EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929516296798208 |
|---|---|
| author | Tang, Jiaxiang Li, Zhaoshuo Hao, Zekun Liu, Xian Zeng, Gang Liu, Ming-Yu Zhang, Qinsheng |
| author_facet | Tang, Jiaxiang Li, Zhaoshuo Hao, Zekun Liu, Xian Zeng, Gang Liu, Ming-Yu Zhang, Qinsheng |
| contents | Current auto-regressive mesh generation methods suffer from issues such as incompleteness, insufficient detail, and poor generalization. In this paper, we propose an Auto-regressive Auto-encoder (ArAE) model capable of generating high-quality 3D meshes with up to 4,000 faces at a spatial resolution of $512^3$. We introduce a novel mesh tokenization algorithm that efficiently compresses triangular meshes into 1D token sequences, significantly enhancing training efficiency. Furthermore, our model compresses variable-length triangular meshes into a fixed-length latent space, enabling training latent diffusion models for better generalization. Extensive experiments demonstrate the superior quality, diversity, and generalization capabilities of our model in both point cloud and image-conditioned mesh generation tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_18114 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation Tang, Jiaxiang Li, Zhaoshuo Hao, Zekun Liu, Xian Zeng, Gang Liu, Ming-Yu Zhang, Qinsheng Computer Vision and Pattern Recognition Current auto-regressive mesh generation methods suffer from issues such as incompleteness, insufficient detail, and poor generalization. In this paper, we propose an Auto-regressive Auto-encoder (ArAE) model capable of generating high-quality 3D meshes with up to 4,000 faces at a spatial resolution of $512^3$. We introduce a novel mesh tokenization algorithm that efficiently compresses triangular meshes into 1D token sequences, significantly enhancing training efficiency. Furthermore, our model compresses variable-length triangular meshes into a fixed-length latent space, enabling training latent diffusion models for better generalization. Extensive experiments demonstrate the superior quality, diversity, and generalization capabilities of our model in both point cloud and image-conditioned mesh generation tasks. |
| title | EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.18114 |