year={2024},
      eprint={2408.13370},
      url={https://arxiv.org/abs/2408.13370}, 
}

Acknowledgments

Our synthetic data is generated using Mitsuba. We thank the 3D models' creators: Keenan Crane for Spot; Stanford Computer Graphics Laboratory for the models Dragon and Bunny; Wenzel Jakob for the model Mistuba Ball. Special thanks to Changxi Zheng for supporting the internship program at Tencent Pixel Lab.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Dataset used to train desmondlzy/bigs