In this project, we introduce Can3Tok, the first 3D scene-level variational autoencoder (VAE) capable of encoding a large number of Gaussian primitives into a low-dimensional latent embedding, which enables high-quality and efficient generative modeling of complex 3D scenes.

Acknowledgement

We would like to thank the authors of the following repositories for their open-source code and datasets, which we built upon in this work:

• 3D Gaussian Splatting
• Lang-Segment-Anything
• Michelangelo
• DL3DV-10K Dataset

Citation

If you find our code or paper useful, please consider citing:

@INPROCEEDINGS{gao2023ICCV,
  author = {Quankai Gao and Iliyan Georgiev and Tuanfeng Y. Wang and Krishna Kumar Singh and Ulrich Neumann and Jae Shin Yoon},
  title = {Can3Tok: Canonical 3D Tokenization and Latent Modeling of Scene-Level 3D Gaussians},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  year = {2025}
}