VertexRegen: Mesh Generation with Continuous Level of Detail
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918123936940032 |
|---|---|
| author | Zhang, Xiang Siddiqui, Yawar Avetisyan, Armen Xie, Chris Engel, Jakob Howard-Jenkins, Henry |
| author_facet | Zhang, Xiang Siddiqui, Yawar Avetisyan, Armen Xie, Chris Engel, Jakob Howard-Jenkins, Henry |
| contents | We introduce VertexRegen, a novel mesh generation framework that enables generation at a continuous level of detail. Existing autoregressive methods generate meshes in a partial-to-complete manner and thus intermediate steps of generation represent incomplete structures. VertexRegen takes inspiration from progressive meshes and reformulates the process as the reversal of edge collapse, i.e. vertex split, learned through a generative model. Experimental results demonstrate that VertexRegen produces meshes of comparable quality to state-of-the-art methods while uniquely offering anytime generation with the flexibility to halt at any step to yield valid meshes with varying levels of detail. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_09062 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VertexRegen: Mesh Generation with Continuous Level of Detail Zhang, Xiang Siddiqui, Yawar Avetisyan, Armen Xie, Chris Engel, Jakob Howard-Jenkins, Henry Graphics Computer Vision and Pattern Recognition Machine Learning We introduce VertexRegen, a novel mesh generation framework that enables generation at a continuous level of detail. Existing autoregressive methods generate meshes in a partial-to-complete manner and thus intermediate steps of generation represent incomplete structures. VertexRegen takes inspiration from progressive meshes and reformulates the process as the reversal of edge collapse, i.e. vertex split, learned through a generative model. Experimental results demonstrate that VertexRegen produces meshes of comparable quality to state-of-the-art methods while uniquely offering anytime generation with the flexibility to halt at any step to yield valid meshes with varying levels of detail. |
| title | VertexRegen: Mesh Generation with Continuous Level of Detail |
| topic | Graphics Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2508.09062 |