MeshMosaic: Scaling Artist Mesh Generation via Local-to-Global Assembly
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909901524041728 |
|---|---|
| author | Xu, Rui Xue, Tianyang Dong, Qiujie Wan, Le Zhu, Zhe Li, Peng Dou, Zhiyang Lin, Cheng Xin, Shiqing Liu, Yuan Wang, Wenping Komura, Taku |
| author_facet | Xu, Rui Xue, Tianyang Dong, Qiujie Wan, Le Zhu, Zhe Li, Peng Dou, Zhiyang Lin, Cheng Xin, Shiqing Liu, Yuan Wang, Wenping Komura, Taku |
| contents | Scaling artist-designed meshes to high triangle numbers remains challenging for autoregressive generative models. Existing transformer-based methods suffer from long-sequence bottlenecks and limited quantization resolution, primarily due to the large number of tokens required and constrained quantization granularity. These issues prevent faithful reproduction of fine geometric details and structured density patterns. We introduce MeshMosaic, a novel local-to-global framework for artist mesh generation that scales to over 100K triangles--substantially surpassing prior methods, which typically handle only around 8K faces. MeshMosaic first segments shapes into patches, generating each patch autoregressively and leveraging shared boundary conditions to promote coherence, symmetry, and seamless connectivity between neighboring regions. This strategy enhances scalability to high-resolution meshes by quantizing patches individually, resulting in more symmetrical and organized mesh density and structure. Extensive experiments across multiple public datasets demonstrate that MeshMosaic significantly outperforms state-of-the-art methods in both geometric fidelity and user preference, supporting superior detail representation and practical mesh generation for real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_19995 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MeshMosaic: Scaling Artist Mesh Generation via Local-to-Global Assembly Xu, Rui Xue, Tianyang Dong, Qiujie Wan, Le Zhu, Zhe Li, Peng Dou, Zhiyang Lin, Cheng Xin, Shiqing Liu, Yuan Wang, Wenping Komura, Taku Graphics Computational Geometry Computer Vision and Pattern Recognition Scaling artist-designed meshes to high triangle numbers remains challenging for autoregressive generative models. Existing transformer-based methods suffer from long-sequence bottlenecks and limited quantization resolution, primarily due to the large number of tokens required and constrained quantization granularity. These issues prevent faithful reproduction of fine geometric details and structured density patterns. We introduce MeshMosaic, a novel local-to-global framework for artist mesh generation that scales to over 100K triangles--substantially surpassing prior methods, which typically handle only around 8K faces. MeshMosaic first segments shapes into patches, generating each patch autoregressively and leveraging shared boundary conditions to promote coherence, symmetry, and seamless connectivity between neighboring regions. This strategy enhances scalability to high-resolution meshes by quantizing patches individually, resulting in more symmetrical and organized mesh density and structure. Extensive experiments across multiple public datasets demonstrate that MeshMosaic significantly outperforms state-of-the-art methods in both geometric fidelity and user preference, supporting superior detail representation and practical mesh generation for real-world applications. |
| title | MeshMosaic: Scaling Artist Mesh Generation via Local-to-Global Assembly |
| topic | Graphics Computational Geometry Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.19995 |