Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2405.20853 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914838810198016 |
|---|---|
| author | Chen, Sijin Chen, Xin Pang, Anqi Zeng, Xianfang Cheng, Wei Fu, Yijun Yin, Fukun Wang, Yanru Wang, Zhibin Zhang, Chi Yu, Jingyi Yu, Gang Fu, Bin Chen, Tao |
| author_facet | Chen, Sijin Chen, Xin Pang, Anqi Zeng, Xianfang Cheng, Wei Fu, Yijun Yin, Fukun Wang, Yanru Wang, Zhibin Zhang, Chi Yu, Jingyi Yu, Gang Fu, Bin Chen, Tao |
| contents | The polygon mesh representation of 3D data exhibits great flexibility, fast rendering speed, and storage efficiency, which is widely preferred in various applications. However, given its unstructured graph representation, the direct generation of high-fidelity 3D meshes is challenging. Fortunately, with a pre-defined ordering strategy, 3D meshes can be represented as sequences, and the generation process can be seamlessly treated as an auto-regressive problem. In this paper, we validate the Neural Coordinate Field (NeurCF), an explicit coordinate representation with implicit neural embeddings, is a simple-yet-effective representation for large-scale sequential mesh modeling. After that, we present MeshXL, a family of generative pre-trained auto-regressive models, which addresses the process of 3D mesh generation with modern large language model approaches. Extensive experiments show that MeshXL is able to generate high-quality 3D meshes, and can also serve as foundation models for various down-stream applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_20853 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MeshXL: Neural Coordinate Field for Generative 3D Foundation Models Chen, Sijin Chen, Xin Pang, Anqi Zeng, Xianfang Cheng, Wei Fu, Yijun Yin, Fukun Wang, Yanru Wang, Zhibin Zhang, Chi Yu, Jingyi Yu, Gang Fu, Bin Chen, Tao Computer Vision and Pattern Recognition The polygon mesh representation of 3D data exhibits great flexibility, fast rendering speed, and storage efficiency, which is widely preferred in various applications. However, given its unstructured graph representation, the direct generation of high-fidelity 3D meshes is challenging. Fortunately, with a pre-defined ordering strategy, 3D meshes can be represented as sequences, and the generation process can be seamlessly treated as an auto-regressive problem. In this paper, we validate the Neural Coordinate Field (NeurCF), an explicit coordinate representation with implicit neural embeddings, is a simple-yet-effective representation for large-scale sequential mesh modeling. After that, we present MeshXL, a family of generative pre-trained auto-regressive models, which addresses the process of 3D mesh generation with modern large language model approaches. Extensive experiments show that MeshXL is able to generate high-quality 3D meshes, and can also serve as foundation models for various down-stream applications. |
| title | MeshXL: Neural Coordinate Field for Generative 3D Foundation Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.20853 |