Scaling Mesh Generation via Compressive Tokenization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910694047219712 |
|---|---|
| author | Weng, Haohan Zhao, Zibo Lei, Biwen Yang, Xianghui Liu, Jian Lai, Zeqiang Chen, Zhuo Liu, Yuhong Jiang, Jie Guo, Chunchao Zhang, Tong Gao, Shenghua Chen, C. L. Philip |
| author_facet | Weng, Haohan Zhao, Zibo Lei, Biwen Yang, Xianghui Liu, Jian Lai, Zeqiang Chen, Zhuo Liu, Yuhong Jiang, Jie Guo, Chunchao Zhang, Tong Gao, Shenghua Chen, C. L. Philip |
| contents | We propose a compressive yet effective mesh representation, Blocked and Patchified Tokenization (BPT), facilitating the generation of meshes exceeding 8k faces. BPT compresses mesh sequences by employing block-wise indexing and patch aggregation, reducing their length by approximately 75\% compared to the original sequences. This compression milestone unlocks the potential to utilize mesh data with significantly more faces, thereby enhancing detail richness and improving generation robustness. Empowered with the BPT, we have built a foundation mesh generative model training on scaled mesh data to support flexible control for point clouds and images. Our model demonstrates the capability to generate meshes with intricate details and accurate topology, achieving SoTA performance on mesh generation and reaching the level for direct product usage. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_07025 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Scaling Mesh Generation via Compressive Tokenization Weng, Haohan Zhao, Zibo Lei, Biwen Yang, Xianghui Liu, Jian Lai, Zeqiang Chen, Zhuo Liu, Yuhong Jiang, Jie Guo, Chunchao Zhang, Tong Gao, Shenghua Chen, C. L. Philip Graphics Computer Vision and Pattern Recognition We propose a compressive yet effective mesh representation, Blocked and Patchified Tokenization (BPT), facilitating the generation of meshes exceeding 8k faces. BPT compresses mesh sequences by employing block-wise indexing and patch aggregation, reducing their length by approximately 75\% compared to the original sequences. This compression milestone unlocks the potential to utilize mesh data with significantly more faces, thereby enhancing detail richness and improving generation robustness. Empowered with the BPT, we have built a foundation mesh generative model training on scaled mesh data to support flexible control for point clouds and images. Our model demonstrates the capability to generate meshes with intricate details and accurate topology, achieving SoTA performance on mesh generation and reaching the level for direct product usage. |
| title | Scaling Mesh Generation via Compressive Tokenization |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.07025 |