QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning

2026-05-16

AI Summary

Existing methods struggle to generate production-ready, anisotropic quad-dominant meshes from point clouds. This work proposes QuadLink, a novel framework that introduces a link-based hybrid polygonal mesh generation paradigm. QuadLink operates through a three-stage pipeline: first predicting vertex and face-center anchors, then learning point-to-point linking relationships conditioned on face centers, and finally assembling high-quality polygonal faces by integrating a quad-prior strategy with geometric validation. The resulting meshes are sparse, edge-coherent, and support arbitrary n-gon topologies. Notably, QuadLink achieves production-level geometric fidelity and topological quality without requiring architectural modifications, significantly outperforming current baselines.

Abstract

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.

Problem

• quad-dominant mesh
• point cloud
• anisotropic meshing
• polygonal topology
• 3D content creation

Innovation

• quad-dominant mesh
• point-relation learning
• centroid-conditioned linking
• anisotropic meshing
• hybrid polygonal topology