{"paper":{"title":"QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"QuadLink generates production-ready quad-dominant meshes from point clouds by learning to link points into structured faces.","cross_cats":["cs.CV"],"primary_cat":"cs.GR","authors_text":"Cheng Lin, Jiepeng Wang, Le Wan, Qiujie Dong, Tianxiao Li, Tingrui Shen, Wenping Wang, Yiheng Zhang, Yuan Liu, Yuwang Wang, Zhe Zhu, Zhiyang Dou, Zhuojiang Cai, Zixing Zhao","submitted_at":"2026-05-16T05:04:10Z","abstract_excerpt":"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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"QuadLink produces production-ready quad-dominant meshes from point clouds and achieves improved geometric fidelity and topological quality compared to prior baselines. This link-based formulation enables efficient generation of sparse and anisotropic quad-dominant meshes with coherent edge flow and meanwhile supporting hybrid polygonal topology.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The Tri-to-Quad Operator converts artistic triangle meshes into quad-dominant training data in a way that does not introduce biases or artifacts that would degrade the learned linking model's performance on real point cloud inputs.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"QuadLink generates anisotropic quad-dominant meshes from point clouds via a hybrid centroid-conditioned vertex linking model and a Tri-to-Quad data conversion operator.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"QuadLink generates production-ready quad-dominant meshes from point clouds by learning to link points into structured faces.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2d891ca9f1458675a4e7538169fb5b73406ad881ad4dbabffc5efd0c2980df11"},"source":{"id":"2605.16813","kind":"arxiv","version":1},"verdict":{"id":"8bb28bef-b368-4ba1-88de-3402c52f93c3","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T19:44:01.456795Z","strongest_claim":"QuadLink produces production-ready quad-dominant meshes from point clouds and achieves improved geometric fidelity and topological quality compared to prior baselines. This link-based formulation enables efficient generation of sparse and anisotropic quad-dominant meshes with coherent edge flow and meanwhile supporting hybrid polygonal topology.","one_line_summary":"QuadLink generates anisotropic quad-dominant meshes from point clouds via a hybrid centroid-conditioned vertex linking model and a Tri-to-Quad data conversion operator.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The Tri-to-Quad Operator converts artistic triangle meshes into quad-dominant training data in a way that does not introduce biases or artifacts that would degrade the learned linking model's performance on real point cloud inputs.","pith_extraction_headline":"QuadLink generates production-ready quad-dominant meshes from point clouds by learning to link points into structured faces."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16813/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T20:01:19.049713Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T19:50:54.723082Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.275882Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.415266Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"eec22f03b56b9b18e0bcc133a9276c83ff945816d7651b42c7fbe4dbcf467224"},"references":{"count":228,"sample":[{"doi":"","year":null,"title":"The Computational Geometry Algorithms Library , author =","work_id":"7dbafdd3-03ff-454a-af12-9ce90c41678c","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Menelaos Karavelas , subtitle =","work_id":"ffa72567-2c45-4826-b827-249fe9c77bee","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"The Computational Geometry Algorithms Library , subtitle =","work_id":"fc5257d9-6631-4927-97b7-de24c02aa093","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"The Parmap library , author =","work_id":"447cebb1-52ef-4f4e-b6a5-94b75fad38f2","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Christopher Anderson and Sophia Drossopoulou , title =","work_id":"fe6bfa48-47c6-4a4f-9d51-b659b347c3bb","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":228,"snapshot_sha256":"268dd2ef579f395154b70bf9414c794048b64b3a212d12a85121b87a3010bb5a","internal_anchors":5},"formal_canon":{"evidence_count":3,"snapshot_sha256":"7f12f42dbcd577cc4797681ece01cf5048e774d3fe045bfe88ba7b76fa620ad9"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}