QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917503010078720 |
|---|---|
| author | Zhang, Yiheng Zhu, Zhe Shen, Tingrui Cai, Zhuojiang Li, Tianxiao Zhao, Zixing Dong, Qiujie Dou, Zhiyang Wang, Jiepeng Wan, Le Wang, Yuwang Wang, Wenping Liu, Yuan Lin, Cheng |
| author_facet | Zhang, Yiheng Zhu, Zhe Shen, Tingrui Cai, Zhuojiang Li, Tianxiao Zhao, Zixing Dong, Qiujie Dou, Zhiyang Wang, Jiepeng Wan, Le Wang, Yuwang Wang, Wenping Liu, Yuan Lin, Cheng |
| contents | The generation of production-ready quad-dominant meshes is a cornerstone of modern 3D content creation. Generating anisotropic quad-dominant meshes from point clouds is challenging, as existing methods are typically limited to producing either pure triangular meshes or pure quadrilateral meshes with isotropic densities. In this paper, we present QuadLink, a unified framework consisting of three stages for quad-dominant mesh generation by linking points into structured faces. QuadLink formulates polygonal mesh generation as a hybrid centroid-conditioned vertex linking model: it first predicts a unified set of anchors (vertices and face centroids), then learns centroid-conditioned links that associate vertices with face centroids, and finally assembles polygonal faces with a quad-first strategy guided by robust geometric verification strategies. This link-based formulation enables efficient generation of sparse and anisotropic quad-dominant meshes with coherent edge flow and meanwhile supporting hybrid polygonal topology. To construct training data for this model, we further introduce a Tri-to-Quad Operator that converts artistic triangle meshes into quad-dominant training data via global merge selection. Extensive experiments show that QuadLink produces production-ready quad-dominant meshes from point clouds and achieves improved geometric fidelity and topological quality compared to prior baselines. Our method natively supports hybrid polygonal topology, generalizing to arbitrary n-gon meshes without architectural changes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_16813 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning Zhang, Yiheng Zhu, Zhe Shen, Tingrui Cai, Zhuojiang Li, Tianxiao Zhao, Zixing Dong, Qiujie Dou, Zhiyang Wang, Jiepeng Wan, Le Wang, Yuwang Wang, Wenping Liu, Yuan Lin, Cheng Graphics Computer Vision and Pattern Recognition The generation of production-ready quad-dominant meshes is a cornerstone of modern 3D content creation. Generating anisotropic quad-dominant meshes from point clouds is challenging, as existing methods are typically limited to producing either pure triangular meshes or pure quadrilateral meshes with isotropic densities. In this paper, we present QuadLink, a unified framework consisting of three stages for quad-dominant mesh generation by linking points into structured faces. QuadLink formulates polygonal mesh generation as a hybrid centroid-conditioned vertex linking model: it first predicts a unified set of anchors (vertices and face centroids), then learns centroid-conditioned links that associate vertices with face centroids, and finally assembles polygonal faces with a quad-first strategy guided by robust geometric verification strategies. This link-based formulation enables efficient generation of sparse and anisotropic quad-dominant meshes with coherent edge flow and meanwhile supporting hybrid polygonal topology. To construct training data for this model, we further introduce a Tri-to-Quad Operator that converts artistic triangle meshes into quad-dominant training data via global merge selection. Extensive experiments show that QuadLink produces production-ready quad-dominant meshes from point clouds and achieves improved geometric fidelity and topological quality compared to prior baselines. Our method natively supports hybrid polygonal topology, generalizing to arbitrary n-gon meshes without architectural changes. |
| title | QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.16813 |