mlsanityData to 7 Oct 2026

MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers

arXiv 2311.15475 ↗First posted 27 Nov 2023cs.CV cs.LGcited by 254

Not on the map. Why?

Cited by 49 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce MeshGPT, a new approach for generating triangle meshes that reflects the compactness typical of artist-created meshes, in contrast to dense triangle meshes extracted by iso-surfacing methods from neural fields. Inspired by recent advances in powerful large language models, we adopt a sequence-based approach to autoregressively generate triangle meshes as sequences of triangles. We first learn a vocabulary of latent quantized embeddings, using graph convolutions, which inform these embeddings of the local mesh geometry and topology. These embeddings are sequenced and decoded into triangles by a decoder, ensuring that they can effectively reconstruct the mesh. A transformer is then trained on this learned vocabulary to predict the index of the next embedding given previous embeddings. Once trained, our model can be autoregressively sampled to generate new triangle meshes, directly generating compact meshes with sharp edges, more closely imitating the efficient triangulation patterns of human-crafted meshes. MeshGPT demonstrates a notable improvement over state of the art mesh generation methods, with a 9% increase in shape coverage and a 30-point enhancement in FID scores across various categories.

Key facts. Cited by 254 papers in the map (data through 7 Oct 2026). Builds on 56 of its 72 references that are in the map. First posted on arXiv 27 Nov 2023.

Builds on

56 of 72 references.

References · 56

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2017Graph Attention Networkscited by 8,854
  5. 2017Inductive Representation Learning on Large Graphscited by 6,284
  6. 2022Generative Adversarial Networkscited by 5,603
  7. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  8. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  9. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  10. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  11. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  12. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
38 more
  1. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  2. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  3. 2022Autoregressive Image Generation using Residual Quantizationcited by 706
  4. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 694
  5. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  6. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  7. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  8. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
  9. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  10. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  11. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  12. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
  13. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
  14. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  15. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 287
  16. 20223D Neural Field Generation using Triplane Diffusioncited by 274
  17. 2020PolyGen: An Autoregressive Generative Model of 3D Meshescited by 267
  18. 2020Learning Gradient Fields for Shape Generationcited by 245
  19. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  20. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  21. 2022DiffRF: Rendering-Guided 3D Radiance Field Diffusioncited by 204
  22. 2023MeshDiffusion: Score-based Generative 3D Mesh Modelingcited by 198
  23. 2017Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputscited by 189
  24. 2021Shape As Points: A Differentiable Poisson Solvercited by 186
  25. 20233DGen: Triplane Latent Diffusion for Textured Mesh Generationcited by 181
  26. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  27. 2020DiffusionNet: Discretization Agnostic Learning on Surfacescited by 163
  28. 2023HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusioncited by 152
  29. 2022Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Modelscited by 151
  30. 2022VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Gridscited by 133
  31. 2022Neural Wavelet-domain Diffusion for 3D Shape Generationcited by 132
  32. 2016Generative and Discriminative Voxel Modeling with Convolutional Neural Networkscited by 128
  33. 2022Diffusion-SDF: Text-to-Shape via Voxelized Diffusioncited by 128
  34. 2020MeshSDF: Differentiable Iso-Surface Extractioncited by 112
  35. 2019SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operatorcited by 89
  36. 2018Point Cloud GANcited by 79
  37. 2019SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scanscited by 77
  38. 2016Unsupervised Learning of 3D Structure from Imagescited by 67

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 63; 2025: 111; 2026: 79.

254 papers.

Sort:

By area:

  1. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 444
  2. 2024MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformerscited by 140
  3. 2024Recent Advances in 3D Gaussian Splattingcited by 130
  4. 2025Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Detailscited by 120
  5. 2024MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenizationcited by 102
  6. 2024BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometrycited by 101
  7. 2024MeshXL: Neural Coordinate Field for Generative 3D Foundation Modelscited by 100
  8. 2024V3D: Video Diffusion Models are Effective 3D Generatorscited by 88
  9. 2025Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assetscited by 85
  10. 2024EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generationcited by 84
  11. 2025Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modelingcited by 84
  12. 2024BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolationcited by 81
38 more
  1. 2025PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformerscited by 78
  2. 2025SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modelingcited by 76
  3. 2024Scaling Mesh Generation via Compressive Tokenizationcited by 71
  4. 2024Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materialscited by 66
  5. 2025Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstructioncited by 66
  6. 2024Advances in 3D Generation: A Surveycited by 62
  7. 2025DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learningcited by 62
  8. 2025OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesioncited by 60
  9. 2024Meta 3D TextureGen: Fast and Consistent Texture Generation for 3D Objectscited by 52
  10. 2024CAD-GPT: Synthesising CAD Construction Sequence with Spatial Reasoning-Enhanced Multimodal LLMscited by 52
  11. 2025Amodal3R: Amodal 3D Reconstruction from Occluded 2D Imagescited by 52
  12. 2024PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidancecited by 47
  13. 2025Efficient Part-level 3D Object Generation via Dual Volume Packingcited by 47
  14. 2024DressCode: Autoregressively Sewing and Generating Garments from Text Guidancecited by 43
  15. 2025MagicArticulate: Make Your 3D Models Articulation-Readycited by 43
  16. 2025Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attentioncited by 43
  17. 2024When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Modelscited by 41
  18. 2025Puppeteer: Rig and Animate Your 3D Modelscited by 41
  19. 2025LATTICE: Democratize High-Fidelity 3D Generation at Scalecited by 41
  20. 2024MeshArt: Generating Articulated Meshes with Structure-Guided Transformerscited by 40
  21. 2023ShapeGPT: 3D Shape Generation with A Unified Multi-modal Language Modelcited by 38
  22. 2024SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAEcited by 38
  23. 2025TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencingcited by 38
  24. 2025Visual Large Language Models for Generalized and Specialized Applicationscited by 35
  25. 2024An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusioncited by 34
  26. 2025ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understandingcited by 34
  27. 2025PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Imagecited by 32
  28. 2025CADCrafter: Generating Computer-Aided Design Models from Unconstrained Imagescited by 31
  29. 2025What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Modelscited by 29
  30. 2024PrEditor3D: Fast and Precise 3D Shape Editingcited by 27
  31. 2025OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generationcited by 27
  32. 2024SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generationcited by 24
  33. 2025Generating Physically Stable and Buildable Brick Structures from Textcited by 23
  34. 2025Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Surveycited by 23
  35. 2025FreeArt3D: Training-Free Articulated Object Generation using 3D Diffusioncited by 22
  36. 20243D-PreMise: Can Large Language Models Generate 3D Shapes with Sharp Features and Parametric Control?cited by 21
  37. 2025Mesh-RFT: Enhancing Mesh Generation via Fine-grained Reinforcement Fine-Tuningcited by 21
  38. 2024Large Language Model Agent as a Mechanical Designercited by 20

50 most cited of 254 All 254 (JSON)