mlsanityData to 7 Oct 2026

Scaling Mesh Generation via Compressive Tokenization

arXiv 2411.07025 ↗First posted 11 Nov 2024cs.GR cs.CVcited by 71

Not on the map. Why?

Abstract (arXiv)

We propose a compressive yet effective mesh representation, Blocked and Patchified Tokenization (BPT), facilitating the generation of meshes exceeding 8k faces. BPT compresses mesh sequences by employing block-wise indexing and patch aggregation, reducing their length by approximately 75% compared to the original sequences. This compression milestone unlocks the potential to utilize mesh data with significantly more faces, thereby enhancing detail richness and improving generation robustness. Empowered with the BPT, we have built a foundation mesh generative model training on scaled mesh data to support flexible control for point clouds and images. Our model demonstrates the capability to generate meshes with intricate details and accurate topology, achieving SoTA performance on mesh generation and reaching the level for direct product usage.

Key facts. Cited by 71 papers in the map (data through 7 Oct 2026). Builds on 47 of its 53 references that are in the map. First posted on arXiv 11 Nov 2024.

Builds on

47 of 53 references.

References · 47

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2022Scalable Diffusion Models with Transformerscited by 5,931
  3. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  5. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  6. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  7. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
  8. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
  9. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
  10. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  11. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 767
  12. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
35 more
  1. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  2. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  3. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Modelcited by 516
  4. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
  5. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  6. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 421
  7. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 376
  8. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusioncited by 364
  9. 2022Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusioncited by 309
  10. 20203D-FUTURE: 3D Furniture shape with TextUREcited by 306
  11. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 298
  12. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 287
  13. 2020PolyGen: An Autoregressive Generative Model of 3D Meshescited by 267
  14. 2023MeshGPT: Generating Triangle Meshes with Decoder-Only Transformerscited by 254
  15. 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representationcited by 225
  16. 2024CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Modelcited by 214
  17. 2023DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Modelcited by 213
  18. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  19. 2022DiffRF: Rendering-Guided 3D Radiance Field Diffusioncited by 204
  20. 2023MeshDiffusion: Score-based Generative 3D Mesh Modelingcited by 198
  21. 20233DGen: Triplane Latent Diffusion for Textured Mesh Generationcited by 181
  22. 2024MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformerscited by 140
  23. 2022Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functionscited by 133
  24. 2023Locally Attentional SDF Diffusion for Controllable 3D Shape Generationcited by 129
  25. 2024MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenizationcited by 102
  26. 2024MeshXL: Neural Coordinate Field for Generative 3D Foundation Modelscited by 100
  27. 2024V3D: Video Diffusion Models are Effective 3D Generatorscited by 88
  28. 2023Consistent123: Improve Consistency for One Image to 3D Object Synthesiscited by 84
  29. 2024EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generationcited by 84
  30. 2023Free3D: Consistent Novel View Synthesis without 3D Representationcited by 72
  31. 2023PolyDiff: Generating 3D Polygonal Meshes with Diffusion Modelscited by 66
  32. 2018Scan2Mesh: From Unstructured Range Scans to 3D Meshescited by 51
  33. 2024PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidancecited by 47
  34. 2023Controllable Mesh Generation Through Sparse Latent Point Diffusion Modelscited by 40
  35. 2024SpaceMesh: A Continuous Representation for Learning Manifold Surface Meshescited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 44; 2026: 27.

71 papers.

Sort:

By area:

  1. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 342
  2. 2025Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Materialcited by 157
  3. 2025Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Detailscited by 120
  4. 2025Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assetscited by 85
  5. 2025DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learningcited by 62
  6. 2025OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesioncited by 60
  7. 2025Efficient Part-level 3D Object Generation via Dual Volume Packingcited by 47
  8. 2025Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attentioncited by 43
  9. 2025X-Part: high fidelity and structure coherent shape decompositioncited by 42
  10. 2025LATTICE: Democratize High-Fidelity 3D Generation at Scalecited by 41
  11. 2025TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencingcited by 38
  12. 2025ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understandingcited by 34
38 more
  1. 2025NANO3D: A Training-Free Approach for Efficient 3D Editing Without Maskscited by 29
  2. 2025OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generationcited by 27
  3. 2025Generating Physically Stable and Buildable Brick Structures from Textcited by 23
  4. 2025Mesh-RFT: Enhancing Mesh Generation via Fine-grained Reinforcement Fine-Tuningcited by 21
  5. 2025Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assetscited by 20
  6. 2025MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Meshcited by 18
  7. 2025FastMesh: Efficient Artistic Mesh Generation via Component Decouplingcited by 17
  8. 2025Pandora3D: A Comprehensive Framework for High-Quality 3D Shape and Texture Generationcited by 14
  9. 2025VertexRegen: Mesh Generation with Continuous Level of Detailcited by 14
  10. 2025iFlame: Interleaving Full and Linear Attention for Efficient Mesh Generationcited by 13
  11. 2025Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generationcited by 13
  12. 2025Efficient Autoregressive Shape Generation via Octree-Based Adaptive Tokenizationcited by 12
  13. 2025BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patchcited by 12
  14. 2025ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Predictioncited by 11
  15. 2025QuadGPT: Native Quadrilateral Mesh Generation with Autoregressive Modelscited by 11
  16. 2026LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtentscited by 10
  17. 2025CoRe3D: Collaborative Reasoning as a Foundation for 3D Intelligencecited by 9
  18. 2025Auto-Regressive Surface Cuttingcited by 8
  19. 2025MeshMosaic: Scaling Artist Mesh Generation via Local-to-Global Assemblycited by 8
  20. 2025MeshRipple: Structured Autoregressive Generation of Artist-Meshescited by 8
  21. 2025Auto-Connect: Connectivity-Preserving RigFormer with Direct Preference Optimizationcited by 7
  22. 2026MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformercited by 7
  23. 2025FreeMesh: Boosting Mesh Generation with Coordinates Mergingcited by 6
  24. 2025Topology-Preserved Auto-regressive Mesh Generation in the Manner of Weaving Silkcited by 6
  25. 2026LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flowcited by 6
  26. 2025XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative Decodingcited by 5
  27. 2025Topology Sculptor, Shape Refiner: Discrete Diffusion Model for High-Fidelity 3D Meshes Generationcited by 5
  28. 2026Nexus: Native Mesh Generation with Diffusioncited by 5
  29. 2025Speculative Coupled Decoding for Training-Free Lossless Acceleration of Autoregressive Visual Generationcited by 4
  30. 2025PartDiffuser: Part-wise 3D Mesh Generation via Discrete Diffusioncited by 4
  31. 2026FACE: A Face-based Autoregressive Representation for High-Fidelity and Efficient Mesh Generationcited by 4
  32. 2025CHARM: Control-point-based 3D Anime Hairstyle Auto-Regressive Modelingcited by 3
  33. 2026PixARMesh: Autoregressive Mesh-Native Single-View Scene Reconstructioncited by 3
  34. 2026Meshy T2: Fast Native Mesh Generation with Flow Matchingcited by 3
  35. 2025SeamCrafter: Enhancing Mesh Seam Generation for Artist UV Unwrapping via Reinforcement Learningcited by 2
  36. 2026HiFi-Mesh: High-Fidelity Efficient 3D Mesh Generation via Compact Autoregressive Dependencecited by 2
  37. 2026Mesh-Pro: Asynchronous Advantage-guided Ranking Preference Optimization for Artist-style Quadrilateral Mesh Generationcited by 2
  38. 2026Strips as Tokens: Artist Mesh Generation with Native UV Segmentationcited by 2

50 most cited of 71 All 71 (JSON)