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

TL;DR

QuadLink is a novel framework for generating high-quality, anisotropic quad-dominant meshes from point clouds, supporting hybrid polygonal topologies with improved fidelity.

Contribution

It introduces a unified, link-based mesh generation method with a Tri-to-Quad operator for training data creation, advancing the state of the art in 3D mesh synthesis.

Findings

Produces production-ready quad-dominant meshes from point clouds.

Supports hybrid polygonal topology without architectural changes.

Achieves better geometric fidelity and topological quality than prior methods.

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.