MeshMosaic: Scaling Artist Mesh Generation via Local-to-Global Assembly

• URL: http://arxiv.org/abs/2509.19995v1
• Date: Wed, 24 Sep 2025 11:02:03 GMT
• Title: MeshMosaic: Scaling Artist Mesh Generation via Local-to-Global Assembly
• Authors: Rui Xu, Tianyang Xue, Qiujie Dong, Le Wan, Zhe Zhu, Peng Li, Zhiyang Dou, Cheng Lin, Shiqing Xin, Yuan Liu, Wenping Wang, Taku Komura,
• Abstract summary: 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.
• Score: 62.48017648785026
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Scaling artist-designed meshes to high triangle numbers remains challenging for autoregressive generative models. Existing transformer-based methods suffer from long-sequence bottlenecks and limited quantization resolution, primarily due to the large number of tokens required and constrained quantization granularity. These issues prevent faithful reproduction of fine geometric details and structured density patterns. We introduce MeshMosaic, a novel local-to-global framework for artist mesh generation that scales to over 100K triangles--substantially surpassing prior methods, which typically handle only around 8K faces. MeshMosaic first segments shapes into patches, generating each patch autoregressively and leveraging shared boundary conditions to promote coherence, symmetry, and seamless connectivity between neighboring regions. This strategy enhances scalability to high-resolution meshes by quantizing patches individually, resulting in more symmetrical and organized mesh density and structure. Extensive experiments across multiple public datasets demonstrate that MeshMosaic significantly outperforms state-of-the-art methods in both geometric fidelity and user preference, supporting superior detail representation and practical mesh generation for real-world applications.

Related papers

• MeshRipple: Structured Autoregressive Generation of Artist-Meshes [43.29985039393799]
  Meshes serve as a primary representation for 3D assets.<n>We introduce MeshRipple, which expands a mesh outward from an active generation frontier, akin to a ripple on a surface.<n>This integrated design enables MeshRipple to generate meshes with high surface fidelity and topological completeness, outperforming strong recent baselines.
  arXiv  Detail & Related papers  (2025-12-08T12:50:23Z)
• Extremal Contours: Gradient-driven contours for compact visual attribution [5.6220652636435915]
  We show how a star-supervised framework can achieve higher complexity with dense masks.<n>On ImageNets, it matches the extremal contours of dense masks while producing compact regions with improved run-to-run vision.
  arXiv  Detail & Related papers  (2025-11-03T10:02:21Z)
• FastMesh: Efficient Artistic Mesh Generation via Component Decoupling [27.21354509059262]
  Mesh generation approaches typically tokenize triangle meshes into sequences of tokens and train autoregressive models to generate these tokens sequentially.<n>This redundancy leads to excessively long token sequences and inefficient generation processes.<n>We propose an efficient framework that generates artistic meshes by treating vertices and faces separately.
  arXiv  Detail & Related papers  (2025-08-26T16:51:02Z)
• TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing [47.919057306538626]
  TreeMeshGPT is an autoregressive Transformer designed to generate artistic meshes aligned with input point clouds.<n>Our approach represents each triangular face with two tokens, achieving a compression rate of approximately 22%.<n>Our method generates mesh with strong normal orientation constraints, minimizing flipped normals commonly encountered in previous methods.
  arXiv  Detail & Related papers  (2025-03-14T17:48:06Z)
• MARS: Mesh AutoRegressive Model for 3D Shape Detailization [85.95365919236212]
  We introduce MARS, a novel approach for 3D shape detailization.<n>We propose a mesh autoregressive model capable of generating such latent representations through next-LOD token prediction.<n>Experiments conducted on the challenging 3D Shape Detailization benchmark demonstrate that our proposed MARS model achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-02-17T03:12:16Z)
• Nautilus: Locality-aware Autoencoder for Scalable Mesh Generation [46.08876528701562]
  We propose Nautilus, a locality-aware autoencoder for artist-like mesh generation.<n>Our approach introduces a novel tokenization algorithm that preserves face proximity relationships.<n>We also develop a Dual-stream Point Conditioner that provides multi-scale guidance.
  arXiv  Detail & Related papers  (2025-01-24T08:22:02Z)
• 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)
• 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.