├── README.md └── assets ├── fig_teaser.jpg └── fig_vq.png /README.md: -------------------------------------------------------------------------------- 1 |
2 | 3 | # 3D representation in 512-Byte: Variational tokenizer is the key for autoregressive 3D generation 4 | 5 | 6 | 7 | 8 | 9 | ![teaser](assets/fig_vq.png) 10 | ![teaser](assets/fig_teaser.jpg) 11 |
12 | 13 | 14 | ## Citation 15 | 16 | ```bibtex 17 | @misc{zhang20243drepresentation512bytevariationaltokenizer, 18 | title={3D representation in 512-Byte:Variational tokenizer is the key for autoregressive 3D generation}, 19 | author={Jinzhi Zhang and Feng Xiong and Mu Xu}, 20 | year={2024}, 21 | eprint={2412.02202}, 22 | archivePrefix={arXiv}, 23 | primaryClass={cs.CV}, 24 | url={https://arxiv.org/abs/2412.02202}, 25 | } 26 | ``` -------------------------------------------------------------------------------- /assets/fig_teaser.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sparse-mvs-2/VAT/044fc6a72440259b7e9982b8414cde089cd671c6/assets/fig_teaser.jpg -------------------------------------------------------------------------------- /assets/fig_vq.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sparse-mvs-2/VAT/044fc6a72440259b7e9982b8414cde089cd671c6/assets/fig_vq.png --------------------------------------------------------------------------------