Meshy T2: Fast Native Mesh Generation with Flow Matching

• URL: http://arxiv.org/abs/2607.28675v1
• Date: Tue, 28 Jul 2026 16:33:54 GMT
• Title: Meshy T2: Fast Native Mesh Generation with Flow Matching
• Abstract summary: We present Meshy T2, a fast native mesh generation framework built on flow matching.<n>In experiments, Meshy T2 achieves state-of-the-art geometric fidelity and completes end-to-end image-to-mesh generation within a median of 6 seconds.
• Score: 8.108033268825832
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Polygonal meshes are the standard surface representation of modern 3D pipelines, and generating high-quality meshes with artist-style topology is essential for film, gaming, and interactive 3D applications. Mainstream approaches serialize a mesh into a token sequence and decode it autoregressively, which is slow at inference and sensitive to error accumulation, making them impractical for interactive asset creation. We present Meshy T2, a fast native mesh generation framework built on flow matching. At its core is a vertex-set mesh VAE that encodes a mesh into one continuous latent token per vertex and decodes vertices, edge connectivity, and face winding order in a single pass, preserving high-precision geometry and artist-authored topology without vertex quantization or welding. Generation proceeds as a coarse-to-fine cascade of two flow-matching models: an image-conditioned voxel flow first sketches the overall shape as a coarse occupancy scaffold, and a mesh flow then populates the scaffold with per-vertex latent tokens, conditioned on the image, the scaffold, and a requested vertex budget. This design delivers three practical capabilities: interactive generation speed through parallel flow-based synthesis; effective face-count control through the requested vertex budget; and native support for multi-part assets, whose components emerge directly from the generated connectivity. In our experiments, Meshy T2 achieves state-of-the-art geometric fidelity and completes end-to-end image-to-mesh generation within a median of 6 seconds, over an order of magnitude faster than autoregressive baselines. Code and weights will be available at https://github.com/meshy-dev/meshy-t2.

Related papers

• Nexus: Native Mesh Generation with Diffusion [42.84943999520515]
  We present Nexus, a diffusion method that achieves holistic mesh generation via decoupled and topology generation.<n>Our method outperforms state-of-the-art autoregressive and two-stage baselines.<n>A blind user study from 3D practitioners confirms strong preference for our results.
  arXiv  Detail & Related papers  (2026-07-15T08:04:46Z)
• LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flow [40.84100683808547]
  We present LATO.2, a factorized flow matching framework for topology-aware mesh generation.<n>We show that LATO.2 surpasses state-of-the-art topology-aware mesh generators in geometric fidelity and connectivity quality.
  arXiv  Detail & Related papers  (2026-07-12T07:38:06Z)
• 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)
• MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer [82.3429532054028]
  MeshFlow is a new method for generating artist-like 3D meshes.<n>Our model generates meshes 18x faster than the fastest AR generator.
  arXiv  Detail & Related papers  (2026-06-03T08:57:15Z)
• 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)
• MeshCraft: Exploring Efficient and Controllable Mesh Generation with Flow-based DiTs [79.45006864728893]
  MeshCraft is a framework for efficient and controllable mesh generation.<n>It uses continuous spatial diffusion to generate discrete triangle faces.<n>It can generate an 800-face mesh in just 3.2 seconds.
  arXiv  Detail & Related papers  (2025-03-29T09:21:50Z)
• MeshPad: Interactive Sketch-Conditioned Artist-Reminiscent Mesh Generation and Editing [64.84885028248395]
  MeshPad is a generative approach that creates 3D meshes from sketch inputs.<n>We focus on enabling consistent edits by decomposing editing into 'deletion' of regions of a mesh, followed by 'addition' of new mesh geometry.<n>Our approach is based on a triangle sequence-based mesh representation, exploiting a large Transformer model for mesh triangle addition and deletion.
  arXiv  Detail & Related papers  (2025-03-03T11:27:44Z)
• MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization [65.15226276553891]
  MeshAnything V2 is an advanced mesh generation model designed to create Artist-Created Meshes.<n>A key innovation behind MeshAnything V2 is our novel Adjacent Mesh Tokenization (AMT) method.
  arXiv  Detail & Related papers  (2024-08-05T15:33:45Z)
• Primal-Dual Mesh Convolutional Neural Networks [62.165239866312334]
  We propose a primal-dual framework drawn from the graph-neural-network literature to triangle meshes. Our method takes features for both edges and faces of a 3D mesh as input and dynamically aggregates them. We provide theoretical insights of our approach using tools from the mesh-simplification literature.
  arXiv  Detail & Related papers  (2020-10-23T14:49:02Z)

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.