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

• URL: http://arxiv.org/abs/2605.16813v1
• Date: Sat, 16 May 2026 05:04:10 GMT
• Title: QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning
• Abstract summary: The generation of production-ready quad-dominant meshes is a cornerstone of modern 3D content creation.<n>Existing methods are typically limited to producing either pure triangular meshes or pure quadrilateral meshes with isotropic densities.<n>We present QuadLink, a unified framework consisting of three stages for quad-dominant mesh generation by linking points into structured faces.
• Score: 46.16011060110813
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields [72.76537377865192]
  TriFlow is a new generative approach for producing compact 3D meshes with artist-like triangle topology directly from input geometry conditions such as signed distance fields.<n>Experiments demonstrate that TriFlow achieves stronger generalization and significantly improved topology quality compared to state-of-the-art learning-based approaches.
  arXiv  Detail & Related papers  (2026-06-18T11:55:00Z)
• MeshWeaver: Sparse-Voxel-Guided Surface Weaving for Autoregressive Mesh Generation [53.06620176910962]
  MeshWeaver is an autoregressive framework that treats mesh generation as a surface weaving process.<n>MeshWeaver achieves a state-of-the-art compression ratio of 18%, can generate meshes with up to 16K faces, and significantly improves geometric fidelity over prior approaches.
  arXiv  Detail & Related papers  (2026-06-03T10:15:43Z)
• SQuadGen: Generating Simple Quad Layouts via Chart Distance Fields [19.100132639513454]
  3D shapes from scanning, reconstruction, or AI-generated content often lack simple quad mesh layouts.<n>Existing quad-remeshing techniques produce complex layouts with irregular loops, leading to tedious manual cleanup.<n>We introduce SQuadGen, a diffusion-based generative framework that leverages Chart Distance Fields (CDF) to synthesize simple quad layouts on 3D shapes.
  arXiv  Detail & Related papers  (2026-04-30T02:15:50Z)
• QuadGPT: Native Quadrilateral Mesh Generation with Autoregressive Models [34.888585681291794]
  We introduce QuadGPT, the first autoregressive framework for generating quadrilateral meshes in an end-to-end manner.<n>Our work establishes a new benchmark for native quad-mesh generation and showcases the power of combining large-scale autoregressive models with topology-aware RL refinement.
  arXiv  Detail & Related papers  (2025-09-25T07:58:36Z)
• TetWeave: Isosurface Extraction using On-The-Fly Delaunay Tetrahedral Grids for Gradient-Based Mesh Optimization [59.318328774645835]
  We introduce TetWeave, a novel isosurface representation for gradient-based mesh optimization.<n>TetWeave constructs tetrahedral grids on-the-fly via Delaunay triangulation.<n>We demonstrate the applicability of TetWeave to a broad range of challenging tasks in computer graphics and vision.
  arXiv  Detail & Related papers  (2025-05-07T17:32:49Z)
• Point2Quad: Generating Quad Meshes from Point Clouds via Face Prediction [8.692983641469612]
  We present Point2Quad, the first learning-based method for quad-only mesh generation from point clouds.<n>The key idea is learning to identify quad mesh with fused pointwise and facewise features.<n>Experiments on both clear and noise data demonstrate the effectiveness and superiority of Point2Quad.
  arXiv  Detail & Related papers  (2025-04-28T07:48:17Z)
• CLR-Wire: Towards Continuous Latent Representations for 3D Curve Wireframe Generation [11.447223770747051]
  CLR ContinuousWire encodes curves as Parametric Curves along with their Parametric Curves into a continuous and fixed latent space.<n>This unified approach generates both geometry and topology.
  arXiv  Detail & Related papers  (2025-04-27T09:32:42Z)
• SpaceMesh: A Continuous Representation for Learning Manifold Surface Meshes [61.110517195874074]
  We present a scheme to directly generate manifold, polygonal meshes of complex connectivity as the output of a neural network.<n>Our key innovation is to define a continuous latent connectivity space at each mesh, which implies the discrete mesh.<n>In applications, this approach not only yields high-quality outputs from generative models, but also enables directly learning challenging geometry processing tasks such as mesh repair.
  arXiv  Detail & Related papers  (2024-09-30T17:59:03Z)
• PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsampling [103.09504572409449]
  We propose a novel deep neural network based method, called PUGeo-Net, to generate uniform dense point clouds. Thanks to its geometry-centric nature, PUGeo-Net works well for both CAD models with sharp features and scanned models with rich geometric details.
  arXiv  Detail & Related papers  (2020-02-24T14:13:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.