SubdivAR: Autoregressive Next-Scale Prediction for Neural Mesh Subdivision

• URL: http://arxiv.org/abs/2606.27088v1
• Date: Thu, 25 Jun 2026 14:24:03 GMT
• Title: SubdivAR: Autoregressive Next-Scale Prediction for Neural Mesh Subdivision
• Abstract summary: Mesh subdivision is a fundamental operation for converting coarse, editable meshes into high-resolution surfaces.<n>We present SubdivAR, a neural mesh subdivision framework based on our proposed Mesh Autoregressive Representation (MAR)<n>MAR arranges meshes at different subdivision levels into an ordered scale sequence, reformulating subdivision as autoregressive next-scale prediction.
• Score: 10.62097148325093
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Mesh subdivision is a fundamental operation for converting coarse, editable meshes into high-resolution surfaces, with broad applications in digital asset creation. Classical rule-based schemes rely on fixed local refinement rules and often produce over-smoothed surfaces. Recent neural subdivision methods improve detail synthesis, but remain constrained by local modeling and exhibit limited generalizability. We present SubdivAR, a neural mesh subdivision framework based on our proposed Mesh Autoregressive Representation (MAR). MAR arranges meshes at different subdivision levels into an ordered scale sequence, reformulating subdivision as autoregressive next-scale prediction. To support this formulation, we introduce a Hybrid Topology-Aware Transformer that combines global semantic attention with topology-constrained local feature aggregation. SubdivAR adopts a next-scale coordinate prediction paradigm, regressing vertex offsets at each refinement stage to preserve subdivision topology while recovering fine-grained geometric details. To enable reliable learning, we construct FII-40K, a curated dataset of nearly 40,000 high-quality meshes with multi-level subdivision supervision. Experiments show that SubdivAR outperforms state-of-the-art baselines, reducing Hausdorff Distance and Chamfer Distance by 18.8% and 14.2%, respectively, and demonstrates strong robustness on complex open-surface geometries.

Related papers

• Multi-Submap Implicit Neural SLAM with Local-to-Global Loop Closure for Large-Scale Scene Reconstruction [38.870967480699186]
  We present a large-scale neural SLAM system featuring a multi-submap architecture and a dual-tier loop closure mechanism.<n>For robust pose estimation, an optical-flow-based tracking module is integrated to handle aggressive motions.<n>Our approach outperforms state-of-the-art neural SLAM methods in reconstruction quality and localization robustness.
  arXiv  Detail & Related papers  (2026-08-10T05:49:55Z)
• ARDepth: Auto-regressive Monocular Depth Estimation with Progressive Visual Conditioning [66.42476564611607]
  Diffusion models assume that depth can be recovered as a globally smooth field through iterative denoising.<n>We introduce ARDepth, which formulates depth estimation as structured auto-regressive generation.<n>We show that our approach achieves strong performance and produces structurally consistent depth predictions across scales.
  arXiv  Detail & Related papers  (2026-07-14T07:06:46Z)
• Dmsh: A Multi-Agent Reinforcement Learning Framework for All-Quad Mesh Generation [0.30786914102688595]
  We introduce Dmsh, a first fully automated reinforcement learning pipeline that unifies geometric decomposition and quadrilateral mesh generation.<n>Dmsh decomposes the problem through three coordinated agents handling topology simplification, geometric regularization, and mesh generation.<n>A learning strategy ensures scalability from simple domains to highly complex geometries, suppressing seed variance.
  arXiv  Detail & Related papers  (2026-06-09T09:04:32Z)
• 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)
• Topologically Consistent Multi-view 3D Head Reconstruction via Coarse-Guided Layered Surface Sampling [15.24889101682807]
  SHELLS is an efficient feed-forward framework for 3D head reconstruction in dense semantic correspondence from multi-view images.<n>It reduces median registration error by 21% to 29% with a 3.5x inference speedup.<n>Our model is trained exclusively on synthetic data yet generalizes effectively to real-world captures.
  arXiv  Detail & Related papers  (2026-05-29T13:14:43Z)
• TopoMesh: High-Fidelity Mesh Autoencoding via Topological Unification [44.632513151214084]
  TopoMesh is a sparse voxel-based VAE that unifies both GT and predicted meshes under a shared Dual Marching Cubes (DMC) topological framework.<n>Our decoder outputs meshes in the same DMC format, ensuring that both predicted and target meshes share identical topological structures.<n>Extensive experiments demonstrate that TopoMesh significantly outperforms existing VAEs in reconstruction fidelity.
  arXiv  Detail & Related papers  (2026-03-25T13:10:34Z)
• PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction [87.33016661440202]
  Autoregressive point cloud generation has long lagged behind diffusion-based approaches in quality.<n>We propose PointNSP, a coarse-to-fine generative framework that preserves global shape structure at low resolutions.<n> Experiments on ShapeNet show that PointNSP establishes state-of-the-art (SOTA) generation quality for the first time within the autoregressive paradigm.
  arXiv  Detail & Related papers  (2025-10-07T06:31:02Z)
• MeshMosaic: Scaling Artist Mesh Generation via Local-to-Global Assembly [62.48017648785026]
  We introduce MeshMosaic, a novel local-to-global framework for artist mesh generation that scales to over 100K triangles.<n>We show that MeshMosaic significantly outperforms state-of-the-art methods in both geometric fidelity and user preference.
  arXiv  Detail & Related papers  (2025-09-24T11:02:03Z)
• Towards Efficient General Feature Prediction in Masked Skeleton Modeling [59.46799426434277]
  We propose a novel General Feature Prediction framework (GFP) for efficient mask skeleton modeling.<n>Our key innovation is replacing conventional low-level reconstruction with high-level feature prediction that spans from local motion patterns to global semantic representations.
  arXiv  Detail & Related papers  (2025-09-03T18:05:02Z)
• Mesh Denoising Transformer [104.5404564075393]
  Mesh denoising is aimed at removing noise from input meshes while preserving their feature structures. SurfaceFormer is a pioneering Transformer-based mesh denoising framework. New representation known as Local Surface Descriptor captures local geometric intricacies. Denoising Transformer module receives the multimodal information and achieves efficient global feature aggregation.
  arXiv  Detail & Related papers  (2024-05-10T15:27:43Z)
• Neural Subdivision [58.97214948753937]
  This paper introduces Neural Subdivision, a novel framework for data-driven coarseto-fine geometry modeling. We optimize for the same set of network weights across all local mesh patches, thus providing an architecture that is not constrained to a specific input mesh, fixed genus, or category. We demonstrate that even when trained on a single high-resolution mesh our method generates reasonable subdivisions for novel shapes.
  arXiv  Detail & Related papers  (2020-05-04T20:03:21Z)

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.