# Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scale

arXiv: https://arxiv.org/abs/2412.09548 · HTML: https://mlsanity.com/paper/2412.09548/

## Key facts

- Cited by 89 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 74 references that are in the map.
- First posted on arXiv 12 Dec 2024.

## Builds on (most cited first, 30 of 36)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [MVDream: Multi-view Diffusion for 3D Generation](https://mlsanity.com/paper/2308.16512/) (2023)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation](https://mlsanity.com/paper/2309.16653/) (2023)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [Ring Attention with Blockwise Transformers for Near-Infinite Context](https://mlsanity.com/paper/2310.01889/) (2023)
- [Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors](https://mlsanity.com/paper/2306.17843/) (2023)
- [Shap-E: Generating Conditional 3D Implicit Functions](https://mlsanity.com/paper/2305.02463/) (2023)
- [Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model](https://mlsanity.com/paper/2311.06214/) (2023)
- [GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation](https://mlsanity.com/paper/2403.14621/) (2024)
- [LongNet: Scaling Transformers to 1,000,000,000 Tokens](https://mlsanity.com/paper/2307.02486/) (2023)
- [DreamGaussian4D: Generative 4D Gaussian Splatting](https://mlsanity.com/paper/2312.17142/) (2023)
- [MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers](https://mlsanity.com/paper/2406.10163/) (2024)
- [MeshLRM: Large Reconstruction Model for High-Quality Meshes](https://mlsanity.com/paper/2404.12385/) (2024)
- [Generative and Discriminative Voxel Modeling with Convolutional Neural Networks](https://mlsanity.com/paper/1608.04236/) (2016)
- [A Length-Extrapolatable Transformer](https://mlsanity.com/paper/2212.10554/) (2022)
- [MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization](https://mlsanity.com/paper/2408.02555/) (2024)
- [MeshXL: Neural Coordinate Field for Generative 3D Foundation Models](https://mlsanity.com/paper/2405.20853/) (2024)
- [Hierarchical Transformers Are More Efficient Language Models](https://mlsanity.com/paper/2110.13711/) (2021)

## Built on by (most cited first, 30 of 89)

- [Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details](https://mlsanity.com/paper/2506.16504/) (2025)
- [Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling](https://mlsanity.com/paper/2505.14521/) (2025)
- [DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning](https://mlsanity.com/paper/2503.15265/) (2025)
- [OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion](https://mlsanity.com/paper/2507.06165/) (2025)
- [Efficient Part-level 3D Object Generation via Dual Volume Packing](https://mlsanity.com/paper/2506.09980/) (2025)
- [Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention](https://mlsanity.com/paper/2507.17745/) (2025)
- [LATTICE: Democratize High-Fidelity 3D Generation at Scale](https://mlsanity.com/paper/2512.03052/) (2025)
- [MeshArt: Generating Articulated Meshes with Structure-Guided Transformers](https://mlsanity.com/paper/2412.11596/) (2024)
- [TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing](https://mlsanity.com/paper/2503.11629/) (2025)
- [ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding](https://mlsanity.com/paper/2506.01853/) (2025)
- [OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generation](https://mlsanity.com/paper/2504.09975/) (2025)
- [Generating Physically Stable and Buildable Brick Structures from Text](https://mlsanity.com/paper/2505.05469/) (2025)
- [Mesh-RFT: Enhancing Mesh Generation via Fine-grained Reinforcement Fine-Tuning](https://mlsanity.com/paper/2505.16761/) (2025)
- [MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh](https://mlsanity.com/paper/2508.01242/) (2025)
- [LL3M: Large Language 3D Modelers](https://mlsanity.com/paper/2508.08228/) (2025)
- [Scaling Laws of Motion Forecasting and Planning -- Technical Report](https://mlsanity.com/paper/2506.08228/) (2025)
- [VertexRegen: Mesh Generation with Continuous Level of Detail](https://mlsanity.com/paper/2508.09062/) (2025)
- [MeshCraft: Exploring Efficient and Controllable Mesh Generation with Flow-based DiTs](https://mlsanity.com/paper/2503.23022/) (2025)
- [iFlame: Interleaving Full and Linear Attention for Efficient Mesh Generation](https://mlsanity.com/paper/2503.16653/) (2025)
- [Efficient Autoregressive Shape Generation via Octree-Based Adaptive Tokenization](https://mlsanity.com/paper/2504.02817/) (2025)
- [Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation](https://mlsanity.com/paper/2509.12815/) (2025)
- [BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patch](https://mlsanity.com/paper/2511.22171/) (2025)
- [QuadGPT: Native Quadrilateral Mesh Generation with Autoregressive Models](https://mlsanity.com/paper/2509.21420/) (2025)
- [DMesh++: An Efficient Differentiable Mesh for Complex Shapes](https://mlsanity.com/paper/2412.16776/) (2024)
- [ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Prediction](https://mlsanity.com/paper/2509.20824/) (2025)
- [MeshRipple: Structured Autoregressive Generation of Artist-Meshes](https://mlsanity.com/paper/2512.07514/) (2025)
- [Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation](https://mlsanity.com/paper/2512.10949/) (2025)
- [CoRe3D: Collaborative Reasoning as a Foundation for 3D Intelligence](https://mlsanity.com/paper/2512.12768/) (2025)
- [LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtents](https://mlsanity.com/paper/2603.06357/) (2026)
- [SegviGen: Repurposing 3D Generative Model for Part Segmentation](https://mlsanity.com/paper/2603.16869/) (2026)

## Abstract (arXiv)

Meshes are fundamental representations of 3D surfaces. However, creating high-quality meshes is a labor-intensive task that requires significant time and expertise in 3D modeling. While a delicate object often requires over 104 faces to be accurately modeled, recent attempts at generating artist-like meshes are limited to 1.6K faces and heavy discretization of vertex coordinates. Hence, scaling both the maximum face count and vertex coordinate resolution is crucial to producing high-quality meshes of realistic, complex 3D objects. We present Meshtron, a novel autoregressive mesh generation model able to generate meshes with up to 64K faces at 1024-level coordinate resolution --over an order of magnitude higher face count and 8× higher coordinate resolution than current state-of-the-art methods. Meshtron's scalability is driven by four key components: (1) an hourglass neural architecture, (2) truncated sequence training, (3) sliding window inference, (4) a robust sampling strategy that enforces the order of mesh sequences. This results in over 50% less training memory, 2.5× faster throughput, and better consistency than existing works. Meshtron generates meshes of detailed, complex 3D objects at unprecedented levels of resolution and fidelity, closely resembling those created by professional artists, and opening the door to more realistic generation of detailed 3D assets for animation, gaming, and virtual environments.